Hydraulic power plant comprehensive skill assessment and evaluation system and method based on virtual reality

Abstract

The invention relates to the technical field of virtual reality, in particular to a hydraulic power plant comprehensive skill assessment and evaluation system and method based on virtual reality, and the method comprises the steps: constructing a three-dimensional model of a hydraulic power plant, and designing skill assessment items and tasks of a plurality of difficulty levels; according to the work data of the employees, a personalized assessment difficulty level is automatically calculated; and constructing an intelligent assessment scoring model based on a neural network, and giving a skill assessment score by analyzing operation data of the employees in a virtual reality environment. According to the invention, a vivid assessment scene is provided by using a virtual reality technology, automation and intelligentization of a whole assessment process are realized through an artificial intelligence algorithm, the skill level of employees can be comprehensively assessed, and the problems of subjectivity and inconsistency in a traditional assessment mode are improved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a comprehensive skill assessment and evaluation system and method for a hydropower plant based on virtual reality. Background Art

[0002] As the scale and complexity of hydropower projects continue to increase, higher requirements are placed on the skill level of hydropower plant staff.

[0003] Traditional skill assessment and evaluation methods have the following shortcomings: Traditional skill assessment is usually conducted at a specific assessment site, and the assessment content and scenarios are relatively simple, making it difficult to comprehensively assess the actual operational ability and adaptability of staff facing complex working conditions. Traditional skill assessment is usually subjectively judged by examiners based on experience, lacking quantitative evaluation criteria, and the scoring results are easily affected by subjective factors, making it difficult to ensure the fairness and objectivity of the assessment process. The assessment risk is high and there are safety hazards. There are certain safety risks in carrying out skill assessment in the actual hydropower plant environment, especially for inexperienced staff, operating errors may cause equipment damage or casualties. The assessment cost is high and the organization is difficult. Carrying out large-scale skill assessment in the actual hydropower plant environment requires a lot of manpower, material and financial resources, which is difficult to organize and the assessment cost is high. The scoring model lacks intelligence and precision. Traditional skill assessment scoring usually relies on the experience and judgment of examiners, lacks a data-driven intelligent scoring model, and is difficult to fully explore the laws and characteristics contained in the assessment data. The accuracy and reliability of the scoring results need to be improved.

[0004] In view of the problems existing in the above-mentioned background technology, the present invention proposes a comprehensive skill assessment and evaluation system for hydropower plants based on virtual reality. Summary of the invention

[0005] To achieve the above purpose, the present invention provides a method and system for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality. The specific technical scheme is as follows: A method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality includes:

[0006] Based on virtual reality technology, a three-dimensional model of a hydropower plant was constructed, and a skill assessment scenario for the hydropower plant was designed and built;

[0007] Creating a skill assessment project in a skill assessment scenario, wherein the skill assessment project includes an operating environment, assessment requirements, and an assessment operation process, and designing multiple assessment tasks of different difficulty levels for each skill assessment project;

[0008] Automatically calculate the difficulty level of the skill assessment of the person being assessed based on the work data of the person being assessed;

[0009] Construct and train an assessment and scoring model based on a neural network model to assess and score the assessed personnel;

[0010] Acquire the characteristic data of the skill assessment items of the assessed personnel in virtual reality, output the assessment scores through the assessment scoring model, and conduct skill assessment on the assessed employees.

[0011] Preferably, the engineering drawings, equipment parameters and operating status data of the hydropower plant are obtained as the basis for building a three-dimensional model; the collected data are classified, sorted and standardized to establish a complete database; the attribute parameters of each equipment and component are defined, including size, material and function;

[0012] Based on the processed data, the hydropower plant is modeled as a whole using 3D modeling software; key equipment in the hydropower plant, including turbine generator sets and transformers, is modeled in detail to ensure that the geometric dimensions and appearance are consistent with the actual equipment; the terrain environment of the hydropower plant is modeled, including terrain undulations and vegetation distribution;

[0013] Assemble the 3D models of each part to form a complete 3D model of the hydropower plant;

[0014] Add realistic materials and textures to the 3D model of the hydropower plant; use UV mapping technology to apply high-precision maps to the model surface to improve the visual quality of the model;

[0015] Set up light sources in the 3D model to simulate the actual lighting conditions of the hydropower plant, including natural light and artificial lighting; extract the environmental sounds in the real hydropower plant and add them to the 3D model of the hydropower plant to simulate the environmental sounds of the hydropower plant in operation in the 3D model;

[0016] Render the constructed three-dimensional model scene of the hydropower plant to complete the construction of the hydropower plant skill assessment scene.

[0017] Preferably, a corresponding operating environment is designed in virtual reality according to the actual working scenario corresponding to the skill assessment item; the operating environment should include the equipment, tools and control panel required for the assessment and be the same as the actual working environment;

[0018] For each skill assessment item, formulate clear assessment requirements, including assessment objectives, achievement standards and time limits; formulate assessment requirements according to the actual working standards and specifications of the hydropower plant, and divide them into different difficulty levels;

[0019] Design the corresponding assessment operation process according to the actual workflow of the skill assessment project; the assessment operation process should include the specific operation content, sequence and time nodes of each step, and set corresponding judgment conditions for each step;

[0020] In the assessment operation process, data collection points are set to record the operation data of the person being assessed in real time, including operation time, operation sequence and operation parameter settings;

[0021] According to the complexity, risk level and operation frequency of the skill assessment items, the assessment tasks are divided into three difficulty levels: primary skill assessment, intermediate skill assessment and advanced skill assessment; the assessment tasks of different difficulty levels are progressively difficult according to the relationship between the difficulty of primary skill assessment, intermediate skill assessment and advanced skill assessment.

[0022] Preferably, the difficulty level of the skill assessment of the person being assessed is automatically calculated based on the work data of the person being assessed;

[0023] Define the assessment variables and parameters of the person being assessed, and calculate the difficulty level D of the person being assessed: D = round (α J +β×log(Y+1)); round(·) represents the rounding function, log(·) represents the natural logarithm function, which is used to perform nonlinear transformation on working years; J represents the job type of the person being assessed, and its value range is [1, N], where N is the total number of job types; Y represents the working years of the person being assessed; D represents the difficulty level of the assessment task, and its value range is [1, 3], where 1 represents primary skill assessment, 2 represents intermediate skill assessment, and 3 represents advanced skill assessment; α j is the difficulty level benchmark value of job type j; β is the difficulty level adjustment coefficient of working years;

[0024] According to the difficulty level D, set the corresponding difficulty coefficient λ:

[0025]

[0026] Among them, δ is the increment of the difficulty coefficient of the difficulty level, which is used to quantify the differences between different difficulty levels; the value of λ reflects the differences in complexity, risk level and evaluation scale of assessment tasks of different difficulty levels.

[0027] Preferably, a long short-term memory network LSTM model is used as the architecture of the neural network model. The input layer receives the input feature vector x and reshapes it into a two-dimensional tensor with m time steps and 3 feature dimensions.

[0028] The output of the LSTM layer is the hidden state of the last time step, and the dimension is the number of hidden units. A fully connected layer is added after the LSTM layer to extract high-level features and perform nonlinear transformations. The number of neurons in the fully connected layer is optimized through cross-validation. The activation function is the Sigmoid function: Map the output value to the range of [0,1] and then multiply it by 100 to get the final assessment score;

[0029] The input features of the assessment and scoring model include: operation time series, operation time interval, operation sequence, and operation parameter settings;

[0030] The operation time sequence includes: recording the start time and end time of each operation step of the assessed person during the assessment process, forming a timestamp sequence t=(t 1 ,t 2 ,…,t m ), where m is the total number of operation steps;

[0031] The operation time interval includes: calculating the time interval between each two consecutive operations according to the operation time sequence to form a time interval sequence d=(d 1 ,d 2 ,…,d m-1 ), where d i =t i+1 -t i ;

[0032] The operation sequence includes: comparing the actual operation steps of the examinee with the standard operation process, generating a binary vector s=(s 1 ,s 2 ,…,s m ), where s i =1 means that the i-th step operation complies with the standard process, s i =0 means not in compliance;

[0033] The operation parameter setting includes: for each parameter value set in the operation, comparing the parameter value with the standard parameter value, calculating the relative error, and forming a parameter setting error vector p=(p 1 ,p 2 ,…,p m );

[0034] Concatenate all feature vectors into a complete input feature vector x = (t, d, s, p) with dimension n = 3m-1;

[0035] The output of the assessment scoring model is the assessment score, which is expressed as a scalar y with a value range of [0,100], representing the percentage score of the assessment result.

[0036] Preferably, an assessment scoring model based on a long short-term memory network (LSTM) model is trained, model training data is prepared, and a certain amount of historical assessment data is obtained, including the operation time series, operation time interval, operation sequence, operation parameter settings, and corresponding expert scores of the assessed personnel;

[0037] Preprocess the collected data, extract the input feature vector x and the output score y, and form a training sample pair (x, y); divide the collected data into a training set, a validation set, and a test set; normalize the input features and scale the value range of each feature to [0, 1];

[0038] Set the number of iterations, batch size, and learning rate hyperparameters, optimize the hyperparameters using methods such as grid search or random search, and select the best performing hyperparameter combination;

[0039] Input the preprocessed training data into the LSTM model according to the set batch size and perform forward propagation; after each iteration, evaluate the performance of the model on the validation set and calculate the mean square error, mean absolute error and accuracy indicators; adjust the hyperparameters or perform early stopping based on the performance of the validation set to prevent the model from overfitting;

[0040] After the training process is completed, the performance of the model is evaluated on the test set to verify the generalization ability of the model;

[0041] Based on the performance on the test set, the model was tweaked by adjusting the number of hidden units in the LSTM layer, adding regularization terms, and modifying the loss function.

[0042] Preferably, the person being assessed performs skill assessment item operations in virtual reality, and records the operation data in real time, including the operation time series t, the operation time interval series d, the operation sequence binary vector s, and the operation parameter setting error vector p;

[0043] Preprocess the recorded operation data and extract the input feature matrix X = [t, d, s, p];

[0044] Input the preprocessed input feature matrix X into the trained assessment and scoring model for forward propagation calculation;

[0045] The assessment and scoring model uses the LSTM layer to capture the temporal dependency of the operation data and outputs the predicted score after being processed by the fully connected layer and the Sigmoid activation function. Scoring the predictions Multiply by 100 to get the final 100-point assessment score

[0046] A comprehensive skill assessment and evaluation system for a hydropower plant based on virtual reality, which is implemented based on the comprehensive skill assessment and evaluation method for a hydropower plant based on virtual reality, comprises: a virtual scene module, an assessment task module, an assessment difficulty allocation module, an assessment scoring model construction module and an assessment scoring module;

[0047] The virtual scene module constructs a three-dimensional model of the hydropower plant based on virtual reality technology, and designs and builds a skill assessment scene for the hydropower plant;

[0048] The assessment task module creates a skill assessment project in a skill assessment scenario. The skill assessment project includes an operating environment, assessment requirements, and an assessment operation process. For each skill assessment project, multiple assessment tasks of different difficulty levels are designed;

[0049] The assessment difficulty allocation module automatically calculates the skill assessment difficulty level of the assessed person based on the work data of the assessed person;

[0050] The assessment and scoring model construction module is used to construct and train an assessment and scoring model based on a neural network model, which is used to assess and score the assessed personnel;

[0051] The assessment and scoring module obtains characteristic data of skill assessment items of the assessed personnel in virtual reality, outputs assessment scores through an assessment and scoring model, and conducts skill assessment on the assessed employees.

[0052] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant by calling the computer program stored in the memory.

[0053] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant.

[0054] Beneficial effects of the invention: The invention constructs a three-dimensional model and assessment scene of a hydropower plant based on virtual reality technology, can provide a realistic and immersive assessment environment, eliminate safety hazards and resource limitations of on-site assessments, and improve the standardization and reusability of assessments.

[0055] By designing skill assessment items and tasks of different difficulty levels in a virtual reality assessment scenario, the present invention can conduct targeted assessments based on the actual skill levels of the persons being assessed, which can not only meet the assessment needs of employees in different positions and at different levels, but also comprehensively evaluate employee skills and improve the pertinence and comprehensiveness of the assessment.

[0056] The present invention automatically calculates the assessment difficulty level according to the work data of the assessed personnel, can realize the personalization and dynamic adjustment of the assessment difficulty, avoids the problem of mismatch between the assessment difficulty and the actual level of the employees, and allows each employee to be assessed at a difficulty level suitable for him / her and give full play to his / her own ability.

[0057] By constructing an intelligent assessment and scoring model based on a neural network, the present invention can automatically learn scoring rules from massive historical assessment data, overcome the subjectivity and inconsistency of manual scoring, greatly improve scoring efficiency and accuracy, and ensure the fairness and justice of assessment results.

[0058] The present invention gives assessment scores through an intelligent scoring model, which can realize the digitization and automation of the entire process of skill assessment, reduce the interference of human factors, provide data support for the accurate evaluation of employee skills, and help enterprises optimize human resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flow chart of a comprehensive skill assessment and evaluation method for a hydropower plant based on virtual reality provided by the present invention;

[0060] Figure 2 A virtual reality skill assessment scenario construction flow chart for the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant provided by the present invention;

[0061] Figure 3 A flow chart of the hydropower plant skill assessment process for the method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality provided by the present invention;

[0062] Figure 4 This is a structural diagram of the comprehensive skill assessment and evaluation system for a hydropower plant based on virtual reality provided by the present invention. DETAILED DESCRIPTION

[0063] In order to better understand the present invention, a more detailed description will be made of various aspects of the present invention with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0064] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The accompanying drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in the present invention, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0065] It should also be understood that expressions such as "comprises", "including", "having", "includes" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present invention, "may" is used to mean "one or more embodiments of the present invention". And, the term "exemplary" is intended to refer to an example or illustration.

[0066] Unless otherwise defined, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which the present invention belongs. It should also be understood that unless there is a clear explanation in the present invention, the words defined in the commonly used dictionary should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0067] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0068] Example 1

[0069] Reference Figure 1 , Figure 2 and Figure 3 ,The first embodiment of the present invention provides a ,comprehensive skill assessment and evaluation method for a hydropower plant based on ,virtual reality.

[0070] S1: Based on virtual reality technology, construct a three-dimensional model of the hydropower plant, and design and build a skill assessment scenario for the hydropower plant.

[0071] Obtain data on the hydropower plant's engineering drawings, equipment parameters, and operating status as the basis for building a 3D model; classify, organize, and standardize the collected data to establish a complete database; define the attribute parameters of each device and component, including size, material, and function, in preparation for subsequent 3D modeling.

[0072] Based on the processed data, use 3D modeling software (such as 3ds Max, Maya, etc.) to model the hydropower plant as a whole; carry out detailed modeling of key equipment in the hydropower plant, including turbine generator sets and transformers, to ensure that the geometric dimensions and appearance are consistent with the actual equipment; model the terrain environment of the hydropower plant, including terrain undulations, vegetation distribution, etc., to improve the realism of the scene.

[0073] Assemble the 3D models of each part to form a complete 3D model of the hydropower plant.

[0074] Add realistic materials and textures to the 3D model of the hydropower plant, such as metal materials on the surface of equipment and concrete materials on buildings. Use UV mapping technology to apply high-precision maps to the model surface to improve the visual quality of the model.

[0075] Light sources are set in the 3D model to simulate the actual lighting conditions of the hydropower plant, including natural light and artificial lighting; ambient sounds in the real hydropower plant are extracted and added to the 3D model of the hydropower plant to simulate the ambient sounds when the hydropower plant is in operation.

[0076] Render the constructed three-dimensional model scene of the hydropower plant to complete the construction of the hydropower plant skill assessment scene.

[0077] S1: Based on virtual reality technology, construct a three-dimensional model of the hydropower plant, and design and build a skill assessment scenario for the hydropower plant.

[0078] Obtain data on the hydropower plant's engineering drawings, equipment parameters, and operating status as the basis for building a 3D model; classify, organize, and standardize the collected data to establish a complete database; define the attribute parameters of each device and component, including size, material, and function, in preparation for subsequent 3D modeling.

[0079] Based on the processed data, use 3D modeling software (such as 3ds Max, Maya, etc.) to model the hydropower plant as a whole; carry out detailed modeling of key equipment in the hydropower plant, including turbine generator sets and transformers, to ensure that the geometric dimensions and appearance are consistent with the actual equipment; model the terrain environment of the hydropower plant, including terrain undulations, vegetation distribution, etc., to improve the realism of the scene.

[0080] Assemble the 3D models of each part to form a complete 3D model of the hydropower plant.

[0081] Add realistic materials and textures to the 3D model of the hydropower plant, such as metal materials on the surface of equipment and concrete materials on buildings. Use UV mapping technology to apply high-precision maps to the model surface to improve the visual quality of the model.

[0082] Light sources are set in the 3D model to simulate the actual lighting conditions of the hydropower plant, including natural light and artificial lighting; ambient sounds in the real hydropower plant are extracted and added to the 3D model of the hydropower plant to simulate the ambient sounds when the hydropower plant is in operation.

[0083] Render the constructed three-dimensional model scene of the hydropower plant to complete the construction of the hydropower plant skill assessment scene.

[0084] Step S1: Through comprehensive 3D modeling of the hydropower plant, a highly realistic hydropower plant scene can be created in a virtual reality environment. This not only provides a real operating environment for skill assessment, but also the digital hydropower plant model can be easily updated and expanded, laying the foundation for the long-term management and development of the hydropower plant.

[0085] S2: Create a skill assessment project in the skill assessment scenario, wherein the skill assessment project includes an operating environment, assessment requirements, and an assessment operation process. For each skill assessment project, design multiple assessment tasks of different difficulty levels.

[0086] Based on the actual work scenarios corresponding to the skill assessment items, design the corresponding operating environment in virtual reality; the operating environment should include the equipment, tools and control panels required for the assessment, and should be the same as the actual working environment.

[0087] For each skill assessment item, clear assessment requirements are formulated, including assessment objectives, achievement standards and time limits; assessment requirements are formulated based on the actual working standards and specifications of the hydropower plant and divided into different difficulty levels.

[0088] According to the complexity, risk level and operation frequency of the skill assessment items, the assessment tasks are divided into three difficulty levels: primary skill assessment, intermediate skill assessment and advanced skill assessment; the assessment tasks of different difficulty levels are progressively difficult according to the relationship between the difficulty of primary skill assessment, intermediate skill assessment and advanced skill assessment.

[0089] The difficulty of the primary skill assessment includes: targeting basic operations and common scenarios, such as starting, stopping, and inspection of equipment, etc., mainly assessing the degree of mastery of operating procedures and specifications by the assessee.

[0090] The difficulty of the intermediate skill assessment includes: operation of hydropower plant equipment and work decision-making, including equipment debugging, fault diagnosis and parameter optimization.

[0091] The difficulty of the advanced skills assessment includes: dynamically adjusting the entire task process of the hydropower plant according to the working conditions of the hydropower plant.

[0092] At each difficulty level, multiple specific assessment task scenarios are designed to simulate different situations in actual work.

[0093] Design the corresponding assessment operation process based on the actual workflow of the skill assessment project; the assessment operation process should include the specific operation content, sequence and time nodes of each step, and set corresponding judgment conditions for each step.

[0094] In the assessment operation process, data collection points are set to record the operation data of the person being assessed in real time, including operation time, operation sequence and operation parameter settings.

[0095] Step S2 designs a variety of skill assessment items and tasks in the virtual reality scene to comprehensively evaluate the actual operation ability of employees. By setting assessment tasks of different difficulty levels, the assessment needs of employees at different positions and levels can be met, and targeted training and capacity improvement can be achieved. Virtual reality technology can also simulate various complex and dangerous working conditions, allowing employees to learn and master coping skills in a safe environment. Standardized assessment processes and evaluation criteria can ensure the fairness of the assessment and provide employees with clear goals and directions for skill improvement.

[0096] S3: Automatically calculate the difficulty level of the skill assessment of the person being assessed based on the work data of the person being assessed.

[0097] The difficulty level of the skill assessment assigned to the person being assessed is automatically calculated based on the work data of the person being assessed.

[0098] Define the assessment variables and parameters of the person being assessed, and calculate the difficulty level D of the person being assessed: D = round (α J +β×log(Y+1)); round(·) represents the rounding function, log(·) represents the natural logarithm function, which is used to perform nonlinear transformation of working years; (Y+1) avoids the undefined problem when Y=0; J is the position type of the person being assessed, and its value range is [1, N], where N is the total number of position types; Y is the working years of the person being assessed, in years; D is the difficulty level of the assessment task, and its value range is [1, 3], where 1 represents primary skill assessment, 2 represents intermediate skill assessment, and 3 represents advanced skill assessment; α j is the baseline value of the difficulty level of job type j, reflecting the complexity of the skills required for the job; β is the difficulty level adjustment coefficient of working years, reflecting the impact of working experience on the difficulty level;

[0099] According to the difficulty level D, set the corresponding difficulty coefficient λ:

[0100]

[0101] Among them, δ is the increment of the difficulty coefficient of the difficulty level, which is used to quantify the differences between different difficulty levels; the value of λ reflects the differences in complexity, risk level and evaluation scale of assessment tasks of different difficulty levels.

[0102] Step S3 automatically calculates the skill assessment difficulty level based on the employee's actual work data, which can achieve a dynamic match between the assessment difficulty and the employee's ability. Automatically calculating the assessment difficulty level can also greatly improve the assessment efficiency and reduce the workload of managers.

[0103] S4: Construct and train an assessment and scoring model based on a neural network model to assess and score the assessed personnel.

[0104] The long short-term memory network LSTM model is used as the basic architecture of the neural network model to effectively process time series data; the input layer receives the input feature vector x and reshapes it into a two-dimensional tensor with m time steps and 3 feature dimensions.

[0105] The number of hidden units in the LSTM layer is set according to actual needs, usually 64 to 256; the output of the LSTM layer is the hidden state of the last time step, and the dimension is the number of hidden units; one or more fully connected layers are added after the LSTM layer to extract high-level features and perform nonlinear transformations; the number of neurons in the fully connected layer can be optimized through cross-validation; the number of neurons in the output layer is 1, and the activation function is the Sigmoid function: Map the output value to the range of [0,1] and then multiply it by 100 to get the final assessment score.

[0106] The input features of the assessment and scoring model include: operation time series, operation time interval, operation sequence and operation parameter settings.

[0107] The operation time sequence includes: recording the start time and end time of each operation step of the assessed person during the assessment process, forming a timestamp sequence t=(t 1 ,t 2 ,…,t m ), where m is the total number of operation steps.

[0108] The operation time interval includes: calculating the time interval between each two consecutive operations according to the operation time sequence to form a time interval sequence d=(d 1 ,d 2 ,…,d m-1) , where d i =t i+1 -t i .

[0109] The operation sequence includes: comparing the actual operation steps of the examinee with the standard operation process, generating a binary vector s=(s 1 ,s 2 ,…,s m ), where s i =1 means that the i-th step operation complies with the standard process, s i =0 means not in compliance.

[0110] The operation parameter setting includes: for each parameter value (such as temperature, pressure, current, etc.) set in each operation step, comparing the parameter value with the standard parameter value, calculating the relative error, and forming a parameter setting error vector p=(p 1 ,p 2 ,…,p m ).

[0111] All feature vectors are concatenated into a complete input feature vector x = (t, d, s, p) with a dimension of n = 3m-1.

[0112] The output of the assessment scoring model is the assessment score, which is expressed as a scalar y with a value range of [0,100], representing the percentage score of the assessment result.

[0113] The mean square error (MSE) is used as the loss function: Where m is the number of samples, y=(y 1 ,y 2 ,…,y m ) is the real score, Scoring predictions; using the Adam optimization algorithm to minimize the loss function, adaptively adjusting the learning rate, and accelerating the convergence of the model.

[0114] Use deep learning frameworks such as TensorFlow or PyTorch to implement neural network models; build the model according to the designed architecture and define the forward propagation process, including the calculation of LSTM layer and fully connected layer; write a training loop to perform forward propagation, calculate loss, backpropagation and parameter update in each iteration; during the training process, record the loss and evaluation indicators of the training set and validation set to monitor the training progress and performance of the model.

[0115] Train the assessment and scoring model based on the long short-term memory network (LSTM) model, prepare model training data, and obtain a certain amount of historical assessment data, including the operation time series, operation time interval, operation sequence, operation parameter settings, and corresponding expert scores of the assessed personnel.

[0116] The collected data is preprocessed to extract the input feature vector x and the output score y, and form a training sample pair (x, y); the collected data is divided into a training set, a validation set, and a test set, with typical proportions of 60%, 20%, and 20%; the input features are normalized, and the value range of each feature is scaled to [0, 1] or [-1, 1] to improve the training efficiency and generalization ability of the model.

[0117] Set the number of iterations, batch size, and learning rate hyperparameters, optimize the hyperparameters through grid search or random search, and select the hyperparameter combination with the best performance.

[0118] The preprocessed training data is input into the long short-term memory network LSTM model according to the set batch size to perform forward propagation; after each iteration cycle, the performance of the model is evaluated on the validation set, and the mean square error, mean absolute error and accuracy indicators are calculated; according to the performance of the validation set, the hyperparameters are adjusted or early stopping is performed to prevent the model from overfitting.

[0119] After the training process is completed, the performance of the model is evaluated on the test set to verify the generalization ability of the model.

[0120] Based on the performance on the test set, the model was tweaked by adjusting the number of hidden units in the LSTM layer, adding regularization terms, and modifying the loss function.

[0121] Step S4 builds an intelligent assessment and scoring model based on a neural network model, which can automatically learn scoring rules and experience from massive historical data and continuously improve the accuracy and consistency of scoring. Compared with manual scoring, the intelligent scoring model can effectively overcome subjectivity and bias and ensure the fairness of the assessment results.

[0122] S5: Obtain the characteristic data of the skill assessment items of the assessed personnel in virtual reality, output the assessment score through the assessment scoring model, and conduct skill assessment on the assessed employees.

[0123] The examinee performs skill assessment item operations in virtual reality and records the operation data in real time, including the operation time series t, the operation time interval series d, the operation sequence binary vector s and the operation parameter setting error vector p.

[0124] Preprocess the recorded operation data and extract the input feature matrix X = [t, d, s, p];

[0125] The preprocessed input feature matrix X is input into the trained assessment and scoring model for forward propagation calculation.

[0126] The assessment and scoring model uses the LSTM layer to capture the temporal dependency of the operation data and outputs the predicted score after being processed by the fully connected layer and the Sigmoid activation function. Scoring the predictions Multiply by 100 to get the final 100-point assessment score

[0127] Step S5 uses virtual reality technology to collect employee operation data and gives assessment scores through an intelligent assessment and scoring model, which can realize the automation and standardization of the entire process of skill assessment. Detailed operation data records provide a detailed basis for the accurate assessment of employee skill levels and also provide direction for subsequent targeted training and improvement. The seamless combination of skill assessment and intelligent scoring will greatly improve the scientific level of human resource management in hydropower plants and provide solid support for the long-term development of enterprises.

[0128] Example 2

[0129] Reference Figure 4 , which is the second embodiment of the present invention, provides a comprehensive skill assessment and evaluation system for hydropower plants based on virtual reality.

[0130] The system comprises: a virtual scene module, an assessment task module, an assessment difficulty allocation module, an assessment scoring model construction module and an assessment scoring module.

[0131] The virtual scene module constructs a three-dimensional model of a hydropower plant based on virtual reality technology, and designs and builds a skill assessment scene for the hydropower plant.

[0132] The assessment task module creates a skill assessment project in a skill assessment scenario. The skill assessment project includes an operating environment, assessment requirements, and an assessment operation process. For each skill assessment project, multiple assessment tasks of different difficulty levels are designed.

[0133] The assessment difficulty allocation module automatically calculates the skill assessment difficulty level of the assessee based on the work data of the assessee.

[0134] The assessment and scoring model construction module is used to construct and train an assessment and scoring model based on a neural network model, which is used to assess and score the assessed personnel.

[0135] The assessment and scoring module obtains characteristic data of skill assessment items of the assessed personnel in virtual reality, outputs assessment scores through an assessment and scoring model, and conducts skill assessment on the assessed employees.

[0136] Example 3

[0137] The present invention also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the above-mentioned virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant may be executed.

[0138] The method or system according to the embodiment of the present invention may also be implemented with the aid of the architecture of the electronic device of the present invention.

[0139] An electronic device may include a bus, one or more CPUs, read-only memory (ROM), random access memory (RAM), a communication port for connecting to a network, input / output components, a hard disk, and the like.

[0140] A storage device in the electronic device, such as a ROM or a hard disk, can store the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant provided by the present invention.

[0141] A comprehensive skill assessment and evaluation method for a hydropower plant based on virtual reality includes: constructing a three-dimensional model of a hydropower plant based on virtual reality technology, designing and building a skill assessment scene for the hydropower plant; creating skill assessment items in the skill assessment scene, wherein the skill assessment items include an operating environment, assessment requirements, and an assessment operation process, and designing a plurality of assessment tasks of different difficulty levels for each skill assessment item; automatically calculating the skill assessment difficulty level of the assessed person based on the work data of the assessed person; constructing and training an assessment scoring model based on a neural network model for assessing and scoring the assessed person; obtaining characteristic data of the skill assessment items of the assessed person in virtual reality, outputting the assessment score through the assessment scoring model, and conducting skill assessment on the assessed employee.

[0142] Furthermore, the electronic device may also include a user interface. Of course, the architecture of the present invention is only exemplary, and when implementing different devices, one or more components in the electronic device disclosed in the present invention may be omitted according to actual needs.

[0143] Example 4

[0144] The invention also discloses a computer-readable storage medium.

[0145] The computer-readable storage medium has computer-readable instructions stored thereon.

[0146] When the computer-readable instructions are executed by the processor, the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant according to an embodiment of the present invention described with reference to the above drawings can be executed.

[0147] The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. In addition, according to an embodiment of the present invention, the process described above with reference to the flowchart may be implemented as a computer software program.

[0148] For example, the present invention provides a non-temporary machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present invention, for example: based on virtual reality technology, construct a three-dimensional model of a hydropower plant, design and build a skill assessment scene for the hydropower plant; create skill assessment items in the skill assessment scene, and the skill assessment items include an operating environment, assessment requirements, and an assessment operation process. For each skill assessment item, a plurality of assessment tasks with different difficulty levels are designed; based on the work data of the person being assessed, the skill assessment difficulty level of the person being assessed is automatically calculated; a neural network model-based assessment scoring model is constructed and trained for assessing and scoring the person being assessed; characteristic data of the skill assessment items of the person being assessed in virtual reality is obtained, and the assessment score is output through the assessment scoring model to conduct skill assessment on the employee being assessed.

[0149] When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are performed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0150] The above sequence for the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless otherwise specifically stated.

[0151] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0152] In addition, the parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0153] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A comprehensive skill assessment and evaluation method for hydropower plants based on virtual reality, characterized in that: include: Based on virtual reality technology, a three-dimensional model of a hydropower plant was constructed, and a skill assessment scenario for the hydropower plant was designed and built; Creating a skill assessment project in a skill assessment scenario, wherein the skill assessment project includes an operating environment, assessment requirements, and an assessment operation process, and designing multiple assessment tasks of different difficulty levels for each skill assessment project; Automatically calculate the difficulty level of the skill assessment of the person being assessed based on the work data of the person being assessed; Construct and train an assessment and scoring model based on a neural network model to assess and score the assessed personnel; Acquire the characteristic data of the skill assessment items of the assessed personnel in virtual reality, output the assessment scores through the assessment scoring model, and conduct skill assessment on the assessed employees.

2. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 1 is characterized in that: Obtain the data of hydropower plant engineering drawings, equipment parameters and operating status as the basis for building a 3D model; classify, organize and standardize the collected data to establish a complete database; define the attribute parameters of each equipment and component, including size, material and function; Based on the processed data, the hydropower plant is modeled as a whole using 3D modeling software; key equipment in the hydropower plant, including turbine generator sets and transformers, is modeled in detail to ensure that the geometric dimensions and appearance are consistent with the actual equipment; the terrain environment of the hydropower plant is modeled, including terrain undulations and vegetation distribution; Assemble the 3D models of each part to form a complete 3D model of the hydropower plant; Add realistic materials and textures to the 3D model of the hydropower plant; use UV mapping technology to apply high-precision maps to the model surface to improve the visual quality of the model; Set up light sources in the 3D model to simulate the actual lighting conditions of the hydropower plant, including natural light and artificial lighting; extract the environmental sounds in the real hydropower plant and add them to the 3D model of the hydropower plant to simulate the environmental sounds of the hydropower plant in operation in the 3D model; Render the constructed three-dimensional model scene of the hydropower plant to complete the construction of the hydropower plant skill assessment scene.

3. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 2 is characterized in that: Design a corresponding operating environment in virtual reality based on the actual work scenarios corresponding to the skill assessment items; the operating environment should include the equipment, tools and control panels required for the assessment and should be the same as the actual working environment; For each skill assessment item, formulate clear assessment requirements, including assessment objectives, achievement standards and time limits; formulate assessment requirements according to the actual working standards and specifications of the hydropower plant, and divide them into different difficulty levels; Design the corresponding assessment operation process according to the actual workflow of the skill assessment project; the assessment operation process should include the specific operation content, sequence and time nodes of each step, and set corresponding judgment conditions for each step; In the assessment operation process, data collection points are set to record the operation data of the person being assessed in real time, including operation time, operation sequence and operation parameter settings; According to the complexity, risk level and operation frequency of the skill assessment items, the assessment tasks are divided into three difficulty levels: primary skill assessment, intermediate skill assessment and advanced skill assessment; the assessment tasks of different difficulty levels are progressively difficult according to the relationship between the difficulty of primary skill assessment, intermediate skill assessment and advanced skill assessment.

4. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 3 is characterized in that: Automatically calculate the difficulty level of the skill assessment of the person being assessed based on the work data of the person being assessed; Define the assessment variables and parameters of the person being assessed, and calculate the difficulty level D of the person being assessed: D = round (α J +β×log(Y+1)); round(·) represents the rounding function, log(·) represents the natural logarithm function, which is used to perform nonlinear transformation on working years; J represents the job type of the person being assessed, and its value range is [1, N], where N is the total number of job types; Y represents the working years of the person being assessed; D represents the difficulty level of the assessment task, and its value range is [1, 3], where 1 represents primary skill assessment, 2 represents intermediate skill assessment, and 3 represents advanced skill assessment; α j is the difficulty level benchmark value of job type j; β is the difficulty level adjustment coefficient of working years; According to the difficulty level D, set the corresponding difficulty coefficient λ: Among them, δ is the increment of the difficulty coefficient of the difficulty level, which is used to quantify the differences between different difficulty levels; the value of λ reflects the differences in complexity, risk level and evaluation scale of assessment tasks of different difficulty levels.

5. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 4 is characterized in that: The long short-term memory network LSTM model is used as the architecture of the neural network model. The input layer receives the input feature vector x and reshapes it into a two-dimensional tensor with m time steps and 3 feature dimensions. The output of the LSTM layer is the hidden state of the last time step, and the dimension is the number of hidden units. A fully connected layer is added after the LSTM layer to extract high-level features and perform nonlinear transformations. The number of neurons in the fully connected layer is optimized through cross-validation. The activation function is the Sigmoid function: Map the output value to the range of [0, 1] and then multiply it by 100 to get the final assessment score; The input features of the assessment and scoring model include: operation time series, operation time interval, operation sequence, and operation parameter settings; The operation time sequence includes: recording the start time and end time of each operation step of the assessed person during the assessment process, forming a timestamp sequence t=(t1, t2, ..., t m ), where m is the total number of operation steps; The operation time interval includes: calculating the time interval between each two consecutive operations according to the operation time sequence to form a time interval sequence d=(d1, d2, ..., d m-1 ), where d i =t i+1 -t i ; The operation sequence includes: comparing the actual operation steps of the examinee with the standard operation process, generating a binary vector s=(s1, s2, ..., s m ), where s i =1 means that the i-th step operation complies with the standard process, s i =0 means not in compliance; The operation parameter setting includes: for each parameter value set in the operation, comparing the parameter value with the standard parameter value, calculating the relative error, and forming a parameter setting error vector p=(p1, p2, ..., p m ); Concatenate all feature vectors into a complete input feature vector x = (t, d, s, p) with dimension n = 3m-1; The output of the assessment scoring model is the assessment score, which is expressed as a scalar y with a value range of [0, 100], representing the percentage score of the assessment result.

6. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 5 is characterized in that: Train the assessment and scoring model based on the long short-term memory network (LSTM) model, prepare model training data, and obtain a certain amount of historical assessment data, including the operation time series, operation time interval, operation sequence, operation parameter settings, and corresponding expert scores of the assessed personnel; Preprocess the collected data, extract the input feature vector x and the output score y, and form a training sample pair (x, y); divide the collected data into a training set, a validation set, and a test set; normalize the input features and scale the value range of each feature to [0, 1]; Set the number of iterations, batch size, and learning rate hyperparameters, optimize the hyperparameters using methods such as grid search or random search, and select the best performing hyperparameter combination; Input the preprocessed training data into the LSTM model according to the set batch size and perform forward propagation; after each iteration, evaluate the performance of the model on the validation set and calculate the mean square error, mean absolute error and accuracy indicators; adjust the hyperparameters or perform early stopping based on the performance of the validation set to prevent the model from overfitting; After the training process is completed, the performance of the model is evaluated on the test set to verify the generalization ability of the model; Based on the performance on the test set, the model was tweaked by adjusting the number of hidden units in the LSTM layer, adding regularization terms, and modifying the loss function.

7. The method for comprehensive skill assessment and evaluation of a hydropower plant based on virtual reality according to claim 6 is characterized in that: The examinee performs skill assessment project operations in virtual reality and records the operation data in real time, including the operation time series t, the operation time interval series d, the operation sequence binary vector s and the operation parameter setting error vector p; Preprocess the recorded operation data and extract the input feature matrix X = [t, d, s, p]; Input the preprocessed input feature matrix X into the trained assessment and scoring model for forward propagation calculation; The assessment and scoring model uses the LSTM layer to capture the temporal dependency of the operation data and outputs the predicted score after being processed by the fully connected layer and the Sigmoid activation function. Scoring the predictions Multiply by 100 to get the final 100-point assessment score 8. A comprehensive skill assessment and evaluation system for a hydropower plant based on virtual reality, which is implemented based on the comprehensive skill assessment and evaluation method for a hydropower plant based on virtual reality according to any one of claims 1 to 7, characterized in that: include: Virtual scene module, assessment task module, assessment difficulty allocation module, assessment scoring model construction module and assessment scoring module; The virtual scene module constructs a three-dimensional model of the hydropower plant based on virtual reality technology, and designs and builds a skill assessment scene for the hydropower plant; The assessment task module creates a skill assessment project in a skill assessment scenario. The skill assessment project includes an operating environment, assessment requirements, and an assessment operation process. For each skill assessment project, multiple assessment tasks of different difficulty levels are designed; The assessment difficulty allocation module automatically calculates the skill assessment difficulty level of the assessed person based on the work data of the assessed person; The assessment and scoring model construction module is used to construct and train an assessment and scoring model based on a neural network model, which is used to assess and score the assessed personnel; The assessment and scoring module obtains characteristic data of skill assessment items of the assessed personnel in virtual reality, outputs assessment scores through an assessment and scoring model, and conducts skill assessment on the assessed employees.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the virtual reality-based comprehensive skill assessment and evaluation method for a hydropower plant as described in any one of claims 1 to 7.

Images