Method for Constructing a Full-Element Digital Twin Model of a Testing Laboratory and an Intelligent Operation and Maintenance System

Abstract

The present invention discloses a method for constructing a full-element digital twin model of a testing laboratory and an intelligent operation and maintenance system, which relates to the field of digital twins. The full-element digital twin model includes: a physical object model of the testing laboratory, a virtual model of the testing laboratory, a full-element data model, a data interaction model, a learning and decision-making model, and an operation and maintenance management model. The physical object model and the virtual model of the testing laboratory maintain real-time mapping; the full-element data model collects, inputs, processes, and updates multi-source heterogeneous data in the digital twin model of the testing laboratory; the data interaction model fuses and transmits real-time data among the models; at the same time, the learning and decision-making model makes autonomous decisions and diagnoses, and through the operation and maintenance management model, function integration and display are carried out, further improving the intelligent operation and maintenance level of the testing laboratory. The digitalization of the entire testing process of the testing laboratory is realized, the communication cost in the testing process is saved, the labor and time costs are saved, and the testing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and more specifically, to a method for constructing a full-element digital twin model of a testing laboratory and an intelligent operation and maintenance system. Background Art

[0002] A testing laboratory is a place for technical operations that determine one or more characteristics or performances of a given product, material, equipment, organism, physical phenomenon, process, or service according to specified procedures. Testing laboratories play an extremely important role in the production and R & D processes of the equipment manufacturing industry. The test results and test reports are key data that large-scale equipment manufacturing enterprises focus on in goals such as improving production processes, enhancing product performance, and reducing production costs.

[0003] During the operation of a testing laboratory, the biggest obstacle to achieving low-cost operation and maintenance management of the testing laboratory is the labor-intensive and time-consuming statistical collation work of test data. It is difficult to comprehensively grasp the real-time status of on-site personnel, equipment, materials, testing methods, testing environment, etc. The real-time test data and problem feedback of the laboratory, as well as the corresponding processing, are not timely enough. The statistical analysis of test data, the management of the test process, and the decision-making for problem handling mainly rely on the experience of the staff, and the work efficiency of the testing laboratory is low, and it is impossible to quickly and accurately analyze and mine a large amount of test data. Summary of the Invention

[0004] In view of this, the present invention provides a full-element digital twin model and an operation and maintenance system for a testing laboratory operation and maintenance system, which are used to solve the problem of low efficiency in the existing testing laboratory operation and maintenance management.

[0005] To achieve the above object, the following solutions are proposed:

[0006] A method for constructing a full-element digital twin model of a testing laboratory, comprising:

[0007] Step 1: For the testing laboratory, specifically analyze the physical objects and data acquisition objects of the testing laboratory, and construct a physical object model of the testing laboratory, where the physical object model of the testing laboratory is , where EO is the physical object of the testing laboratory, and DCO is the data acquisition object of the testing laboratory; the physical objects of the testing laboratory include the laboratory layout, testing equipment, samples to be tested, testing personnel, and testing conditions; the data acquisition objects of the testing laboratory include data acquisition equipment and data transceiver modules. The data acquisition equipment includes testing-related sensors and PLC-based laboratory data acquisition equipment, and the data transceiver modules include data acquisition gateways and industrial switches;

[0008] Step 2: Based on the physical object model of the testing laboratory, construct a virtual model of the testing laboratory based on digital twins, where the virtual model of the testing laboratory is where GM is the geometric model of the test laboratory; RM is the rule model of the test laboratory; FM is the process model of the test laboratory. The geometric model of the test environment and test equipment is constructed by means of 3D scanning modeling, point cloud data processing and mesh patch rendering. The process model of the laboratory is established by sorting out the mechanism coupling relationship between the basic information and the test process information of the test laboratory. The rule model of the laboratory is constructed through the geometric model of the laboratory, the process model of the laboratory, the linkage of multiple device mechanisms and the operation and maintenance system function of cross-regional test data sharing.

[0009] Step 3: Based on the test laboratory data sets of each model, construct a full-element data model of the test laboratory, where the full-element data model is ; is the test laboratory environment configuration data set generated when running the physical object model of the test laboratory; is the basic data of the test equipment, the geometric model simulation data and the process model test result data when running the virtual model of the test laboratory; and are the operation and maintenance status data and operation and maintenance knowledge data generated when running the operation and maintenance management system and function display respectively; is the decision optimization data set formed by running the learning decision model to autonomously analyze, learn and make decisions on the above multi-source data;

[0010] Step 4: According to the test laboratory operation and maintenance management tasks, construct an operation and maintenance management model, where the operation and maintenance management model is , where TS is the technical service module, UT is the user service module, and FA is the function application module;

[0011] The technical service module is a set of technical services required for function operation, and the technical service module is:

[0012]

[0013] is the model service module, is the data service module, is the comprehensive service module;

[0014] The user service module is a service support constructed based on the full-element resources of people-machine-material-method-environment-measurement-audit around the entire test process; the function application module is used to integrate the function services required in the test laboratory operation and maintenance management process.

[0015] Step 5: Construct a learning decision model to analyze the status of the test equipment in the test laboratory for the real-time data received by the data interaction model, where the learning decision model is , Execution control is carried out according to the action strategy selected based on the detection task and laboratory environment information. The reward and punishment mechanism includes a reward function and a punishment function. Set conditions for the algorithm.

[0016] Step 6: Based on the constructed physical object model of the detection laboratory, virtual model of the detection laboratory, operation and maintenance management model, learning and decision-making model, and all-element data model, analyze the data interaction relationships among the models of the detection laboratory, and construct a data interaction model of the detection laboratory. Among them, the data interaction model is , , and are respectively the real-time data interactions between the physical object model of the detection laboratory and the all-element data model, virtual model of the detection laboratory, and operation and maintenance management model; and are respectively the real-time data interactions between the virtual model of the detection laboratory and the all-element data model and operation and maintenance management model; is the real-time data interaction between the operation and maintenance management model and the all-element data model; is the real-time data interaction between the all-element data model and the learning and decision-making model;

[0017] Step 7: Based on the constructed models of the detection laboratory, analyze the correlation relationships in the detection process for the entire detection process and all detection elements, and construct an element digital twin model for the staff to build an intelligent operation and maintenance system for the detection laboratory based on the all-element digital twin model. Among them, the all-element digital twin model is .

[0018] Preferably, in step 2, the process model is used to control the docking process of the overall business process of the detection laboratory; the rule model is used to describe and depict the test information and detection process of the sample to be tested.

[0019] The basic information for constructing the process model includes: laboratory environment, test conditions, detection equipment, and operators; the detection process information includes test entrustment, test execution, and report release.

[0020] Preferably, in step 3, the detection laboratory environment configuration data set includes: operating status of detection equipment, test personnel configuration, detection cycle, laboratory power supply, ventilation, and temperature and humidity environment;

[0021] The operation and maintenance status data generated during the operation of the operation and maintenance management system includes data type conversion, preprocessing, classification, and integration;

[0022] The operation and maintenance knowledge data includes inspection records, repair and maintenance records, detection expert knowledge and experience, detection equipment operation manuals, and laboratory management plans.

[0023] Preferably, the process of the learning and decision-making model analyzing the state of the testing equipment in the testing laboratory based on the real-time data received by the data interaction model includes:

[0024] After the learning and decision-making model receives the real-time data transmitted by the data interaction model, it matches the real-time data from different sources with the algorithms in the preset algorithm set, and performs fault diagnosis, anomaly detection, remaining useful life prediction, and multi-objective optimization on the testing equipment in the testing laboratory based on the matched algorithms.

[0025] Preferably, in step five, the execution control performed according to the action strategy selected based on the testing task and laboratory environment information includes: installation of the sample to be tested, parameter setting, performance testing, environmental adaptability testing, data collection and analysis, and report compilation;

[0026] The reward function in the reward and punishment mechanism is used to motivate the operator to select the current action strategy signal, and the punishment function is used to adjust the operator's current action strategy signal. Among them, the reward function includes action reward, position reward, and distance reward, and the punishment function includes collision punishment, in-area punishment, and time punishment;

[0027] The algorithm setting conditions are the conditions required to complete the learning and decision-making training, including algorithm network structure design, training parameter setting, and round termination condition setting.

[0028] Preferably, in step seven, the full elements of the detection include detector - detection equipment - detection sample - detection method - detection environment - detection result - report review; the full process of the detection includes test environment configuration, detector operation, laboratory operation and maintenance management, system intelligent decision-making, and detection report generation.

[0029] A testing laboratory intelligent operation and maintenance system is constructed based on the full-element digital twin model constructed by the foregoing construction method. The system architecture includes: a testing laboratory, a system support layer, a twin model layer, and an application display layer;

[0030] The system function modules include a laboratory operation module, a laboratory management module, a test equipment management module, and a test data analysis module.

[0031] As can be seen from the above technical solution, the present invention provides a method for constructing a full-element digital twin model of a testing laboratory and an intelligent operation and maintenance system. The constructed full-element digital twin model includes: a physical object model of the testing laboratory, a virtual model of the testing laboratory, a full-element data model, a data interaction model, a learning and decision-making model, and an operation and maintenance management model. The full-element data model is used to collect, input, process, and update multi-source heterogeneous data in the full-element digital twin model; the data interaction model fuses and transmits real-time data between various models in the full-element digital twin model through a preset communication protocol. The present invention realizes the digitization of the testing process. Through the real-time mapping of the physical object model of the testing laboratory and the virtual model of the testing laboratory, the communication cost in the testing process is saved, the labor and time costs are saved, and the testing efficiency is improved. At the same time, machine learning algorithms are introduced for autonomous decision-making and diagnosis, further improving the intelligent operation and maintenance control level of the testing laboratory.

[0032] The digital system effectively avoids human errors and omissions, further improving the accuracy of the test report. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to the provided drawings.

[0034] Figure 1 Schematic diagram of the relationships between various models of a full-element data twin model of a testing laboratory provided by an embodiment of the present invention;

[0035] Figure 2 Schematic diagram of the construction process of the full-element data model provided by an embodiment of the present invention;

[0036] Figure 3 Schematic diagram of the full-element resource data provided by an embodiment of the present invention;

[0037] Figure 4 Full testing flow chart provided by an embodiment of the present invention;

[0038] Figure 5 Flow chart of the construction of the learning and decision-making model provided by an embodiment of the present invention;

[0039] Figure 6 Architecture diagram of the testing laboratory operation and maintenance system provided by an embodiment of the present invention;

[0040] Figure 7 Flow chart of the construction of the testing laboratory operation and maintenance system provided by an embodiment of the present invention;

[0041] Figure 8 Schematic diagram of the functions of the detection laboratory operation and maintenance system provided by the embodiments of the present invention. Detailed implementation manners

[0042] Next, the accompanying drawings in the embodiments of the present invention will be combined to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] First, in combination with Figure 1 the all-element digital twin model of the detection laboratory operation and maintenance system provided by the embodiments of the present invention will be introduced. The present invention constructs an all-element digital twin model for the detection laboratory operation and maintenance system based on the entire detection process of the detection laboratory, all-element detection data, and multi-layer twin model analysis :

[0044] .

[0045] All-element digital twin model of the detection laboratory operation and maintenance system includes the physical object model PM of the detection laboratory, the virtual model VM of the detection laboratory, the all-element data model DD, the data interaction model CN, the learning and decision-making model LD, and the operation and maintenance management model Ss. The relationships between the models are as Figure 1 shown.

[0046] The physical object model PM and the virtual model VM of the detection laboratory are the general basic models of the all-element digital twin model of the detection laboratory .

[0047] The all-element data model DD is the core driving model of the all-element digital twin model of the detection laboratory, responsible for collecting, inputting, processing, and updating the multi-source heterogeneous data in the all-element digital twin model . The data is uniformly stored in a database, and different data management systems are established for different models such as the physical object model PM of the detection laboratory, the virtual model VM of the detection laboratory, and the operation and maintenance management model Ss, to drive the dynamic operation of each model in the all-element digital twin model in real time. The data interaction model CN transmits real-time data in the all-element digital twin model through a preset communication protocol

[0048] ​Fusion transmission is carried out among the models. The data interaction model, through a series of communication protocols and communication devices, transmits all-element real-time data such as physical perception data, simulation data, and control instruction signals among the models of the all-element digital twin model for fusion transmission, enabling the physical object model PM of the test laboratory and the virtual model VM of the test laboratory to maintain real-time mapping.

[0049] The learning and decision-making model LD is based on the all-element data model DD as the driving foundation. The learning and decision-making model LD analyzes the status of the testing equipment in the test laboratory through the real-time data received by the data interaction model CN, obtains the analysis results, and feeds back the analysis results to the operation and maintenance management model Ss for display. After receiving the real-time data transmitted by the data interaction model CN, the learning and decision-making model LD matches the real-time data from different sources with the algorithms in the preset algorithm set, and analyzes the status of the testing equipment in the test laboratory based on the matched algorithms. The preset algorithm set can be an intelligent operation and maintenance decision algorithm set formed by calling a series of machine learning algorithms such as gradient boosting, denoising autoencoders, support vector machines, and deep belief networks. Use powerful computing resources for offline training of intelligent operation and maintenance algorithms and model deployment. Conduct fault diagnosis, anomaly detection, remaining useful life prediction, and multi-objective optimization of the laboratory testing equipment through the real-time data received by the data interaction model CN.

[0050] The operation and maintenance management model Ss, based on the existing model technology support and user terminal requirements, realizes function applications such as operation and maintenance management of the test laboratory / test equipment and test data analysis through the big data storage / calculation / mining / analysis technology in the all-element data model DD and the predictive maintenance technology of testing equipment based on artificial intelligence in the learning and decision-making model LD. Laboratory staff can adjust and optimize the management strategy according to the analysis results displayed by the operation and maintenance management model Ss, realizing the intelligent operation and maintenance of the test laboratory.

[0051] As can be seen from the above technical solutions, the embodiments of the present invention provide a method for constructing a full-element digital twin model of a testing laboratory and an intelligent operation and maintenance system. The constructed full-element digital twin model includes: a physical object model of the testing laboratory, a virtual model of the testing laboratory, a full-element data model, a data interaction model, a learning and decision-making model, and an operation and maintenance management model. The full-element data model is used to collect, input, process, and update multi-source heterogeneous data in the full-element digital twin model; the data interaction model fuses and transmits real-time data between various models in the full-element digital twin model through a preset communication protocol. The embodiments of the present invention realize the digitization of the testing process. Through the real-time mapping of the physical object model of the testing laboratory and the virtual model of the testing laboratory, the communication cost of the testing process is saved, the labor and time costs are saved, and the testing efficiency is improved. At the same time, machine learning algorithms are introduced for autonomous decision-making and diagnosis, further improving the intelligent operation and maintenance control level of the testing laboratory.

[0052] Next, the embodiments of the present invention introduce a method for constructing a full-element digital twin model of a testing laboratory, and the process is as follows:

[0053] Step 1: For the testing laboratory, specifically analyze the entity objects and data collection objects of the testing laboratory, and construct a physical object model of the testing laboratory.

[0054] Specifically, the physical object model PM is the basis of the full-element digital twin model, and is the main part of the operation and maintenance system and the collection of various management elements. It mainly includes the entity objects (EO, Enity Objects) of the testing laboratory and the data collection objects (DCO, Data Collection Objects). The physical object model of the testing laboratory is . The entity objects of the testing laboratory include elements such as laboratory layout, testing equipment, samples to be tested, and operators; the data collection objects of the testing laboratory include testing-related sensors, PLCs and other laboratory data collection devices, and data transceiver modules such as data acquisition gateways and industrial switches.

[0055] Step 2: Based on the physical object model of the testing laboratory, construct a virtual model of the testing laboratory based on digital twin.

[0056] Specifically, the virtual model VM of the testing laboratory is the engine of the full-element digital twin model, and is the real-time mapping of the physical object model of the testing laboratory in the virtual scene. It mainly includes the geometric model (Geometry Model, GM), rule model (Rule Model, RM), and process model (Flow Model, FM) of the laboratory. The virtual model of the testing laboratory is .

[0057] Construct the laboratory geometric models of the test environment and testing equipment through 3D scanning and modeling, point cloud data processing, and mesh patch rendering. For example: Use the environmental scanning method to construct the geometric parameters and physical motion characteristics of the equipment and environment in the testing laboratory. Based on the entity objects in the physical object model of the testing laboratory, construct a 3D simulation model through 3D rendering and model lightweighting engine to realize the construction, rendering, and lightweight optimization of the laboratory geometric simulation models of the test environment and testing equipment.

[0058] By sorting out the mechanism coupling relationship between the basic information and the testing process information of the testing laboratory, establish the laboratory process model. Among them, the basic information includes the laboratory environment, test conditions, testing equipment, operators, etc.; the testing process information includes test entrustment, test execution, and report release, etc. By sorting out the coupling relationship and related mechanism formulas in the basic information and the testing process information, the process model is used to control the overall business process docking process of the testing laboratory, solve the problems of resource scheduling and report release in the testing process, realize the standardization and visualization of the business process of the testing laboratory, and improve the operation and maintenance efficiency.

[0059] Construct the laboratory rule model through a series of operation and maintenance system functions such as the geometric model of the testing laboratory, the laboratory process model, the linkage of multiple equipment mechanisms, and the sharing of test data across regions. The rule model is used to completely describe and depict the test information and testing process of the samples to be tested.

[0060] Step 3: Based on the test dataset of each model of the testing laboratory, construct the full-element data model of the testing laboratory.

[0061] Specifically, the full-element data model DD is as Figure 2 shown. The acquisition and drive interaction of the full-element data model DD is the power source of the actual testing laboratory operation and maintenance management system. The full-element data model DD is for the full-element data of the testing process such as Figure 3 shown as "man-machine-material-method-environment-measurement-review". The full-element data model is , where is the test laboratory environment configuration dataset generated when running the physical object model of the testing laboratory, including the laboratory site, environment, test condition templates, operating status of test equipment and personnel configuration, test cycle, laboratory power supply, ventilation, temperature and humidity environment, and operation data of each facility and its corresponding lighting, ventilation, water, electricity, gas, etc.; is the basic data of test equipment, geometric model simulation data, and process model test result data when running the virtual model of the testing laboratory; and are the operation and maintenance status data and operation and maintenance knowledge data generated when running the operation and maintenance management model respectively; The decision optimization dataset formed by autonomously analyzing, learning, and making decisions on the above multi-source data for running the learning decision model.

[0062] Data of the virtual model of the testing laboratory , including basic equipment data such as test equipment number, name, model, manufacturer, quantity, unit price, purchase date, and affiliated laboratory ; geometric model simulation data of the test equipment such as startup, shutdown, failure, and equipment test results ; process model test result data such as supported test items, test standards, test methods, operating parameters, and test results .

[0063] Operation and maintenance status data including data type conversion, preprocessing, classification, integration, etc. generated during the operation of the operation and maintenance management system and function display; operation and maintenance knowledge data including inspection records, maintenance records, expert knowledge and experience in testing, operation manuals of testing equipment, spare parts management and replacement records, and laboratory management plans, etc.

[0064] The learning decision model mutually complements and integrates the above multi-source data and combines with the random forest algorithm for autonomous analysis, learning, and decision-making, realizing the optimization prediction of production scheduling management plans such as equipment maintenance and personnel arrangement in each testing laboratory, and forming a decision optimization dataset. The learning decision model LD combines historical statistical data, real-time monitoring data, and process twin data, etc. for autonomous analysis, learning, decision-making, and reasoning, realizing the optimization prediction of production scheduling management plans such as equipment maintenance and personnel arrangement in each testing laboratory, analyzing data such as the number of contracts, working hours, and contract amounts over the years, improving the utilization rate of testing equipment and maximizing the testing capacity.

[0065] Step 4: Construct an operation and maintenance management model according to the operation and maintenance management tasks of the testing laboratory.

[0066] Specifically, the operation and maintenance management model Ss is a full-element digital twin model The purpose is to realize the service set required for the operation and maintenance management tasks of the testing laboratory. It includes a technical service module TS, a user service module UT, and a function application module FA. Among them, the operation and maintenance management model is , TS is the technical service module, UT is the user service module, and FA is the function application module. The technical service module is a set of technical services required for function operation, and the technical service module is . The technical service module includes a model service module for model services such as model construction, rendering, and baking ; a data service module for data services such as database design, data analysis, processing, and storage ; An integrated service module for integrated services such as interface encapsulation, communication protocols, and algorithm verification

[0067] User service module is the service support required for the LIMS system constructed based on all-element resources around people - machines - materials - methods - environment - measurement - audit throughout the entire detection process. The detection business process is as Figure 4 shown, including links such as customer commission - task registration and assignment - sample receipt and delivery - test scheduling and execution - report compilation / verification / issuance / archiving. The entire detection process includes detection test tasks, detection equipment management, detection sample management, detection process monitoring, detection data optimization, detection environment configuration, operation and maintenance decision analysis, online report generation, and operation and maintenance guidance training, etc. The functional application module FA is the functional service required for the operation and maintenance management process of the detection laboratory, including laboratory operation, laboratory management, laboratory equipment management, and laboratory data analysis, etc.

[0068] Step Five: Construct a learning and decision-making model to analyze the status of the detection equipment in the detection laboratory based on the real-time data received by the data interaction model.

[0069] Specifically, the learning and decision-making model is , the execution control is carried out according to the action strategy selected based on the detection task and laboratory environment information, is the reward and punishment mechanism, including a reward function and a punishment function; is the condition setting for the algorithm;

[0070] The execution control carried out according to the action strategy selected based on the detection task and laboratory environment information includes: installation of samples to be tested, parameter setting, performance testing, environmental adaptability testing, data collection and analysis, and report compilation.

[0071] Reward and punishment mechanism is the evaluation mechanism for the execution control The reward function in the reward and punishment mechanism is used to encourage the operator to select the current action strategy signal, and the punishment function is used to adjust the operator's current action strategy signal. Among them, the reward function includes action reward, position reward, and distance reward, and the punishment function includes collision penalty, in-region penalty, and time penalty.

[0072] Algorithm setting conditions are the conditions required to complete the learning and decision-making training, including algorithm network structure design, training parameter setting, and round termination condition setting.

[0073] The learning and decision-making model LD is a full-element digital twin model Provide data-driven methods and intelligent algorithms to solve the hidden faults existing in the testing equipment of the testing laboratory; usually, hidden faults mostly occur in the operating mechanisms composed of the internal mechanical system and electrical system of the testing equipment, and the fault factors include bearing vibration, motor voltage and current, motor resistance temperature, etc. The fault factors are complex and there is a coupling effect, and it is difficult for the operation and maintenance management personnel of the testing laboratory to detect and judge only through the appearance of the components.

[0074] The construction process of the learning decision model LD is as Figure 5 shown. By collecting real-time multi-source data such as the operating status of the testing laboratory equipment, equipment testing tasks, and the fault status of key equipment and components, and constructing training sample data with the historical testing equipment data in the database, feature extraction algorithms such as stacked denoising autoencoders and support vector machines are used to obtain the relevant fault features of the testing equipment and determine the key coupling factors, and then algorithms such as random forest, GBDT, and XGBOOST based on gradient ascent are used for model training to achieve predictive maintenance of the testing equipment.

[0075] After the learning decision model LD receives the real-time data transmitted by the data interaction model, it matches the real-time data from different sources with the algorithms in the preset algorithm set, and analyzes the fault diagnosis, anomaly detection, remaining service life prediction, and multi-objective optimization of the testing equipment in the testing laboratory based on the matched algorithms. For the hidden faults that are difficult to detect and judge in the testing equipment, an intelligent operation and maintenance decision algorithm set is established using machine learning algorithms, the multi-source heterogeneous real-time data is matched with the algorithm set, and it is continuously iteratively optimized through online learning decision and offline algorithm training and associated with the operation and maintenance management model Ss in the system, thereby reducing the operation and maintenance difficulty.

[0076] Step 6: Based on the constructed physical object model, virtual model, operation and maintenance management model, learning decision model, and full-element data model of the testing laboratory, analyze the data interaction relationship between the models of the testing laboratory, and construct the data interaction model of the testing laboratory.

[0077] Specifically, the data interaction model CN is the artery of the full-element digital twin model and is the core to realize the dynamic operation of the system and the integration of the virtual and real spaces. Among them, the data interaction model is:

[0078]

[0079] is the interaction between PM and DD, Multiple sensor nodes are combined to form a self-organizing network to collect and detect information of the physical object model PM in the test laboratory. For the equipment layer (equipment controller), acquisition layer (data acquisition hardware / system), and management layer (data acquisition management platform) in the test laboratory, a low-cost communication network based on industrial Ethernet is constructed, and the data of the physical object model PM in the test laboratory collected is transmitted to the all-element data model DD. At the same time, For the interaction between PM and Ss, each controller in the physical object model PM of the test laboratory can receive feedback data and generate control instructions to adjust and optimize the operation and maintenance management process of the test laboratory.

[0080] For the interaction between PM and VM, Using a similar implementation method, the real-time collected data is transmitted to the virtual model VM of the test laboratory to drive the virtual model VM of the test laboratory to perform dynamic simulation. At the same time, data such as the simulation results, prediction and forecasting, and decision-making schemes of the virtual model of the test laboratory are converted into relevant control instructions and transmitted to the corresponding physical entities in the physical object model PM of the test laboratory for real-time control and management.

[0081] For the interaction between VM and DD, It is to establish a connection with the database through interface technologies such as JDBC and ODBC, transmit data such as learning strategies, simulation simulations, and management plans to the all-element data model DD for storage in real time, and can read the latest data in the database to drive the construction of the virtual model VM of the test laboratory.

[0082] For the interaction between VM and Ss, It is to establish a data connection between the virtual model VM of the test laboratory and the operation and maintenance management model Ss through communication mechanisms such as TCP / IP to realize data sending and receiving, synchronous update, instruction transfer, etc. between the virtual model VM of the test laboratory and the operation and maintenance management model Ss.

[0083] For the interaction between Ss and DD, Using a similar technology to establish a real-time connection with the database, transmit the data generated during the operation of the operation and maintenance management model Ss to the database for storage, and can also read historical data, model parameters, and common algorithms in the database in real time to support the operation and optimization of the operation and maintenance management model Ss.

[0084] For the interaction between DD and LD, It uses communication mechanisms such as Socket to connect and interact the learning environment with an external trainer, combines twin data and environmental information for learning and decision-making to obtain an optimal management strategy, and stores the learning results in the twin database.

[0085] Step 7: Based on the models of the constructed detection laboratory, analyze the correlation relationships in the detection process for the entire detection process and all detection elements, and construct an element digital twin model for the staff to build an intelligent operation and maintenance system for the detection laboratory based on the all-element digital twin model.

[0086] Specifically, the all-element digital twin model is .

[0087] The all-element digital twin model provided by the embodiments of the present invention includes a multi-level twin model of a detection equipment digital twin model, a detection process digital twin model, and a detection laboratory operation and maintenance management digital twin model.

[0088] The embodiments of the present invention construct an all-element digital twin model for the operation and maintenance system of the detection laboratory, use data acquisition devices such as sensors and PLCs to construct a virtual model of the detection laboratory that can truly reflect the real-time state of the physical object model of the laboratory, realize the mapping from the physical object model of the detection laboratory to the virtual model of the detection laboratory, and collect the data sets generated during the test process in real time, further improving the operation and maintenance efficiency of the detection laboratory.

[0089] Based on the all-element digital twin model constructed above, the embodiments of the present invention design an operation and maintenance system for a detection laboratory based on digital twins, as Figure 6 shown. The system architecture mainly includes: a detection laboratory, a system support layer, a data acquisition layer, and an application display layer, etc. Design is carried out according to the system construction process as Figure 7 shown.

[0090] Combined with the functional requirements of the detection laboratory, the functional modules of the detection laboratory operation and maintenance system include a laboratory operation module, a laboratory management module, a test equipment management module, and a test data analysis module. As Figure 8 shown, the detection laboratory operation and maintenance system includes 4 major functional modules and 23 functions, which can realize data acquisition, data monitoring, data query, data curve, data statistics, data report, system integration and general functions of the detection laboratory, support standard communication protocols of more than 50 mainstream control systems,

[0091] The operation and maintenance system of the testing laboratory is developed based on the overall system architecture and related functional modules, and is developed and deployed in a front-end and back-end separated manner. Among them, the front-end is developed based on technologies such as React, zustand, and less, receiving and displaying device data, and the back-end provides device data interfaces and real-time mqtt data. The operation and maintenance system can realize operation and maintenance management such as the operation management of the testing laboratory, the management of test equipment, and the analysis of test data.

[0092] Based on digital twin technology, through means such as virtual-real interaction feedback, data fusion analysis, and decision iteration optimization in the full-element digital twin model, an intelligent operation and maintenance system for testing laboratories based on digital twin is developed to monitor, diagnose, simulate, make decisions, and control the entire life cycle process of the physical entities in the testing laboratory, realizing visual operation and maintenance management of the testing process and the digital transformation and upgrading of the testing laboratory.

[0093] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0094] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts among the various embodiments can be referred to each other.

[0095] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a full-factor digital twin model of a testing laboratory, characterized in that: include: Step 1: Analyze the physical objects and data collection objects of the detection laboratory and build a physical object model of the detection laboratory. EO is the physical object of the testing laboratory, and DCO is the data collection object of the testing laboratory; the physical object of the testing laboratory includes the laboratory layout, testing equipment, tested samples, testing personnel, and testing conditions; the data collection object of the testing laboratory includes data collection equipment and data transceiver modules. The data collection equipment includes laboratory data collection equipment for testing related sensors and PLCs, and the data transceiver modules include data collection gateways and industrial switches; Step 2: Based on the physical object model of the test laboratory, a virtual model of the test laboratory based on digital twin is constructed. GM is the geometric model of the testing laboratory; RM is the rule model of the testing laboratory; FM is the process model of the testing laboratory; the laboratory geometric model of the test environment and testing equipment is constructed by means of 3D scanning modeling, point cloud data processing and mesh surface rendering; the laboratory process model is established by combing the mechanism coupling relationship between the basic information of the testing laboratory and the testing process information; the laboratory rule model is constructed through the laboratory geometric model, laboratory process model and the operation and maintenance system functions of multi-equipment mechanism linkage and cross-regional test data sharing; Step 3: Based on the test laboratory data sets of each model, construct the full-factor data model of the test laboratory, where the full-factor data model is ; a test lab environment configuration data set generated when running the test lab physical object model; The basic data of the test equipment, the simulation data of the geometric model and the test result data of the process model when running the virtual model of the test laboratory; and They are respectively the operation and maintenance status data and operation and maintenance knowledge data generated when running the operation and maintenance management system and function display; In order to run the learning decision model, the above multi-source data is autonomously analyzed, learned and decided to form a decision optimization data set; Step 4: According to the operation and maintenance management tasks of the testing laboratory, build an operation and maintenance management model, where the operation and maintenance management model is , TS is the technical service module, UT is the user service module, and FA is the functional application module; The technical service module is a collection of technical services required for the function operation. The technical service modules are: For the model service module, For the data service module, It is a comprehensive service module; The user service module is a service support built around the full-factor resources of man-machine-material-method-environment-test-audit in the whole process of testing; the functional application module is used to integrate the functional services required in the operation and maintenance management of the testing laboratory; Step 5: Construct a learning decision model to analyze the status of the testing equipment in the testing laboratory based on the real-time data received by the data interaction model. The learning decision model is , It is the execution control based on the action strategy selected according to the detection task and laboratory environment information. The reward and punishment mechanism includes reward function and penalty function. Set conditions for the algorithm; Step 6: Based on the constructed physical object model of the testing laboratory, the virtual model of the testing laboratory, the operation and maintenance management model, the learning decision model and the full-factor data model, the data interaction relationship between the various models of the testing laboratory is analyzed, and the data interaction model of the testing laboratory is constructed. , , and They are the real-time data interaction between the physical object model of the testing laboratory and the full-factor data model, the virtual model of the testing laboratory and the operation and maintenance management model; and They are the real-time data interaction between the virtual model of the testing laboratory and the full-factor data model and the operation and maintenance management model respectively; To provide real-time data interaction between the operation and maintenance management model and the full-factor data model; Real-time data interaction between the full-factor data model and the learning decision model; Step 7: Based on the constructed models of the testing laboratory, analyze the correlation between the testing process and all the elements of the testing process, and build a digital twin model of the elements, so that the staff can build an intelligent operation and maintenance system for the testing laboratory based on the full-element digital twin model. The full-element digital twin model is .

2. The method for constructing a full-factor digital twin model of a detection laboratory according to claim 1, characterized in that: In step 2, the process model is used to control the docking process of the overall business process of the testing laboratory; The rule model is used to describe and characterize the test information and detection process of the sample to be tested; The basic information for constructing the process model includes: laboratory environment, test conditions, testing equipment and operators; Testing process information includes test commissioning, test execution and report release.

3. The method for constructing a full-factor digital twin model of a detection laboratory according to claim 1, characterized in that: In step 3, the test laboratory environment configuration data set includes: test equipment operation status, test personnel configuration, test cycle, laboratory power supply, ventilation and temperature and humidity environment; The operation and maintenance status data generated during the operation of the operation and maintenance management system includes data type conversion, preprocessing, classification and integration; Operation and maintenance knowledge data includes inspection records, repair and maintenance records, knowledge and experience of testing experts, testing equipment manuals and laboratory management plans.

4. The method for constructing a full-factor digital twin model of a testing laboratory according to claim 1 is characterized in that: The process of the learning decision model analyzing the status of the testing equipment in the testing laboratory based on the real-time data received by the data interaction model includes: After the learning decision model receives the real-time data transmitted by the data interaction model, it matches the real-time data from different sources with the algorithms in the preset algorithm set, and performs fault diagnosis, anomaly detection, remaining service life prediction and multi-objective optimization on the testing equipment in the testing laboratory based on the matched algorithms.

5. The method for constructing a full-factor digital twin model of a testing laboratory according to claim 1 is characterized in that: In step 5, the execution control is performed based on the action strategy selected according to the detection task and the laboratory environment information, including: installation of the sample to be tested, parameter setting, performance testing, environmental adaptability testing, data collection and analysis, and report preparation; The reward function in the reward and punishment mechanism is used to motivate the operator to select the current action strategy signal, and the penalty function is used to adjust the operator's current action strategy signal. The reward function includes action reward, position reward and distance reward, and the penalty function includes collision penalty, intra-region penalty and time penalty. The algorithm setting conditions are the conditions that need to be set to complete learning and decision-making training, including algorithm network structure design, training parameter setting, and round termination condition setting.

6. The method for constructing a full-factor digital twin model of a detection laboratory according to any one of claims 1 to 5, characterized in that: In step seven, all the testing elements include testing personnel-testing equipment-testing samples-testing methods-testing environment-testing results-report review; the entire testing process includes test environment configuration, testing personnel operation, laboratory operation and maintenance management, system intelligent decision-making and test report generation.

7. An intelligent operation and maintenance system for a testing laboratory, characterized in that: The full-factor digital twin model constructed based on the construction method of any one of claims 1 to 6 is constructed, and the system architecture includes: a testing laboratory, a system support layer, a twin model layer, and an application display layer; The system functional modules include laboratory operation module, laboratory management module, test equipment management module and test data analysis module.

Images