Comprehensive training system for thermal DCS (Distributed Control System) of power plant

Abstract

The invention discloses a power plant thermotechnical DCS comprehensive training system, and relates to the technical field of thermotechnical training, and the system comprises the steps: carrying out the technical analysis of a power plant thermotechnical process based on a DCS comprehensive training system, and determining the training demand information; determining a plurality of learning paths, and constructing DCS training environment parameters; obtaining user test data, making a plurality of training plans for training based on the user test data, and determining a plurality of training results; screening the plurality of training plans to generate a recommended review list; and obtaining a thermotechnical training information set, and performing operation optimization verification on the power plant. The technical problems that in the prior art, a complex operation scene of a thermal DCS (Distributed Control System) of a power plant is difficult to truly simulate, and personalized training paths for different user requirements and skill levels are lacked, so that training pertinence is insufficient, learning evaluation is incomplete, and skill improvement efficiency is poor are solved. The technical effects of enhancing the training effect and improving the skill improvement efficiency are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to thermal engineering training, and in particular to a comprehensive training system for thermal engineering DCS of a power plant. Background Art

[0002] In the operation of modern power plants, the thermal control system (DCS, distributed control system) is the core system for real-time monitoring, optimization and control of equipment operation status. Its complexity and importance require operators to have solid theoretical knowledge and proficient practical skills. However, the current training methods for thermal DCS operators in power plants still have many shortcomings and are difficult to adapt to the needs of efficient operation and intelligent development of modern power plants. Traditional thermal training is mainly based on classroom lectures and basic simulation exercises, lacking a real operating environment and dynamic personalized learning content. Trainees passively accept knowledge points and cannot flexibly respond to complex problems that arise in actual work. In addition, the existing simulation system can usually only simply display the thermal operation logic and cannot fully reflect the operation scenario of the actual DCS system, resulting in a large gap between the training effect and the actual application. In addition, there is a lack of a scientific learning evaluation mechanism, and it is difficult to quantify the learning effect of trainees. The weak links encountered by trainees in the learning process are not identified and solved in time, resulting in low training efficiency, lack of dynamic adjustment and optimization, and inability to formulate targeted training paths according to the characteristics and needs of different trainees. There is no direct connection between the improvement of trainees' skills and the improvement of the operating efficiency of power plants, and it is difficult to reflect the true value of training.

[0003] Therefore, at the current stage, there are technical problems in the comprehensive training related technologies of thermal DCS, such as difficulty in truly simulating the complex operating scenarios of thermal DCS (distributed control systems) of power plants and lack of personalized training paths for different user needs and skill levels, which leads to insufficient targeted training, incomplete learning evaluation and poor efficiency in skill improvement. Summary of the invention

[0004] This application provides a comprehensive training system for thermal DCS of a power plant, thereby solving the technical problems existing in the prior art, such as difficulty in truly simulating the complex operating scenarios of thermal DCS (distributed control system) of a power plant, lack of personalized training paths for different user needs and skill levels, resulting in insufficient training targeting, incomplete learning evaluation, and poor efficiency in skill improvement, thereby achieving the technical effect of enhancing training effects and improving the efficiency of skill improvement.

[0005] The present application provides a DCS comprehensive training system for thermal engineering of a power plant, the system comprising: a training demand information determination module, used for performing technical analysis of thermal engineering of a power plant based on a DCS comprehensive training system, and determining training demand information; a DCS training environment parameter construction module, used for performing reinforcement learning according to the training demand information, determining multiple learning paths, and constructing DCS training environment parameters; a user test data acquisition module, used for performing testing according to the DCS training environment parameters through a user terminal, obtaining user test data, formulating multiple training plans for training based on the user test data, and determining multiple training results; a recommended review list generation module, used for performing thermal engineering learning evaluation according to the multiple training results, generating learning effect feedback parameters, screening the multiple training plans according to the learning effect feedback parameters, and generating a recommended review list; a thermal engineering training information set acquisition module, used for performing thermal engineering application training according to the recommended review list, obtaining a thermal engineering training information set, and performing operation optimization verification of the power plant according to the thermal engineering training information set.

[0006] In a possible implementation, the DCS training environment parameter construction module also performs the following processing: based on the training demand information, a user state analysis is performed in combination with the user end to construct a user state space; based on the training demand information, a learning action analysis is performed in combination with the teaching end to construct a teaching action space; a reward function is introduced to perform a learning dynamic analysis on the user state space and the teaching action space to generate multiple learning paths; according to the training demand information, the multiple learning paths are clustered and analyzed, and the multiple learning paths are divided according to the clustering results to obtain a theoretical priority path, a practical priority path, and a comprehensive path; based on the theoretical priority path, the practical priority path, and the comprehensive path, a path dynamic optimization is performed to obtain a learning optimization path, and the DCS training environment parameters are defined according to the learning optimization path.

[0007] In a possible implementation, the DCS training environment parameter construction module also performs the following processing: performing DCS theoretical analysis based on the theoretical priority path to generate DCS knowledge information to be supplemented; performing practical analysis based on the practical priority path to generate practical training information; performing teaching analysis based on the comprehensive path to generate teaching balance information; determining DCS theoretical parameters based on the DCS knowledge information to be supplemented in combination with the theoretical priority path; determining practical configuration parameters based on the practical training information to be supplemented in combination with the practical priority path; determining teaching scenario information based on the teaching balance information in combination with the comprehensive path; associating and integrating the DCS theoretical parameters, the practical configuration parameters, and the teaching scenario information to configure the DCS training environment parameters.

[0008] In a possible implementation, the user test data acquisition module also performs the following processing: classify the user test data using a classification algorithm to obtain a theoretical blind spot data class and an operational error data class; strengthen the theory of the user end according to the theoretical blind spot data class in combination with the teaching end to generate a theoretical training plan; strengthen the practical operation of the user end according to the operational error data class in combination with the teaching end to generate a practical training plan; construct a conditional probability table based on the theoretical training plan and the practical training plan in combination with the DCS training environment parameters; traverse the theoretical training plan and the practical training plan respectively according to the conditional probability table to perform fault diagnosis and determine the probability of occurrence of theoretical training faults and the probability of occurrence of practical training faults; add the theoretical training fault probability and the practical training fault probability to the multiple training results.

[0009] In a possible implementation, the recommended review list generation module also performs the following processing: based on the probability of occurrence of theoretical training failures, a thermal engineering learning evaluation is performed on the theoretical training plan to construct a theoretical learning curve; based on the probability of occurrence of practical training failures, a thermal engineering learning evaluation is performed on the practical training plan to construct a practical learning curve; based on the theoretical learning curve, a multi-stage evaluation is performed to generate a plurality of theoretical mastery scores; based on the practical learning curve, a multi-stage evaluation is performed to generate a plurality of practical proficiency scores; a learning progress analysis is performed on the multiple theoretical mastery scores and the multiple practical proficiency scores to generate a multi-stage learning effect, and the multi-stage learning effect is serialized according to the learning sequence to generate the learning effect feedback parameters.

[0010] In a possible implementation, the recommended review list generation module also performs the following processing: fitting the theoretical learning curve and the practical learning curve according to the learning effect feedback parameters according to the learning sequence to generate a learning fitting curve; performing forgetting assessment based on the learning fitting curve to obtain a learning forgetting rate; screening and identifying the theoretical training plan according to the learning forgetting rate in combination with the multiple theoretical mastery scores to generate multiple theoretical review modules; screening and identifying the practical training plan according to the learning forgetting rate in combination with the multiple practical proficiency scores to generate multiple practical review modules; formulating a review priority rule based on the learning forgetting rate, and processing the multiple theoretical review modules and the multiple practical review modules in descending order according to the review priority rule to generate a theoretical review sequence and a practical review sequence; performing adaptability analysis on the theoretical review sequence and the practical review sequence to obtain a learning adaptability coefficient, and integrating the theoretical review sequence with the practical review sequence based on the learning adaptability coefficient to generate the recommended review list.

[0011] In a possible implementation, the recommended review list generation module further performs the following processing: review and select the multiple theoretical review modules according to the theoretical review sequence, conduct thermal engineering application training according to the first review content, and generate thermal engineering theory review data; review and select the multiple practical review modules according to the practical review sequence, conduct thermal engineering application training according to the second review content, and generate thermal engineering practical review data; perform training monitoring based on the thermal engineering theory review data to obtain thermal engineering theory training information; perform training monitoring based on the thermal engineering practical review data to obtain thermal engineering practical training information; synchronize the thermal engineering theory training information and the thermal engineering practical training information to the DCS comprehensive training system for comprehensive evaluation to obtain a thermal engineering DCS comprehensive training score; and add the thermal engineering DCS comprehensive training score to the thermal engineering training information set.

[0012] In a possible implementation, the thermal engineering training information set acquisition module further performs the following processing: mapping the thermal engineering theoretical training information to the DCS comprehensive training system according to the knowledge dimension for storage, performing data verification on the first storage result, and generating a theoretical data verification result; mapping the thermal engineering practical training information to the DCS comprehensive training system according to the skill dimension for storage, performing data verification on the second storage result, and generating a practical data verification result; calculating the thermal engineering theoretical training information based on the theoretical data verification result to obtain a thermal engineering theoretical score; calculating the thermal engineering practical training information based on the practical data verification result to obtain a thermal engineering practical score; normalizing the thermal engineering theoretical score and the thermal engineering practical score to generate the thermal engineering DCS comprehensive training score.

[0013] The application proposes a power plant thermal DCS comprehensive training system, which conducts a technical analysis of the thermal engineering of the power plant based on the DCS comprehensive training system, determines the training demand information; determines multiple learning paths, builds DCS training environment parameters; obtains user test data, formulates multiple training plans based on the user test data for training, and determines multiple training results; screens multiple training plans and generates a recommended review list; obtains a thermal training information set, and performs operation optimization verification on the power plant. It solves the technical problems existing in the prior art, such as the difficulty in truly simulating the complex operation scenarios of the thermal DCS (distributed control system) of the power plant, the lack of personalized training paths for different user needs and skill levels, resulting in insufficient training targeting, incomplete learning evaluation, and poor efficiency in skill improvement, and achieves the technical effect of enhancing training effects and improving skill improvement efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a power plant thermal DCS comprehensive training system provided in an embodiment of the present application; Figure 2 A schematic diagram of the execution process of a DCS training environment parameter construction module in a power plant thermal DCS comprehensive training system provided in an embodiment of the present application.

[0016] Description of the accompanying drawings: training demand information determining module 10, DCS training environment parameter building module 20, user test data obtaining module 30, recommended review list generating module 40, thermal engineering training information set obtaining module 50. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a comprehensive training system for thermal DCS of a power plant, such as Figure 1 As shown, the system comprises: The training requirement information determination module 10 is used to perform a technical analysis of thermal engineering of a power plant based on a DCS comprehensive training system and determine training requirement information.

[0021] Preferably, the technical capabilities of the DCS comprehensive training system are used to conduct a comprehensive analysis of the operating characteristics, operational complexity and current status of personnel skills of the thermal system of the power plant, so as to clarify the specific learning needs of different training targets. Specifically, the thermal system of the power plant is analyzed, including the composition and function of the thermal system, the system operating characteristics (including multi-variable, strongly coupled dynamic characteristics) and key equipment and operational complexity (such as boiler combustion control, main steam parameter adjustment, turbine load control). Among them, the thermal system mainly includes boilers, turbines, generators and their auxiliary equipment, involving key links such as heat transfer, pressure regulation, and steam quality control; the DCS control system analysis includes common control strategies such as PID control, logic control, and fuzzy control , dynamic collaboration between multiple control loops (such as coordinated control of boilers, turbines and power grids); personnel skill status analysis refers to the assessment of the theoretical knowledge level, practical skills and problem-solving ability of operators, comparing existing skills with job requirements, and identifying weak links (such as insufficient parameter adjustment capabilities or unskilled emergency handling); then generate training needs information based on these analysis results, which may include training objectives, such as proficient operation of DCS interface, mastery of boiler combustion adjustment logic, and rapid response to alarm signals. Design training content for key equipment and operating scenarios identified in the analysis, such as load adjustment strategy, parameter setting and optimization, and equipment interlocking operation. Design personalized learning paths and corresponding training methods based on the skill levels and responsibilities of different personnel.

[0022] The DCS training environment parameter construction module 20 is used to perform reinforcement learning according to the training demand information, determine multiple learning paths, and construct DCS training environment parameters.

[0023] Preferably, the reinforcement learning technology in artificial intelligence is used to provide trainees with personalized, accurate training content and a real simulation environment for the needs of thermal engineering training in power plants through continuously optimized learning path generation and dynamic environment construction. Specifically, reinforcement learning is used to generate the best learning path for trainees of different levels and needs. Each path corresponds to different training focuses and operation processes to ensure personalized learning, from basic knowledge to complex operations, to achieve progressive learning. The training environment is dynamically simulated according to the operating conditions of the real power plant, so that trainees can deal with various operation scenarios and faults in the simulation environment, that is, various settings and indicators required for constructing virtual training scenarios, including the complexity of the training content, the details of the scenario simulation, etc. Specifically, according to The actual operating data of the power plant is used to set the initial values ​​and variation ranges of the main thermal parameters (such as pressure, temperature, flow, etc.) in the DCS training scenario to ensure that the scenario is close to the actual working conditions. Operation scenarios of different difficulty levels are constructed, and dynamic response characteristics are configured for the virtual equipment in the DCS training system. For example, the delay characteristics of pressure changes when the temperature rises, simulate the operation feedback of real equipment, and finally, according to the learning path generated by reinforcement learning, configure specific training scenarios and parameters for different trainees. For example, the training environment for novice trainees tends to be basic parameter adjustment and single-device operation, while the training environment for advanced trainees simulates multi-device collaborative control and complex working conditions, thereby effectively improving the pertinence and practicality of the training, ensuring that trainees can master key skills while learning efficiently.

[0024] The user test data acquisition module 30 is used to perform a test according to the DCS training environment parameters through the user terminal to obtain user test data, formulate multiple training plans based on the user test data for training, and determine multiple training results.

[0025] Preferably, the virtual environment and learning path constructed by the DCS training system are used to conduct interactive testing through the user end (such as the trainee operation interface), collect the user's operation data, learning performance and test results during the test as input information, and further generate and implement personalized training plans to help trainees improve their skills and generate specific evaluation results of the training effect. Specifically, the user end test is the core step of the DCS training system, which mainly evaluates the trainees' initial ability and learning effect by simulating real scenarios. The test environment is set according to the generated DCS training environment parameters, including the operation scenarios of thermal equipment (such as boiler regulation, turbine control, etc.), dynamically changing thermal parameters (such as temperature, pressure, etc.), and the training environment parameters. , flow) and fault or alarm simulation (such as over-temperature alarm, abnormal flow, etc.). The test content is designed to correspond to the actual work tasks, and then every step of the trainee's operation in the test process is recorded in real time, including command input, operation time, response results, etc., to form user test data; the user test data is analyzed to evaluate the trainee's ability, extract key indicators, analyze the reasons, etc., and generate multiple targeted training plans. Each training plan is customized according to the trainee's test performance. For example, special training is designed for trainees with many alarm processing errors. The training content is divided into multiple modules, and the progress of the trainees in the training process is monitored in real time. The training plan is dynamically adjusted according to feedback, and finally multiple training results are determined to improve operational efficiency and ability level.

[0026] The recommended review list generating module 40 is used to perform thermal engineering learning evaluation according to the plurality of training results, generate learning effect feedback parameters, screen the plurality of training plans according to the learning effect feedback parameters, and generate a recommended review list.

[0027] Preferably, by evaluating the performance data of trainees during the training process, key parameters reflecting the learning effect are extracted, and these parameters are used to optimize and adjust the training plan, and finally a personalized review list is generated for each trainee to strengthen weak links and consolidate the learned knowledge. Specifically, the thermal engineering learning evaluation is to conduct a comprehensive analysis of the trainees' skill mastery, learning progress and weak links based on their performance in multiple training results, including knowledge mastery, such as the degree of understanding of thermal engineering principles and DCS operating logic, operational capabilities, such as the skills of adjusting parameters and handling alarms under different operating conditions, and comprehensive capabilities, such as the comprehensive judgment and execution capabilities of multi-device collaborative control. Then, the evaluation results are quantified and output to obtain learning effect feedback parameters, which are used to reflect the main characteristics and deficiencies in the trainees' learning process, which may include mastery parameters to reflect the trainees' mastery of the contents of different modules, such as alarm handling mastery: 80%; error distribution parameters, record The types and frequencies of students' errors are recorded, such as the fault judgment error rate: 20%; efficiency parameters, which indicate changes in the efficiency of students completing tasks, such as a decrease in average operation time: 30%; comprehensive evaluation parameters, such as a learning progress index: 0.85; finally, based on the learning effect feedback parameters, multiple training plans are selected to determine the most suitable content for subsequent review. Specifically, training plans containing relevant content are given priority based on the students' weak links, and the content of the training plans is matched through feedback parameters to eliminate repetitive content that is less meaningful to students, and training plans targeting students' weak links are retained first. For example, if the student's "fault judgment error rate" is high, a training plan containing alarm processing training is given priority; if the student performs poorly in the "multi-device linkage control" task, a plan for related complex scenarios is selected; and a recommended review list is generated to help students efficiently consolidate what they have learned. The recommended review list contains detailed information for each review task.

[0028] The thermal engineering training information set acquisition module 50 is used to perform thermal engineering application training according to the recommended review list, obtain a thermal engineering training information set, and perform operation optimization verification of the power plant according to the thermal engineering training information set.

[0029] Preferably, the generated recommended review list is used to organize trainees to conduct further practical operation and application training, and the key data of the training process (i.e., the thermal engineering training information set) is systematically and comprehensively recorded. This information is then fed back to the power plant operation system, and simulation or actual testing is used to verify whether the training results can effectively improve the operation efficiency and safety of the power plant. Specifically, according to the task content in the recommended review list, a scenario close to the actual operation of the power plant is set, and special operation training is arranged for the skills that trainees performed relatively weakly in the previous assessment (such as multi-device linkage control, alarm processing, etc.). The key data such as operation data and parameter information during the training process are recorded in real time to form a thermal engineering training information set, including trainee performance, equipment parameter response, and task completion effect, such as trainees' operation records, parameter adjustment values, alarm response time, fault handling steps, etc. during training, as well as behavioral analysis in completing tasks. data, types of operating errors, frequency of misoperations, etc.; finally, use the data in the thermal engineering training information set to simulate or verify the operating strategy of the power plant in actual operation to confirm the applicability and effectiveness of the training results in the actual environment, including importing the data of the thermal engineering training information set into the simulation system, virtually simulating the operating scenarios of the power plant, and using the best operating data of the trainees in the training to test whether the operating efficiency of key equipment such as boilers, turbines, and condensers can be effectively optimized; apply the parameter adjustment strategies used by trainees in training to actual equipment and observe their effects. In real alarm situations, use the best response process in training to test the efficiency and effectiveness of problem solving, and verify the actual effects of the multi-equipment collaborative control strategies in training, such as the accuracy of boiler and turbine load matching, thereby realizing a closed loop from training to actual production optimization, so that trainees’ skills improvement and power plant operating efficiency improvement can be carried out simultaneously.

[0030] A comprehensive training system for thermal DCS of a power plant according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as the difficulty in truly simulating the complex operation scenarios of thermal DCS (distributed control system) of a power plant, the lack of personalized training paths for different user needs and skill levels, resulting in insufficient training pertinence, incomplete learning evaluation, and poor efficiency of skill improvement, thereby achieving the technical effect of enhancing training effects and improving skill improvement efficiency. A comprehensive training system for thermal DCS of a power plant includes: a training demand information determination module 10, a DCS training environment parameter construction module 20, a user test data acquisition module 30, a recommended review list generation module 40, and a thermal training information set acquisition module 50.

[0031] The specific configuration of the DCS training environment parameter building module 20 will be described in detail below. Figure 2As shown, the execution steps of the DCS training environment parameter construction module 20 include: performing user state analysis based on the training demand information in combination with the user end to construct a user state space; performing learning action analysis based on the training demand information in combination with the teaching end to construct a teaching action space; introducing a reward function, performing learning dynamic analysis on the user state space and the teaching action space, and generating multiple learning paths; performing cluster analysis on the multiple learning paths according to the training demand information, dividing the multiple learning paths according to the clustering results, and obtaining a theoretical priority path, a practical priority path, and a comprehensive path; performing path dynamic optimization based on the theoretical priority path, the practical priority path, and the comprehensive path to obtain a learning optimization path, and defining the DCS training environment parameters according to the learning optimization path.

[0032] Preferably, user state analysis is performed on the user side according to the training demand information, that is, the current ability level and learning behavior of the trainees during the training process are analyzed, including the knowledge mastery, operation skills, learning efficiency, etc., and a user state space is constructed, including all possible user states of the user during the learning process, such as the trainees' current knowledge level, skill score, learning progress, operation accuracy, etc.; learning action analysis is performed on the teaching side according to the training demand information, including course push, task arrangement, knowledge point explanation, simulated operation, etc., and a teaching action space is constructed, including all possible teaching actions, such as selecting learning modules, adjusting the course sequence, etc.; a reward function is introduced, and the user state space and the teaching action space are subjected to learning dynamic analysis, that is, the reinforcement learning method and the reward function are used to dynamically analyze and evaluate the impact of teaching actions on the user state, and generate multiple learning paths for trainees in different states.

[0033] Preferably, cluster analysis is performed on multiple learning paths according to the training demand information, that is, according to the characteristics of the learning paths, they are divided into different categories, such as theory-oriented paths (focusing on the imparting of theoretical knowledge, suitable for novice students), practice-oriented paths (focusing on the improvement of practical skills), and comprehensive paths (equal emphasis on theory and practice). Cluster analysis results in theory-first paths (suitable for gradually accumulating knowledge in theoretical learning and then entering the practical stage), practice-first paths (suitable for quickly entering operational practice, with theoretical learning as an auxiliary), and comprehensive paths (theory and practice are carried out alternately to improve the comprehensive ability of students in a balanced manner); then the learning paths are dynamically Optimization means adjusting the path content according to the real-time performance of the trainees (such as completion time and changes in error rate). The learning optimization path generated by dynamic optimization is the optimal learning path designed according to the personalized needs of the trainees. Each path balances the theoretical and practical content according to the characteristics of the trainees to ensure the maximum learning effect. Finally, the training environment parameters are set according to the needs of the optimization path. For example, the parameter range (such as pressure, temperature, flow, etc.) is set according to the equipment operation involved in the path, and more complex equipment dynamic responses are built for the practical priority path to simulate real operation scenarios, thereby improving the pertinence and efficiency of training, while ensuring that the training content is close to the actual application scenarios.

[0034] The specific configuration of the DCS training environment parameter construction module 20 will be described in detail below. The execution steps of the DCS training environment parameter construction module 20 include: performing DCS theoretical analysis based on the theoretical priority path to generate DCS knowledge information to be supplemented; performing practical analysis based on the practical priority path to generate practical training information; performing teaching analysis based on the comprehensive path to generate teaching balance information; determining DCS theoretical parameters based on the DCS knowledge information to be supplemented in combination with the theoretical priority path; determining practical configuration parameters based on the practical training information to be combined with the practical priority path; determining teaching scenario information based on the teaching balance information in combination with the comprehensive path; associating and integrating the DCS theoretical parameters, the practical configuration parameters, and the teaching scenario information to configure the DCS training environment parameters.

[0035] Preferably, a DCS theoretical analysis is performed according to a theory-first path, including analysis of the basic working principles of thermal equipment (such as boilers, steam turbines, etc.), the control structure of the DCS system, parameter setting methods, monitoring interface analysis, and theoretical analysis of common faults, to generate a list of knowledge points that need to be supplemented, i.e., DCS knowledge information to be supplemented, such as the signal transmission principle between DCS modules, the theoretical basis for parameter adjustment, the energy flow characteristics of the thermal system, etc., and then a practical analysis is performed according to a practical-first path, i.e., analyzing the performance of trainees in the operation tasks (such as parameter adjustment errors, alarm processing errors), evaluating the trainees' reaction speed and operation accuracy in dynamic scenarios, and generating operation tasks that need to be focused on training, i.e., information to be practically trained, such as precise control of boiler feed water flow regulation, the operation sequence of multi-device linkage adjustment after alarm triggering, and parameter optimization under high load conditions; a teaching analysis is performed according to a comprehensive path, i.e., evaluating the trainees' mastery of theory and practice, and generating teaching suggestions for balancing theory and practice as teaching balance information, such as adding practical case analysis to the theoretical module and supplementing theoretical background knowledge in practical tasks.

[0036] Preferably, according to the content in the theory-first path, the knowledge points to be supplemented are converted into specific DCS theoretical parameters, including the theoretical parameter set of thermal equipment, the default setting value of DCS control logic, etc., such as the pressure range, temperature range, flow standard value, alarm triggering critical value and adjustment parameters (such as PID parameters) in the control logic of thermal equipment; according to the task requirements in the practical-first path, the operation tasks to be trained are converted into specific practical configuration parameters, including the input parameters of dynamic training scenarios, the target range of practical tasks, the response delay and dynamic characteristics of simulated equipment, such as equipment operating parameters under high load conditions (such as boiler load rate, steam flow), the multi-device linkage response sequence under alarm conditions and environmental parameters in dynamic scenarios (such as external temperature, load fluctuation frequency); according to the teaching balance information combined with the comprehensive path refers to according to In view of the need for a balance between theory and practice in the comprehensive path, teaching scenarios are designed, including dynamic configuration of mixed scenarios (such as the alternating order of theory and practice), scenario prompts supported by theory, and theoretical knowledge supplementation of practical background. For example, some scenarios of practical exercises are embedded in theoretical teaching (such as theoretical explanation of boiler overpressure combined with simulation processing), and theoretical prompts are added to practical tasks (such as providing background knowledge of control logic in alarm processing tasks); finally, theoretical parameters, practical parameters, and teaching scenario information are integrated into a complete DCS training environment parameter set through correlation analysis, including basic parameters, such as the default operating parameter range of equipment, dynamic configuration, such as equipment linkage response rules after alarm triggering, and learning rhythm, such as the alternating time between theory and practice, and the priority of key tasks, while achieving an organic combination of theory and practice to ensure the pertinence and practicality of the training content.

[0037] The specific configuration of the user test data acquisition module 30 will be described in detail below. The execution steps of the user test data acquisition module 30 include: using a classification algorithm to classify the user test data to obtain a theoretical blind spot data class and an operational error data class; according to the theoretical blind spot data class combined with the teaching end, the user end is theoretically strengthened to generate a theoretical training plan; according to the operational error data class combined with the teaching end, the user end is practically strengthened to generate a practical training plan; based on the theoretical training plan and the practical training plan combined with the DCS training environment parameters, a conditional probability table is constructed; according to the conditional probability table, the theoretical training plan and the practical training plan are traversed respectively to perform fault diagnosis, and the theoretical training fault probability and the practical training fault probability are determined; the theoretical training fault probability and the practical training fault probability are added to the multiple training results.

[0038] Preferably, a classification algorithm (such as decision tree, support vector machine, KNN) is used to process the data, and the user test data is divided into a theoretical blind spot data class and an operational error data class, wherein the theoretical blind spot data class represents the user's weaknesses in theoretical knowledge, such as insufficient understanding of certain control logics (such as PID adjustment principles), and the operational error data class represents the user's typical problems in actual operation, such as the wrong order of parameter adjustment; special training is designed for the knowledge points involved in the theoretical blind spot data class, such as re-explaining certain thermal engineering principles, and generating a theoretical training plan, including supplementary teaching modules for blind spots (such as "alarm logic enhancement"); special operational training is designed for the problems involved in the operational error data class, such as simulating alarm processing under specific working conditions, generating a practical training plan, including special training tasks for errors, and adding dynamic simulation scenarios (such as fault recovery tasks for multi-device linkage).

[0039] Preferably, a conditional probability table is constructed according to the theoretical training plan and the practical training plan in combination with the DCS training environment parameters to describe the probability of failure in different theoretical and practical tasks, specifically including variables, tasks in the theoretical training plan and the practical training plan and their associated parameters, conditional relationships, the failure probability of a certain task depends on the user's mastery of the knowledge points or operations, and the conditional probability of successful or failed task completion is calculated based on historical data and user performance recorded during the training process; all training tasks are traversed, possible failure points and their occurrence probabilities are analyzed, and the failure probability of each task is evaluated using the conditional probability table. For example, if multiple blind spot knowledge points of the theoretical task are associated, then the total failure probability is the combination of each independent probabilities. If multiple misoperations of the practical task may cause equipment abnormalities, then the cumulative impact of these misoperations is analyzed to determine the failure probability of theoretical training (the probability of error in a specific theoretical task) and the failure probability of practical training (the probability of failure of a specific operation task); the failure probability is used as a key indicator and added to the training results, thereby improving the learning efficiency and training effect of the trainees, while reducing the potential failure risk in actual operation.

[0040] The specific configuration of the recommended review list generation module 40 will be described in detail below. The execution steps of the recommended review list generation module 40 include: conducting a thermal engineering learning evaluation on the theoretical training plan based on the probability of occurrence of the theoretical training failure, and constructing a theoretical learning curve; conducting a thermal engineering learning evaluation on the practical training plan based on the probability of occurrence of the practical training failure, and constructing a practical learning curve; conducting a multi-stage evaluation based on the theoretical learning curve, and generating a plurality of theoretical mastery scores; conducting a multi-stage evaluation based on the practical learning curve, and generating a plurality of practical proficiency scores; conducting a learning progress analysis on the plurality of theoretical mastery scores and the plurality of practical proficiency scores, and generating a multi-stage learning effect; and serializing the multi-stage learning effect according to the learning sequence to generate the learning effect feedback parameter.

[0041] Preferably, a thermal engineering learning evaluation is performed based on the probability of failure occurrence in theoretical training, that is, the learning effect of trainees in theoretical training is analyzed, especially the degree of mastery of fault-related knowledge points, such as quantifying the performance of trainees in different tasks, using function fitting methods (such as polynomial fitting) to generate a learning curve, which shows the changes in the degree of mastery of knowledge points by trainees over time, and constructing a theoretical learning curve to show the changing trend of trainees' knowledge mastery in theoretical training, where the horizontal axis is learning time or learning stage, and the vertical axis is knowledge mastery (such as task completion rate, accuracy rate); a thermal engineering learning evaluation is performed on the practical training plan based on the probability of failure occurrence in practical training, that is, the skill improvement effect of trainees in practical training is analyzed, especially the proficiency in actual operation tasks, such as quantifying the skill improvement based on the performance of trainees in different operation tasks, using function fitting methods to generate a learning curve to show the changes in trainees' skill proficiency over time, and constructing a practical learning curve to show the changing trend of trainees' proficiency in practical training, where the horizontal axis represents learning time or operation stage, and the vertical axis represents skill proficiency (such as task success rate, completion efficiency).

[0042] Preferably, multi-stage evaluation based on the theoretical learning curve means dividing the theoretical learning process into multiple stages (such as the initial, middle and late stages), evaluating the learning effect of each stage respectively, and generating multiple theoretical mastery scores, that is, generating a score for each stage, indicating the degree of mastery of the knowledge points by the students at that stage, and intuitively quantifying the extent of the students' progress in theoretical learning; multi-stage evaluation based on the practical learning curve means dividing the practical learning curve into multiple stages, evaluating the proficiency of practical skills in each stage, generating multiple practical proficiency scores, and intuitively showing the improvement of students in practical skills; combining the theoretical mastery score and the practical proficiency score, calculating the overall learning progress of the students through difference analysis and trend analysis, generating the learning effect of the students at each stage, and then serializing the multi-stage learning effect according to the learning time sequence, that is, organizing the multi-stage learning effect into serialized data according to the time sequence, and generating learning effect feedback parameters, including theoretical improvement range parameters (student theoretical knowledge growth rate), practical improvement range parameters (student practical skills growth rate) and comprehensive progress parameters (theoretical and practical balance growth index), which are used to dynamically optimize subsequent learning paths and training plans and improve the overall training effect.

[0043] The specific configuration of the recommended review list generation module 40 will be described in detail below. The execution steps of the recommended review list generation module 40 include: fitting the theoretical learning curve and the practical learning curve according to the learning time sequence using the learning effect feedback parameters to generate a learning fitting curve; performing forgetting evaluation based on the learning fitting curve to obtain a learning forgetting rate; screening and identifying the theoretical training plan according to the learning forgetting rate combined with the multiple theoretical mastery scores to generate multiple theoretical review modules; screening and identifying the practical training plan according to the learning forgetting rate combined with the multiple practical proficiency scores to generate multiple practical review modules; formulating a review priority rule based on the learning forgetting rate, and processing the multiple theoretical review modules and the multiple practical review modules in descending order according to the review priority rule to generate a theoretical review sequence and a practical review sequence; performing adaptability analysis on the theoretical review sequence and the practical review sequence to obtain a learning adaptability coefficient, and integrating the theoretical review sequence and the practical review sequence based on the learning adaptability coefficient to generate the recommended review list.

[0044] Preferably, the learning effect feedback parameters are used to fit the theoretical learning curve and the practical learning curve according to the learning sequence, that is, a curve fitting method (such as polynomial fitting, nonlinear regression, etc.) is used to generate a learning fitting curve to comprehensively reflect the overall learning progress and learning trend of the trainees, and a forgetting assessment is performed based on the learning fitting curve, that is, the trainees' knowledge or skill forgetting speed is assessed according to the trend of the learning fitting curve, including the time point when the knowledge point or skill mastery level declines most significantly, and the learning forgetting rate is output to guide the formulation of the review plan; according to the learning forgetting rate, the knowledge points that are forgotten faster are marked as review priorities, for example, the content corresponding to the theoretical mastery score below a certain threshold (such as 70%) is marked first, and each theoretical review module contains specific knowledge points, review content and adapted learning resources; according to the learning forgetting rate, the operation tasks with faster skill forgetting are marked as review priorities, and the tasks corresponding to the practical proficiency score below a certain threshold (such as 65%) are marked first, and each practical review module contains specific operation tasks, training content and dynamic scenes to improve the trainees' practical skills.

[0045] Preferably, the review modules are sorted according to the learning forgetting rate, and the modules with faster forgetting rate have higher priority. The theoretical and practical modules are respectively arranged in descending order according to their importance and forgetting rate to obtain a theoretical review sequence (a list of theoretical review modules arranged according to priority) and a practical review sequence (a list of practical review modules arranged according to priority). The adaptability of the theoretical review sequence and the practical review sequence is analyzed to evaluate the students' adaptability to the theoretical review modules and the practical review modules, and the learning adaptability coefficient is obtained to reflect the students' balance ability in theoretical and practical review; finally, the theoretical review sequence and the practical review sequence are integrated according to the learning adaptability coefficient. Specifically, the arrangement order of the theoretical review sequence and the practical review sequence is adjusted according to the learning adaptability coefficient. If the theoretical adaptability is stronger, the theoretical module is given priority. If the practical adaptability is stronger, the practical module is given priority. Then a recommended review list is generated, which includes a comprehensive review plan for the theoretical review modules and the practical review modules, thereby maximizing the review efficiency and learning effect.

[0046] The specific configuration of the recommended review list generation module 40 will be described in detail below. The execution steps of the recommended review list generation module 40 include: reviewing and selecting the plurality of theoretical review modules according to the theoretical review sequence, conducting thermal engineering application training according to the first review content, and generating thermal engineering theory review data; reviewing and selecting the plurality of practical review modules according to the practical review sequence, conducting thermal engineering application training according to the second review content, and generating thermal engineering practical review data; conducting training monitoring based on the thermal engineering theory review data to obtain thermal engineering theory training information; conducting training monitoring based on the thermal engineering practical review data to obtain thermal engineering practical training information; synchronizing the thermal engineering theory training information and the thermal engineering practical training information to the DCS comprehensive training system for comprehensive evaluation to obtain a thermal engineering DCS comprehensive training score; and adding the thermal engineering DCS comprehensive training score to the thermal engineering training information set.

[0047] Preferably, reviewing and selecting multiple theoretical review modules according to the theoretical review sequence means selecting the modules to be reviewed based on the priority in the theoretical review sequence, and then conducting applied training on the selected theoretical review modules according to the first review content, so that trainees can understand the practical application of the theory through the explanation of knowledge points combined with simulated application scenarios. For example, by simulating the triggering and release of DCS alarms, theoretical knowledge can be verified and thermal engineering theory review data can be generated, including trainees' mastery of knowledge points (such as test accuracy), trainees' answering speed, accuracy, error types, etc. during the training process, and theoretical training results. The training effect improvement data (such as the degree of improvement in the mastery rate) is collected; multiple practical review modules are selected for review according to the practical review sequence, that is, based on the priority in the practical review sequence, the modules that need to be reviewed are selected, and thermal application training is carried out for the selected practical review modules according to the second review content. The trainees' operational capabilities are strengthened through dynamic simulation scenarios. For example, the operating conditions of increased boiler pressure are simulated in a virtual scenario to guide trainees to complete correct operations and generate thermal engineering practical review data, including the trainees' success rate in operational tasks, response time, and error types in simulation tasks (such as incorrect parameter adjustment sequence), etc.

[0048] Preferably, training monitoring based on thermal engineering theory review data refers to real-time monitoring of trainees' performance during the theoretical review training process, recording trainees' mastery of knowledge points as thermal engineering theory training information, such as knowledge point coverage (the scope of knowledge points reviewed by trainees and the degree of mastery), theoretical test accuracy (the accuracy of trainees' answers after review) and theoretical training efficiency (completion time and degree of improvement of review content); similarly, training monitoring based on thermal engineering practical review data refers to real-time monitoring of trainees' performance during the practical review training process, recording trainees' completion of operating tasks, and obtaining thermal engineering practical training information; synchronizing thermal engineering theory training information and thermal engineering practical training information to the DCS comprehensive training system, integrating theoretical training information and practical training information, and uniformly evaluating trainees' comprehensive capabilities, such as weighted calculation of theoretical scores and practical scores, obtaining thermal engineering DCS comprehensive training scores, and then adding them to the thermal engineering training information set, which includes complete data on trainee training in the DCS comprehensive training system.

[0049] The specific configuration of the thermal engineering training information set acquisition module 50 will be described in detail below. The execution steps of the thermal engineering training information set acquisition module 50 include: mapping the thermal engineering theory training information to the DCS comprehensive training system according to the knowledge dimension for storage, performing data verification on the first storage result, and generating a theoretical data verification result; mapping the thermal engineering practical training information to the DCS comprehensive training system according to the skill dimension for storage, performing data verification on the second storage result, and generating a practical data verification result; calculating the thermal engineering theory training information based on the theoretical data verification result to obtain a thermal engineering theory score; calculating the thermal engineering practical training information based on the practical data verification result to obtain a thermal engineering practical score; normalizing the thermal engineering theory score and the thermal engineering practical score to generate the thermal engineering DCS comprehensive training score.

[0050] Preferably, the thermal engineering theory training information is decomposed into specific knowledge point dimensions, and each piece of theoretical training data is stored in correspondence with a knowledge point label. For example, a trainee's accuracy rate on "DCS alarm trigger mechanism" is 85%, which is mapped to the corresponding knowledge point storage module, and the knowledge point label corresponds to the training data (accuracy, completion time, error type, etc.). The first storage result is data verified, including verifying the correctness and consistency of the data to avoid scoring deviation due to input errors, and generating a theoretical data verification result, which is output as a Boolean value (pass / fail) to point out problems in storage; similarly, the thermal engineering practical training information is decomposed into specific skill dimensions, and each piece of practical training data is stored in correspondence with a skill label, and then the second storage result is data verified, including verifying the consistency and completeness of the data to ensure the correct storage of task data, and generating a practical data verification result, which is output as a Boolean value (pass / fail) to point out problems in storage.

[0051] Preferably, the thermal engineering theory training information is calculated based on the theoretical data verification results, that is, the trainee's theoretical score is calculated according to the training information of each knowledge point (such as accuracy, error rate, completion time), and the thermal engineering theory score is obtained; the thermal engineering practical training information is calculated based on the practical data verification results, that is, the trainee's practical score is calculated according to the training information of each skill dimension (such as success rate, response time, error rate), and the thermal engineering practical score is obtained; the thermal engineering theory score and the thermal engineering practical score are normalized, and the theoretical score and the practical score are normalized to the same scale range (for example, 0~00), and the normalized theoretical score and practical score are weighted to calculate the comprehensive score to generate the thermal engineering DCS comprehensive training score, which is used to comprehensively evaluate the training effect of the trainees.

[0052] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0053] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A comprehensive training system for thermal DCS of a power plant, characterized in that: The system comprises: The training demand information determination module is used to conduct technical analysis of thermal engineering of power plants based on the DCS comprehensive training system and determine training demand information; A DCS training environment parameter construction module, used to perform reinforcement learning according to the training demand information, determine multiple learning paths, and construct DCS training environment parameters; A user test data acquisition module is used to perform a test according to the DCS training environment parameters through the user terminal to obtain user test data, formulate multiple training plans based on the user test data for training, and determine multiple training results; A recommended review list generating module, used for performing thermal engineering learning evaluation according to the plurality of training results, generating learning effect feedback parameters, screening the plurality of training plans according to the learning effect feedback parameters, and generating a recommended review list; The thermal engineering training information set acquisition module is used to perform thermal engineering application training according to the recommended review list, obtain the thermal engineering training information set, and perform operation optimization verification of the power plant according to the thermal engineering training information set.

2. A power plant thermal DCS comprehensive training system as claimed in claim 1, characterized in that: Reinforce learning is performed according to the training demand information, multiple learning paths are determined, and DCS training environment parameters are constructed. The system includes: Based on the training demand information and in combination with the user end, a user state analysis is performed to construct a user state space; Based on the training demand information and combined with the teaching end, the learning action analysis is performed to construct a teaching action space; Introducing a reward function, performing a learning dynamic analysis on the user state space and the teaching action space, and generating multiple learning paths; Performing cluster analysis on the multiple learning paths according to the training demand information, and dividing the multiple learning paths according to the clustering results to obtain a theory priority path, a practical operation priority path, and a comprehensive path; Based on the theory priority path, the practical operation priority path and the comprehensive path, path dynamic optimization is performed to obtain a learning optimization path, and the DCS training environment parameters are defined according to the learning optimization path.

3. A power plant thermal DCS comprehensive training system as claimed in claim 2, characterized in that: Based on the theory priority path, the practice priority path, and the comprehensive path, the path is dynamically optimized to obtain a learning optimization path, and the DCS training environment parameters are defined according to the learning optimization path. The system includes: Perform DCS theoretical analysis based on the theoretical priority path to generate DCS knowledge information to be supplemented; Performing a practical analysis based on the practical priority path to generate training information to be practiced; Conducting teaching analysis based on the comprehensive path to generate teaching balance information; Determine DCS theoretical parameters according to the DCS knowledge information to be supplemented and the theoretical priority path; Determine the practical operation configuration parameters according to the to-be-practiced training information and the practical operation priority path; Determine teaching scenario information according to the teaching balance information combined with the comprehensive path; The DCS theoretical parameters, the practical configuration parameters, and the teaching scenario information are associated and integrated to configure the DCS training environment parameters.

4. A power plant thermal DCS comprehensive training system as claimed in claim 1, characterized in that: Formulate the plurality of training plans based on the user test data to perform training and determine a plurality of training results, the system comprising: Using a classification algorithm to classify the user test data to obtain a theoretical blind spot data class and an operational error data class; According to the theoretical blind spot data category, the user end is theoretically strengthened in combination with the teaching end to generate a theoretical training plan; According to the operation error data category and the teaching end, the user end is strengthened in practical operation, and a practical training plan is generated; Constructing a conditional probability table based on the theoretical training plan, the practical training plan and the DCS training environment parameters; According to the conditional probability table, the theoretical training plan and the practical training plan are traversed to perform fault diagnosis, and the probability of occurrence of theoretical training faults and the probability of occurrence of practical training faults are determined; The theoretical training failure occurrence probability and the practical training failure occurrence probability are added to the multiple training results.

5. A power plant thermal DCS comprehensive training system as claimed in claim 4, characterized in that: The system performs thermal engineering learning evaluation according to the plurality of training results and generates learning effect feedback parameters, and includes: Conducting a thermal engineering learning evaluation on the theoretical training plan based on the probability of occurrence of the theoretical training failure, and constructing a theoretical learning curve; Performing a thermal engineering learning evaluation on the practical training plan based on the probability of occurrence of the practical training failure, and constructing a practical learning curve; Perform a multi-stage assessment based on the theoretical learning curve to generate multiple theoretical mastery scores; Perform a multi-stage assessment based on the practical learning curve to generate multiple practical proficiency scores; The multiple theoretical mastery scores and the multiple practical proficiency scores are subjected to a learning progress analysis to generate a multi-stage learning effect, and the multi-stage learning effect is serialized according to a learning sequence to generate the learning effect feedback parameter.

6. A power plant thermal DCS comprehensive training system as claimed in claim 5, characterized in that: The plurality of training plans are screened according to the learning effect feedback parameters to generate a recommended review list, the system comprising: Fitting the theoretical learning curve with the practical learning curve according to the learning time sequence using the learning effect feedback parameter to generate a learning fitting curve; Perform forgetting assessment based on the learning fitting curve to obtain a learning forgetting rate; The theoretical training plan is screened and marked according to the learning forgetting rate and the plurality of theoretical mastery scores, and a plurality of theoretical review modules are generated; The practical training plan is screened and marked according to the learning forgetting rate and the multiple practical proficiency scores to generate multiple practical review modules; Formulate a review priority rule based on the learning forgetting rate, and process the multiple theoretical review modules and the multiple practical review modules in descending order according to the review priority rule to generate a theoretical review sequence and a practical review sequence; The adaptability of the theoretical review sequence and the practical review sequence is analyzed to obtain a learning adaptability coefficient, and the theoretical review sequence and the practical review sequence are integrated based on the learning adaptability coefficient to generate the recommended review list.

7. A power plant thermal DCS comprehensive training system as claimed in claim 6, characterized in that: Conduct thermal application training according to the recommended review list to obtain a thermal training information set, the system includes: Review and select the plurality of theoretical review modules according to the theoretical review sequence, conduct thermal engineering application training according to the first review content, and generate thermal engineering theory review data; Review and select the plurality of practical review modules according to the practical review sequence, conduct thermal engineering application training according to the second review content, and generate thermal engineering practical review data; Perform training monitoring based on the thermal engineering theory review data to obtain thermal engineering theory training information; Perform training monitoring based on the thermal engineering practice review data to obtain thermal engineering practice training information; Synchronize the thermal engineering theory training information and the thermal engineering practical training information to the DCS comprehensive training system for comprehensive evaluation to obtain a thermal engineering DCS comprehensive training score; The thermal engineering DCS comprehensive training score is added to the thermal engineering training information set.

8. A power plant thermal DCS comprehensive training system as claimed in claim 7, characterized in that: The thermal engineering theory training information and the thermal engineering practical training information are synchronized to the DCS comprehensive training system for comprehensive evaluation to obtain the thermal engineering DCS comprehensive training score. The system includes: Mapping the thermal engineering theory training information to the DCS comprehensive training system according to the knowledge dimension for storage, performing data verification on the first storage result, and generating a theoretical data verification result; Mapping the thermal engineering practical training information to the DCS comprehensive training system according to the skill dimension for storage, performing data verification on the second storage result, and generating a practical data verification result; Calculating the thermal engineering theory training information based on the theoretical data verification result to obtain a thermal engineering theory score; Calculating the thermal engineering practical training information based on the practical operation data verification result to obtain a thermal engineering practical operation score; The thermal engineering theory score and the thermal engineering practical operation score are normalized to generate the thermal engineering DCS comprehensive training score.

Images