CN117970818A - Industrial equipment control method based on Internet of Things - Google Patents
Industrial equipment control method based on Internet of Things Download PDFInfo
- Publication number
- CN117970818A CN117970818A CN202410383958.7A CN202410383958A CN117970818A CN 117970818 A CN117970818 A CN 117970818A CN 202410383958 A CN202410383958 A CN 202410383958A CN 117970818 A CN117970818 A CN 117970818A
- Authority
- CN
- China
- Prior art keywords
- spraying
- spraying equipment
- repair
- parameter set
- repairing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/004—Arrangements for controlling delivery; Arrangements for controlling the spray area comprising sensors for monitoring the delivery, e.g. by displaying the sensed value or generating an alarm
- B05B12/006—Pressure or flow rate sensors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/084—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to condition of liquid or other fluent material already sprayed on the target, e.g. coating thickness, weight or pattern
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/12—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/12—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus
- B05B12/124—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to conditions of ambient medium or target, e.g. humidity, temperature position or movement of the target relative to the spray apparatus responsive to distance between spray apparatus and target
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Fluid Mechanics (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Mathematical Physics (AREA)
- Computer Graphics (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
本发明属于喷涂设备调控技术领域，本发明公开了一种基于物联网的工业设备调控方法，包括，S1：采集同一喷涂原料的喷涂设备历史数据，喷涂设备历史数据包括喷涂设备参数集、环境参数集和修补件特征数据集；S2：根据喷涂设备历史数据训练机器学习模型，将当前环境参数集和当前修补件特征数据集输入机器学习模型，获得机器学习模型输出的喷涂设备参数集编号。本发明通过喷涂设备历史数据对机器学习模型进行训练，能够输出对应的喷涂设备参数，便于根据喷涂设备参数对喷涂设备进行调控，避免人工需要调控喷涂设备参数以及人工调控的繁琐，在对修补部进行修补时，能进行精准的喷涂。
The present invention belongs to the technical field of spray equipment control. The present invention discloses an industrial equipment control method based on the Internet of Things, including: S1: collecting historical data of spray equipment of the same spraying raw material, the historical data of spray equipment including spray equipment parameter set, environmental parameter set and repair part feature data set; S2: training a machine learning model according to the historical data of spray equipment, inputting the current environmental parameter set and the current repair part feature data set into the machine learning model, and obtaining the spray equipment parameter set number output by the machine learning model. The present invention trains the machine learning model through the historical data of spray equipment, and can output the corresponding spray equipment parameters, so as to facilitate the control of the spray equipment according to the spray equipment parameters, avoid the need for manual control of the spray equipment parameters and the tediousness of manual control, and can perform precise spraying when repairing the repair part.
Description
Technical Field
The invention relates to the technical field of spray equipment regulation and control, in particular to an industrial equipment regulation and control method based on the Internet of things.
Background
The industrial Internet of things is characterized in that various acquisition and control sensors or controllers with sensing and monitoring capabilities, mobile communication, intelligent analysis and other technologies are continuously integrated into various links of an industrial production process, so that the manufacturing efficiency is greatly improved, the product quality is improved, the product cost and the resource consumption are reduced, and finally the traditional industry is improved to an intelligent new stage. From the application form, the application of the industrial Internet of things has the characteristics of instantaneity, automation, embedded (software), safety, information intercommunication and interconnection and the like. The background technology of the industrial equipment regulation and control method based on the Internet of things mainly comes from the development trend of industrial automation, informatization and intellectualization. With the rapid development of global industrialization, the number and complexity of industrial equipment are continuously increased, and the traditional manual monitoring and management mode cannot meet the requirements of high efficiency, safety and environmental protection of the modern industry. Therefore, the industrial equipment regulation and control method based on the Internet of things is generated, and the purpose of realizing intelligent management and regulation and control of industrial equipment through an informatization means is achieved.
When repairing the existing repairing parts through the spraying equipment, the parameters of the spraying equipment are mostly regulated and controlled manually, and because the spraying parameters of the spraying equipment corresponding to the repairing parts of different repairing parts are different, the repairing parts of part of the repairing parts are often required to be sprayed for many times when repairing the repairing parts, but the total thickness of the spraying for many times cannot correspond to the incomplete thickness of the repairing parts, and the spraying accuracy is required to be improved.
In view of the above, the present invention proposes an industrial equipment regulation and control method based on the internet of things to solve the above problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the following technical scheme for achieving the purposes: an industrial equipment regulation and control method based on the Internet of things comprises,
S1: collecting historical data of spraying equipment of the same spraying raw material, wherein the historical data of the spraying equipment comprise a parameter set of the spraying equipment, an environmental parameter set and a characteristic data set of a repairing piece;
S2: training a machine learning model according to historical data of the spraying equipment, inputting a current environment parameter set and a current repair piece characteristic data set into the machine learning model, obtaining a spraying equipment parameter set number output by the machine learning model, taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as a current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set;
S3: and repairing the repair piece through the regulated spraying equipment, judging whether the repair piece reaches the expected repair thickness, if so, not regulating the spraying equipment, and if not, continuing regulating the spraying equipment.
Further, in said S1,
The spraying equipment parameter set comprises a spraying flow rate and a spraying distance;
the environmental parameter set includes an ambient temperature, an ambient humidity, an air flow rate, and an air granularity;
The repair feature data set includes repair surface finish values, repair incomplete thickness, and repair scope.
Further, in the spraying device parameter set, the step of obtaining the spraying flow rate and the spraying distance includes:
the method comprises the steps of installing an infrared distance measuring device, a flow sensor, a time sensor and a pressure sensor on spraying equipment;
The flow sensor, the time sensor and the pressure sensor are used for obtaining the descending amount, the spraying time and the spraying pressure of the spraying coating, and the spraying flow rate is obtained based on the descending amount, the spraying time and the spraying pressure of the spraying coating, so that the calculation formula of the spraying flow rate is as follows:
，
Wherein, For the spray-coating flow rate,In order to achieve the spraying pressure, the coating composition,In order to reduce the amount of drop of the spray coating,The spraying time is;
Acquiring the radial distance between the front center point of the nozzle on the spraying equipment and the repairing part on the repairing piece, and marking the radial distance as the spraying distance;
the spraying flow rate and the spraying distance of each repair are taken as one spraying equipment parameter data.
Further, in the environmental parameter set, the step of acquiring the environmental temperature, the environmental humidity, the air flow rate and the air granularity includes,
Installing a temperature sensor around the spraying equipment to obtain the ambient temperature;
Installing humidity sensors around the spraying equipment to obtain the ambient humidity;
Installing a wind speed sensor around the spraying equipment to obtain the air flow rate;
Installing particle sensors around the spraying equipment to obtain air granularity;
The ambient temperature, ambient humidity, air flow rate and air granularity of each repair are taken as one environmental parameter data.
Further, in the repair feature data set, the step of obtaining a repair part surface finish value, a repair part incomplete thickness, and a repair part range, includes,
Shooting the repairing part through the image pickup equipment to obtain an original image, converting the original image into a gray image, preprocessing the original image by adopting Gaussian smoothing, improving a Laplacian operator through a weight function, performing edge detection on the original image by improving the Laplacian operator, and obtaining the range of the repairing part through any one of a Monte Carlo method and a grid method;
Scanning a repairing part of the repairing piece through a laser scanner to obtain three-dimensional point cloud data, carrying out surface reconstruction on the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a three-dimensional virtual model through surface fitting or triangular mesh reconstruction; selecting a region of the repair part based on the repair part range in the three-dimensional virtual model, determining a measuring surface, measuring the vertical distance from the measuring surface to a reference surface on the selected measuring surface, and recording the vertical distance as the total spraying thickness; presetting a thickness threshold, layering the three-dimensional virtual model according to the thickness threshold to obtain layering numbers, wherein the layering numbers are equal to the spraying times, and taking each layering thickness as the incomplete thickness of the repairing part;
Calculating the leveling value of the measuring surface in the three-dimensional virtual model by adopting weighted average sum to obtain the leveling value of the surface of the repairing part;
the repair part surface flatness value, repair part incomplete thickness and repair part range of each repair are taken as a repair part characteristic data set.
Further, the Gaussian smoothing formula is that,
，
Wherein,The value of the two-dimensional Gaussian function is simply called a kernel function; is the standard deviation of the gaussian distribution, Is the bottom of the natural logarithm,In order to achieve a peripheral rate of the material,AndRepresenting the variables in the gaussian function, representing the horizontal and vertical positions of the pixels in the original image, respectively.
Further, in the improved Laplacian operator, a weight function is preset, and the formula is,
，
Wherein,As the weight value of the weight,Representing the coordinates of the pixels in the original image,Is the horizontal position of the pixel and,Is the vertical position of the pixel; And Representing gray values inside and outside the edge respectively,To adjust parameters;
The formula of the modified Laplacian operator is,
Wherein, the method comprises the steps of, wherein,Expressed in coordinatesA second derivative of the position, namely a response value of the Laplacian operator; representing the original image at coordinates Gray values at the positions, namely pixel values of the original image;、、、 Respectively representing the original image at coordinates 、、、The gray values at which, i.e. the adjacent pixel values of the original image,Representing the original image at coordinatesFour times the gray value at the point, for approximately calculating the response value of the Laplacian operator.
Further, the calculation formula of the surface leveling value of the repairing part is as follows:
，
Wherein, The surface flatness value of the repairing part is indicated,Represents the average roughness of the surface of the repaired portion,Indicating the maximum peak-to-valley height of the repair surface,Representing the height deviation of each measurement point,Indicating the number of measured points of the repair surface,The height of the highest point of the repair part surface is shown,Indicating the height of the lowest point of the repair surface,A weight coefficient indicating the average roughness of the surface of the repair part,A weight coefficient indicating the maximum peak-to-valley height of the repair part surface,。
Further, in said S2, the step of training a machine learning model based on the spray equipment history data, comprises,
Taking a spraying equipment parameter set in the historical data of the spraying equipment as a sample set;
Numerical numbering is carried out on the parameter set of the spraying equipment;
Respectively constructing a first characteristic vector P1 and a second characteristic vector P2 from a repair piece characteristic data set and an environment parameter set in historical data of spraying equipment, defining an input layer and an output layer by using TensorFlow, constructing a machine learning frame, taking the first characteristic vector P1 and the second characteristic vector P2 as input layer data, and taking the number of the parameter set of the spraying equipment as output layer data;
Dividing the sample set into a training set and a testing set, constructing a machine learning model, training the machine learning model to obtain the machine learning model, testing the initially constructed machine learning model by using the testing set, and outputting the machine learning model conforming to the preset accuracy;
inputting the current environment parameter set and the current repair feature data set into a machine learning model, obtaining a spraying equipment parameter set number output by the machine learning model, taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set, wherein the method comprises the following steps of:
collecting the ambient temperature, the ambient humidity, the air flow rate and the air granularity in real time as a current ambient parameter set;
collecting the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in real time as a characteristic data set of the current repairing part;
inputting the current environment parameter set and the current repair feature data set into a trained machine learning model to obtain a spraying equipment parameter set number output by the machine learning model;
and taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set.
Further, in the step S3, the repair part is repaired by the adjusted parameters of the spraying device, whether the repair part reaches the expected repair thickness is judged, if yes, the adjusting and controlling of the spraying device are not needed, if not, the adjusting and controlling of the spraying device are continued, including,
Spraying and repairing the repairing piece through the regulated spraying equipment parameters, and rescanning the repairing part through a laser scanner after each spraying is completed, so as to update the three-dimensional virtual model to obtain the latest three-dimensional virtual model;
judging whether the last spraying thickness reaches an expected repairing thickness or not according to the latest three-dimensional virtual model, wherein the expected repairing thickness is the incomplete thickness of the last sprayed repairing part;
If so, the parameters of the spraying equipment are not required to be regulated and controlled, and if not, the parameters of the spraying equipment are regulated and controlled according to the latest three-dimensional virtual model until the repair is completed.
The industrial equipment regulation and control method based on the Internet of things has the technical effects and advantages that:
1. The influence of different parameters on the coating spraying can be known by collecting the parameter data of the spraying equipment, including the spraying flow rate and the spraying distance, and data support is provided for the optimization of the subsequent spraying process; the temperature, the humidity, the air flow rate and the air granularity of the environmental parameter data are collected, so that the coating environment is controlled, the coating quality is improved, and the influence of environmental factors on the coating process is reduced; the state of the repairing part can be comprehensively known through the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in the characteristic data of the repairing part, so that a basis is provided for subsequent repairing work; the spraying flow rate of the coating can be accurately obtained through a calculation formula of the spraying flow rate, so that the control of the spraying amount of the coating is facilitated, and the uniformity and the stability of spraying are improved; the leveling value of the surface of the repairing part can be quantitatively evaluated through a leveling value calculation formula, so that a proper spraying equipment parameter set can be conveniently output.
2. Through the spraying equipment historical data of gathering same spraying raw materials, train machine learning model according to spraying equipment historical data to can export the spraying equipment parameter set serial number that corresponds, be convenient for regulate and control spraying equipment according to spraying equipment parameter, regulate and control comparatively accurately, avoid the manual work to need regulate and control spraying equipment parameter and manual regulation's loaded down with trivial details, thereby when repairing repair portion, can carry out accurate spraying to it, repair portion's incomplete thickness that repair portion that can be accurate, repair quality is higher.
Drawings
Fig. 1 is a schematic structural diagram of an industrial equipment control method based on the internet of things;
FIG. 2 is a schematic diagram of a control flow scheme according to the present invention;
fig. 3 is a schematic view of the reference and measurement surfaces of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1 to 3, the method for controlling industrial equipment based on the internet of things in this embodiment includes:
s1, collecting historical data of spraying equipment of the same spraying raw material, wherein the historical data of the spraying equipment comprise a parameter set of the spraying equipment, an environmental parameter set and a characteristic data set of a repairing piece;
Wherein the spraying equipment parameter set comprises spraying flow rate and spraying distance;
the environmental parameter set includes an ambient temperature, an ambient humidity, an air flow rate, and an air granularity;
the repair feature data set comprises repair surface flatness values, repair incomplete thickness and repair scope;
the method comprises the steps of obtaining the spraying flow rate and the spraying distance in a spraying equipment parameter set, and comprises the following steps:
the method comprises the steps of installing an infrared distance measuring device, a flow sensor, a time sensor and a pressure sensor on spraying equipment;
The flow sensor, the time sensor and the pressure sensor are used for obtaining the descending amount, the spraying time and the spraying pressure of the spraying coating, and the spraying flow rate is obtained based on the descending amount, the spraying time and the spraying pressure of the spraying coating, so that the calculation formula of the spraying flow rate is as follows:
，
Wherein, For the spray-coating flow rate,In order to achieve the spraying pressure, the coating composition,In order to reduce the amount of drop of the spray coating,The spraying time is;
Acquiring the radial distance between the front center point of the nozzle on the spraying equipment and the repairing part on the repairing piece, and marking the radial distance as the spraying distance;
taking the spraying flow rate and the spraying distance of each repair as parameter data of spraying equipment;
Specifically, in the same spray coating, different spray coating flow rates correspond to different spray coating thicknesses; the descending amount of the sprayed coating is obtained by subtracting the total amount of the coating after each spraying from the total amount of the coating before each spraying, or a weight sensor can be adopted, and the difference between the total amount of the coating before each spraying and the total amount of the coating after each spraying is detected by the weight sensor, namely the descending amount of the sprayed coating. Through obtaining spraying pressure, the decline volume and the spraying time of spraying coating, enable spraying equipment and realize accurate control at control spraying velocity of flow, ensure the stability and the uniformity of spraying velocity of flow, through accurate control spraying velocity of flow, can furthest improve spraying efficiency, reduce the waste of coating, reduction in production cost reduces the defect that the coating flow is inhomogeneous to lead to, improves spraying quality.
In the environmental parameter set, the steps of obtaining the environmental temperature, the environmental humidity, the air flow rate and the air granularity comprise,
Installing a temperature sensor around the spraying equipment to obtain the ambient temperature;
Installing humidity sensors around the spraying equipment to obtain the ambient humidity;
Installing a wind speed sensor around the spraying equipment to obtain the air flow rate;
Installing particle sensors around the spraying equipment to obtain air granularity;
taking the ambient temperature, ambient humidity, air flow rate and air granularity of each repair as one environmental parameter data;
Specifically, the ambient temperature has a direct influence on the fluidity and drying speed of the paint, the paint flows more easily at higher ambient temperature, and the paint fluidity is reduced at lower temperature, which easily causes uneven spraying or caking; humidity affects the drying speed and viscosity of the coating; the air flow rate can affect the spray uniformity and drying speed of the paint, and higher air flow rates can cause drift or uneven spray during paint spraying, affecting the spray quality. For example, too high an air flow rate can also increase the drying speed of the coating, possibly resulting in uneven drying or formation of bubbles, particles in the air can affect the spray quality and surface finish of the coating, and when the air particle size is high, the resistance of the air flow rate is easily increased, so that the air flow rate is reduced.
The step of obtaining a repair part surface finish value, a repair part incomplete thickness, and a repair part range in the repair part characteristic data set, includes,
Shooting the repairing part through the image pickup equipment to obtain an original image, converting the original image into a gray image, preprocessing the original image by adopting Gaussian smoothing, improving a Laplacian operator through a weight function, performing edge detection on the original image by improving the Laplacian operator, and obtaining the range of the repairing part through any one of a Monte Carlo method and a grid method;
The gaussian smoothing formula is given by the formula,
，
Wherein,The value of the two-dimensional Gaussian function is simply called a kernel function; is the standard deviation of the gaussian distribution, Is the bottom of the natural logarithm,In order to achieve a peripheral rate of the material,AndRepresenting variables in the gaussian function, representing the horizontal and vertical positions of pixels in the original image, respectively;
Specifically, the Gaussian smoothing can blur details and noise in the original image, and reduce the noise in the original image by averaging gray values of neighborhood pixels, so that the original image is smoother and clearer, the Gaussian smoothing can preserve edge information in the original image while reducing noise, and compared with other filtering methods, the Gaussian smoothing can better maintain edge definition and structural integrity of the original image, and is beneficial to accuracy and stability of subsequent Laplacian operators on the original image; in edge detection, this smoothing effect helps to refine the edges and can reduce false edges due to noise; gaussian smoothing will make the edge portions in the original image more prominent because the difference in gray values of pixels near the edges is more pronounced, which helps to improve the response of the Laplacian operator to the edges, making the detected edges more sharp and noticeable.
In the improvement of the Laplacian operator, a weight function is preset, so that the response intensity of the Laplacian operator is increased when the gray value change in the edge is large, the response intensity of the Laplacian operator is reduced when the gray value change in the edge is small, the formula is that,
，
Wherein,As a function of the weight function value,Representing the coordinates of the pixels in the original image,Is the horizontal position of the pixel and,Is the vertical position of the pixel; And Representing gray values inside and outside the edge respectively,To adjust the parameters. Adjusting parametersA proper initial value can be selected according to experience, and is obtained by continuous adjustment through experiments; by adjusting parametersThe slope of the weight function can be controlled, so that the sensitivity of edge detection can be flexibly adjusted;
Specifically, the original image after Gaussian smoothing is subjected to preliminary edge detection through a Sobel operator, gradient amplitude values of the original image in the horizontal direction and the vertical direction are calculated, the gradient amplitude value of each pixel point is calculated, then a gradient threshold value is set according to the distribution condition of the gradient amplitude values to distinguish the edge inside from the edge outside, and if the gradient amplitude value of each pixel point in the image is larger than the gradient threshold value, the pixel point is divided into the edge inside, otherwise, the pixel point is divided into the edge outside, and therefore the original image can be divided into the edge inside region and the edge outside region. The gradient threshold can be obtained through a test method, and the optimal threshold is selected through observing the edge detection result; the gradient threshold may also be obtained by calculating the mean and standard deviation of the gradient magnitudes of the entire image, and selecting an appropriate multiple as the threshold, such as the mean plus or minus an appropriate multiple times the standard deviation.
The formula for improving the Laplacian operator is,
Wherein, the method comprises the steps of, wherein,Expressed in coordinatesA second derivative of the position, namely a response value of the Laplacian operator; representing the original image at coordinates Gray values at the positions, namely pixel values of the original image;、、、 Respectively representing the original image at coordinates 、、、The gray values at which, i.e. the adjacent pixel values of the original image,Representing the original image at coordinatesFour times the gray value at the point, for approximately calculating the response value of the Laplacian operator.
Specifically, by setting a weight function in the improved Laplacian operator, when an edge exists in an original image, the change of the gray value in the edge is larger, and at the moment, the edge can be better highlighted by increasing the response intensity of the Laplacian operator, so that the edge is clearer and more obvious, and the edge detection and the edge positioning are facilitated; in the original image, there are areas outside the edges, and as the gray value change is small, the response of the Laplacian operator to these areas may increase noise interference, for example, when the gray value difference between the inside and outside of the edges is large, the value of the weight function is close to 1, which indicates that the response of the Laplacian operator is enhanced, and when the gray value difference is small, the value of the weight function is close to 0, which indicates that the response of the Laplacian operator is weakened; noise in the areas can be effectively restrained by reducing the response intensity of the Laplacian operator, and the quality and definition of an original image are improved; the edge in the original image can be more accurately positioned by adjusting the response intensity of the Laplacian operator, the accuracy and the stability of edge detection can be improved, the extraction of the edge of the repairing part in the subsequent original image can be facilitated, and the repairing part range can be obtained by any one of a Monte Carlo method and a grid method;
For example, an original image is converted into a gray image through an image pickup device, the gray image is preprocessed through a Gaussian kernel function, gray value difference is increased, then response intensity of edges is adjusted through a weight function, the edges are better highlighted, the edges are clearer and more obvious, convolution operation is carried out on a Laplacian operator template in a discrete form, the Laplacian operator can detect second derivative changes in the original image, and therefore edges in the original image are found, edges are extracted, and repair part edges are obtained.
The method for obtaining the repair part range by the Monte Carlo method comprises the following steps: and randomly generating a large number of points in the edge of the repairing part, judging whether each randomly generated point is positioned in the edge of the repairing part, counting the number of the points positioned in the edge of the repairing part, comparing the number of the points with the total random number, and estimating the inner area of the edge of the repairing part according to the proportion of the points positioned in the edge of the repairing part, namely the range of the repairing part.
The step of obtaining the repair part range by the grid method comprises the following steps: dividing the inside of the repair part edge into small grids, calculating the number of pixels or other characteristics in the repair part edge for each grid, comparing the characteristics of each grid with a preset threshold value to determine the range of the repair part edge, marking the certain grid as the inside of the repair part edge if the characteristics of the certain grid exceed the threshold value, and adding the areas of all the grid units determined as the inside of the repair part edge to obtain the repair part range.
Scanning a repairing part of the repairing piece through a laser scanner to obtain three-dimensional point cloud data, carrying out surface reconstruction on the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a three-dimensional virtual model through surface fitting or triangular mesh reconstruction; in the three-dimensional virtual model, selecting a region of a repairing part based on the range of the repairing part, determining a measuring surface, measuring the vertical distance from the measuring surface to a reference surface on the selected measuring surface, and recording the vertical distance as the total spraying thickness, wherein the measuring surface is the plane with the farthest distance from the repairing part to the reference surface, the reference surface is the peripheral surface of the repairing part, a thickness threshold is preset, layering is carried out on the three-dimensional virtual model according to the thickness threshold to obtain layering numbers, the layering numbers are equal to the spraying times, and each layering thickness is taken as the incomplete thickness of the repairing part;
The thickness threshold is obtained by the optimal spraying effect in the spraying experiment, and the optimal spraying effect is obtained by related personnel in the spraying experiment;
the calculation formula of the layering number is as follows: the total spraying thickness is divided by the thickness threshold value to obtain multiple, if the multiple is integral, the multiple is the number of layers, and if the multiple is not integral, 1 is added as the number of layers on the basis of the multiple.
For example, if the total spraying thickness is 5mm, the thickness threshold is 1mm, the layering number is 5, and the repair part incomplete thickness is 1mm, 1mm respectively;
if the thickness of the repair part is 5.5mm, the thickness threshold is 2mm, the number of layers is 3, and the thickness of the repair part is 2mm, 2mm and 1.5mm respectively.
Calculating the leveling value of the measuring surface in the three-dimensional virtual model by adopting weighted average sum to obtain the leveling value of the surface of the repairing part;
The calculation formula of the surface leveling value of the repairing part is as follows:
，
Wherein, The surface flatness value of the repairing part is indicated,Represents the average roughness of the surface of the repaired portion,Indicating the maximum peak-to-valley height of the repair surface,Representing the height deviation of each measurement point,Indicating the number of measured points of the repair surface,The height of the highest point of the repair part surface is shown,Indicating the height of the lowest point of the repair surface,A weight coefficient indicating the average roughness of the surface of the repair part,A weight coefficient indicating the maximum peak-to-valley height of the repair part surface,；
Specifically, the leveling value of the surface of the repair part can be more accurately estimated by adopting weighted average and calculating the leveling value of the measurement surface in the three-dimensional virtual model, and the weighted average can take importance of different areas into consideration and weight according to the contribution degree of the leveling value, thereby improving accuracy.
According to the embodiment, by collecting the parameter data of the spraying equipment, including the spraying flow rate and the spraying distance, the influence of different parameters on the spraying of the paint can be known, and data support is provided for the optimization of the follow-up spraying process; the temperature, the humidity, the air flow rate and the air granularity of the environmental parameter data are collected, so that the coating environment is controlled, the coating quality is improved, and the influence of environmental factors on the coating process is reduced; the state of the repairing part can be comprehensively known through the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in the characteristic data of the repairing part, so that a basis is provided for subsequent repairing work; the spraying flow rate of the coating can be accurately obtained through a calculation formula of the spraying flow rate, so that the control of the spraying amount of the coating is facilitated, and the uniformity and the stability of spraying are improved; the leveling value of the surface of the repairing part can be quantitatively evaluated through a leveling value calculation formula, so that a proper spraying equipment parameter set can be conveniently output.
Example 2
Referring to fig. 1 to 2, the method for controlling industrial equipment based on the internet of things in this embodiment includes:
S2, training a machine learning model according to historical data of the spraying equipment, regulating and controlling the spraying equipment through a parameter set of the spraying equipment output by the machine learning model, comprising the steps of,
Taking a spraying equipment parameter set in the historical data of the spraying equipment as a sample set;
Numerical numbering is carried out on the parameter set of the spraying equipment;
Respectively constructing a first characteristic vector P1 and a second characteristic vector P2 from a repair piece characteristic data set and an environment parameter set in historical data of spraying equipment, defining an input layer and an output layer by using TensorFlow, constructing a machine learning frame, taking the first characteristic vector P1 and the second characteristic vector P2 as input layer data, and taking the number of the parameter set of the spraying equipment as output layer data;
Dividing the sample set into a training set and a testing set, constructing a machine learning model, training the machine learning model to obtain the machine learning model, testing the initially constructed machine learning model by using the testing set, and outputting the machine learning model conforming to the preset accuracy;
the machine learning model is one of a logistic regression model, a decision tree, and a random forest or neural network model.
Meets the requirements of preset precision:
Has the following components Test sample, for the firstSamples are set as predictive valueThe actual value isThe average absolute error is:
，
Wherein, As an average of the absolute error of the values,Representing the error between the predicted value and the actual value, and presetting the maximum average absolute error asIf (3)The prediction precision of the model is considered to meet the requirements, otherwise, the prediction precision of the model is considered to be not met;
inputting the current environment parameter set and the current repair feature data set into a machine learning model, obtaining a spraying equipment parameter set number output by the machine learning model, taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set, wherein the method comprises the following steps of:
collecting the ambient temperature, the ambient humidity, the air flow rate and the air granularity in real time as a current ambient parameter set;
collecting the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in real time as a characteristic data set of the current repairing part;
inputting the current environment parameter set and the current repair feature data set into a trained machine learning model to obtain a spraying equipment parameter set number output by the machine learning model;
and taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set.
S3, repairing the repair piece through the regulated and controlled parameters of the spraying equipment, judging whether the repair piece reaches the expected repairing thickness, if so, not regulating and controlling the spraying equipment, and if not, continuing to regulate and control the spraying equipment, wherein the method comprises the steps of,
Spraying and repairing the repairing piece through the regulated spraying equipment parameters, and rescanning the repairing part through a laser scanner after each spraying is completed, so as to update the three-dimensional virtual model to obtain the latest three-dimensional virtual model;
judging whether the last spraying thickness reaches an expected repairing thickness or not according to the latest three-dimensional virtual model, wherein the expected repairing thickness is the incomplete thickness of the last sprayed repairing part;
The mode for judging whether the last spraying thickness reaches the expected repair thickness is as follows: whether the difference value of the total spraying thickness of the latest three-dimensional virtual model and the previous three-dimensional virtual model is the same as the expected repairing thickness or not;
If so, the parameters of the spraying equipment are not required to be regulated and controlled, otherwise, the parameters of the spraying equipment are regulated and controlled according to the latest three-dimensional virtual model until the repair is completed;
The process for regulating and controlling the parameters of the spraying equipment according to the latest three-dimensional virtual model comprises the following steps:
The difference value can be positive number or negative number, the difference value and the incomplete thickness of the next repairing part are added to obtain the incomplete thickness of the new repairing part, the incomplete thickness of the new repairing part is input into a machine learning model to obtain new spraying equipment parameters, and the spraying equipment is regulated and controlled according to the new spraying equipment parameters until the repairing is completed.
When repairing the repairing part, the repairing part is required to be pretreated, the pretreatment comprises removal of oil stains, dust and particles on the surface, filling of deeper pits and cracks and cleaning of the edge of the repairing part, and the repairing part is used for ensuring the stability of the edge of the repairing part and avoiding the conditions of warping, swelling and excessive unevenness of the edge of the repairing part. The ambient temperature, ambient humidity, air flow rate and air granularity in the ambient parameter set can all be controlled in the repair shop.
According to the embodiment, the machine learning model is trained according to the historical data of the spraying equipment by collecting the historical data of the spraying equipment of the same spraying raw material, so that the corresponding parameter set number of the spraying equipment can be output, the spraying equipment can be regulated and controlled according to the parameter of the spraying equipment, when the repairing part is repaired, the repairing part can be precisely sprayed, the incomplete thickness of the repairing part can be precisely repaired, and the repairing quality is higher.
The spraying flow rate, the spraying pressure, the descending amount of the spraying coating, the spraying time and the spraying distance are collected in the parameter set of the spraying equipment, so that the spraying flow rate can be accurately controlled, and the stable spraying thickness is formed conveniently; the spraying effect can be optimized by collecting the environmental temperature, the environmental humidity, the air flow rate and the air granularity in the environmental parameter set; the proper ambient temperature and humidity are beneficial to ensuring the uniformity and adhesiveness of the coating in the spraying process and reducing the spraying defects caused by environmental factors; the state of the repairing part can be comprehensively known through the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in the characteristic data of the repairing part, so that a basis is provided for subsequent repairing work; the spraying flow rate of the coating can be accurately obtained through a calculation formula of the spraying flow rate, so that the control of the spraying amount of the coating is facilitated, and the uniformity and the stability of spraying are improved; the leveling value of the surface of the repairing part can be quantitatively evaluated through a leveling value calculation formula, so that a proper spraying equipment parameter set can be conveniently output; through the spraying equipment historical data of gathering same spraying raw materials, training machine learning model according to spraying equipment historical data to can export the spraying equipment parameter set serial number that corresponds, be convenient for regulate and control spraying equipment according to spraying equipment parameter, avoid the manual work to need regulate and control spraying equipment parameter and manual work loaded down with trivial details of regulation and control, thereby when repairing repair the portion, can carry out accurate spraying to it, repair the incomplete thickness of repair portion that can be accurate, repair the quality is higher.
The basic principles of the present application have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (10)
1. An industrial equipment regulation and control method based on the Internet of things is characterized by comprising the following steps of,
S1: collecting historical data of spraying equipment of the same spraying raw material, wherein the historical data of the spraying equipment comprise a parameter set of the spraying equipment, an environmental parameter set and a characteristic data set of a repairing piece;
S2: training a machine learning model according to historical data of the spraying equipment, inputting a current environment parameter set and a current repair piece characteristic data set into the machine learning model, obtaining a spraying equipment parameter set number output by the machine learning model, taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as a current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set;
S3: and repairing the repair piece through the regulated spraying equipment, judging whether the repair piece reaches the expected repair thickness, if so, not regulating the spraying equipment, and if not, continuing regulating the spraying equipment.
2. The method for controlling industrial equipment based on the Internet of things according to claim 1, wherein in the step S1,
The spraying equipment parameter set comprises a spraying flow rate and a spraying distance;
the environmental parameter set includes an ambient temperature, an ambient humidity, an air flow rate, and an air granularity;
The repair feature data set includes repair surface finish values, repair incomplete thickness, and repair scope.
3. The method for controlling industrial equipment based on the internet of things according to claim 2, wherein the step of obtaining the spraying flow rate and the spraying distance in the spraying equipment parameter set comprises the steps of,
The method comprises the steps of installing an infrared distance measuring device, a flow sensor, a time sensor and a pressure sensor on spraying equipment;
The flow sensor, the time sensor and the pressure sensor are used for obtaining the descending amount, the spraying time and the spraying pressure of the spraying coating, and the spraying flow rate is obtained based on the descending amount, the spraying time and the spraying pressure of the spraying coating, so that the calculation formula of the spraying flow rate is as follows:
，
Wherein, For spray flow rate,For spraying pressure,For the descending amount of the spray coating material,The spraying time is;
Acquiring the radial distance between the front center point of the nozzle on the spraying equipment and the repairing part on the repairing piece, and marking the radial distance as the spraying distance;
the spraying flow rate and the spraying distance of each repair are taken as one spraying equipment parameter data.
4. The method for controlling industrial equipment based on the internet of things according to claim 2, wherein the step of acquiring the ambient temperature, the ambient humidity, the air flow rate and the air granularity in the ambient parameter set comprises,
Installing a temperature sensor around the spraying equipment to obtain the ambient temperature;
Installing humidity sensors around the spraying equipment to obtain the ambient humidity;
Installing a wind speed sensor around the spraying equipment to obtain the air flow rate;
Installing particle sensors around the spraying equipment to obtain air granularity;
The ambient temperature, ambient humidity, air flow rate and air granularity of each repair are taken as one environmental parameter data.
5. The method according to claim 2, wherein the step of obtaining the repair part surface evenness value, repair part incomplete thickness, and repair part range in the repair part feature data set comprises,
Shooting the repairing part through the image pickup equipment to obtain an original image, converting the original image into a gray image, preprocessing the original image by adopting Gaussian smoothing, improving a Laplacian operator through a weight function, performing edge detection on the original image by improving the Laplacian operator, and obtaining the range of the repairing part through any one of a Monte Carlo method and a grid method;
Scanning a repairing part of the repairing piece through a laser scanner to obtain three-dimensional point cloud data, carrying out surface reconstruction on the three-dimensional point cloud data, and converting the three-dimensional point cloud data into a three-dimensional virtual model through surface fitting or triangular mesh reconstruction; selecting a region of the repair part based on the repair part range in the three-dimensional virtual model, determining a measuring surface, measuring the vertical distance from the measuring surface to a reference surface on the selected measuring surface, and recording the vertical distance as the total spraying thickness; presetting a thickness threshold, layering the three-dimensional virtual model according to the thickness threshold to obtain layering numbers, wherein the layering numbers are equal to the spraying times, and taking each layering thickness as the incomplete thickness of the repairing part;
Calculating the leveling value of the measuring surface in the three-dimensional virtual model by adopting weighted average sum to obtain the leveling value of the surface of the repairing part;
the repair part surface flatness value, repair part incomplete thickness and repair part range of each repair are taken as a repair part characteristic data set.
6. The method for industrial equipment regulation and control based on the Internet of things according to claim 5, wherein the Gaussian smoothing formula is as follows,
，
Wherein,The value of the two-dimensional Gaussian function is simply called a kernel function; /(I)Is the standard deviation of Gaussian distribution,Is the bottom of natural logarithm,Is the circumference ratio,AndRepresenting the variables in the gaussian function, representing the horizontal and vertical positions of the pixels in the original image, respectively.
7. The method according to claim 5, wherein a weight function is preset in the improved Laplacian operator, and the formula is,
，
Wherein,Is a weight valueRepresenting pixel coordinates in the original image,Is the horizontal position of the pixel,Is the vertical position of the pixel; /(I)AndRepresenting gray values inside and outside the edge, respectively,To adjust parameters;
The formula of the modified Laplacian operator is,
WhereinExpressed in coordinatesA second derivative of the position, namely a response value of the Laplacian operator; /(I)Representing the original image at coordinatesGray values at the positions, namely pixel values of the original image; /(I)、、、Respectively represent the original image at coordinates、、、Gray values at, i.e. adjacent pixel values of the original image,Representing the original image at coordinatesFour times the gray value at the point, for approximately calculating the response value of the Laplacian operator.
8. The industrial equipment regulation and control method based on the internet of things according to claim 5, wherein the calculation formula of the surface leveling value of the repairing part is:
，
Wherein, Representing the surface flatness value of the repaired portion,Represents the average roughness of the surface of the repaired portion,Representing the maximum peak-to-valley height of the repair surface,Representing the height deviation of each measurement point,Representing the number of measurement points on the surface of the repair part,Representing the height of the highest point of the repair part surface,Representing the height of the lowest point of the repair part surface,Weight coefficient representing average roughness of repair part surface,A weight coefficient indicating the maximum peak-to-valley height of the repair surface.
9. The method according to claim 1, wherein in S2, the step of training a machine learning model based on historical data of the spraying equipment comprises,
Taking a spraying equipment parameter set in the historical data of the spraying equipment as a sample set;
Numerical numbering is carried out on the parameter set of the spraying equipment;
Respectively constructing a first characteristic vector P1 and a second characteristic vector P2 from a repair piece characteristic data set and an environment parameter set in historical data of spraying equipment, defining an input layer and an output layer by using TensorFlow, constructing a machine learning frame, taking the first characteristic vector P1 and the second characteristic vector P2 as input layer data, and taking the number of the parameter set of the spraying equipment as output layer data;
Dividing the sample set into a training set and a testing set, constructing a machine learning model, training the machine learning model to obtain the machine learning model, testing the initially constructed machine learning model by using the testing set, and outputting the machine learning model conforming to the preset accuracy;
inputting the current environment parameter set and the current repair feature data set into a machine learning model, obtaining a spraying equipment parameter set number output by the machine learning model, taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set, wherein the method comprises the following steps of:
collecting the ambient temperature, the ambient humidity, the air flow rate and the air granularity in real time as a current ambient parameter set;
collecting the surface leveling value of the repairing part, the incomplete thickness of the repairing part and the range of the repairing part in real time as a characteristic data set of the current repairing part;
inputting the current environment parameter set and the current repair feature data set into a trained machine learning model to obtain a spraying equipment parameter set number output by the machine learning model;
and taking the spraying equipment parameter set corresponding to the spraying equipment parameter set number as the current spraying equipment parameter set, and regulating and controlling the spraying equipment according to the current spraying equipment parameter set.
10. The method for controlling industrial equipment based on the internet of things according to claim 1, wherein in S3, the repair part is repaired by the parameters of the spraying equipment after the control, and whether the repair part reaches the expected repair thickness is judged, if yes, the spraying equipment is not required to be controlled, and if not, the step of controlling the spraying equipment is continued, including,
Spraying and repairing the repairing piece through the regulated spraying equipment parameters, and rescanning the repairing part through a laser scanner after each spraying is completed, so as to update the three-dimensional virtual model to obtain the latest three-dimensional virtual model;
judging whether the last spraying thickness reaches an expected repairing thickness or not according to the latest three-dimensional virtual model, wherein the expected repairing thickness is the incomplete thickness of the last sprayed repairing part;
If so, the parameters of the spraying equipment are not required to be regulated and controlled, and if not, the parameters of the spraying equipment are regulated and controlled according to the latest three-dimensional virtual model until the repair is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410383958.7A CN117970818B (en) | 2024-04-01 | 2024-04-01 | Industrial equipment regulation and control method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410383958.7A CN117970818B (en) | 2024-04-01 | 2024-04-01 | Industrial equipment regulation and control method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117970818A true CN117970818A (en) | 2024-05-03 |
| CN117970818B CN117970818B (en) | 2024-05-31 |
Family
ID=90864935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410383958.7A Active CN117970818B (en) | 2024-04-01 | 2024-04-01 | Industrial equipment regulation and control method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117970818B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118327298A (en) * | 2024-06-13 | 2024-07-12 | 中国电建集团西北勘测设计研究院有限公司 | Construction device and method for self-spraying type flexible concrete sealing structure |
| CN118601247A (en) * | 2024-05-28 | 2024-09-06 | 广州番禺职业技术学院 | One-step spraying method, system and spraying robot for indoor walls |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19936146A1 (en) * | 1999-07-31 | 2001-02-01 | Abb Research Ltd | Method for determining the layer thickness distribution in a lacquer layer |
| DE10219743A1 (en) * | 2002-05-02 | 2003-11-13 | Abb Patent Gmbh | Determining coating thickness distribution in paint coating produced by spray device involves computing rotating Gaussian bell curve as phenomenological model of quasi-three-dimensional spray image |
| AT519277A1 (en) * | 2016-11-03 | 2018-05-15 | Primetals Technologies Austria GmbH | Casting and rolling plant |
| CN110955147A (en) * | 2019-12-16 | 2020-04-03 | 泉州华中科技大学智能制造研究院 | Sizing process parameter optimization method |
| US20200391241A1 (en) * | 2019-06-17 | 2020-12-17 | Siemens Industry Software Ltd. | Method and system for generating a robotic program for industrial coating |
| CN113160228A (en) * | 2021-05-27 | 2021-07-23 | 河南科技大学 | Computer vision auxiliary method for intelligent spraying equipment for factory steel structure |
| CN115238581A (en) * | 2022-07-25 | 2022-10-25 | 苏州大学 | Method for predicting HVOF coating performance optimization spraying parameters based on HML |
| CN116306311A (en) * | 2023-04-06 | 2023-06-23 | 江苏海洋大学 | Automatic spraying equipment control method and system |
| CN116377370A (en) * | 2023-03-20 | 2023-07-04 | 重庆四态益联科技有限责任公司 | Plasma spraying control system and method based on digital twin |
| CN117740797A (en) * | 2023-11-05 | 2024-03-22 | 曹成 | Defect flaw detection method for aluminum alloy |
-
2024
- 2024-04-01 CN CN202410383958.7A patent/CN117970818B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19936146A1 (en) * | 1999-07-31 | 2001-02-01 | Abb Research Ltd | Method for determining the layer thickness distribution in a lacquer layer |
| DE10219743A1 (en) * | 2002-05-02 | 2003-11-13 | Abb Patent Gmbh | Determining coating thickness distribution in paint coating produced by spray device involves computing rotating Gaussian bell curve as phenomenological model of quasi-three-dimensional spray image |
| AT519277A1 (en) * | 2016-11-03 | 2018-05-15 | Primetals Technologies Austria GmbH | Casting and rolling plant |
| US20200391241A1 (en) * | 2019-06-17 | 2020-12-17 | Siemens Industry Software Ltd. | Method and system for generating a robotic program for industrial coating |
| CN110955147A (en) * | 2019-12-16 | 2020-04-03 | 泉州华中科技大学智能制造研究院 | Sizing process parameter optimization method |
| CN113160228A (en) * | 2021-05-27 | 2021-07-23 | 河南科技大学 | Computer vision auxiliary method for intelligent spraying equipment for factory steel structure |
| CN115238581A (en) * | 2022-07-25 | 2022-10-25 | 苏州大学 | Method for predicting HVOF coating performance optimization spraying parameters based on HML |
| CN116377370A (en) * | 2023-03-20 | 2023-07-04 | 重庆四态益联科技有限责任公司 | Plasma spraying control system and method based on digital twin |
| CN116306311A (en) * | 2023-04-06 | 2023-06-23 | 江苏海洋大学 | Automatic spraying equipment control method and system |
| CN117740797A (en) * | 2023-11-05 | 2024-03-22 | 曹成 | Defect flaw detection method for aluminum alloy |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118601247A (en) * | 2024-05-28 | 2024-09-06 | 广州番禺职业技术学院 | One-step spraying method, system and spraying robot for indoor walls |
| CN118327298A (en) * | 2024-06-13 | 2024-07-12 | 中国电建集团西北勘测设计研究院有限公司 | Construction device and method for self-spraying type flexible concrete sealing structure |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117970818B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117970818B (en) | Industrial equipment regulation and control method based on Internet of things | |
| CN118134062B (en) | Numerical control machine tool casting quality tracking system | |
| CN117974665B (en) | Metal mold on-line detection method and equipment based on computer vision | |
| CN113781585B (en) | Online detection method and system for surface defects of additive manufactured parts | |
| CN106881462B (en) | An online detection and optimization system for laser selective melting forming defects | |
| CN102253049B (en) | Method for accurately detecting surface quality on line in production process of band steel | |
| CN117930750B (en) | Coating machine control method and coating machine system | |
| WO2016201947A1 (en) | Method for automated detection of defects in cast wheel products | |
| CN118566241B (en) | Artificial intelligence-based automobile interior part noise reducer spraying defect detection method | |
| CN115906557B (en) | An intelligent detection method for determining forming defects by contour deviation of stamping blank | |
| CN110789128A (en) | A system and method for predicting and controlling the forming quality of additively manufactured parts | |
| CN119457154B (en) | A fast metal printing system and method based on machine vision feedback | |
| CN118777305A (en) | A real-time detection method and system for casting surface defects | |
| CN119717546B (en) | Automatic coating method of titanium anode and related equipment | |
| CN120013925A (en) | A forging flaw detection method and system based on real-time image recognition | |
| CN119148659A (en) | Vamp spraying control method and vamp spraying control system for intelligent shoemaking production line | |
| CN115601313A (en) | Visual monitoring management system for tempered glass production process | |
| CN119495587B (en) | Wafer film defect detection system and method | |
| CN119067976B (en) | A 3D printing anomaly detection and early warning method based on machine vision | |
| CN120196063A (en) | Automatic control method and system for gluing of automobile damping bushing | |
| CN120495224B (en) | Image Recognition-Based Method for Detecting Printing Accuracy of Color and Pattern Designs on Color-Coated Steel Sheets | |
| CN120696657B (en) | Methods for detecting and repairing welding defects in 1000MPa grade hydroelectric steel | |
| CN120850612B (en) | Seal ring life prediction method, system and storage medium | |
| CN119666862A (en) | Defect detection method for HDPE pipe production based on machine vision | |
| CN119126680B (en) | A high-precision cutting machine motion control method based on Z-axis control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |