CN119149923A - Digital twin method, system, computing device and storage medium based on industrial automation - Google Patents
Digital twin method, system, computing device and storage medium based on industrial automation Download PDFInfo
- Publication number
- CN119149923A CN119149923A CN202411069912.4A CN202411069912A CN119149923A CN 119149923 A CN119149923 A CN 119149923A CN 202411069912 A CN202411069912 A CN 202411069912A CN 119149923 A CN119149923 A CN 119149923A
- Authority
- CN
- China
- Prior art keywords
- physical system
- digital twin
- physical
- model
- real
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本申请提供一种基于工业自动化的数字孪生方法、系统、计算设备及存储介质。其中，获取来自物理系统的实时运行参数；基于所述实时运行参数和预设的物理模型，在虚拟环境中构建所述物理系统的数字孪生体；使用所述数字孪生体模拟所述物理系统的运行状态，并预测所述物理系统在不同工况下的表现，以生成模拟结果；将所述模拟结果与获取的所述物理系统的实际运行数据进行比对，以对所述数字孪生体进行评估，获取评估结果；根据所述评估结果调整所述物理模型，以更新所述数字孪生体；利用更新后的所述数字孪生体进行故障预测和/或优化所述物理系统的运行参数。本申请提供的技术方案能够持续优化数字孪生体和调整物理模型。
The present application provides a digital twin method, system, computing device and storage medium based on industrial automation. Among them, real-time operating parameters from a physical system are obtained; based on the real-time operating parameters and a preset physical model, a digital twin of the physical system is constructed in a virtual environment; the digital twin is used to simulate the operating state of the physical system, and the performance of the physical system under different working conditions is predicted to generate simulation results; the simulation results are compared with the actual operating data of the physical system obtained to evaluate the digital twin and obtain evaluation results; the physical model is adjusted according to the evaluation results to update the digital twin; the updated digital twin is used to predict faults and/or optimize the operating parameters of the physical system. The technical solution provided by the present application can continuously optimize the digital twin and adjust the physical model.
Description
Technical Field
The embodiment of the application relates to the technical field of digital twinning, in particular to a digital twinning method, a digital twinning system, a digital twinning computing device and a digital twinning storage medium based on industrial automation.
Background
With the development of technology, digital twin technology is widely used in the field of industrial automation. Digital twin is a multidisciplinary optimization dynamic simulation process integrating data such as physical model, sensor update, operation history and the like. The real-time monitoring, prediction and optimization of the physical entity are realized by constructing a virtual model of the physical system. In the field of industrial automation, digital twin technology can be used for predicting various aspects of maintenance, performance optimization, fault diagnosis and the like.
Conventional industrial automation systems typically rely on static models and post-hoc analysis, which, although enabling basic monitoring of the operating state of the plant to some extent, have disadvantages in terms of predictability and initiative. With the continuous improvement of production efficiency and product quality requirements, the traditional industrial automation method is more and more difficult to meet the requirements of modern industrial production. Therefore, it becomes particularly important to develop new technologies that can monitor and predict the operating state of a physical system in real time.
Existing digital twinning techniques, while capable of improving the predictive power and operating efficiency of the system to some extent, still have some limitations. For example, these techniques often require extensive historical data to train the model, may not be able to make accurate predictions for new or atypical operating conditions, and in addition, the updating of the model often relies on manual intervention, lacks automated mechanisms to continuously optimize and adjust the model, which limits the application of digital twinning techniques in the field of industrial automation.
Disclosure of Invention
The embodiment of the application provides a digital twin method, a digital twin system, a digital twin computing device and a digital storage medium based on industrial automation, which are used for solving the problem that an automatic mechanism is lacked to continuously optimize a digital twin body and adjust a physical model in the prior art.
In a first aspect, an embodiment of the present application provides an industrial automation-based digital twin method, including:
acquiring real-time operation parameters from a physical system;
Constructing a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
simulating the running state of the physical system by using the digital twin body, and predicting the performance of the physical system under different working conditions to generate a simulation result;
comparing the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin body and obtain an evaluation result;
adjusting the physical model according to the evaluation result to update the digital twin;
and carrying out fault prediction and/or optimizing the operation parameters of the physical system by using the updated digital twin body.
Optionally, the acquiring the real-time operation parameters from the physical system includes:
acquiring real-time sensing data of a physical system through Internet of things equipment;
and preprocessing the real-time sensing data to generate real-time operation parameters, wherein the preprocessing at least comprises data cleaning, abnormal value detection and missing value filling.
Optionally, the constructing a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model includes:
analyzing real-time operation parameters of the physical system by using a machine learning algorithm to extract key features;
Constructing a dynamic mathematical model of the physical system based on the key features;
and simulating the running state of the physical system in the virtual environment, and updating in real time through the dynamic mathematical model to complete the construction of the digital twin of the physical system.
Optionally, the simulating the operation state of the physical system using the digital twin body and predicting the performance of the physical system under different working conditions to generate a simulation result includes:
simulating the performance of the physical system under normal operating conditions using the digital twin;
simulating the performance of the physical system under abnormal operation conditions by using the digital twin body, and predicting the occurrence probability of potential faults;
Generating a simulation result according to the performance of the physical system under the normal operation condition, the performance of the physical system under the abnormal operation condition and the occurrence probability of the potential fault;
The predicting the occurrence probability of the potential fault comprises:
Predicting occurrence probability of the potential fault through a fault prediction model, wherein the fault prediction model calculates the occurrence probability of the potential fault through the following formula:
Where P (f) is denoted as probability of occurrence of a potential failure, w 0、wi、vij is denoted as bias term, linear weight, and cross term weight, respectively, x i is denoted as the value of the ith operating parameter, x j is denoted as the value of the jth operating parameter, where j > i, n is denoted as the number of operating parameters.
Optionally, the comparing the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin body, to obtain an evaluation result, includes:
calculating the difference between the simulation result and the obtained actual operation data of the physical system by using a statistical method;
Determining the accuracy of the digital twin body through error analysis to obtain an evaluation result;
The determining the accuracy of the digital twin body through error analysis to obtain an evaluation result comprises:
By the formula: calculating the accuracy of the digital twin body to obtain an evaluation result, wherein RMSE is represented as the evaluation result, y i is represented as actual operation data, Expressed as simulation results, N is expressed as the number of data points.
Optionally, said adjusting the physical model according to the evaluation result to update the digital twin comprises:
Optimizing model parameters in the physical model by a back propagation algorithm;
wherein the back propagation algorithm updates the model parameters by the following formula:
Where w j is denoted as the j-th model parameter, η is denoted as the learning rate, Expressed as the partial derivative of the loss function with respect to the model parameters w j, λ is expressed as the weight of the regularization term, L is expressed as the loss function, where,
Optionally, the performing fault prediction and/or optimizing the operation parameters of the physical system by using the updated digital twin body includes:
performing fault prediction by using the updated digital twin body so as to take preventive measures according to the occurrence probability of potential faults;
Automatically adjusting the operation parameters of the physical system through an optimization algorithm, wherein the operation parameter optimization calculates an optimal parameter set p * of the physical system through the following formula:
where f (p) is denoted as the objective function, p is denoted as the parameter set, p * is denoted as the optimal parameter set, and λ is denoted as the weight of the regularization term.
In a second aspect, embodiments of the present application provide an industrial automation-based digital twin system, comprising:
the acquisition module is used for acquiring real-time operation parameters from the physical system;
the building module is used for building a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
The generation module is used for simulating the running state of the physical system by using the digital twin body and predicting the performance of the physical system under different working conditions so as to generate a simulation result;
The acquisition module is also used for comparing the simulation result with the acquired actual operation data of the physical system so as to evaluate the digital twin body and acquire an evaluation result;
An updating module for adjusting the physical model according to the evaluation result to update the digital twin;
and the processing module is used for carrying out fault prediction and/or optimizing the operation parameters of the physical system by utilizing the updated digital twin body.
In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component, where the storage component stores one or more computer instructions, and the one or more computer instructions are used to be invoked and executed by the processing component to implement the digital twin method based on industrial automation according to the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, where the computer program is executed by a computer to implement the digital twin method based on industrial automation according to the first aspect.
In the embodiment of the application, real-time operation parameters from a physical system are acquired, a digital twin body of the physical system is constructed in a virtual environment based on the real-time operation parameters and a preset physical model, the operation state of the physical system is simulated by using the digital twin body, the performance of the physical system under different working conditions is predicted to generate a simulation result, the simulation result is compared with the acquired actual operation data of the physical system to evaluate the digital twin body, the evaluation result is acquired, the physical model is adjusted according to the evaluation result to update the digital twin body, and the updated digital twin body is utilized to conduct fault prediction and/or optimize the operation parameters of the physical system.
The technical scheme of the application has the following remarkable beneficial effects:
The prediction accuracy is improved, namely the digital twin body can more accurately simulate the operation state of a physical system through the operation parameters and the physical model updated in real time, and the accuracy of a prediction result is improved.
The adaptability of the system is enhanced, an automatic model adjustment mechanism enables the digital twin body to adapt to the changes under different working conditions, and the self-adaptive capacity of the system is improved.
And optimizing the operation parameters, namely, the operation parameters of the physical system can be timely found and optimized through the comparison of the simulation result and the actual operation data, so that the overall performance of the system is improved.
The maintenance cost is reduced, namely, through fault prediction, measures can be taken in advance to avoid equipment faults, the unplanned downtime is reduced, and the maintenance cost is reduced.
The production efficiency is improved, and the accurate prediction and optimization capability is beneficial to improving the production efficiency, so that the equipment is ensured to be in an optimal running state.
The decision support is enhanced, the prediction result and the optimization suggestion provided by the digital twin body provide powerful support for a decision maker, and the decision maker is facilitated to make a more scientific and reasonable decision.
In conclusion, the scheme of the application not only improves the prediction precision of the digital twin body, but also enhances the self-adaptability and the optimizing capability of the system, thereby effectively improving the overall performance and the economic benefit of the industrial automation system.
These and other aspects of the application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a digital twin method based on industrial automation provided by an embodiment of the present application;
FIG. 2 is a schematic diagram of a digital twin system based on industrial automation according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of a computing device according to an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present application with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present application and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
According to the background technology, in order to solve the defects of the prior art, the application provides a digital twin method based on industrial automation, which constructs a digital twin body of a physical system in a virtual environment by acquiring real-time operation parameters of the physical system and based on the parameters and a preset physical model. The physical model of the digital twin body is continuously adjusted and optimized by simulating the operation state of the physical system and comparing with actual operation data, so that the accuracy of prediction is improved, and the fault prediction and the optimization of operation parameters are realized.
The following description of the embodiments of the present application 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 application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Fig. 1 is a flowchart of a digital twin method based on industrial automation according to an embodiment of the present application, as shown in fig. 1, the method includes:
101. Acquiring real-time operation parameters from a physical system;
Optionally, in the embodiment of the present application, step 101 may specifically include collecting real-time sensing data of a physical system through an internet of things device, and preprocessing the real-time sensing data to generate real-time operation parameters, where the preprocessing at least includes data cleaning, outlier detection and missing value filling.
In the step, the Internet of things equipment refers to a sensor or terminal equipment which can be connected to the Internet and transmit data in a wireless or wired mode. These devices may be installed on industrial equipment for real-time monitoring of the status and environmental conditions of the equipment.
Real-time sensing data refers to various types of data, such as temperature, pressure, vibration and the like, collected by the internet of things equipment from a physical system. These data are typically collected continuously at a frequency.
Preprocessing, which is a processing step performed on the original data before data analysis to improve the quality and usability of the data. Preprocessing typically includes data cleansing, outlier detection, and missing value padding.
Data cleansing refers to removing or correcting errors and inconsistencies in data, such as removing duplicate data, correcting spelling errors, etc.
Outlier detection, detecting data points in the data that deviate significantly from other data, which may be due to measurement errors or system faults.
Filling the missing value by using a proper method for filling the missing data points so as to ensure the integrity of the data.
In an embodiment of the present application, an equipment monitoring system in an automated manufacturing facility is considered that is intended to monitor the operating status of production equipment to discover potential failures and to perform maintenance in advance.
Real-time sensing data of a physical system are acquired through Internet of things equipment, wherein the Internet of things equipment comprises a temperature sensor, a pressure sensor, a vibration sensor and the like which are arranged on production equipment. These sensors send data to the central control system once every 1 second. The data includes information such as temperature, pressure, and vibration amplitude of the device.
Preprocessing the real-time sensing data to generate real-time operation parameters, namely cleaning the data, removing repeated data records, and correcting occasional reading errors of the sensor. Outlier detection using statistical methods (e.g., Z-score) to identify outliers outside of the normal range. For example, for temperature sensor data, a reading is considered outliers if it is far above or below the average temperature. Missing value filling-in, using nearest neighbor or moving average methods to fill in occasional missing sensor data. For example, if a temperature sensor does not transmit data for a period of time, the average temperature value of two time points before and after can be used to fill the temperature data of the period of time.
And generating real-time operation parameters, wherein the real-time operation parameters comprise stable and accurate temperature, pressure and vibration data after pretreatment, and the data can be used for monitoring the health condition of equipment.
Through the steps, the operation state of the equipment can be monitored in real time by the factory, and potential faults are predicted by analyzing the change trend of the parameters, so that necessary maintenance measures are taken, and the efficient operation of the equipment is ensured.
102. Constructing a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
optionally, in the embodiment of the present application, step 102 may specifically include:
1021. analyzing real-time operation parameters of the physical system by using a machine learning algorithm to extract key features;
1022. constructing a dynamic mathematical model of the physical system based on the key features;
1023. and simulating the running state of the physical system in the virtual environment, and updating in real time through the dynamic mathematical model to complete the construction of the digital twin of the physical system.
In this step, real-time operating parameters are real-time data collected from the physical system including, but not limited to, temperature, pressure, flow, vibration, etc. These data are used to reflect the current operating state of the physical system.
The preset physical model refers to a mathematical model established based on a physical law or an empirical formula and is used for describing the dynamic characteristics of a physical system. For example, a thermodynamic model may be used to describe the heat exchange process of an engine.
Machine learning algorithm is a statistical method used to automatically "learn" patterns and rules from data. These algorithms may be used to identify key features in the data, such as support vector machines, neural networks, and the like.
Key features are factors extracted from the data, which have important influence on the system behavior. These features can help build a more accurate model.
Dynamic mathematical model, a mathematical expression for describing the behavior of the system over time. Such a model may be in the form of a set of differential equations, a state space model, or the like.
Digital twins are exact copies of physical entities in a virtual environment. It uses real-time data to simulate the performance of physical entities and to enable predictions of future behavior.
Virtual environment-a computer-generated environment that can be used to simulate real-world system behavior. In a virtual environment, different scenarios may be created and tested by software.
Simulation, using the model on the computer to reproduce the operating state of the physical system. Simulations can be used to predict the behavior of the system under different conditions.
In the embodiments of the present application, it is assumed that we need to construct a digital twin for monitoring and predicting the performance of wind turbines. The method comprises the following specific steps:
The real-time operation parameters of the physical system are analyzed by using a machine learning algorithm to extract key characteristics, namely, collecting the real-time operation parameters of the wind driven generator, such as wind speed, blade rotation speed, generator temperature and the like. These data are analyzed using machine learning algorithms (e.g., cluster analysis, principal component analysis PCA, etc.) to identify key variables that have a significant impact on generator performance, such as wind speed versus blade speed.
And constructing a dynamic mathematical model of the physical system based on the key characteristics, namely constructing a dynamic mathematical model to describe the operation characteristics of the generator based on the relation between the extracted key characteristics, such as wind speed and blade rotation speed. This model may include physical equations describing how wind power is converted to mechanical energy, and electrical equations describing how mechanical energy is converted to electrical energy.
Simulating the running state of the physical system in the virtual environment, and updating the running state in real time through the dynamic mathematical model to complete the construction of the digital twin body of the physical system, wherein the running state of the wind driven generator is simulated in the virtual environment by utilizing the dynamic mathematical model. The wind speed data collected in real time is input into the simulation environment, and parameters in the model are dynamically updated to reflect the real-time running state of the wind power generator in the real world. The digital twins are able to predict problems that may occur with the generator from real-time data and provide preventive maintenance advice.
Through the steps, a digital twin body capable of reflecting the state of the wind driven generator in real time can be constructed, so that the operation efficiency of the generator is improved, and the maintenance cost is reduced.
From the above examples, it can be seen that the construction of a digital twin is a process involving data acquisition, analysis and modeling. In the embodiment of the application, by analyzing real-time operation parameters of the wind driven generator by using a machine learning algorithm, key features are extracted, and a dynamic mathematical model is constructed based on the features. Then, the running state of the generator is simulated in the virtual environment, and the construction of the digital twin body is completed by updating the model in real time. The method can be widely applied to monitoring and prediction of other physical systems.
103. Simulating the running state of the physical system by using the digital twin body, and predicting the performance of the physical system under different working conditions to generate a simulation result;
optionally, in the embodiment of the present application, step 103 may specifically include:
1031. simulating the performance of the physical system under normal operating conditions using the digital twin;
1032. Simulating the performance of the physical system under abnormal operation conditions by using the digital twin body, and predicting the occurrence probability of potential faults;
1033. Generating a simulation result according to the performance of the physical system under the normal operation condition, the performance of the physical system under the abnormal operation condition and the occurrence probability of the potential fault;
The method comprises the steps of predicting the occurrence probability of the potential faults through a fault prediction model, wherein the fault prediction model calculates the occurrence probability of the potential faults through the following formula:
Where P (f) is denoted as probability of occurrence of a potential failure, w 0、wi、vij is denoted as bias term, linear weight, and cross term weight, respectively, x i is denoted as the value of the ith operating parameter, x j is denoted as the value of the jth operating parameter, where j > i, n is denoted as the number of operating parameters.
In this step, the digital twin is a virtual representation of the physical system that reflects the state of the physical system in real time and can be updated based on real-time data of the physical system.
Simulation-the behavior of a physical system under given conditions is reproduced in a digital twin.
Normal operating conditions-the state in which the physical system operates within the intended operating range is typically within design specifications and safety constraints.
Abnormal operation condition, i.e. the operation state of the physical system when the physical system is out of the normal range or fails.
Probability of occurrence of potential faults by analyzing the performance of the physical system under abnormal conditions, the probability of occurrence of faults of the system is predicted.
The failure prediction model is a mathematical model used for estimating the probability of physical system failure. The model is typically trained based on historical data and current operating parameters.
The bias term, a constant term in the model, reflects the probability of a potential fault occurring even though all operating parameters are zero.
Linear weight-a coefficient associated with each operating parameter (x i), reflects the direct impact of that parameter on the probability of occurrence of a potential fault.
Cross term weight-a coefficient related to the product of two operating parameters (x i and x j), reflects the impact of the two parameters interaction on the probability of occurrence of a potential fault.
In the embodiment of the application, it is assumed that a digital twin body is being developed for simulating the running state of a turbocharged engine and predicting the performance of the turbocharged engine under different working conditions. The method comprises the following specific steps:
the digital twin body is used to simulate the performance of the physical system under normal operation conditions, firstly, we collect real-time data of the engine under normal operation conditions, such as rotation speed, temperature, pressure and the like. We then simulated the behavior of the engine under these conditions in a digital twin to verify the accuracy of the model.
The digital twin body is used for simulating the performance of the physical system under the abnormal operation condition and predicting the occurrence probability of potential faults, and then, the operation parameters are changed to simulate the operation state of the engine under the abnormal condition. We use a fault prediction model to predict the probability of an engine failing under these abnormal conditions.
Generating a simulation result according to the performance of the physical system under the normal operation condition, the performance of the physical system under the abnormal operation condition and the occurrence probability of the potential fault: finally, we combine the performance under normal operation conditions, the performance under abnormal conditions and the probability of occurrence of potential faults to generate a complete simulation result.
The following is a specific example:
let us assume that we have the following operating parameters:
Rotational speed (x 1);
temperature (x 2);
Pressure (x 3);
the following model parameters:
Bias term w 0 = -2;
Linear weight w 1＝0.05,w2＝0.1,w3 = 0.15;
cross term weight v 12＝0.001,v13＝0.002,v23 = 0.003;
For a particular operating state, assume that the operating parameter values are:
Rotational speed x 1 =2000;
Temperature x 2 = 90 ℃;
pressure x 3 = 15bar;
the occurrence probability P (f) of the potential fault is calculated according to the formula:
Substituting the specific numerical values:
and (3) calculating to obtain:
since e -127.3 is a very small positive number, we can approximate P (f) to be 1, which means that the probability of occurrence of a potential failure is very high in this case.
By such calculation, we can predict the potential failure probability of the engine under abnormal operation conditions and take preventive measures accordingly.
104. Comparing the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin body and obtain an evaluation result;
Optionally, in the embodiment of the present application, step 104 may specifically include:
1041. Calculating the difference between the simulation result and the obtained actual operation data of the physical system by using a statistical method;
1042. Determining the accuracy of the digital twin body through error analysis to obtain an evaluation result;
wherein the determining the accuracy of the digital twin body through error analysis to obtain an evaluation result includes:
By the formula: calculating the accuracy of the digital twin body to obtain an evaluation result, wherein RMSE is represented as the evaluation result, y i is represented as actual operation data, Expressed as simulation results, N is expressed as the number of data points.
In the above RMSE formula, RMSE is expressed as root mean square error, represents the average error between the digital twin simulation result and the actual operating data, y i is expressed as the actual operating data of the i-th data point,The simulation result, denoted as the i-th data point, N represents the total number of data points.
In this step, the simulation results are obtained by simulating the behaviour of the physical system under different conditions by means of a digital twin.
Actual operation data-data collected by the physical system during actual operation, which can be used to verify the simulation results of a digital twin.
Statistical methods-a series of mathematical methods used to analyze and interpret the data to reveal relationships or trends between the data.
The difference is the difference between the simulation result and the actual operation data, and is used for evaluating the simulation accuracy of the digital twin.
And (3) error analysis, namely determining the accuracy degree of the digital twin body by calculating the error between the simulation result and the actual data.
Root Mean Square Error (RMSE), a commonly used error metric, is used to measure the average error magnitude between the digital twin simulation results and the actual operational data.
In the present embodiment, it is assumed that we are evaluating a digital twin for simulating the performance of a wind turbine. Our goal is to evaluate the differences between the digital twin simulation results and the actual operational data.
And calculating the difference between the simulation result and the obtained actual operation data of the physical system by using a statistical method, wherein the actual operation data of the wind driven generator is collected, and the actual operation data comprise wind speed, power output and the like. The power output of the wind driven generator at different wind speeds is simulated by using a digital twin body. The simulation results are compared with actual operating data and statistical methods (e.g., calculating differences, plotting scatter plots, etc.) are used to evaluate the differences between the two.
The accuracy of the digital twin is determined by error analysis to obtain an evaluation result using Root Mean Square Error (RMSE) to quantify the error between the simulation result and the actual operational data. The RMSE value is obtained through a calculation formula, so that the accuracy degree of the digital twin is estimated.
The following is a specific example:
Suppose we collect the actual power output data and corresponding simulation results for 10 groups of wind turbines at different wind speeds as shown in table 1 below:
TABLE 1
Based on table 1 above, we used RMSE formula to calculate the accuracy of the digital twins:
substituting the specific values in table 1 above:
RMSE=2
This means that the average error between the power output of the digital twin body simulation and the actual power output is 2kW, and this average error is taken as an evaluation result. By such calculation, we can evaluate the accuracy of the digital twin and make the necessary adjustments accordingly to improve its accuracy.
105. Adjusting the physical model according to the evaluation result to update the digital twin;
Optionally, in an embodiment of the present application, step 105 may specifically include optimizing model parameters in the physical model by a back propagation algorithm;
wherein the back propagation algorithm updates the model parameters by the following formula:
Where w j is denoted as the j-th model parameter, η is denoted as the learning rate, Expressed as the partial derivative of the loss function with respect to the model parameters w j, λ is expressed as the weight of the regularization term, L is expressed as the loss function, where,
In this step, the result is evaluated by an evaluation index, such as Root Mean Square Error (RMSE), obtained by comparing the simulation result of the digital twin with the actual operation data of the physical system.
Physical model-a mathematical model that describes the behavior of a physical system, typically contains a set of equations and parameters.
Digital twins-a virtual representation of a physical system that simulates the behavior of the physical system through a physical model.
Back propagation algorithm a supervised learning method for training a neural network adjusts model parameters by minimizing a loss function.
Model parameters-variables in the physical model that determine the behavior of the model.
Learning rate, which is to control the super-parameters of the parameter update amplitude in each iteration.
The loss function is a function for quantifying the difference between the predicted value and the true value, here the square of the root mean square error.
Partial derivative, the rate of change of the loss function relative to a parameter, is used to guide the update direction of the parameter.
Regularization term a penalty term for preventing overfitting is implemented by adding the sum of squares of the model parameters.
In the embodiment of the application, assuming that a digital twin body is used for simulating the performance of the wind driven generator, parameters in a physical model are required to be adjusted according to the evaluation result so as to improve the accuracy of the digital twin body.
The physical model is adapted according to the evaluation result using a previously calculated Root Mean Square Error (RMSE) as the evaluation result. A loss function is constructed which is the square of RMSE, i.e. l=rmse 2. A back propagation algorithm is used to adjust parameters in the physical model.
Model parameters in the physical model are optimized through a back propagation algorithm, namely a learning rate eta and a regularization term weight lambda are set. The partial derivative of the loss function with respect to each parameter is calculated. Model parameters are updated to minimize the loss function.
The following is a specific example:
Assuming we have calculated the square l=4 of RMSE (based on the previous embodiment), we now have to update the model parameters by a back propagation algorithm.
We set the learning rate to η=0.1 and the regularization term weight λ=0.01.
Let us assume that we have two parameters w 1 and w 2, the initial values being 2 and 3, respectively.
We need to calculate the partial derivatives of the loss function with respect to each parameterAnd
For simplicity of explanation, we assume thatAnd
The parameters w 1 and w 2 are updated according to the formula:
w1=2-0.1(1+0.01·2)
w1=2-0.1(1.02)
w1=2-0.102
w1=1.898
likewise, for w 2:
w2=3-0.1(2+0.01·3)
w2=3-0.1(2.03)
w2=3-0.203
w2=2.797
Thus, the updated parameters are w 1 = 1.898 and w 2 = 2.797.
Through such an iterative process, we can gradually optimize parameters in the physical model, thereby improving the accuracy of the digital twins. This process may require multiple iterations until satisfactory accuracy is achieved or a stop condition is met.
106. And carrying out fault prediction and/or optimizing the operation parameters of the physical system by using the updated digital twin body.
Optionally, in the embodiment of the present application, step 106 may specifically include:
1061. performing fault prediction by using the updated digital twin body so as to take preventive measures according to the occurrence probability of potential faults;
1062. Automatically adjusting the operation parameters of the physical system through an optimization algorithm, wherein the operation parameter optimization calculates an optimal parameter set p * of the physical system through the following formula:
where f (p) is denoted as the objective function, p is denoted as the parameter set, p * is denoted as the optimal parameter set, and λ is denoted as the weight of the regularization term.
In this step, the updated digital twin is evaluated and parameter adjusted to more accurately reflect the physical system behavior.
Fault prediction-using digital twins to predict possible faults in a physical system to take precautions.
Probability of occurrence of potential faults, namely probability of possible faults of a physical system under different working conditions, which is obtained through digital twin body simulation.
Precautions measures are taken to reduce or avoid the occurrence of faults based on the probability of potential faults.
And (3) optimizing the operation parameters, namely adjusting the operation parameters of the physical system through an optimization algorithm so as to improve the performance of the system.
Optimization algorithms-algorithms for finding optimal solutions, such as gradient descent methods, genetic algorithms, etc.
Objective function a function for quantifying the impact of operating parameters on system performance, the objective of the optimization being to find a set of parameters that minimizes the objective function.
Regularization term a penalty term for preventing overfitting, by adding the sum of squares of the parameters.
Optimal parameter set-parameter set that minimizes the objective function.
In the present embodiment, it is assumed that we are using digital twins to monitor and optimize the performance of a wind turbine. The method comprises the following specific steps:
and carrying out fault prediction by using the updated digital twin body, namely simulating the performances of the wind driven generator under different working conditions by using the digital twin body. And calculating the occurrence probability of the potential faults through a fault prediction model. If the probability of occurrence of a potential failure exceeds a threshold, precautions are taken, such as adjusting maintenance plans or replacing parts in advance.
The operating parameters of the physical system are automatically adjusted by an optimization algorithm by defining an objective function, such as maximum power output or minimum energy consumption. An optimization algorithm, such as a gradient descent method, is used to find the optimal set of operating parameters. And calculating an optimal parameter set p by an optimization algorithm.
The following is a specific example:
Assuming that we want to optimize the maximum power output of the wind generator, we can do this by:
the updated digital twin is used for fault prediction, assuming that we have calculated the probability of occurrence P (f) of the potential fault. If P (f) is greater than a preset threshold, such as 0.5, then a potential fault is deemed to exist. Corresponding precautions are taken, for example increasing the frequency of maintenance checks.
And automatically adjusting the operation parameters of the physical system through an optimization algorithm, namely defining an objective function f (p) as the maximum power output of the wind driven generator. The regularization term weight λ is set to 0.01. The optimal parameter set p is calculated using a gradient descent method or other optimization algorithm.
In particular, we assume that we have three operating parameters p 1,p2,p3 and define the objective function f (p) as the maximum power output of the wind turbine. We want to find the optimal parameter set p by an optimization algorithm.
Let us assume that we have defined the objective function f (p) and set the weight λ=0.01 of the regularization term. We now find the optimal parameter set p to maximize the power output.
Calculating an optimal parameter set p according to the formula:
For simplicity of explanation, we assume that we have a simple gradient descent method, with an initial parameter of p 1＝1,p2＝2,p3 =3 and a learning rate of η=0.1.
Assuming a gradient of the objective function f (p) ofNamely:
calculating parameters after primary gradient descent update:
p1=1-0.1(1+0.01·1)
p1=1-0.1(1.01)
p1=0.899
Likewise, for p 2 and p 3:
p2=2-0.1(2+0.01·2)
p2=2-0.1(2.02)
p2=1.798
p3=3-0.1(3+0.01·3)
p3=3-0.1(3.03)
p3=2.697
thus, the updated parameter is p 1＝0.899,p2＝1.798,p3 = 2.697.
Through such an iterative process, we can gradually optimize the operating parameters of the physical system to achieve optimal performance. This process may require multiple iterations until satisfactory performance is achieved or a stop condition is met. Through the steps, the digital twin body can be used for fault prediction and operation parameter optimization, so that the reliability and the efficiency of a physical system are improved.
Fig. 2 is a schematic structural diagram of a digital twin system based on industrial automation according to an embodiment of the present application, as shown in fig. 2, the system includes:
An acquisition module 21 for acquiring real-time operation parameters from the physical system;
A construction module 22, configured to construct a digital twin of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
The generating module 23 is configured to simulate an operation state of the physical system using the digital twin body, and predict performances of the physical system under different working conditions to generate a simulation result;
the obtaining module 21 is further configured to compare the simulation result with the obtained actual operation data of the physical system, so as to evaluate the digital twin body and obtain an evaluation result;
an updating module 24 for adjusting the physical model according to the evaluation result to update the digital twin;
a processing module 25 for performing fault prediction and/or optimizing the operation parameters of the physical system using the updated digital twin.
Optionally, in the embodiment of the present application, the acquiring module 21 is specifically configured to acquire real-time sensing data of a physical system through an internet of things device, and perform preprocessing on the real-time sensing data to generate real-time operation parameters, where the preprocessing at least includes data cleaning, outlier detection and missing value filling.
Optionally, in the embodiment of the present application, the construction module 22 is specifically configured to analyze real-time operation parameters of the physical system by using a machine learning algorithm to extract key features, construct a dynamic mathematical model of the physical system based on the key features, simulate an operation state of the physical system in the virtual environment, and update the operation state in real time by using the dynamic mathematical model to complete construction of a digital twin body of the physical system.
Optionally, in the embodiment of the present application, the generating module 23 is specifically configured to simulate the performance of the physical system under the normal operation condition by using the digital twin body, simulate the performance of the physical system under the abnormal operation condition by using the digital twin body, and predict the occurrence probability of the potential fault, generate the simulation result according to the performance of the physical system under the normal operation condition, the performance of the physical system under the abnormal operation condition, and the occurrence probability of the potential fault, and predict the occurrence probability of the potential fault, including predicting the occurrence probability of the potential fault by using a fault prediction model, where the fault prediction model calculates the occurrence probability of the potential fault by using the following formula:
Where P (f) is denoted as probability of occurrence of a potential failure, w 0、wi、vij is denoted as bias term, linear weight, and cross term weight, respectively, x i is denoted as the value of the ith operating parameter, x j is denoted as the value of the jth operating parameter, where j > i, n is denoted as the number of operating parameters.
Optionally, in the embodiment of the present application, the obtaining module 21 is specifically configured to calculate a difference between the simulation result and the obtained actual operation data of the physical system by using a statistical method, determine an accuracy degree of the digital twin body through error analysis to obtain an evaluation result, and determine the accuracy degree of the digital twin body through error analysis to obtain the evaluation result, where the obtaining includes:
By the formula: calculating the accuracy of the digital twin body to obtain an evaluation result, wherein RMSE is represented as the evaluation result, y i is represented as actual operation data, Expressed as simulation results, N is expressed as the number of data points.
Optionally, in the embodiment of the present application, the updating module 24 is specifically configured to optimize the model parameters in the physical model through a back propagation algorithm, where the back propagation algorithm updates the model parameters through the following formula:
Where w j is denoted as the j-th model parameter, η is denoted as the learning rate, Expressed as the partial derivative of the loss function with respect to the model parameters w j, λ is expressed as the weight of the regularization term, L is expressed as the loss function, where,
Optionally, in the embodiment of the present application, the processing module 25 is specifically configured to use the updated digital twin to perform fault prediction to take precautionary measures according to occurrence probability of potential faults, and automatically adjust an operation parameter of the physical system through an optimization algorithm, where the operation parameter optimization calculates an optimal parameter set p * of the physical system according to the following formula:
where f (p) is denoted as the objective function, p is denoted as the parameter set, p * is denoted as the optimal parameter set, and λ is denoted as the weight of the regularization term.
The digital twin system based on industrial automation described in fig. 2 may perform the digital twin method based on industrial automation described in the embodiment shown in fig. 1, and its principle and technical effects will not be described again. The specific manner in which the various modules, units, and operations of the industrial automation-based digital twin system of the above embodiments are performed has been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
In one possible design, the industrial automation-based digital twinning system of the embodiment shown in FIG. 2 may be implemented as a computing device, which may include a storage component 31 and a processing component 32, as shown in FIG. 3;
the storage component 31 stores one or more computer instructions for execution by the processing component 32.
The processing component 32 is configured to obtain real-time operation parameters from a physical system, construct a digital twin of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model, simulate an operation state of the physical system using the digital twin and predict performances of the physical system under different working conditions to generate a simulation result, compare the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin to obtain an evaluation result, adjust the physical model according to the evaluation result to update the digital twin, and perform fault prediction and/or optimize the operation parameters of the physical system using the updated digital twin.
Wherein the processing component 32 may include one or more processors to execute computer instructions to perform all or part of the steps of the methods described above. Of course, the processing component may also be implemented as one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for executing the methods described above.
The storage component 31 is configured to store various types of data to support operations at the terminal. The memory component may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
Of course, the computing device may necessarily include other components as well, such as input/output interfaces, display components, communication components, and the like.
The input/output interface provides an interface between the processing component and a peripheral interface module, which may be an output device, an input device, etc.
The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, and the like.
The computing device may be a physical device or an elastic computing host provided by the cloud computing platform, and at this time, the computing device may be a cloud server, and the processing component, the storage component, and the like may be a base server resource rented or purchased from the cloud computing platform.
The embodiment of the application also provides a computer storage medium, which stores a computer program, and the computer program can realize the digital twin method based on industrial automation of the embodiment shown in the figure 1 when being executed by a computer.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same, and although the present application has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present application.
Claims (10)
1. A digital twin method based on industrial automation, comprising:
acquiring real-time operation parameters from a physical system;
Constructing a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
simulating the running state of the physical system by using the digital twin body, and predicting the performance of the physical system under different working conditions to generate a simulation result;
comparing the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin body and obtain an evaluation result;
adjusting the physical model according to the evaluation result to update the digital twin;
and carrying out fault prediction and/or optimizing the operation parameters of the physical system by using the updated digital twin body.
2. The method of claim 1, wherein the obtaining real-time operating parameters from a physical system comprises:
acquiring real-time sensing data of a physical system through Internet of things equipment;
and preprocessing the real-time sensing data to generate real-time operation parameters, wherein the preprocessing at least comprises data cleaning, abnormal value detection and missing value filling.
3. The method of claim 1, wherein said constructing a digital twin of said physical system in a virtual environment based on said real-time operating parameters and a preset physical model comprises:
analyzing real-time operation parameters of the physical system by using a machine learning algorithm to extract key features;
Constructing a dynamic mathematical model of the physical system based on the key features;
and simulating the running state of the physical system in the virtual environment, and updating in real time through the dynamic mathematical model to complete the construction of the digital twin of the physical system.
4. A method according to claim 3, wherein said simulating the operating state of the physical system using the digital twin body and predicting the performance of the physical system under different conditions to generate simulation results comprises:
simulating the performance of the physical system under normal operating conditions using the digital twin;
simulating the performance of the physical system under abnormal operation conditions by using the digital twin body, and predicting the occurrence probability of potential faults;
Generating a simulation result according to the performance of the physical system under the normal operation condition, the performance of the physical system under the abnormal operation condition and the occurrence probability of the potential fault;
The predicting the occurrence probability of the potential fault comprises:
Predicting occurrence probability of the potential fault through a fault prediction model, wherein the fault prediction model calculates the occurrence probability of the potential fault through the following formula:
Where P (f) is denoted as probability of occurrence of a potential failure, w 0、wi、vij is denoted as bias term, linear weight, and cross term weight, respectively, x i is denoted as the value of the ith operating parameter, x j is denoted as the value of the jth operating parameter, where j > i, n is denoted as the number of operating parameters.
5. The method of claim 1, wherein the comparing the simulation result with the obtained actual operation data of the physical system to evaluate the digital twin body to obtain an evaluation result comprises:
calculating the difference between the simulation result and the obtained actual operation data of the physical system by using a statistical method;
Determining the accuracy of the digital twin body through error analysis to obtain an evaluation result;
The determining the accuracy of the digital twin body through error analysis to obtain an evaluation result comprises:
By the formula: calculating the accuracy of the digital twin body to obtain an evaluation result, wherein RMSE is represented as the evaluation result, y i is represented as actual operation data, Expressed as simulation results, N is expressed as the number of data points.
6. The method of claim 1, wherein said adjusting the physical model to update the digital twin based on the evaluation result comprises:
Optimizing model parameters in the physical model by a back propagation algorithm;
wherein the back propagation algorithm updates the model parameters by the following formula:
Where w j is denoted as the j-th model parameter, η is denoted as the learning rate, Expressed as the partial derivative of the loss function with respect to the model parameters w j, λ is expressed as the weight of the regularization term, L is expressed as the loss function, where,
7. The method of claim 1, wherein said utilizing the updated digital twins for fault prediction and/or optimizing the operating parameters of the physical system comprises:
performing fault prediction by using the updated digital twin body so as to take preventive measures according to the occurrence probability of potential faults;
Automatically adjusting the operation parameters of the physical system through an optimization algorithm, wherein the operation parameter optimization calculates an optimal parameter set p * of the physical system through the following formula:
where f (p) is denoted as the objective function, p is denoted as the parameter set, p * is denoted as the optimal parameter set, and λ is denoted as the weight of the regularization term.
8. A digital twin system based on industrial automation, comprising:
the acquisition module is used for acquiring real-time operation parameters from the physical system;
the building module is used for building a digital twin body of the physical system in a virtual environment based on the real-time operation parameters and a preset physical model;
The generation module is used for simulating the running state of the physical system by using the digital twin body and predicting the performance of the physical system under different working conditions so as to generate a simulation result;
The acquisition module is also used for comparing the simulation result with the acquired actual operation data of the physical system so as to evaluate the digital twin body and acquire an evaluation result;
An updating module for adjusting the physical model according to the evaluation result to update the digital twin;
and the processing module is used for carrying out fault prediction and/or optimizing the operation parameters of the physical system by utilizing the updated digital twin body.
9. A computing device, comprising a processing component and a storage component, the storage component storing one or more computer instructions for execution by the processing component to implement the industrial automation-based digital twinning method of any one of claims 1-7.
10. A computer storage medium, wherein a computer program is stored, which when executed by a computer, implements the industrial automation-based digital twin method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411069912.4A CN119149923A (en) | 2024-08-06 | 2024-08-06 | Digital twin method, system, computing device and storage medium based on industrial automation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411069912.4A CN119149923A (en) | 2024-08-06 | 2024-08-06 | Digital twin method, system, computing device and storage medium based on industrial automation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119149923A true CN119149923A (en) | 2024-12-17 |
Family
ID=93808672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411069912.4A Withdrawn CN119149923A (en) | 2024-08-06 | 2024-08-06 | Digital twin method, system, computing device and storage medium based on industrial automation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119149923A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119361049A (en) * | 2024-12-27 | 2025-01-24 | 青岛超瑞纳米新材料科技有限公司 | Carbon nanotube growth prediction evaluation model based on digital twin and AI and establishment method thereof |
| CN119537083A (en) * | 2025-01-21 | 2025-02-28 | 国家工业信息安全发展研究中心 | Industrial Internet equipment fault prediction method and system based on digital twin |
| CN119556571A (en) * | 2025-01-24 | 2025-03-04 | 湖南伟村信息科技有限公司 | A lightweight processing method for digital twin models |
| CN119774901A (en) * | 2025-03-11 | 2025-04-08 | 一夫科技股份有限公司 | Preparation process adjusting method for gypsum |
| CN119891171A (en) * | 2024-12-27 | 2025-04-25 | 北京京能清洁能源电力股份有限公司内蒙古分公司 | New energy field safety monitoring method and system based on digital twin technology |
| CN120046264A (en) * | 2025-01-23 | 2025-05-27 | 西峡县众德汽车部件有限公司 | Data twinning-based turbocharger shell three-dimensional model construction method |
| CN120313918A (en) * | 2025-02-07 | 2025-07-15 | 四川跃纳科技有限公司 | A performance test method for a small fluid thrust vector turbojet engine |
-
2024
- 2024-08-06 CN CN202411069912.4A patent/CN119149923A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119361049A (en) * | 2024-12-27 | 2025-01-24 | 青岛超瑞纳米新材料科技有限公司 | Carbon nanotube growth prediction evaluation model based on digital twin and AI and establishment method thereof |
| CN119891171A (en) * | 2024-12-27 | 2025-04-25 | 北京京能清洁能源电力股份有限公司内蒙古分公司 | New energy field safety monitoring method and system based on digital twin technology |
| CN119537083A (en) * | 2025-01-21 | 2025-02-28 | 国家工业信息安全发展研究中心 | Industrial Internet equipment fault prediction method and system based on digital twin |
| CN120046264A (en) * | 2025-01-23 | 2025-05-27 | 西峡县众德汽车部件有限公司 | Data twinning-based turbocharger shell three-dimensional model construction method |
| CN119556571A (en) * | 2025-01-24 | 2025-03-04 | 湖南伟村信息科技有限公司 | A lightweight processing method for digital twin models |
| CN119556571B (en) * | 2025-01-24 | 2025-05-16 | 湖南伟村信息科技有限公司 | Light-weight processing method for digital twin model |
| CN120313918A (en) * | 2025-02-07 | 2025-07-15 | 四川跃纳科技有限公司 | A performance test method for a small fluid thrust vector turbojet engine |
| CN119774901A (en) * | 2025-03-11 | 2025-04-08 | 一夫科技股份有限公司 | Preparation process adjusting method for gypsum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119149923A (en) | Digital twin method, system, computing device and storage medium based on industrial automation | |
| JP7069269B2 (en) | Semi-supervised methods and systems for deep anomaly detection for large industrial surveillance systems based on time series data using digital twin simulation data | |
| CN113570138B (en) | A method and device for predicting the remaining service life of equipment using a temporal convolutional network | |
| CN110442833A (en) | One kind assessing Wind turbines health state evaluation method based on various dimensions SCADA data | |
| CN115034147B (en) | Intelligent manufacturing system based on digital twins | |
| CN118739436B (en) | An algorithm for load output based on automatic adjustment of renewable energy output | |
| CN118881549B (en) | A pump pressure pulsation prediction system and method based on digital twin | |
| CN110737948A (en) | method for predicting residual life of aero-engine based on deep FNN-LSTM hybrid network | |
| CN114676887A (en) | A river water quality prediction method based on graph convolution STG-LSTM | |
| CN119209886A (en) | A power plant load visualization control method and system based on digital twin | |
| CN113988210A (en) | Distorted data restoration method, device and storage medium for structural monitoring sensor network | |
| CN114201825A (en) | Evaluation method and system for equipment performance degradation state based on combined features | |
| CN120046430A (en) | Hydrogen fuel cell production management method and system based on digital twin technology | |
| Wang et al. | Hierarchical graph neural network with adaptive cross-graph fusion for remaining useful life prediction | |
| CN111400850B (en) | Equipment fault analysis method, device, equipment and storage medium | |
| Lutska et al. | Forecasting the efficiency of the control system of the technological object on the basis of neural networks | |
| CN116722653A (en) | A power system dynamic state detection method and system | |
| CN119966504B (en) | A port communication optical cable routing detection method and system based on digital twin | |
| CN119844315B (en) | Wind turbine running state analysis method and system based on rotation speed monitoring | |
| CN107818523B (en) | Discrimination and Inference Method of Data Truth Value of Power Communication System Based on Unsteady Frequency Distribution and Frequency Factor Learning | |
| CN115438897A (en) | Industrial process product quality prediction method based on BLSTM neural network | |
| CN119356124A (en) | Control method and system for assembly equipment | |
| Caricato et al. | Prognostic techniques for aeroengine health assessment and Remaining Useful Life estimation | |
| Ayub et al. | Health Index Estimation of Wind Power Plant Using Neurofuzzy Modeling | |
| Gultekin et al. | Predictive analytics in IoT and CPS: Enhancing industrial machinery reliability through sensor data-driven remaining useful life estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20241217 |