CN118387952B - Hydraulic particle intelligent separation control method and system - Google Patents
Hydraulic particle intelligent separation control method and system Download PDFInfo
- Publication number
- CN118387952B CN118387952B CN202410487184.2A CN202410487184A CN118387952B CN 118387952 B CN118387952 B CN 118387952B CN 202410487184 A CN202410487184 A CN 202410487184A CN 118387952 B CN118387952 B CN 118387952B
- Authority
- CN
- China
- Prior art keywords
- separation
- sediment
- particle
- floating object
- water body
- 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.)
- Active
Links
- 238000000926 separation method Methods 0.000 title claims abstract description 419
- 239000002245 particle Substances 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000013049 sediment Substances 0.000 claims abstract description 285
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 105
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 239000011164 primary particle Substances 0.000 claims abstract description 18
- 239000011163 secondary particle Substances 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims description 42
- 239000000203 mixture Substances 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 9
- 230000003213 activating effect Effects 0.000 abstract description 6
- 208000034699 Vitreous floaters Diseases 0.000 description 91
- 235000019580 granularity Nutrition 0.000 description 23
- 238000012512 characterization method Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 239000004927 clay Substances 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000011362 coarse particle Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 235000019587 texture Nutrition 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
- G01N15/075—Investigating concentration of particle suspensions by optical means
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/001—Processes for the treatment of water whereby the filtration technique is of importance
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/38—Treatment of water, waste water, or sewage by centrifugal separation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F2301/00—General aspects of water treatment
- C02F2301/08—Multistage treatments, e.g. repetition of the same process step under different conditions
Landscapes
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Hydrology & Water Resources (AREA)
- Environmental & Geological Engineering (AREA)
- Water Supply & Treatment (AREA)
- Organic Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Mechanical Engineering (AREA)
- Separation Of Solids By Using Liquids Or Pneumatic Power (AREA)
Abstract
The invention provides an intelligent hydraulic particle separation control method and system, which relate to the technical field of hydraulic particle separation and comprise the steps of obtaining first water body information when a water body to be separated enters a first detection area of a conveying pipeline; the method comprises the steps of matching in a preset separation standard library to obtain a first separation standard and a second separation standard, wherein the preset separation standard library comprises a preset floater separation standard and a preset sediment separation standard, activating a first separation screen set and a second separation screen set to perform primary particle separation to obtain a first separation result, transmitting the first separation result to a separation assembly to obtain second water body information, obtaining a sediment separation control scheme, controlling a centrifuge to perform secondary particle separation to obtain a second separation result, and transmitting the second separation result to a clean water storage pool as clean water body. The invention solves the technical problems of poor separation effect and low efficiency caused by the lack of effective granularity control and more manual intervention in the particle separation process in the traditional method.
Description
Technical Field
The invention relates to the technical field of hydraulic particle separation, in particular to an intelligent hydraulic particle separation control method and system.
Background
The hydraulic particle separation is mainly applied to environmental protection and water resource management such as sewage treatment, urban pipeline sewer management and the like, can improve water quality, protect ecological environment and improve water resource utilization efficiency, and has some technical problems in the traditional hydraulic particle separation process; on the other hand, conventional hydraulic particle separation often requires manual intervention and adjustment, resulting in complex operations and time and effort consuming.
Disclosure of Invention
The application provides an intelligent hydraulic particle separation control method, which aims to solve the technical problems of poor separation effect and low efficiency caused by the lack of effective particle size control and more manual intervention in the particle separation process of the traditional method.
In view of the above problems, the application provides a hydraulic particle intelligent separation control method and a hydraulic particle intelligent separation control system.
The first aspect of the application discloses a hydraulic particle intelligent separation control method, which is applied to a hydraulic particle intelligent separation device, wherein the hydraulic particle intelligent separation device comprises a conveying pipeline and a separation assembly, the method comprises the steps of obtaining first water body information when a water body to be separated enters a first detection area of the conveying pipeline, wherein the first water body information comprises a floater characteristic and a sediment characteristic, carrying out matching in a preset separation standard library based on the floater characteristic and the sediment characteristic to obtain a first separation standard and a second separation standard, wherein the first separation standard comprises a first separation granularity and the second separation standard comprises a second separation granularity, wherein the preset separation standard library comprises a preset floater separation standard and a preset sediment separation standard, activating a first separation screen set in the first separation area of the conveying pipeline based on the first separation granularity, activating a second separation screen set in the second separation area of the conveying pipeline, carrying out first-stage separation on the water body to be separated based on the floater characteristic and the sediment characteristic, carrying out sediment control on the first separation standard and the sediment characteristic, carrying out sediment separation to obtain sediment separation on the sediment information, carrying out sediment separation in a first separation assembly, carrying out sediment separation to obtain sediment separation on the sediment information, carrying out sediment control on the sediment separation assembly, carrying out sediment separation in the first separation area, carrying out sediment separation control on the sediment separation assembly, and obtaining sediment separation information, carrying out sediment separation on the sediment control on the sediment separation assembly, and obtaining sediment separation information, and carrying out sediment separation on sediment control on sediment separation on a sediment in the first separation assembly, and obtaining sediment separation on a sediment, and conveying the second separation result to a clean water storage pool as a clean water body.
The application discloses a second aspect, which provides an intelligent hydraulic particle separation control system, wherein the system is applied to an intelligent hydraulic particle separation device, the intelligent hydraulic particle separation device comprises a conveying pipeline and a separation assembly, the system is used for the intelligent hydraulic particle separation control method, and the system comprises a first detection module, a second detection module and a third detection module, wherein the first detection module is used for obtaining first water body information when a water body to be separated enters a first detection area of the conveying pipeline, and the first water body information comprises a floater characteristic and a sediment characteristic; the system comprises a separation standard matching module, a standard library description module, a primary particle separation module and a secondary detection module, wherein the separation standard matching module is used for matching in a preset separation standard library based on the characteristics of floaters and the characteristics of sediments to obtain a first separation standard and a second separation standard, the first separation standard comprises a first separation granularity and the second separation standard comprises a second separation granularity, the preset separation standard library is used for the preset separation standard library, the preset separation standard library comprises the preset floaters and the preset sediments, the primary particle separation module is used for activating a first separation screen set in a first separation area of a conveying pipeline based on the first separation granularity and a second separation screen set in a second separation area of the conveying pipeline based on the second separation granularity to perform primary particle separation on a water body to be separated to obtain a first separation result, the second detection module is used for conveying the first separation result to a separation assembly and obtaining second water body information through a second detection area of the separation assembly, the second water body information comprises sediment characteristics, a separation control analysis module, a secondary particle separation module and a separation control analysis module, wherein the separation control analysis module is used for carrying out sediment separation control analysis based on the sediment characteristics to obtain a sediment separation control scheme, and the secondary particle separation module is used for controlling a centrifuge of the separation assembly to carry out secondary particle separation on the first separation result based on the sediment separation control scheme to obtain a second separation result, and the second separation result is used as a clean water body to be transmitted to a clean water storage pool.
In a third aspect of the present disclosure, there is provided a computer device comprising a memory storing a computer program and a processor implementing any of the steps of the first aspect of the present disclosure when the computer program is executed by the processor.
In a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs any of the steps of the first aspect of the present disclosure.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The method comprises the steps of automatically identifying floating matters and sediments in a water body to be separated, improving the automation degree of the separation process, improving the separation efficiency and accuracy, matching the characteristics of the floating matters and the sediments in a preset separation standard library, obtaining a first separation standard and a second separation standard, carrying out primary particle separation of the floating matters and the sediments, realizing the accurate separation of different particles, improving the separation effect and stability, obtaining the characteristics of sediment in the second water body information, generating a sediment separation control scheme, controlling a centrifugal machine to carry out secondary particle separation, realizing the effective treatment and separation of sediment, and improving the sediment treatment efficiency and accuracy. In summary, the hydraulic particle intelligent separation control method effectively solves the technical problems existing in the traditional hydraulic particle separation process through means of automatic identification, multi-stage particle size separation and the like, and achieves the technical effects of improving the separation efficiency, stability and accuracy.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of a hydraulic particle intelligent separation control method provided by an embodiment of the application;
FIG. 2 is a schematic structural diagram of a hydraulic particle intelligent separation control system according to an embodiment of the present application;
Fig. 3 is an internal structure diagram of a computer device according to an embodiment of the present application.
Reference numerals illustrate the first detection module 10, the separation criteria matching module 20, the criteria library illustration module 30, the primary particle separation module 40, the second detection module 50, the separation control analysis module 60, and the secondary particle separation module 70.
Detailed Description
The embodiment of the application solves the technical problems of poor separation effect and low efficiency caused by the lack of effective granularity control and more manual intervention in the particle separation process of the traditional method by providing the hydraulic particle intelligent separation control method.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, an embodiment of the present application provides a hydraulic particle intelligent separation control method, where the method is applied to a hydraulic particle intelligent separation device, and the hydraulic particle intelligent separation device includes a conveying pipeline and a separation component, and the method includes:
When a water body to be separated enters a first detection area of the conveying pipeline, first water body information is obtained, wherein the first water body information comprises a floater characteristic and a sediment characteristic;
The hydraulic particle intelligent separation control method provided by the embodiment of the application is applied to a hydraulic particle intelligent separation device, the hydraulic particle intelligent separation device comprises a conveying pipeline and a separation assembly, wherein the conveying pipeline is a pipeline for a water body to be treated to pass through, the conveying pipeline comprises a first detection area, a first separation area and a second separation area, the conveying pipeline conveys the water body from an input end to an output end in the process and carries out large particle separation treatment on the water body in the middle, and the separation assembly is a device for separating sediment in the water body and comprises a centrifuge and other equipment for separating small particle sediment in the water body so as to generate clean water body.
Firstly, a water body to be separated is guided to a set first detection area through a conveying pipeline, the first detection area comprises an image acquisition device and a laser sounding device, the image acquisition device is used for acquiring images of the surface of the water body, the image acquisition result is subjected to floater characteristic analysis to obtain floater characteristics, the floater characteristics comprise floater type characteristics, floater size characteristics and floater quantity characteristics, the laser sounding device is used for performing laser sounding on the bottom of the water body to be separated, and the sediment characteristics are obtained based on laser sounding data, wherein the sediment characteristics comprise sediment type characteristics, sediment size characteristics and sediment quantity characteristics. And integrating the obtained floater characteristics and the sediment characteristics to form complete first water body information, and providing data support for subsequent processing steps.
Based on the floater characteristics and the sediment characteristics, matching in a preset separation standard library to obtain a first separation standard and a second separation standard, wherein the first separation standard comprises a first separation granularity, and the second separation standard comprises a second separation granularity;
The library of preset separation criteria comprises already set separation criteria corresponding to different float characteristics and sediment characteristics, which library can be built up from experimental or historical data, including the separation criteria settings in each case.
According to the obtained float characteristics and sediment characteristics, the standards matched with the float characteristics are found from a preset separation standard library, the float characteristics comprise float type characteristics, float size characteristics and float quantity characteristics, the float characteristics are matched with the preset float separation standards, for example, a plurality of first separation granularities are matched according to a plurality of size intervals of the floats, and the matched screen sizes are selected. The sediment characteristics include sediment type characteristics, sediment size characteristics, and sediment quantity characteristics, and as such, a plurality of second separation granularities are obtained by matching the sediment characteristics with a predetermined sediment separation standard. Thus, the characteristics of the floating matters and the sediments can be comprehensively considered, and the separation standard which is most suitable for the current situation can be determined.
Wherein the preset separation standard library comprises preset floater separation standards and preset sediment separation standards;
the preset separation criteria library comprises two main parts, namely a preset float separation criteria and a preset sediment separation criteria, which respectively set a series of criteria for the separation of floats and sediment, so that the system can perform effective particle separation according to the characteristics of the water body.
The preset floater separation standard comprises separation standards set for various characteristics of the floaters, the standards are based on the characteristics of the types, the sizes, the shapes, the densities and the like of the floaters, and the preset floater separation standard can be obtained according to experimental data and historical data so as to ensure that the system can effectively separate the floaters from the water body.
The preset sediment separation standard comprises separation standards set for various characteristics of sediment, the standards are based on the characteristics of the type, the size, the concentration, the weight and the like of the sediment, and the preset sediment separation standard can be obtained according to experimental data and historical data so as to ensure that the system can effectively separate the sediment from the water body.
Through the preset floater separation standard and sediment separation standard, a proper separation scheme can be rapidly determined according to the detected characteristics in the water body in actual operation, so that efficient particle separation is realized.
Activating a first separation screen set in a first separation area of the conveying pipeline based on the first separation granularity, and activating a second separation screen set in a second separation area of the conveying pipeline based on the second separation granularity, so as to perform primary particle separation on the water body to be separated, and obtain a first separation result;
According to a first separation granularity in a determined first separation criterion, a first collection of separation screens is activated in a first separation region of the transfer conduit, the first collection of separation screens comprising a series of screens set according to the criterion, the apertures of the screens being capable of screening according to the size of the float. Likewise, according to a second separation particle size in the determined first separation criterion, a second collection of separation screens is activated in a second separation zone of the transfer conduit, the second collection of separation screens comprising a series of screens set according to the criterion, the apertures of these screens being capable of screening according to the size of the sediment
The water body to be separated passes through a conveying pipeline, and passes through a first separation area and a second separation area, wherein the first separation screen set and the second separation screen set separate particles in the water body according to the size of the particles according to the specific sieve mesh size of the first separation screen set and the second separation screen set, so that the particles are separated, and a first separation result is obtained after treatment.
Further, performing primary particle separation on the water body to be separated to obtain a first separation result, including:
Generating a first screen selection scheme based on the first separation granularity, wherein the first screen selection scheme comprises a first screen number and a first screen mesh size set;
selecting a screen based on the first screen selection scheme to obtain a first collection of separation screens;
generating a second screen selection scheme based on the second separation granularity, wherein the second screen selection scheme comprises a second screen number and a second screen mesh size set;
Selecting a screen based on the second screen selection scheme to obtain a second collection of separation screens;
and carrying out primary particle separation of the water body to be separated by the first separation screen mesh collection and the second separation screen mesh collection to obtain a first separation result.
Transmitting the first separation result to a separation assembly, and obtaining second water body information through a second detection area of the separation assembly, wherein the second water body information comprises sediment characteristics;
The first separation result is transmitted to the separation assembly, and is detected through a second detection area of the separation assembly, wherein the second detection area comprises a device for detecting sediment, such as a component detection device, a weight detection device and the like, and the first separation result is detected in the second detection area to obtain second water body information, wherein the second water body information comprises sediment characteristics including sediment particle composition characteristics, sediment particle concentration characteristics and sediment particle weight characteristics.
Based on the sediment characteristics, sediment separation control analysis is carried out, and a sediment separation control scheme is obtained;
The obtained characteristics of the sediment are used for carrying out sediment separation control analysis, for example, the distribution condition of the particle size in the sediment is analyzed to determine proper separation parameters, different sediment treatment schemes are evaluated, different control parameters are adopted to determine the optimal separation control scheme, the obtained scheme comprises parameter setting of a separation device so as to realize effective separation and treatment of the sediment, and a specific sediment separation control analysis method is described in detail in the following steps and is only mentioned briefly herein.
And controlling a centrifugal machine of the separation assembly to perform secondary particle separation on the first separation result based on the sediment separation control scheme to obtain a second separation result, and transmitting the second separation result as a clean water body to a clean water storage pool.
And controlling a centrifugal machine in the separation assembly according to the parameters determined in the sediment separation control scheme, and adjusting parameters such as rotating speed, inclination angle and the like by the centrifugal machine according to the preset control scheme so as to realize further separation of sediment in the first separation result. In the separation process, sediment is further separated according to the action of centrifugal force to form a second separation result, and the obtained second separation result is a relatively purer water body and does not contain heavier sediment and other particles. The second separation result is transferred to a clean water storage tank for further processing or direct supply to the sector requiring clean water.
Further, when a water body to be separated enters a first detection area of the conveying pipeline, first water body information is obtained, wherein the first water body information comprises a floater characteristic and a sediment characteristic, and the method comprises the following steps:
The first detection area comprises an image acquisition device and a laser sounding device;
The image acquisition device is used for acquiring images of the surface of the water body to be separated, so that an image acquisition result is obtained;
performing floater characteristic analysis on the image acquisition result to obtain floater characteristics, wherein the floater characteristics comprise floater type characteristics, floater size characteristics and floater quantity characteristics;
Performing laser sounding on the bottom of the water body to be separated through the laser sounding device to obtain laser sounding data;
The sediment characterization is obtained based on the laser sounding data, wherein the sediment characterization includes a sediment type characterization, a sediment size characterization, a sediment quantity characterization.
The first detection area is used for detecting the water body to be separated and comprises an image acquisition device and a laser sounding device, wherein the devices are arranged in a conveying pipeline or at fixed positions beside the pipeline. The laser sounding device is used for acquiring laser sounding data of sediment at the bottom of the water body.
The method comprises the steps of carrying out image acquisition on the surface of the water body to be separated through an image acquisition device, including shooting a picture or recording a video of the surface of the water body so as to acquire information such as distribution condition, shape, size and the like of floaters in the water body, and forming an image acquisition result.
The image acquisition results are analyzed to identify and extract the float features in the image, including the application of image processing techniques such as edge detection, feature extraction, etc., to separate the float information from the image. The floater characteristics comprise floater type characteristics, floater size characteristics and floater quantity characteristics, wherein the floater type characteristics comprise plastics, wood, fallen leaves and the like, the floater size characteristics comprise the length, the width, the area and the like of the floaters, and the floater quantity characteristics are used for calculating the quantity of the floaters and reflecting the density and the distribution condition of the floaters in the water body.
The laser sounding device emits laser beams to the water surface, then reflects the laser beams back, detects sediment, and comprises the steps of obtaining sediment types such as sediment, sludge and the like, estimating the size or the shape of the sediment, and counting the quantity of sediment at the bottom. And obtaining characteristic information of the bottom sediment through analysis, wherein the characteristic information comprises characteristics such as types, sizes, quantity and the like.
Further, performing a float feature analysis on the image acquisition result to obtain the float feature, including:
detecting the edges of the floaters according to the image acquisition result to obtain a plurality of floaters images, wherein the floaters images correspond to a plurality of floaters areas;
Obtaining the float size feature, the float quantity feature based on the plurality of float areas;
Inputting the plurality of float images into a float type identifier, outputting a plurality of float types as the float type features;
The construction process of the floater type identifier is as follows:
acquiring a sample floater image characteristic set according to the floater processing record;
carrying out float type marking on the sample float image feature set to obtain a sample float type set;
Based on a convolutional neural network, the sample floater image characteristic set is used as input data, the sample floater type set is used as label data, and the floater type identifier is obtained through training.
The method comprises the steps of carrying out floating object edge detection on an image by using an image processing algorithm, identifying edges of floating objects in the image by using an edge detection algorithm, identifying outlines of the floating objects by using the edge detection, dividing the image into a plurality of floating object areas, extracting the areas from an original image by using each floating object area corresponding to one floating object, and generating a corresponding floating object image.
For each float area, the size characteristics such as length, width, area and the like are calculated by measuring the bounding box of the float area, and the number characteristics of the floats are obtained by counting the number of the float areas, wherein each float area corresponds to one float, so that the number of the float areas is the number of the floats.
The float type identifier is a trained deep learning model for identifying the float type in an image, which is constructed based on Convolutional Neural Network (CNN) or other technique, and is capable of extracting features from the image and matching them to known float types. A plurality of float images are taken as input, the float type identifier is input one by one for identification, each float image corresponds to one float, the type of each float is obtained by respectively identifying the images, and the identification results are taken as float type characteristics and are used for describing the type of each float.
The construction process of the floater type identifier is as follows:
a series of sample float image data is obtained from previous float treatment recordings, the sample images containing floats of various types and shapes, representative of various conditions of floats treated in the past. Each sample float image is marked to determine its float type. After marking, each sample float image is associated with a particular float type, forming a sample float type set.
The Convolutional Neural Network (CNN) is a deep learning model, is suitable for image recognition tasks, is formed by alternately stacking a plurality of convolutional layers and pooling layers, and can effectively extract the characteristics of an image.
The method comprises the steps of taking a sample floater image characteristic set as input data, wherein the image characteristics comprise pixel values, color distribution, textures and the like of images, taking a sample floater type set as tag data, wherein the real type of each sample floater is contained, and for each floater image, a corresponding tag is used for representing the real type of the floater.
The prepared input data and label data are input into a CNN model for training, in the training process, the CNN model adjusts model parameters by learning the relation between the input data and the label data, so that the model can accurately predict the type of a floater, in the training process, an optimization algorithm such as gradient descent is utilized to minimize the difference between a prediction result and a real label, after the training is finished, the model is evaluated to ensure that the model has good generalization capability on unseen data, and through the process, a floater type identifier can be trained, and the type of the floater can be accurately predicted according to the characteristics of a floater image.
Further, performing a float edge detection on the image acquisition result to obtain a plurality of float images, including:
graying treatment is carried out on the image acquisition result to obtain a gray value set;
Clustering the gray value sets to obtain a plurality of clusters;
And carrying out connected region analysis based on the clusters to obtain a plurality of floater regions, and carrying out image buckling on the plurality of floater regions to obtain a plurality of floater images.
The graying process is a process of converting a color image into a gray image in which the value range of each pixel is 0 to 255, representing the gray level of the pixel, 0 representing black, and 255 representing white. For a gray image, gray values of each pixel are obtained to form a gray value set, wherein gray value information of all pixels in the image is contained.
The cluster analysis is an unsupervised learning method, and aims to divide samples in a dataset into a plurality of categories, so that samples in the same category have higher similarity, and samples in different categories have larger difference. And taking the gray value set as input data, analyzing the gray value set by using a clustering algorithm, wherein the clustering algorithm divides pixels in the gray value set into a plurality of clusters, each cluster has a specific gray value range, and the pixels in the clusters have similar gray characteristics.
And grouping adjacent pixel points in the image according to the gray values thereof by using a method of connected region analysis to form a plurality of connected regions, wherein each connected region represents one floater region in the image, and the pixels have similar gray characteristics. For each communication area, judging whether the communication area is a floater area according to the characteristics of the gray value, the size, the shape and the like of the pixel, and obtaining a plurality of floater areas.
For each connected region identified as a float region, the corresponding pixel is extracted from the original image to form a new float image, the purpose of which is to separate the float from the original image for subsequent analysis.
Further, based on the silt characteristics, performing silt separation control analysis to obtain a silt separation control scheme, including:
The sediment characteristics comprise sediment particle composition characteristics, sediment particle concentration characteristics and sediment particle weight characteristics;
a sediment treatment record set is called, each sediment treatment record comprises a sample sediment characteristic and a sample sediment separation control decision, wherein the sample sediment characteristic comprises a sample sediment particle composition, a sample sediment particle concentration and a sample sediment particle weight;
Performing sediment characteristic matching on the sediment treatment record set based on the sediment characteristics to obtain a plurality of sample sediment characteristic matching results, wherein the plurality of sample sediment characteristic matching results comprise a plurality of matching coefficients;
And based on the plurality of matching coefficients, carrying out decision extraction on the sediment treatment record set to obtain the sediment separation control scheme.
The composition characteristics of the sediment particles describe the distribution of different particle sizes, shapes and components in the sediment, such as the distribution of coarse particles, fine particles, clay particles, sand particles and other types of particles in the sediment, the concentration characteristics of the sediment particles describe the quantity of the sediment particles contained in the unit volume of water, and the weight characteristics of the sediment particles describe the total mass of the sediment particles contained in the unit volume of water.
The sediment treatment record set is a data set of historical sediment treatment, wherein the past sediment treatment condition is recorded, each record corresponds to one sediment treatment process and contains characteristic information of sample sediment and a current sediment separation control decision. Specifically, each sediment treatment record comprises characteristic information of sample sediment, including characteristics of sample sediment particle composition, sample sediment particle concentration, sample sediment particle weight and the like, and the characteristics describe the property and content of the sediment at the time. Each sediment treatment record also comprises a corresponding sediment separation control decision, which is a treatment scheme formulated according to characteristic information of sediment at the time, and relates to different equipment control parameters.
The characteristics of the current sediment and the characteristics of sample sediment in the sediment treatment record set are matched one by one, the matching process comprises the steps of comparing the characteristics of particle composition, particle concentration, particle weight and the like of the sediment so as to judge the similarity between the characteristics, and for each sample sediment characteristic, a matching coefficient is obtained in the matching process and used for representing the matching degree of the current sediment and the sample sediment.
Comparing the sizes of the plurality of matching coefficients to obtain the largest matching coefficient, wherein a sample corresponding to the matching coefficient is the most similar to the current sediment characteristic, and obtaining a sample sediment separation control decision of the sample as a sediment separation control scheme of the current sediment characteristic so as to realize effective treatment and separation of the current sediment.
Further, based on the sediment characteristics, sediment characteristic matching is performed on the sediment treatment record set, and a plurality of sample sediment characteristic matching results are obtained, including:
carrying out similarity analysis on the composition characteristics of the sediment particles and the composition of the sediment particles of the first sample to obtain a first similarity;
performing similarity analysis on the sediment particle concentration characteristics and the sediment particle concentration of the first sample to obtain a second similarity;
performing similarity analysis on the weight characteristics of the sediment particles and the weight of the sediment particles of the first sample to obtain a third similarity;
and carrying out weighted summation on the first similarity, the second similarity and the third similarity to obtain a first matching coefficient, and adding the first matching coefficient to the plurality of matching coefficients.
Comparing the particle composition characteristics of the current sediment with those of the first sample sediment, calculating the similarity between the particle composition characteristics of the current sediment and the first sample sediment, wherein various methods such as cosine similarity, euclidean distance and the like can be adopted for similarity analysis to determine the similarity between the particle composition characteristics of the current sediment and the first sample sediment, the first similarity is obtained through similarity analysis and used for representing the similarity between the particle composition characteristics of the current sediment and the particle composition characteristics of the first sample sediment, and the higher the similarity value is, the more similar the particle composition characteristics of the current sediment and the particle composition characteristics of the first sample sediment are.
And carrying out similarity analysis on the sediment particle concentration characteristics and the sediment particle concentration of the first sample by the same method, and carrying out similarity analysis on the sediment particle weight characteristics and the sediment particle weight of the first sample to obtain a second similarity and a third similarity.
And aiming at the first similarity, the second similarity and the third similarity, carrying out weighted summation on the first similarity, the second similarity and the third similarity to obtain comprehensive matching coefficients, wherein the weighted summation weights can be set according to actual conditions and specific requirements to represent the importance of each similarity, the comprehensive matching coefficients are first matching coefficients, and the first matching coefficients integrate the information of a plurality of similarities and are used for evaluating the overall similarity degree between current sediment and first sample sediment. And adding the first matching coefficient into the plurality of matching coefficients to comprehensively evaluate the matching degree between the current sediment and the plurality of sample sediment.
In summary, the hydraulic particle intelligent separation control method provided by the embodiment of the application has the following technical effects:
1. By automatically identifying the floaters and the sediments in the water body to be separated, the automation degree of the separation process is improved, and the separation efficiency and accuracy are improved;
2. The characteristics of the floaters and the sediments are matched in a preset separation standard library, so that a first separation standard and a second separation standard are obtained, primary particle separation of the floaters and the sediments is performed, accurate separation of different particles is realized, and the separation effect and stability are improved;
3. By acquiring the sediment characteristics in the second water body information and generating a sediment separation control scheme, the centrifugal machine is controlled to perform secondary particle separation, so that the sediment is effectively treated and separated, and the sediment treatment efficiency and accuracy are improved.
In summary, the hydraulic particle intelligent separation control method effectively solves the technical problems existing in the traditional hydraulic particle separation process through means of automatic identification, multi-stage particle size separation and the like, and achieves the technical effects of improving the separation efficiency, stability and accuracy.
Based on the same inventive concept as the hydraulic particle intelligent separation control method of the foregoing embodiment, as shown in fig. 2, the present application provides a hydraulic particle intelligent separation control system, which is applied to a hydraulic particle intelligent separation device, the hydraulic particle intelligent separation device includes a transmission pipeline, a separation assembly, and the system includes:
The first detection module 10 is configured to obtain first water body information when a water body to be separated enters a first detection area of the conveying pipeline, where the first water body information includes a floater characteristic and a sediment characteristic;
The separation standard matching module 20 is configured to match in a preset separation standard library based on the floater characteristics and the precipitate characteristics, so as to obtain a first separation standard and a second separation standard, where the first separation standard includes a first separation granularity, and the second separation standard includes a second separation granularity;
A standard library specification module 30 for use therein, the preset separation standard library comprising preset float separation standards, preset sediment separation standards;
the primary particle separation module 40 is configured to activate a first separation screen set in a first separation area of the conveying pipeline based on the first separation granularity, activate a second separation screen set in a second separation area of the conveying pipeline based on the second separation granularity, and perform primary particle separation on the water body to be separated to obtain a first separation result;
The second detection module 50 is configured to transmit the first separation result to a separation assembly, and obtain second water body information through a second detection area of the separation assembly, where the second water body information includes sediment characteristics;
The separation control analysis module 60, wherein the separation control analysis module 60 is used for performing a silt separation control analysis based on the silt characteristics to obtain a silt separation control scheme;
And the secondary particle separation module 70 is used for controlling a centrifuge of the separation assembly to perform secondary particle separation on the first separation result based on the sediment separation control scheme to obtain a second separation result, and transmitting the second separation result to a clean water storage pool as a clean water body.
Further, the system also comprises a feature acquisition module for executing the following operation steps:
The first detection area comprises an image acquisition device and a laser sounding device;
The image acquisition device is used for acquiring images of the surface of the water body to be separated, so that an image acquisition result is obtained;
performing floater characteristic analysis on the image acquisition result to obtain floater characteristics, wherein the floater characteristics comprise floater type characteristics, floater size characteristics and floater quantity characteristics;
Performing laser sounding on the bottom of the water body to be separated through the laser sounding device to obtain laser sounding data;
The sediment characterization is obtained based on the laser sounding data, wherein the sediment characterization includes a sediment type characterization, a sediment size characterization, a sediment quantity characterization.
Further, the system also comprises an image analysis module for executing the following operation steps:
detecting the edges of the floaters according to the image acquisition result to obtain a plurality of floaters images, wherein the floaters images correspond to a plurality of floaters areas;
Obtaining the float size feature, the float quantity feature based on the plurality of float areas;
Inputting the plurality of float images into a float type identifier, outputting a plurality of float types as the float type features;
The construction process of the floater type identifier is as follows:
acquiring a sample floater image characteristic set according to the floater processing record;
carrying out float type marking on the sample float image feature set to obtain a sample float type set;
Based on a convolutional neural network, the sample floater image characteristic set is used as input data, the sample floater type set is used as label data, and the floater type identifier is obtained through training.
Further, the system also includes a float image acquisition module to perform the following operational steps:
graying treatment is carried out on the image acquisition result to obtain a gray value set;
Clustering the gray value sets to obtain a plurality of clusters;
And carrying out connected region analysis based on the clusters to obtain a plurality of floater regions, and carrying out image buckling on the plurality of floater regions to obtain a plurality of floater images.
Further, the system further comprises a first separation result acquisition module to execute the following operation steps:
Generating a first screen selection scheme based on the first separation granularity, wherein the first screen selection scheme comprises a first screen number and a first screen mesh size set;
selecting a screen based on the first screen selection scheme to obtain a first collection of separation screens;
generating a second screen selection scheme based on the second separation granularity, wherein the second screen selection scheme comprises a second screen number and a second screen mesh size set;
Selecting a screen based on the second screen selection scheme to obtain a second collection of separation screens;
and carrying out primary particle separation of the water body to be separated by the first separation screen mesh collection and the second separation screen mesh collection to obtain a first separation result.
Further, the system also comprises a sediment separation control scheme acquisition module for executing the following operation steps:
The sediment characteristics comprise sediment particle composition characteristics, sediment particle concentration characteristics and sediment particle weight characteristics;
a sediment treatment record set is called, each sediment treatment record comprises a sample sediment characteristic and a sample sediment separation control decision, wherein the sample sediment characteristic comprises a sample sediment particle composition, a sample sediment particle concentration and a sample sediment particle weight;
Performing sediment characteristic matching on the sediment treatment record set based on the sediment characteristics to obtain a plurality of sample sediment characteristic matching results, wherein the plurality of sample sediment characteristic matching results comprise a plurality of matching coefficients;
And based on the plurality of matching coefficients, carrying out decision extraction on the sediment treatment record set to obtain the sediment separation control scheme.
Further, the system also comprises a matching coefficient acquisition module for executing the following operation steps:
carrying out similarity analysis on the composition characteristics of the sediment particles and the composition of the sediment particles of the first sample to obtain a first similarity;
performing similarity analysis on the sediment particle concentration characteristics and the sediment particle concentration of the first sample to obtain a second similarity;
performing similarity analysis on the weight characteristics of the sediment particles and the weight of the sediment particles of the first sample to obtain a third similarity;
and carrying out weighted summation on the first similarity, the second similarity and the third similarity to obtain a first matching coefficient, and adding the first matching coefficient to the plurality of matching coefficients.
The foregoing detailed description of the hydraulic particle intelligent separation control method will be clear to those skilled in the art, and the hydraulic particle intelligent separation control system in this embodiment is relatively simple to describe because it corresponds to the method disclosed in the embodiments, and the relevant points refer to the description of the method section.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device comprises a processor, a memory and a network interface which are connected through a system bus, wherein the processor of the computer device is used for providing computing and control capability, the memory of the computer device comprises a nonvolatile storage medium and an internal memory, the nonvolatile storage medium stores an operating system, a computer program and a database, the internal memory is used for providing an environment for the operation of the operating system and the computer program in the nonvolatile storage medium, and the network interface of the computer device is used for communicating with an external terminal through network connection. The computer program is executed by the processor to implement the hydraulic particle intelligent separation control method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410487184.2A CN118387952B (en) | 2024-04-23 | 2024-04-23 | Hydraulic particle intelligent separation control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410487184.2A CN118387952B (en) | 2024-04-23 | 2024-04-23 | Hydraulic particle intelligent separation control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118387952A CN118387952A (en) | 2024-07-26 |
| CN118387952B true CN118387952B (en) | 2024-12-17 |
Family
ID=91998409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410487184.2A Active CN118387952B (en) | 2024-04-23 | 2024-04-23 | Hydraulic particle intelligent separation control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118387952B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115557550A (en) * | 2022-08-31 | 2023-01-03 | 达斯玛环境科技（北京）有限公司 | Sewage pretreatment method and system |
| CN116310999A (en) * | 2023-05-05 | 2023-06-23 | 贵州中水能源股份有限公司 | Method for detecting large floaters in reservoir area of hydroelectric power station |
| CN117884269A (en) * | 2024-03-05 | 2024-04-16 | 西南石油大学 | Centrifuge control system based on granularity detection |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6873725B2 (en) * | 2002-09-09 | 2005-03-29 | Coulter International Corp. | Simultaneous measurement and display of 3-D size distributions of particulate materials in suspensions |
| CN103712927B (en) * | 2012-09-29 | 2016-12-21 | 埃科莱布美国股份有限公司 | Detecting system and method and water treatment system and method |
| CN115220347B (en) * | 2022-07-15 | 2023-08-08 | 江苏邦鼎科技有限公司 | Material particle screening control method and system |
-
2024
- 2024-04-23 CN CN202410487184.2A patent/CN118387952B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115557550A (en) * | 2022-08-31 | 2023-01-03 | 达斯玛环境科技（北京）有限公司 | Sewage pretreatment method and system |
| CN116310999A (en) * | 2023-05-05 | 2023-06-23 | 贵州中水能源股份有限公司 | Method for detecting large floaters in reservoir area of hydroelectric power station |
| CN117884269A (en) * | 2024-03-05 | 2024-04-16 | 西南石油大学 | Centrifuge control system based on granularity detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118387952A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113435459B (en) | Rock component identification method, device, equipment and medium based on machine learning | |
| CN113344050B (en) | Lithology intelligent recognition method and system based on deep learning | |
| CN112017192B (en) | Glandular cell image segmentation method and glandular cell image segmentation system based on improved U-Net network | |
| Liu et al. | Remote sensing image change detection based on information transmission and attention mechanism | |
| Zhu et al. | Parameter optimization for automated concrete detection in image data | |
| CN109800736A (en) | A kind of method for extracting roads based on remote sensing image and deep learning | |
| CN108596046A (en) | A kind of cell detection method of counting and system based on deep learning | |
| CN111968081B (en) | Automatic fish shoal counting method and device, electronic equipment and storage medium | |
| Pramunendar et al. | A classification method of coconut wood quality based on Gray Level Co-occurrence matrices | |
| CN104346620A (en) | Inputted image pixel classification method and device, and image processing system | |
| CN112418028A (en) | Satellite image ship identification and segmentation method based on deep learning | |
| CN105354600A (en) | Automatic classification method for sandstone microsections | |
| CN113762153A (en) | Novel tailing pond detection method and system based on remote sensing data | |
| CN109472294A (en) | A method, device, storage medium and equipment for identifying urban water bodies | |
| CN114612787B (en) | Urban green space deep learning extraction method supported by scale change strategy | |
| Sengupta et al. | Seagrassdetect: A novel method for the detection of seagrass from unlabelled underwater videos | |
| CN115631413A (en) | Detection method, system and storage medium of deep-sea aquaculture floating rafts based on remote sensing images | |
| CN114373129B (en) | Remote sensing monitoring method and system for river and lake disturbance based on domain adaptation and change detection | |
| CN118747821B (en) | A method for automatically identifying floating objects | |
| CN118387952B (en) | Hydraulic particle intelligent separation control method and system | |
| Yu et al. | A multi-stage adaptive otsu thresholding algorithm for pore segmentation in rock thin-section images | |
| CN116051966A (en) | Pen and stone image recognition method based on deep learning network and model training method thereof | |
| CN116664545B (en) | Offshore benthos quantitative detection method and system based on deep learning | |
| Li et al. | Point Cloud-Based Pavement Crack Extraction Using MSAC and KNN Algorithm | |
| CN118015327A (en) | Image classification method for training-free negative sample in specific scene |
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 |