Thermal power generation enterprise safety practical training method based on virtual reality technology

Abstract

The invention discloses a thermal power generation enterprise safety practical training method based on a virtual reality technology. The method comprises the steps of data acquisition, construction of a practical training basic framework, construction of a practical training role function model, potential safety hazard monitoring and comprehensive practical training. The invention relates to the technical field of practical training safety management, in particular to a thermal power generation enterprise safety practical training method based on a virtual reality technology, which improves the reality and practicability of a scene by generating a practical training scene and constructing a virtual practical training role framework; by designing an excitation function and performing multi-dimensional quantum fusion, the generalization ability and feature extraction ability of the model are improved, the efficiency and accuracy of information fusion are improved, and the accuracy and reliability of a prediction result are improved; real-time hidden danger monitoring is carried out by designing a matching degree calculation function, designing a data cluster center point updating function and setting an anomaly check threshold, the real-time performance and accuracy of monitoring are improved, and the recognition efficiency of potential safety hazards is improved.

Description

Technical Field

[0001] The invention relates to the technical field of practical training safety management, and in particular to a safety practical training method for a thermal power generation enterprise based on virtual reality technology. Background Art

[0002] A safety training method for thermal power generation enterprises based on virtual reality technology is to combine virtual reality technology and artificial intelligence technology to build a real and comprehensive scenario model, provide a highly immersive and realistic simulation environment, and provide intelligent feedback based on the trainees' operations and responses. However, the traditional safety training method for thermal power generation enterprises has problems such as insufficient reality of scenario construction, insufficient complexity assessment, and single role framework when constructing the basic framework of the training; the traditional safety training method for thermal power generation enterprises has problems such as insufficient model generalization ability, insufficient feature extraction, and lack of efficient information fusion mechanism when constructing the training role function model; the traditional safety training method for thermal power generation enterprises has problems such as insufficient monitoring accuracy, weak real-time performance, and difficulty in effectively identifying potential safety hazards in terms of safety hazard monitoring. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a safety training method for thermal power generation enterprises based on virtual reality technology. In view of the problems that the scene construction is not realistic enough, the complexity assessment is insufficient, and the role framework is single when constructing the basic training framework of the traditional thermal power generation enterprise safety training method, this solution improves the realism and practicality of the scene by defining element complexity, calculating scene complexity, generating training scenes, and constructing a virtual training role framework, making the virtual training role more three-dimensional and rich; in view of the problems that the traditional thermal power generation enterprise safety training method has inadequate model generalization ability, insufficient feature extraction, and lack of To address the problem of efficient information fusion mechanism, this solution improves the generalization and feature extraction capabilities of the model, the efficiency and accuracy of information fusion, and the accuracy and reliability of prediction results by designing incentive functions and performing multi-dimensional quantum fusion. In response to the problems of insufficient monitoring accuracy, poor real-time performance, and difficulty in effectively identifying potential safety hazards in the safety training methods of traditional thermal power generation enterprises in terms of safety hazard monitoring, this solution improves the real-time and accuracy of monitoring by defining enhanced correlation distances, designing matching calculation functions, designing data cluster center point update functions, setting abnormality detection thresholds and real-time hazard monitoring, and improves the efficiency and accuracy of identifying safety hazards.

[0004] The technical solution adopted by the present invention is as follows: a safety training method for thermal power generation enterprises based on virtual reality technology, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: Constructing the basic framework of practical training;

[0007] Step S3: constructing a training role function model;

[0008] Step S4: Safety hazard monitoring;

[0009] Step S5: Comprehensive training.

[0010] Furthermore, in step S1, the data collection is to collect equipment operation data, personnel operation data, historical fault data, virtual scene data and training role data; the equipment operation data includes the operation parameters of the generator, boiler, cooling system and flue gas treatment system; the personnel operation data includes the operator's operation content and operation results, and the operation results include normal and abnormal; the historical fault data is the historical equipment failure records and the equipment parameters at the time of the failure; the virtual scene data includes the equipment model, building model and terrain model of the training site; the training role data is the information of the training instructor who has training experience in reality.

[0011] Furthermore, in step S2, the construction of the basic training framework specifically includes the following steps:

[0012] Step S21: constructing a training scene, using the collected equipment model, building model and terrain model of the training site to construct a virtual training scene, specifically including the following steps:

[0013] Step S211: define element complexity, set each device, building and terrain as an element, and define element complexity, which is expressed as follows:

[0014] ;

[0015] Among them, q represents the index of the element, represents the complexity of the qth element, , and represents the complexity weight, represents the volume of the qth element, represents the number of components of the qth element, Indicates the number of interactive functions of the qth element;

[0016] Step S212: Calculate the scene complexity, combine the equipment model, building model and terrain model of the training site, and generate an initial training scene, which is expressed as follows:

[0017] ;

[0018] Among them, U represents the index of the initial training scene, represents the scene complexity of the U-th training scene, Indicates the total number of elements in the training scene. The balance weight of the qth element;

[0019] Step S213: Generate a training scenario, calculate the scenario complexity of the generated initial training scenario, and select the scenario with the lowest complexity as the final training scenario;

[0020] Step S22: construct a virtual training role framework and create attribute items of the virtual training instructor. The attributes of the virtual training instructor include: name, gender, appearance characteristics, personality, professional knowledge, behavioral style and background story. Input the collected training role data into the created attribute items to construct the framework of the virtual training role.

[0021] Furthermore, in step S3, the construction of the training role function model specifically includes the following steps:

[0022] Step S31: setting model label data, setting the operation result data as label data of the model;

[0023] Step S32: Design the input layer, which is expressed as follows:

[0024] ;

[0025] in, represents the output value of the input layer, represents the initial weight, d represents the total number of input features, , and Represent the 1st, 2nd and dth input features respectively;

[0026] Step S33: Design a directional excitation function, which is expressed as follows:

[0027] ;

[0028] in, represents the input value of the directional activation function, and represents the scale parameter, represents the directional activation function;

[0029] Step S34: Design the hidden layer, which is expressed as follows:

[0030] ;

[0031] in, represents the output value of the lth hidden layer, represents the weight of the lth hidden layer, represents the input value of the lth hidden layer, represents the bias of the lth hidden layer;

[0032] Step S35: multi-dimensional quantum fusion, specifically including the following steps:

[0033] Step S351: quantum state initialization, expressed as follows:

[0034] ;

[0035] Where r represents the index of the quantum bit, R represents the maximum number of quantum bits, represents the initial state of the rth quantum bit, and is satisfied plural of and is the base state of the qubit;

[0036] Step S352: quantum feature encoding, expressed as follows:

[0037] ;

[0038] Where Qe represents a quantum eigenvector consisting of R quantum states, represents the initial state of the first quantum bit, represents the initial state of the second quantum bit, represents the initial state of the Rth quantum bit;

[0039] Step S353: quantum transformation, expressed as follows:

[0040] ;

[0041] in, represents the transformed state of the rth quantum bit after the quantum change, represents a two-by-two complex matrix, deo represents a random integer between 1 and R, represents the initial state of the deoth quantum bit, A tensor product operator representing qubits;

[0042] Step S354: Quantum feature fusion, expressed as follows:

[0043] ;

[0044] in, represents the feature vector after quantum feature fusion, represents the quantum feature fusion weight;

[0045] Step S36: Design the output layer, which is expressed as follows:

[0046] ;

[0047] in, Represents the operation prediction result output by the output layer, It means taking the result with the highest probability among the predicted results. represents the normalized exponential activation function, , and Represent the weights, input values, and bias of the output layer respectively.

[0048] Furthermore, in step S4, the potential safety hazard monitoring specifically includes the following steps:

[0049] Step S41: define the enhanced association distance, which is expressed as follows:

[0050] ;

[0051] Among them, i and j represent the index of the data point, and Respectively represent the positions of the i-th data point and the j-th data point, represents the enhanced association distance function, represents the enhanced association distance between the i-th data point and the j-th data point, Indicates taking the maximum value, and Respectively represent the horizontal and vertical coordinates of the i-th data point, and Respectively represent the horizontal and vertical coordinates of the jth data point, Indicates taking the absolute value, represents the reinforcement weight, Indicates square root;

[0052] Step S42: Design a matching degree calculation function, which is expressed as follows:

[0053] ;

[0054] in, represents the matching degree between the i-th data point and the j-th data point, Represents the dimension index of the data, represents the maximum dimension of the data, Indicates the Euclidean distance. represents the i-th data point Data dimension values, represents the jth data point Data dimension value;

[0055] Step S43: Design a data cluster center point update function, which is expressed as follows:

[0056] ;

[0057] Among them, k represents the index of the data cluster, t represents the number of times the data cluster is updated, represents the position of the center of the kth data cluster when the t+1th data cluster is updated, It means taking the closest data point. represents the total number of data points in the k-th data cluster, ki represents the data point index of the k-th data cluster, represents the position of the kith data point, Indicates the location of the center of the kth data cluster when the tth data cluster is updated;

[0058] Step S44: Cluster construction: randomly select B data points from all data points as the initial cluster center points, calculate the matching degree between each data point and each cluster center point, assign the data point to the cluster to which the cluster center with the highest matching degree belongs, update the position of the cluster center, increase the number of updates by one, and iterate the update process until the position of the cluster center no longer changes, thus forming the final data cluster;

[0059] Step S45: Setting the abnormality detection threshold, as shown below:

[0060] ;

[0061] in, represents the anomaly detection threshold, Represents the Euclidean distance between the two cluster centers that are farthest apart in the final data cluster;

[0062] Step S46: Real-time hidden danger monitoring, real-time collection of user's training data, calculation of the Euclidean distance between the user's training data point and each cluster center point. If the Euclidean distance between the user's training data point and any cluster center point is less than the abnormality detection threshold, the training data point is normal at this time; otherwise, there is a safety hazard and an early warning message is issued.

[0063] Furthermore, in step S5, the comprehensive training collects data from user training in real time and inputs the training role function model. The model processes and analyzes the user's training operations, outputs predicted operation results, provides real-time training guidance, and monitors the user's training data for safety hazards.

[0064] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0065] (1) In view of the problems of insufficient reality in scene construction, insufficient complexity assessment and single role framework in the construction of the basic training framework of traditional thermal power generation enterprises' safety training methods, this solution improves the realism and practicality of the scene by defining element complexity, calculating scene complexity, generating training scenes and constructing a virtual training role framework, making the virtual training roles more three-dimensional and rich.

[0066] (2) In view of the problems of insufficient model generalization ability, insufficient feature extraction and lack of efficient information fusion mechanism in the construction of training role function model in the traditional safety training method of thermal power generation enterprises, this scheme improves the generalization ability and feature extraction ability of the model by designing the incentive function and performing multi-dimensional quantum fusion, improves the efficiency and accuracy of information fusion, and improves the accuracy and reliability of the prediction results.

[0067] (3) In order to address the problems of insufficient monitoring accuracy, poor real-time performance, and difficulty in effectively identifying potential safety hazards in the safety training methods of traditional thermal power generation enterprises, this solution improves the real-time and accuracy of monitoring and improves the efficiency and accuracy of identifying safety hazards by defining enhanced correlation distances, designing matching calculation functions, designing data cluster center point update functions, setting abnormality detection thresholds, and real-time hazard monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A flow chart of a safety training method for thermal power generation enterprises based on virtual reality technology provided by the present invention;

[0069] Figure 2 is a schematic flow chart of step S2;

[0070] Figure 3 is a schematic flow chart of step S3;

[0071] Figure 4 It is a schematic diagram of the process of step S4.

[0072] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0073] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0074] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0075] Example 1, see Figure 1 The present invention provides a safety training method for thermal power generation enterprises based on virtual reality technology, which includes the following steps:

[0076] Step S1: data collection, collecting equipment operation data, personnel operation data, historical fault data, virtual scene data and training role data;

[0077] Step S2: constructing a basic training framework, by constructing a training scenario and a virtual training role framework;

[0078] Step S3: constructing a training role function model, by designing an input layer, designing an excitation function, designing a hidden layer, multi-dimensional quantum fusion and designing an output layer to construct the training role function model;

[0079] Step S4: Safety hazard monitoring, by defining the enhanced correlation distance, designing the matching degree calculation function, designing the data cluster center point update function and setting the abnormality detection threshold to perform safety hazard monitoring;

[0080] Step S5: Comprehensive training, real-time collection of data from user training, input into the training role function model, the model conducts real-time training guidance, and at the same time monitors the safety hazards of the user's training data.

[0081] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the data collection is to collect equipment operation data, personnel operation data, historical fault data, virtual scene data and training role data; the equipment operation data includes the operation parameters of the generator, boiler, cooling system and flue gas treatment system; the personnel operation data includes the operator's operation content and operation results, and the operation results include normal and abnormal; the historical fault data is the historical equipment fault records and the equipment parameters at the time of the fault; the virtual scene data includes the equipment model, building model and terrain model of the training site; the training role data is the information of the training instructor who has training experience in reality.

[0082] Example 3, see Figure 1 and Figure 2This embodiment is based on the above embodiment. In step S2, the construction of the training basic framework specifically includes the following steps:

[0083] Step S21: constructing a training scene, using the collected equipment model, building model and terrain model of the training site to construct a virtual training scene, specifically including the following steps:

[0084] Step S211: define element complexity, set each device, building and terrain as an element, and define element complexity, which is expressed as follows:

[0085] ;

[0086] Among them, q represents the index of the element, represents the complexity of the qth element, , and represents the complexity weight, represents the volume of the qth element, represents the number of components of the qth element, Indicates the number of interactive functions of the qth element;

[0087] Step S212: Calculate the scene complexity, combine the equipment model, building model and terrain model of the training site, and generate an initial training scene, which is expressed as follows:

[0088] ;

[0089] Among them, U represents the index of the initial training scene, represents the scene complexity of the U-th training scene, Indicates the total number of elements in the training scene. The balance weight of the qth element;

[0090] Step S213: Generate a training scenario, calculate the scenario complexity of the generated initial training scenario, and select the scenario with the lowest complexity as the final training scenario;

[0091] Step S22: construct a virtual training role framework and create attribute items of the virtual training instructor. The attributes of the virtual training instructor include: name, gender, appearance characteristics, personality, professional knowledge, behavioral style and background story. Input the collected training role data into the created attribute items to construct the framework of the virtual training role.

[0092] By performing the above operations, in order to address the problems of traditional thermal power generation enterprises' safety training methods when constructing the basic training framework, such as insufficient scene construction, insufficient complexity assessment and a single role framework, this solution improves the realism and practicality of the scene by defining element complexity, calculating scene complexity, generating training scenes and constructing a virtual training role framework, making the virtual training roles more three-dimensional and rich.

[0093] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment, and the construction of the training role function model specifically includes the following steps:

[0094] Step S31: setting model label data, setting the operation result data as label data of the model;

[0095] Step S32: Design the input layer, which is expressed as follows:

[0096] ;

[0097] in, represents the output value of the input layer, represents the initial weight, d represents the total number of input features, , and Represent the 1st, 2nd and dth input features respectively;

[0098] Step S33: Design a directional excitation function, which is expressed as follows:

[0099] ;

[0100] in, represents the input value of the directional activation function, and represents the scale parameter, represents the directional activation function;

[0101] Step S34: Design the hidden layer, which is expressed as follows:

[0102] ;

[0103] in, represents the output value of the lth hidden layer, represents the weight of the lth hidden layer, represents the input value of the lth hidden layer, represents the bias of the lth hidden layer;

[0104] Step S35: multi-dimensional quantum fusion, specifically including the following steps:

[0105] Step S351: quantum state initialization, expressed as follows:

[0106] ;

[0107] Where r represents the index of the quantum bit, R represents the maximum number of quantum bits, represents the initial state of the rth quantum bit, and is satisfied plural of and is the base state of the qubit;

[0108] Step S352: quantum feature encoding, expressed as follows:

[0109] ;

[0110] Where Qe represents a quantum eigenvector consisting of R quantum states, represents the initial state of the first quantum bit, represents the initial state of the second quantum bit, represents the initial state of the Rth quantum bit;

[0111] Step S353: quantum transformation, expressed as follows:

[0112] ;

[0113] in, represents the transformed state of the rth quantum bit after the quantum change, represents a two-by-two complex matrix, deo represents a random integer between 1 and R, represents the initial state of the deoth quantum bit, A tensor product operator representing qubits;

[0114] Step S354: Quantum feature fusion, expressed as follows:

[0115] ;

[0116] in, represents the feature vector after quantum feature fusion, represents the quantum feature fusion weight;

[0117] Step S36: Design the output layer, which is expressed as follows:

[0118] ;

[0119] in, Represents the operation prediction result output by the output layer, It means taking the result with the highest probability among the predicted results. represents the normalized exponential activation function, , and Represent the weights, input values, and bias of the output layer respectively.

[0120] By performing the above operations, this scheme aims to address the problems of insufficient model generalization ability, insufficient feature extraction and lack of efficient information fusion mechanism in the construction of training role function models in traditional thermal power generation enterprise safety training methods. By designing incentive functions and performing multi-dimensional quantum fusion, this scheme improves the generalization ability and feature extraction ability of the model, improves the efficiency and accuracy of information fusion, and improves the accuracy and reliability of prediction results.

[0121] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, the safety hazard monitoring specifically includes the following steps:

[0122] Step S41: define the enhanced association distance, which is expressed as follows:

[0123] ;

[0124] Among them, i and j represent the index of the data point, and Respectively represent the positions of the i-th data point and the j-th data point, represents the enhanced association distance function, represents the enhanced association distance between the i-th data point and the j-th data point, Indicates taking the maximum value, and Respectively represent the horizontal and vertical coordinates of the i-th data point, and Respectively represent the horizontal and vertical coordinates of the jth data point, Indicates taking the absolute value, represents the reinforcement weight, Indicates square root;

[0125] Step S42: Design a matching degree calculation function, which is expressed as follows:

[0126] ;

[0127] in, represents the matching degree between the i-th data point and the j-th data point, Represents the dimension index of the data, Represents the maximum dimension of the data, Indicates the Euclidean distance. represents the i-th data point Data dimension values, represents the jth data point Data dimension value;

[0128] Step S43: Design a data cluster center point update function, which is expressed as follows:

[0129] ;

[0130] Among them, k represents the index of the data cluster, t represents the number of times the data cluster is updated, represents the position of the center of the kth data cluster when the t+1th data cluster is updated, It means taking the closest data point. represents the total number of data points in the k-th data cluster, ki represents the data point index of the k-th data cluster, represents the position of the kith data point, Indicates the location of the center of the kth data cluster when the tth data cluster is updated;

[0131] Step S44: Cluster construction: randomly select B data points from all data points as the initial cluster center points, calculate the matching degree between each data point and each cluster center point, assign the data point to the cluster to which the cluster center with the highest matching degree belongs, update the position of the cluster center, increase the number of updates by one, and iterate the update process until the position of the cluster center no longer changes, thus forming the final data cluster;

[0132] Step S45: Setting the abnormality detection threshold, as shown below:

[0133] ;

[0134] in, represents the anomaly detection threshold, Represents the Euclidean distance between the two cluster centers that are farthest apart in the final data cluster;

[0135] Step S46: Real-time hidden danger monitoring, real-time collection of user's training data, calculation of the Euclidean distance between the user's training data point and each cluster center point. If the Euclidean distance between the user's training data point and any cluster center point is less than the abnormality detection threshold, the training data point is normal at this time; otherwise, there is a safety hazard and an early warning message is issued.

[0136] By performing the above operations, in order to address the problems of insufficient monitoring accuracy, poor real-time performance, and difficulty in effectively identifying potential safety hazards in the safety training methods of traditional thermal power generation enterprises, this solution improves the real-time and accuracy of monitoring by defining enhanced correlation distances, designing matching calculation functions, designing data cluster center point update functions, setting abnormality detection thresholds and real-time hazard monitoring, and improves the efficiency and accuracy of identifying safety hazards.

[0137] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the comprehensive training collects data from user training in real time and inputs the training role function model. The model processes and analyzes the user's training operations, outputs predicted operation results, and provides real-time training guidance. At the same time, the user's training data is monitored for safety hazards.

[0138] It should be noted that, in this article, relational terms such as first and second, etc. 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 terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0139] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0140] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A safety training method for thermal power generation enterprises based on virtual reality technology, characterized in that: The method comprises the following steps: Step S1: data collection, collecting equipment operation data, personnel operation data, historical fault data, virtual scene data and training role data; Step S2: constructing a basic training framework, by constructing a training scenario and a virtual training role framework; Step S3: constructing a training role function model, by designing an input layer, designing an excitation function, designing a hidden layer, multi-dimensional quantum fusion and designing an output layer to construct the training role function model; Step S4: Safety hazard monitoring, by defining the enhanced correlation distance, designing the matching degree calculation function, designing the data cluster center point update function and setting the abnormality detection threshold to perform safety hazard monitoring; Step S5: Comprehensive training, real-time collection of data from user training, input into the training role function model, the model conducts real-time training guidance, and at the same time monitors the safety hazards of the user's training data.

2. A safety training method for thermal power generation enterprises based on virtual reality technology according to claim 1, characterized in that: In step S3, the construction of the training role function model specifically includes the following steps: Step S31: setting model label data, setting the operation result data as label data of the model; Step S32: Design the input layer, which is expressed as follows: ； in, represents the output value of the input layer, represents the initial weight, d represents the total number of input features, , and Represent the 1st, 2nd and dth input features respectively; Step S33: Design a directional excitation function, which is expressed as follows: ； in, represents the input value of the directional excitation function, e represents a natural constant, and represents the scale parameter, represents the directional activation function; Step S34: Design the hidden layer, which is expressed as follows: ； in, represents the output value of the lth hidden layer, represents the weight of the lth hidden layer, represents the input value of the lth hidden layer, represents the bias of the lth hidden layer; Step S35: multi-dimensional quantum fusion, specifically including the following steps: Step S351: quantum state initialization, expressed as follows: ； Where r represents the index of the quantum bit, R represents the maximum number of quantum bits, represents the initial state of the rth quantum bit, and is satisfied plural of and is the base state of the qubit; Step S352: quantum feature encoding, expressed as follows: ； Where Qe represents a quantum eigenvector consisting of R quantum states, represents the initial state of the first quantum bit, represents the initial state of the second quantum bit, represents the initial state of the Rth quantum bit; Step S353: quantum transformation, expressed as follows: ； in, represents the transformed state of the rth quantum bit after the quantum change, represents a two-by-two complex matrix, deo represents a random integer between 1 and R, represents the initial state of the deoth quantum bit, A tensor product operator representing qubits; Step S354: Quantum feature fusion, expressed as follows: ； in, represents the feature vector after quantum feature fusion, represents the quantum feature fusion weight; Step S36: Design the output layer, which is expressed as follows: ； in, Represents the operation prediction result output by the output layer, It means taking the result with the highest probability among the predicted results. represents the normalized exponential activation function, , and Represent the weights, input values, and bias of the output layer respectively.

3. A safety training method for thermal power generation enterprises based on virtual reality technology according to claim 1, characterized in that: In step S4, the potential safety hazard monitoring specifically includes the following steps: Step S41: define the enhanced association distance, which is expressed as follows: ； Among them, i and j represent the index of the data point, and Respectively represent the positions of the i-th data point and the j-th data point, represents the enhanced association distance function, represents the enhanced association distance between the i-th data point and the j-th data point, Indicates taking the maximum value, and Respectively represent the horizontal and vertical coordinates of the i-th data point, and Respectively represent the horizontal and vertical coordinates of the jth data point, Indicates taking the absolute value, represents the reinforcement weight, Indicates square root; Step S42: Design a matching degree calculation function, which is expressed as follows: ； in, represents the matching degree between the i-th data point and the j-th data point, Represents the dimension index of the data, represents the maximum dimension of the data, Indicates the Euclidean distance. represents the i-th data point Data dimension values, represents the jth data point Data dimension value; Step S43: Design a data cluster center point update function, which is expressed as follows: ； Among them, k represents the index of the data cluster, t represents the number of times the data cluster is updated, represents the position of the center of the kth data cluster when the t+1th data cluster is updated, It means taking the closest data point. represents the total number of data points in the k-th data cluster, ki represents the data point index of the k-th data cluster, represents the position of the kith data point, Indicates the location of the center of the kth data cluster when the tth data cluster is updated; Step S44: Cluster construction: randomly select B data points from all data points as the initial cluster center points, calculate the matching degree between each data point and each cluster center point, assign the data point to the cluster to which the cluster center with the highest matching degree belongs, update the position of the cluster center, increase the number of updates by one, and iterate the update process until the position of the cluster center no longer changes, thus forming the final data cluster; Step S45: Setting the abnormality detection threshold, as shown below: ； in, represents the anomaly detection threshold, Represents the Euclidean distance between the two cluster centers that are farthest apart in the final data cluster; Step S46: Real-time hidden danger monitoring, real-time collection of user's training data, calculation of the Euclidean distance between the user's training data point and each cluster center point. If the Euclidean distance between the user's training data point and any cluster center point is less than the abnormality detection threshold, the training data point is normal at this time; otherwise, there is a safety hazard and an early warning message is issued.

4. A safety training method for thermal power generation enterprises based on virtual reality technology according to claim 1, characterized in that: In step S2, the construction of the basic training framework specifically includes the following steps: Step S21: constructing a training scene, using the collected equipment model, building model and terrain model of the training site to construct a virtual training scene, specifically including the following steps: Step S211: define element complexity, set each device, building and terrain as an element, and define element complexity, which is expressed as follows: ； Among them, q represents the index of the element, represents the complexity of the qth element, , and represents the complexity weight, represents the volume of the qth element, represents the number of components of the qth element, Indicates the number of interactive functions of the qth element; Step S212: Calculate the scene complexity, combine the equipment model, building model and terrain model of the training site, and generate an initial training scene, which is expressed as follows: ； Among them, U represents the index of the initial training scene, represents the scene complexity of the U-th training scene, Indicates the total number of elements in the training scene. The balance weight of the qth element; Step S213: Generate a training scenario, calculate the scenario complexity of the generated initial training scenario, and select the scenario with the lowest complexity as the final training scenario; Step S22: construct a virtual training role framework and create attribute items of the virtual training instructor. The attributes of the virtual training instructor include: name, gender, appearance characteristics, personality, professional knowledge, behavioral style and background story. Input the collected training role data into the created attribute items to construct the framework of the virtual training role.

5. A safety training method for thermal power generation enterprises based on virtual reality technology according to claim 1, characterized in that: In step S1, the data collection is to collect equipment operation data, personnel operation data, historical fault data, virtual scene data and training role data; the equipment operation data includes the operation parameters of the generator, boiler, cooling system and flue gas treatment system; the personnel operation data includes the operator's operation content and operation results, and the operation results include normal and abnormal; the historical fault data is the historical equipment fault records and the equipment parameters at the time of the fault; the virtual scene data includes the equipment model, building model and terrain model of the training site; the training role data is the information of the training instructor who has training experience in reality; In step S5, the comprehensive training collects data from user training in real time and inputs the training role function model. The model processes and analyzes the user's training operations, outputs predicted operation results, provides real-time training guidance, and monitors the user's training data for safety hazards.

Images