A method for constructing a digital twin simulation and debugging teaching platform

Abstract

The present invention relates to the technical field of simulation modeling, and discloses a method for constructing a digital twin simulation and debugging teaching platform, the method comprising: collecting operating data of an actual system, the data comprising data of various sensors and controllers, and data of human-computer interaction, and performing denoising, interpolation and normalization operations on the collected data to obtain pre-processed system operating data; using a data-driven modeling simulation and debugging teaching platform based on the pre-processed system operating data, designing a virtual environment according to application scenarios and teaching objectives, the virtual scene is based on the simulation and debugging teaching platform, and constructing a twin simulation environment through digital images, sounds and video information; students interact with the twin simulation environment through teaching tools and collect interaction data in real time, and feed back the collected interaction data to the twin simulation environment for adjustment and optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of simulation modeling, and in particular to a method for constructing a digital twin simulation and debugging teaching platform. Background Art

[0002] Digital twin refers to the technology of simulating and debugging physical systems in the physical world through digital models. It is based on theories and methods in the fields of physical modeling, mathematical modeling and computer science, and can simulate the behavior and performance of real systems, and improve the design, operation and maintenance efficiency of physical systems through analysis and optimization of digital twins. Digital twin technology has broad application prospects in many fields such as manufacturing, energy, and urban planning. The simulation and debugging teaching method of digital twins is an important part of digital twin technology. It can provide a new teaching method by combining technical means such as virtual reality, interactive simulation and intelligent assistance, so that learners can perform actual operations and real-time feedback in a virtual environment, thereby deepening their understanding of system behavior and performance. The present invention proposes a method for constructing a simulation and debugging teaching platform for digital twins, which places learners in a virtual operating environment, allowing them to personally experience and perceive the behavior and performance of the system, so as to have a deeper understanding of the relevant knowledge. Summary of the invention

[0003] In view of this, the present invention provides a method for constructing a digital twin simulation and debugging teaching platform, the purpose of which is to: 1) propose a method for constructing a digital twin simulation and debugging teaching platform, which improves the effectiveness and experience in the field of experimental teaching through comprehensive data utilization, modeling method selection, virtual environment design and real-time interactive feedback; 2) adopt a data-driven analysis method based on rule mining for modeling, pay more attention to the mining of rules and logic, and improve the interpretability and generalization ability of the model; 3) when designing a virtual environment, the twin simulation environment is used as the basis, and a virtual scene is constructed in combination with digital images, sounds and video information. The comprehensive use of multimodal information can provide a more realistic and rich simulation experience, thereby enhancing students' sense of participation and learning effects.

[0004] To achieve the above purpose, the present invention provides a method for constructing a digital twin simulation and debugging teaching platform, comprising the following steps:

[0005] S1: Collecting the actual system operation data, including data from various sensors and controllers, and data from human-computer interaction, and performing denoising, interpolation and normalization operations on the collected data to obtain pre-processed system operation data;

[0006] S2: Using a data-driven modeling simulation debugging teaching platform based on the preprocessed system operation data, wherein a data-driven analysis method based on rule mining is the main implementation method for modeling the simulation debugging teaching platform;

[0007] S3: Design a virtual environment according to the application scenario and teaching objectives. The virtual scene is based on the simulation debugging teaching platform and constructs a twin simulation environment through digital images, sounds and video information;

[0008] S4: Students interact with the twin simulation environment through teaching tools and collect interaction data in real time, and then feed back the collected interaction data to the twin simulation environment for adjustment and optimization.

[0009] As a further improvement method of the present invention:

[0010] Optionally, in step S1, performing denoising, interpolation and normalization operations on the collected data to obtain pre-processed system operation data includes:

[0011] S21: Perform Kalman filtering on the collected data to obtain denoised system operation data;

[0012] S22: performing interpolation fitting on the denoised system operation data to fill in missing data to obtain fitted system operation data, wherein Newton interpolation is a main implementation method for the data fitting.

[0013] In step S21, Kalman filtering is performed on the collected data, including:

[0014] S31: Randomly initialized state estimate and covariance matrix P0;

[0015] S32: Perform state estimation based on the system's state transfer matrix F and the state at the previous moment The calculation formula is:

[0016]

[0017] According to the system state transfer matrix F, process noise covariance matrix Q and the covariance matrix of the previous moment, the covariance matrix P is predicted k-1|k-1 , the calculation formula is:

[0018] P k-1|k-1 =F*P k-1 *F T +Q

[0019] S33: Calculate the Kalman gain according to the predicted covariance matrix, and update the state estimation and covariance matrix;

[0020] S34: repeating steps S32 to S33 until all data points are processed;

[0021] in,

[0022] represents the estimate of the state at time k at time k-1;

[0023] P k-1|k-1 represents the uncertainty of the state estimate at time k at time k-1;

[0024] F represents the state transfer matrix;

[0025] Q represents the process noise covariance matrix.

[0026] In the step S33, the Kalman gain is calculated according to the predicted covariance matrix, and the state estimation and covariance matrix are updated, including:

[0027] S41: Calculate the Kalman gain K based on the predicted covariance matrix, the observation matrix H and the measurement noise covariance matrix R k , the calculation formula is:

[0028] K k =P k-1|k-1 *H T *(H*P k-1|k-1 *H T +R) -1

[0029] S42: Based on the predicted state estimation, Kalman gain and observation data z k Update state estimate The calculation formula is:

[0030]

[0031] S43: Update the covariance matrix P according to the predicted covariance matrix, Kalman gain and observation matrix k|k , the calculation formula is:

[0032] P k|k =(IK k *H)*P k-1|k-1

[0033] in,

[0034] represents the estimate of the state at time k at time k-1;

[0035] P k-|k-1 represents the uncertainty of the state estimate at time k at time k-1;

[0036] F represents the state transfer matrix;

[0037] Q represents the process noise covariance matrix;

[0038] K k represents the Kalman gain;

[0039] z k represents the observation value at time k;

[0040] H represents the observation matrix;

[0041] R represents the measurement noise covariance matrix;

[0042] represents the estimate of the state at time k;

[0043] P k|k represents the uncertainty of the state estimate at time k.

[0044] In the step S22, interpolation fitting is performed on the denoised system operation data, including:

[0045] S51: For data points {(x 0 ,y 0 ), (x 1 ,y 1 ),...,(x n ,y n )} Calculate the difference quotient and form a difference quotient table;

[0046] S52: Using the diagonal elements in the difference quotient table as polynomial coefficients to construct an interpolation polynomial f(x) to complete the fitting, the calculation formula is:

[0047] f(x)=f[x 0 ]+f[x 0 , x 1 ](xx 0 )+f[x 0 , x 1 , x 2 ](xx 0 )(xx 1 )+...+f[x 0 , x 1 , ..., x n ](x

[0048] -x 0 )(xx 1 )...(xx n-1 )

[0049] in:

[0050] n represents the number of data points;

[0051] x i represents the independent variable of the ith data point;

[0052] y i represents the dependent variable of the ith data point;

[0053] f[x i ] indicates that x i is the first-order derivative of the node;

[0054] f[x i , x j ] indicates that (x i , x j ) is the second-order derivative of the node;

[0055] f[x i , x j , x k ] indicates that (x i , x j , x k ) is the third-order derivative of the node;

[0056] f[x 0 , x 1 , ..., x n ]With (x 0 , x 1 , ..., x n ) is the nth-order derivative of the node.

[0057] In the step S2, a data-driven modeling simulation debugging teaching platform is used based on the preprocessed system operation data, including:

[0058] Run the data mining system operation rules from the preprocessed system, including:

[0059] S61: Initialize candidate set C 1 and the frequent set L 1 ;

[0060] S62: According to the frequent set L k-1 , generate candidate set C through self-join operation k ;

[0061] S63: For data set D, scan each transaction and count candidate set C k The number of times each item set appears in , and calculate its support;

[0062] S64: According to the minimum support threshold, filter out the item sets that meet the conditions to form the frequent set L k ;

[0063] S65: If L kIf it is empty, the iteration is terminated; otherwise, iterate steps S62 to S64;

[0064] S66: For frequent set L k For each item set in , enumerate all its non-empty subsets, and for each subset, calculate its support and confidence, and filter out the association rules that meet the minimum support and minimum confidence thresholds as the system operation rules.

[0065] Optionally, in step S3, constructing a twin simulation environment through digital image, sound and video information includes:

[0066] S71: adding tags and metadata to each image, sound and video clip, and extracting features of the image, sound and video data;

[0067] S72: Based on the labeled and feature-extracted data, a digital twin model is established to align and associate the image, sound, and video data with their corresponding digital twins, and to establish a mapping relationship between the real system and the digital model.

[0068] The digital twin model is established in step S72 to align and associate the image, sound and video data with their corresponding digital twins, including:

[0069] S81: Preprocess the image, sound and video data, represent different types of data in a unified vector, use a neural network model to extract features of the image, sound and video data, and obtain feature vectors of different modal data;

[0070] S82: The features extracted from different modal data are fused by attention mechanism to obtain a fused feature vector;

[0071] S83: Construct a deep neural twin mapping model to map multimodal features to the digital twin space, wherein the TripletNetwork structure is the network structure of the deep neural twin mapping model, and the correspondence between multimodal data and digital twins is learned by sharing weights.

[0072] In the step S82, the features extracted from the different modal data are fused by the attention mechanism to obtain a fused feature vector, including:

[0073] S91: For each eigenvector f i Calculate the corresponding weight α i , the calculation formula is:

[0074]

[0075] Among them, e i Represents the learned feature f iThe importance evaluation value of; n represents the number of features;

[0076] S92: Based on the calculated weights, different feature vectors are weighted averaged to obtain a fused feature vector. The calculation formula is:

[0077]

[0078] Among them, F represents the fused feature vector.

[0079] In order to solve the above problems, the present invention provides a system for constructing a digital twin simulation and debugging teaching platform, characterized in that the device comprises:

[0080] An information collection device is used to collect the actual system operation data, and to perform denoising, interpolation and normalization operations on the collected data to obtain the pre-processed system operation data;

[0081] The modeling simulation debugging module is used to use the data-driven modeling simulation debugging teaching platform according to the preprocessed system operation data, and design the virtual environment according to the application scenario and teaching objectives;

[0082] The adjustment and optimization module is used to interact with the twin simulation environment through teaching tools and collect interaction data in real time, and to adjust and optimize the twin simulation environment based on the collected interaction data.

[0083] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0084] A memory storing at least one instruction;

[0085] Communication interface, enabling electronic equipment to communicate; and

[0086] The processor executes the instructions stored in the memory to implement the method for constructing the digital twin simulation and debugging teaching platform described above.

[0087] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the method for constructing the above-mentioned digital twin simulation and debugging teaching platform.

[0088] Compared with the prior art, the present invention proposes a method for constructing a digital twin simulation and debugging teaching platform, which has the following advantages:

[0089] First of all, this plan proposes a method for constructing a digital twin simulation and debugging teaching platform. This technical solution improves the effectiveness and experience in the field of experimental teaching through comprehensive data utilization, modeling method selection, virtual environment design and real-time interactive feedback.

[0090] At the same time, this solution adopts a data-driven analysis method based on rule mining for modeling, which pays more attention to the mining of rules and logic, and can improve the interpretability and generalization ability of the model.

[0091] In addition, this program designs the virtual environment based on the twin simulation environment, combines digital images, sounds and video information to construct virtual scenes, and comprehensively utilizes multimodal information to provide a more realistic and rich simulation experience, enhancing students' sense of participation and learning effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 A schematic diagram of a process for constructing a digital twin simulation and debugging teaching platform provided by one embodiment of the present invention;

[0093] Figure 2 A functional module diagram of a system for constructing a digital twin simulation and debugging teaching platform provided by one embodiment of the present invention;

[0094] Figure 2 In: 100 construction system of simulation and debugging teaching platform of digital twin, 101 information acquisition device, 102 modeling simulation debugging module, 103 adjustment and optimization module;

[0095] Figure 3 A schematic diagram of the structure of an electronic device for implementing a method for constructing a simulation and debugging teaching platform for digital twins provided by an embodiment of the present invention;

[0096] Figure 3 In: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.

[0097] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0098] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0099] The embodiment of the present application provides a method for constructing a simulation and debugging teaching platform for digital twins. The execution subject of the method for constructing the simulation and debugging teaching platform for digital twins includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for constructing the simulation and debugging teaching platform for digital twins can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0100] Embodiment 1:

[0101] S1: Collecting the operating data of the actual system, which includes data from various sensors and controllers, as well as data from human-computer interactions, and performing denoising, interpolation and normalization operations on the collected data to obtain pre-processed system operating data.

[0102] In the step S1, the collected data is subjected to denoising, interpolation and normalization operations to obtain pre-processed system operation data, including:

[0103] S21: Perform Kalman filtering on the collected data to obtain denoised system operation data;

[0104] S22: performing interpolation fitting on the denoised system operation data to fill in missing data to obtain fitted system operation data, wherein Newton interpolation is a main implementation method for the data fitting.

[0105] In step S21, Kalman filtering is performed on the collected data, including:

[0106] S31: Randomly initialized state estimate and the covariance matrix P 0 ;

[0107] S32: Perform state estimation based on the system's state transfer matrix F and the state at the previous moment The calculation formula is:

[0108]

[0109] According to the system state transfer matrix F, process noise covariance matrix Q and the covariance matrix of the previous moment, the covariance matrix P is predicted k-1|k-1 , the calculation formula is:

[0110] P k-1|k-1 =F*P k-1 *F T +Q

[0111] S33: Calculate the Kalman gain according to the predicted covariance matrix, and update the state estimation and covariance matrix;

[0112] S34: repeating steps S32 to S33 until all data points are processed;

[0113] in,

[0114] represents the estimate of the state at time k at time k-1;

[0115] P k-1|k-1 represents the uncertainty of the state estimate at time k at time k-1;

[0116] F represents the state transfer matrix;

[0117] Q represents the process noise covariance matrix.

[0118] In the step S33, the Kalman gain is calculated according to the predicted covariance matrix, and the state estimation and covariance matrix are updated, including:

[0119] S41: Calculate the Kalman gain K based on the predicted covariance matrix, the observation matrix H and the measurement noise covariance matrix R k , the calculation formula is:

[0120] K k =P k-1|k-1 *H T* (H*P k-1|k-1 *H T +R) -1

[0121] S42: Based on the predicted state estimation, Kalman gain and observation data z k Update state estimate The calculation formula is:

[0122]

[0123] S43: Update the covariance matrix P according to the predicted covariance matrix, Kalman gain and observation matrix k|k , the calculation formula is:

[0124] P k|k =(IK k *H)*P k-1|k-1

[0125] in,

[0126] represents the estimate of the state at time k at time k-1;

[0127] P k-1|k-1represents the uncertainty of the state estimate at time k at time k-1;

[0128] F represents the state transfer matrix;

[0129] Q represents the process noise covariance matrix;

[0130] K k represents the Kalman gain;

[0131] z k represents the observation value at time k;

[0132] H represents the observation matrix;

[0133] R represents the measurement noise covariance matrix;

[0134] represents the estimate of the state at time k;

[0135] P k|k represents the uncertainty of the state estimate at time k.

[0136] In the step S22, interpolation fitting is performed on the denoised system operation data, including:

[0137] S51: For data points {(x 0 ,y 0 ), (x 1 ,y 1 ),...,(x n ,y n )} Calculate the difference quotient and form a difference quotient table;

[0138] S52: Using the diagonal elements in the difference quotient table as polynomial coefficients to construct an interpolation polynomial f(x) to complete the fitting, the calculation formula is:

[0139] f(x)=f[x 0 ]+f[x 0 , x 1 ](xx 0 )+f[x 0 , x 1 , x 2 ](xx 0 )(xx 1 )+...+f[x 0 , x 1 , ..., x n ](x

[0140] -x 0 )(xx 1 )...(xx n - 1 )

[0141] in:

[0142] n represents the number of data points;

[0143] x i represents the independent variable of the ith data point;

[0144] y i represents the dependent variable of the ith data point;

[0145] f[x i ] indicates that x i is the first-order derivative of the node;

[0146] f[x i , x j ] indicates that (x i , x j ) is the second-order derivative of the node;

[0147] f[x i , x j , x k ] indicates that (x i , x j , x k ) is the third-order derivative of the node;

[0148] f[x 0 , x 1 , ..., x n ]With (x 0 , x 1 , ..., x n ) is the nth-order derivative of the node.

[0149] S2: Using data-driven modeling simulation debugging teaching platform based on preprocessed system operation data, wherein the data-driven analysis method based on rule mining is the main implementation method for modeling the simulation debugging teaching platform.

[0150] In the step S2, a data-driven modeling simulation debugging teaching platform is used based on the preprocessed system operation data, including:

[0151] Run the data mining system operation rules from the preprocessed system, including:

[0152] S61: Initialize candidate set C 1 and the frequent set L 1 ;

[0153] S62: According to the frequent set L k-1 , generate candidate set C through self-join operation k ;

[0154] S63: For data set D, scan each transaction and count candidate set C k The number of times each item set appears in , and calculate its support;

[0155] S64: According to the minimum support threshold, filter out the item sets that meet the conditions to form the frequent set L k ;

[0156] S65: If L k If it is empty, the iteration is terminated; otherwise, iterate steps S62 to S64;

[0157] S66: For frequent set L k For each item set in , enumerate all its non-empty subsets, and for each subset, calculate its support and confidence, and filter out the association rules that meet the minimum support and minimum confidence thresholds as the system operation rules.

[0158] S3: Design a virtual environment according to the application scenario and teaching objectives. The virtual scene is based on the simulation debugging teaching platform and constructs a twin simulation environment through digital images, sounds and video information.

[0159] In the step S3, a twin simulation environment is constructed through digital image, sound and video information, including:

[0160] S71: adding tags and metadata to each image, sound and video clip, and extracting features of the image, sound and video data;

[0161] S72: Based on the labeled and feature-extracted data, a digital twin model is established to align and associate the image, sound, and video data with their corresponding digital twins, and to establish a mapping relationship between the real system and the digital model.

[0162] The digital twin model is established in step S72 to align and associate the image, sound and video data with their corresponding digital twins, including:

[0163] S81: Preprocess the image, sound and video data, represent different types of data in a unified vector, use a neural network model to extract features of the image, sound and video data, and obtain feature vectors of different modal data;

[0164] S82: The features extracted from different modal data are fused by attention mechanism to obtain a fused feature vector;

[0165] S83: Construct a deep neural twin mapping model to map multimodal features to the digital twin space, wherein the Triplet Network structure is the network structure of the deep neural twin mapping model, and the correspondence between multimodal data and digital twins is learned by sharing weights.

[0166] In the step S82, the features extracted from the different modal data are fused by the attention mechanism to obtain a fused feature vector, including:

[0167] S91: For each eigenvector f i Calculate the corresponding weight α i , the calculation formula is:

[0168]

[0169] Among them, e i Represents the learned feature f i The importance evaluation value of; n represents the number of features;

[0170] S92: Based on the calculated weights, different feature vectors are weighted averaged to obtain a fused feature vector. The calculation formula is:

[0171]

[0172] Among them, F represents the fused feature vector.

[0173] S4: Students interact with the twin simulation environment through teaching tools and collect interaction data in real time, and then feed back the collected interaction data to the twin simulation environment for adjustment and optimization.

[0174] Embodiment 2:

[0175] like Figure 2 As shown, it is a functional module diagram of a device for constructing a simulation and debugging teaching platform for a digital twin provided by an embodiment of the present invention, which can implement the method for constructing a simulation and debugging teaching platform for a digital twin in Example 1.

[0176] The construction device 100 of the simulation and debugging teaching platform of the digital twin of the present invention can be installed in an electronic device. According to the functions implemented, the construction device of the simulation and debugging teaching platform of the digital twin may include an information acquisition device 101, a modeling simulation debugging module 102 and an adjustment and optimization module 103. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0177] The information collection device 101 is used to collect the actual system operation data, and perform denoising, interpolation and normalization operations on the collected data to obtain the pre-processed system operation data;

[0178] The modeling simulation debugging module 102 is used to use the data-driven modeling simulation debugging teaching platform according to the preprocessed system operation data, and design the virtual environment according to the application scenario and teaching objectives;

[0179] The adjustment and optimization module 103 is used to interact with the twin simulation environment through teaching tools and collect interaction data in real time, and feed back the collected interaction data to the twin simulation environment for adjustment and optimization.

[0180] In detail, each module in the construction device 100 of the digital twin simulation and debugging teaching platform in the embodiment of the present invention is used in the same manner as described above. Figure 1 The simulation and debugging teaching platform of the digital twin described in the text uses the same technical means and can produce the same technical effects, so I will not go into details here.

[0181] Embodiment 3:

[0182] like Figure 3 As shown, it is a structural schematic diagram of an electronic device for implementing a method for constructing a simulation and debugging teaching platform for digital twins provided by one embodiment of the present invention.

[0183] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0184] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0185] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the program or module stored in the memory 11 (a program 12 for building a simulation and debugging teaching platform for digital twins, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0186] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0187] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0188] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0189] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0190] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0191] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0192] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0193] Collect the actual system operation data, and perform denoising, interpolation and normalization operations on the collected data to obtain the pre-processed system operation data;

[0194] Use data-driven modeling simulation debugging teaching platform based on pre-processed system operation data;

[0195] Design virtual environments according to application scenarios and teaching objectives, and construct twin simulation environments through digital images, sounds, and video information;

[0196] Students interact with the twin simulation environment through teaching tools and collect interaction data in real time, and then adjust and optimize the twin simulation environment based on the collected interaction data.

[0197] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0198] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for constructing a digital twin simulation and debugging teaching platform, characterized in that: The method comprises: S1: Collecting the actual system operation data, including data from various sensors and controllers, and data from human-computer interaction, and performing denoising, interpolation and normalization operations on the collected data to obtain pre-processed system operation data; S2: Using a data-driven simulation debugging teaching platform to build a model based on the preprocessed system operation data, wherein a data-driven analysis method based on rule mining is the main implementation method of the simulation debugging teaching platform modeling; S3: Design a virtual scene according to the application scenario and teaching objectives. The virtual scene is based on the simulation debugging teaching platform and constructs a twin simulation environment through digital images, sounds and video information; S4: Students interact with the twin simulation environment through teaching tools and collect interaction data in real time. The collected interaction data is fed back to the twin simulation environment for adjustment and optimization; In the step S1, the collected data is subjected to denoising, interpolation and normalization operations to obtain pre-processed system operation data, including: S21: Perform Kalman filtering on the collected data to obtain denoised system operation data; S22: performing interpolation fitting on the denoised system operation data to fill in missing data to obtain fitted system operation data, wherein Newton interpolation is the main implementation method of the data fitting; performing interpolation fitting on the denoised system operation data in step S22 includes: S51: For data points {(x0,y0),(x1,y1),...,(x n ,y n )} Calculate the difference quotient and form a difference quotient table; S52: Using the diagonal elements in the difference quotient table as polynomial coefficients to construct an interpolation polynomial f(x) to complete the fitting, the calculation formula is: f(x)= f[x0]+f[x0,x1](x-x0)+f[x0,x1,x2](x-x0)(x-x1)+...+f[x0,x1,...,x n ](x-x0)(x-x1)...(xx n-1 ) in: n represents the number of data points; x i represents the independent variable of the ith data point; y i represents the dependent variable of the ith data point; f[x i ] indicates that x i is the first-order derivative of the node; f[x i ,x j ] indicates that (x i ,x j ) is the second-order derivative of the node; f[x i ,x j ,x k ] indicates that (x i ,x j ,x k ) is the third-order derivative of the node; f[x0,x1,...,x n ] with (x0,x1,...,x n ) is the nth-order derivative of the node; in the step S2, a data-driven modeling simulation debugging teaching platform is used based on the preprocessed system operation data, including: Run the data mining system operation rules from the preprocessed system, including: S61: Initialize candidate set C1 and frequent set L1; S62: According to the frequent set L k-1 , generate candidate set C through self-join operation k ; S63: For data set D, scan each transaction and count candidate set C k The number of times each item set appears in , and calculate its support; S64: According to the minimum support threshold, filter out the item sets that meet the conditions to form the frequent set L k ; S65: If L k If it is empty, the iteration is terminated; otherwise, iterate steps S62 to S64; S66: For frequent set L k For each item set in , enumerate all its non-empty subsets, and for each subset, calculate its support and confidence, and select the association rules that meet the minimum support and minimum confidence thresholds as the system operation rules; In the step S3, a twin simulation environment is constructed through digital image, sound and video information, including: S71: adding tags and metadata to each image, sound and video clip, and extracting features of the image, sound and video data; S72: Based on the annotated and feature-extracted data, a digital twin model is established to align and associate the image, sound, and video data with their corresponding digital twins, and to establish a mapping relationship between the real system and the digital model; The digital twin model is established in step S72 to align and associate the image, sound and video data with their corresponding digital twins, including: S81: Preprocess the image, sound and video data, represent different types of data in a unified vector, use a neural network model to extract features of the image, sound and video data, and obtain feature vectors of different modal data; S82: The features extracted from different modal data are fused by attention mechanism to obtain a fused feature vector; S83: Construct a deep neural twin mapping model for mapping multimodal features to a digital twin space, wherein a TripletNetwork structure is a network structure of the deep neural twin mapping model, and the correspondence between multimodal data and digital twins is learned by sharing weights; In the step S82, the features extracted from the different modal data are fused by the attention mechanism to obtain a fused feature vector, including: S91: For each eigenvector f i Calculate the corresponding weight α i , the calculation formula is: Among them, e i Represents the learned feature f i The importance evaluation value of; n represents the number of features; S92: Based on the calculated weights, different feature vectors are weighted averaged to obtain a fused feature vector. The calculation formula is: Where F represents the fused feature vector.

2. The method for constructing a digital twin simulation and debugging teaching platform according to claim 1, characterized in that: In step S21, Kalman filtering is performed on the collected data, including: S31: Randomly initialized state estimate and covariance matrix P0; S32: Perform state estimation based on the system's state transfer matrix F and the state at the previous moment The calculation formula is: According to the system state transfer matrix F, process noise covariance matrix Q and the covariance matrix of the previous moment, the covariance matrix P is predicted k-1 | k-1 , the calculation formula is: P k-1 | k-1 =F*P k-1 *F T +Q S33: Calculate the Kalman gain according to the predicted covariance matrix, and update the state estimation and covariance matrix; S34: repeating steps S32 to S33 until all data points are processed; in, represents the estimate of the state at time k at time k-1; P k-1 | k-1 represents the uncertainty of the state estimate at time k at time k-1; F represents the state transfer matrix; Q represents the process noise covariance matrix.

3. The method for constructing a digital twin simulation and debugging teaching platform according to claim 2, characterized in that: In the step S33, the Kalman gain is calculated according to the predicted covariance matrix, and the state estimation and covariance matrix are updated, including: S41: Calculate the Kalman gain K based on the predicted covariance matrix, the observation matrix H and the measurement noise covariance matrix R k , the calculation formula is: K k =P k-1 | k-1 *H T *(H*P k-1 | k-1 *H T +R) -1 S42: Based on the predicted state estimation, Kalman gain and observation data z k Update state estimate The calculation formula is: S43: Update the covariance matrix P according to the predicted covariance matrix, Kalman gain and observation matrix k | k , the calculation formula is: P k | k =(I-K k *H)*P k-1 | k-1 in, represents the estimate of the state at time k at time k-1; P k-1 | k-1 represents the uncertainty of the state estimate at time k at time k-1; F represents the state transfer matrix; Q represents the process noise covariance matrix; K k represents the Kalman gain; z k represents the observation value at time k; H represents the observation matrix; R represents the measurement noise covariance matrix; represents the estimate of the state at time k; P k | k represents the uncertainty of the state estimate at time k.

4. A system for constructing a digital twin simulation and debugging teaching platform, used to implement a method for constructing a digital twin simulation and debugging teaching platform as described in claims 1-3, characterized in that: The system comprises: An information collection device is used to collect the actual system operation data, and to perform denoising, interpolation and normalization operations on the collected data to obtain the pre-processed system operation data; The modeling simulation debugging module is used to use the data-driven modeling simulation debugging teaching platform according to the preprocessed system operation data, and design virtual scenes according to application scenarios and teaching objectives; The adjustment and optimization module is used to interact with the twin simulation environment through teaching tools and collect interaction data in real time, and to adjust and optimize the twin simulation environment based on the collected interaction data.

Images