Method and system for constructing hydropower station simulation training system based on multi-source collaboration

Abstract

This invention provides a method and system for constructing a hydropower station simulation training system based on multi-source collaboration, belonging to the field of hydropower station training technology. First, it integrates core multi-source training resources of hydropower stations to form a multi-source training core resource pool, covering core resources for equipment operation, work processes, and scenario responses. Next, it constructs a dynamic collaborative architecture for each resource within the multi-source training core resource pool and builds multi-directional interactive links based on this dynamic collaborative architecture to achieve real-time data interaction and scenario and behavior linkage. Based on the dynamic collaborative architecture and multi-directional interactive links, it generates an adaptive simulation training scenario that integrates the collaborative content of the multi-source training core resources. Finally, it collects feedback optimization data and iteratively adjusts the architecture parameters and link rules to form a closed loop. This invention improves the comprehensiveness, collaboration, and personalization of hydropower station training.

Description

Technical Field

[0001] This invention relates to the field of hydropower station training technology, and more specifically, to a method and system for constructing a hydropower station simulation training system based on multi-source collaboration. Background Technology

[0002] In the field of hydropower station training, traditional training methods often have many limitations. On the one hand, existing hydropower station training often relies on single resources, such as equipment operation manuals, simple video tutorials, or on-site explanations. The training content covered by these methods is relatively one-sided, and key training elements such as core knowledge of equipment operation, standardized operating procedures, and response strategies in different scenarios are difficult to integrate comprehensively and organically. As a result, trainees cannot form a complete understanding of the overall operation and management of hydropower stations.

[0003] On the other hand, traditional training lacks effective collaboration mechanisms and interactive feedback. During the training process, various training resources operate independently, failing to achieve real-time data interaction and coordinated scheduling. This results in a significant lag between the presentation of the training scenario and the behavioral feedback of trainees, making it impossible to adjust the training content and difficulty in a timely manner based on trainees' actions and feedback. Furthermore, training systems are often static, unable to be dynamically optimized and adjusted based on actual training results. This makes it difficult to meet the needs of different trainees and adapt to the constantly changing operating environment and training requirements of hydropower stations, thus affecting the quality and effectiveness of training. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, the present invention provides a method for constructing a multi-source collaborative hydropower station simulation training system, the method comprising:

[0005] Integrate the core resources of multi-source training for hydropower stations to form a multi-source training core resource pool, which includes core resources for equipment operation, core resources for work processes, and core resources for scenario response.

[0006] A dynamic collaborative architecture is constructed for each resource within the multi-source training core resource pool. This dynamic collaborative architecture carries the real-time data interaction and associated scheduling between the resources.

[0007] A multi-directional interaction link is constructed based on the dynamic collaborative architecture, which enables real-time linkage between the presentation of the simulation training scenario and the feedback of training behavior.

[0008] Based on the aforementioned dynamic collaborative architecture and multi-directional interaction links, an adaptive simulation training scenario is generated that integrates collaborative content from multiple sources of core training resources.

[0009] The system collects feedback optimization data during the operation of the adaptive simulation training scenario, iteratively adjusts the scheduling parameters of the dynamic collaborative architecture and the linkage rules of the multi-directional interaction links, and forms a multi-source collaborative simulation training closed loop.

[0010] Furthermore, this invention also provides a system for constructing a multi-source collaborative hydropower station simulation training system, comprising:

[0011] A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described method for constructing a multi-source collaborative hydropower station simulation training system by executing the machine-executable instructions.

[0012] In another aspect, the present invention also provides a computer program product, the computer program product including machine-executable instructions, the machine-executable instructions being stored in a computer-readable storage medium, the processor of the multi-source collaborative hydropower station simulation training system construction system reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the multi-source collaborative hydropower station simulation training system construction system to execute the above-described multi-source collaborative hydropower station simulation training system construction method.

[0013] Based on the above, a multi-source training core resource pool is formed by integrating core resources from multiple sources in hydropower stations. This pool aggregates core resources related to equipment operation, work processes, and scenario responses. A dynamic collaborative architecture is then constructed to facilitate real-time data interaction and scheduling among these resources. Furthermore, a multi-directional interactive link is built to achieve real-time linkage between simulated training scenario presentation and training behavior feedback. Trainees can adjust the training scenario and content promptly based on their real-time operations and behaviors, achieving a close integration of training scenarios and training behaviors, thus improving the relevance and effectiveness of training. Adaptive simulated training scenarios, which integrate collaborative content from multiple sources of training core resources, are generated based on the dynamic collaborative architecture and multi-directional interactive links. These scenarios can automatically adjust the training difficulty and content according to the different levels and needs of trainees, providing a personalized training experience. By collecting feedback and optimizing data, and iteratively adjusting the scheduling parameters of the dynamic collaborative architecture and the linkage rules of the multi-directional interactive links, a closed loop of multi-source collaborative simulation training is formed. This allows the training system to continuously optimize and improve itself, maintaining consistently good training results and effectively enhancing the quality and efficiency of hydropower station training. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the execution flow of the method for constructing a hydropower station simulation training system based on multi-source collaboration provided in an embodiment of the present invention.

[0015] Figure 2This is a schematic diagram of exemplary hardware and software components of the hydropower station simulation training system construction system based on multi-source collaboration provided in an embodiment of the present invention. Detailed Implementation

[0016] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a method for constructing a hydropower station simulation training system based on multi-source collaboration, according to an embodiment of the present invention. The following is a detailed description of this method.

[0017] Step S110: Integrate the core resources of multi-source training for hydropower stations to form a multi-source training core resource pool, which includes core resources for equipment operation, core resources for work processes, and core resources for scenario response.

[0018] This embodiment uses hydropower station turbine generator unit operation and maintenance training as a unified application scenario. The core resources for equipment operation include equipment structural feature information such as the stator winding structure and rotor magnetic pole distribution of the turbine generator unit; equipment operating status information such as the unit's speed, stator voltage, and stator current during operation; equipment operation specifications such as checking lubricating oil pressure before startup and performing braking operations when shutting down; and equipment association and adaptation information such as the control signal interface type between the unit and the governor, and the compatibility with the voltage regulation range of the excitation system.

[0019] The core resources of the operation process include the breakdown information of the operation steps in the start-up process of the hydro-generator unit, such as "checking the lubricating oil system", "engaging the excitation system" and "starting the water guide mechanism", the step connection logic information that the "engaging the excitation system" operation can only be performed after the "checking the lubricating oil system" is completed, the process execution standard information that the "checking the lubricating oil system" must be completed within a specified time and the lubricating oil pressure must reach the specified range, and the process-related constraint information that the grid frequency must be kept stable within the specified range when the start-up process is executed.

[0020] The core resources for scenario response cover trigger condition information for scenarios such as unit overspeed and bearing overtemperature, response actions such as emergency shutdown and parameter adjustment required after triggering, transition logic between scenarios, and information on related equipment such as hydro-generators and governors involved in the scenarios. All of these resources are categorized and stored to form a multi-source training core resource pool.

[0021] Step S120: Construct a dynamic collaborative architecture for each resource in the multi-source training core resource pool. The dynamic collaborative architecture carries the real-time data interaction and associated scheduling between each resource.

[0022] Step S121: Extract the resource attribute information of the core resources for equipment operation in the multi-source training core resource pool. The resource attribute information includes equipment structural feature information, equipment operating status information, equipment operation specification information, and equipment association and adaptation information.

[0023] Resource attribute information is extracted from the core resources of equipment operation. Specific equipment structural characteristics include the stator winding configuration and rotor pole number of the hydro-generator unit; equipment operating status information includes the current unit speed, stator voltage, and stator current; equipment operation specifications include the opening sequence of the water guiding mechanism during startup and braking operation requirements during shutdown; and equipment compatibility information includes the control signal interface type between the hydro-generator unit and the governor, and the compatibility with the voltage regulation range of the excitation system.

[0024] Step S122: Extract the process execution information of the core resources of the work process in the multi-source training core resource pool. The process execution information includes work step decomposition information, step connection logic information, process execution standard information, and process association constraint information.

[0025] Process execution information is extracted from the core resources of the work process. The work step decomposition information specifically includes steps such as "checking the lubrication system," "engaging the excitation system," and "starting the water guide mechanism" in the turbine generator unit start-up process; the step connection logic information specifically states that the "engaging the excitation system" operation can only be performed after the "checking the lubrication system" is completed; the process execution standard information specifically states that the "checking the lubrication system" must be completed within the specified time and the lubrication oil pressure must reach the specified range; the process association constraint information specifically states that the grid frequency must be kept stable within the specified range during the start-up process.

[0026] Step S123: Extract the scene adaptation information of the scene response core resources in the multi-source training core resource pool. The scene adaptation information includes scene triggering condition information, scene response action information, scene conversion logic information, and scene associated device information.

[0027] Scene adaptation information is extracted from the core resources of the scene response. The scene triggering condition information is specifically such as the unit speed exceeding the specified value, the bearing temperature exceeding the specified value, etc.; the scene response action information is specifically such as the need to perform emergency shutdown operation and adjust cooling system parameters after triggering; the scene conversion logic information is specifically such that after the unit overspeed scene is triggered, if the emergency shutdown operation fails, it will be converted to the bearing temperature too high scene; the scene associated equipment information is specifically such as the unit overspeed scene involving equipment such as hydro-generator sets and governors.

[0028] Step S124: Identify the associated nodes by linking the resource attribute information of the core resources for equipment operation with the process execution information of the core resources for the work process. Determine the direct associated nodes between the equipment and the process based on the correspondence between the equipment operation specification information and the work step decomposition information. Determine the indirect associated nodes between the equipment and the process based on the adaptation relationship between the equipment operation status information and the process execution standard information.

[0029] The resource attribute information of the core resources for equipment operation is correlated with the process execution information of the core resources for the work process to identify associated nodes. Based on the correspondence between the "opening sequence of the water guiding mechanism at startup" in the equipment operation specification information and the "opening the water guiding mechanism" step in the work step decomposition information, the direct association nodes between the equipment and the process are determined to be the water guiding mechanism operation node and the water guiding mechanism opening step node. Based on the fit between the "lubricating oil pressure must reach the specified range" in the equipment operation status information and the "checking the lubricating oil system to ensure that the lubricating oil pressure reaches the specified range" in the process execution standard information, the indirect association nodes between the equipment and the process are determined to be the lubricating oil pressure monitoring node and the lubricating oil system check step node.

[0030] Step S125: Identify the associated nodes by linking the process execution information of the core resources of the work process with the scene adaptation information of the core resources of the scene response. Based on the correspondence between the step connection logic information and the scene trigger condition information, determine the direct associated nodes between the process and the scene. Based on the adaptation relationship between the process association constraint information and the scene transformation logic information, determine the indirect associated nodes between the process and the scene.

[0031] The process execution information of the core resources of the work process is associated with the scenario adaptation information of the core resources of the scenario response to identify related nodes. Based on the correspondence between the step connection logic information "'Checking the lubricating oil system' can only be performed after the 'Activation of the excitation system' operation is completed" and the scenario trigger condition information "If 'Checking the lubricating oil system' is not completed, an abnormal scenario is triggered", the direct association nodes between the process and the scenario are determined to be the lubricating oil system check step node and the abnormal scenario trigger node. Based on the adaptation relationship between the process association constraint information "When the startup process is executed, it is necessary to ensure that the power grid frequency is stable within the specified range" and the scenario transition logic information "If the power grid frequency is unstable, the startup process scenario is converted to a power grid abnormal scenario", the indirect association nodes between the process and the scenario are determined to be the power grid frequency monitoring node and the startup process scenario node.

[0032] Step S126: Identify the associated nodes by associating the scene adaptation information of the scene response core resource with the resource attribute information of the device operation core resource. Determine the direct associated nodes between the scene and the device based on the correspondence between the scene response action information and the device operation specification information. Determine the indirect associated nodes between the scene and the device based on the adaptation relationship between the scene-associated device information and the device-associated adaptation information.

[0033] The system identifies associating scenario adaptation information of core scenario response resources with resource attribute information of core equipment operation resources. Based on the correspondence between "triggering emergency shutdown operation" in scenario response action information and "the water guide mechanism must be closed during emergency shutdown" in equipment operation specification information, the direct association nodes between scenarios and equipment are determined to be the emergency shutdown scenario node and the water guide mechanism operation node. Based on the adaptation relationship between "the unit overspeed scenario involves the governor" in scenario-associated equipment information and "the control signal interface type between the governor and the hydro-generator unit" in equipment association adaptation information, the indirect association nodes between scenarios and equipment are determined to be the governor status monitoring node and the unit overspeed scenario node.

[0034] Step S127: Based on all directly associated nodes and indirectly associated nodes, construct a multi-source resource association node network. The multi-source resource association node network includes the connection relationship of each node, the data interaction direction, and the association identifier. The association identifier is set based on the correspondence between the node and the training requirement information.

[0035] Step S1271: Perform node classification and marking operations, classify all directly related nodes and indirectly related nodes, and mark the resource type combination corresponding to each node. The resource type combination includes equipment process combination, process scenario combination, and scenario equipment combination.

[0036] All directly and indirectly related nodes are categorized and labeled. Equipment process combination nodes are labeled as combination nodes of core resources for equipment operation and core resources for work processes, such as the water guiding mechanism operation node and the water guiding mechanism activation step node; process scenario combination nodes are labeled as combination nodes of core resources for work processes and core resources for scenario responses, such as the lubricating oil system inspection step node and the abnormal scenario trigger node; scenario equipment combination nodes are labeled as combination nodes of core resources for scenario responses and core resources for equipment operation, such as the emergency shutdown scenario node and the water guiding mechanism operation node.

[0037] Step S1272: Assign a unique node identifier to the associated nodes of each resource type combination. The node identifier includes the resource type code, node sequence number and association type identifier. The node identifier is used to distinguish and manage each associated node.

[0038] Assign a unique node identifier to the associated nodes for each resource type combination. The resource type code for the equipment process combination node is set to "SF", the node number is arranged sequentially, and the association type identifier is set to "D" for direct association and "J" for indirect association. For example, the node identifier for the water guiding mechanism operation node and the water guiding mechanism start step node is "SF001D". The resource type code for the process scenario combination node is set to "LC", the node number is arranged sequentially, and the association type identifier is set to "D" for direct association and "J" for indirect association. For example, the node identifier for the lubricating oil system check step node and the abnormal scenario trigger node is "LC001D". The resource type code for the scenario equipment combination node is set to "CJ", the node number is arranged sequentially, and the association type identifier is set to "D" for direct association and "J" for indirect association. For example, the node identifier for the emergency stop scenario node and the water guiding mechanism operation node is "CJ001D".

[0039] Step S1273: Based on the resource attribute information, process execution information and scenario adaptation information of each associated node, determine the connection relationship between nodes. The nodes of the device process combination and the nodes of the process scenario combination are connected based on process resources. The nodes of the process scenario combination and the nodes of the scenario device combination are connected based on scenario resources. The nodes of the scenario device combination and the nodes of the device process combination are connected based on device resources.

[0040] The connection relationships between nodes are determined based on the relevant information of each associated node. The "SF001D" node of the equipment process combination and the "LC001D" node of the process scenario combination are connected based on the "start water guiding mechanism" step in the process resources; the "LC001D" node of the process scenario combination and the "CJ001D" node of the scenario equipment combination are connected based on the abnormal scenario in the scenario resources; the "CJ001D" node of the scenario equipment combination and the "SF001D" node of the equipment process combination are connected based on the water guiding mechanism in the equipment resources.

[0041] Step S1274: Based on the logical order of resource interaction, determine the data interaction direction of each connection relationship. The node of the device process combination transmits device status associated data to the node of the process scenario combination, the node of the process scenario combination transmits process execution associated data to the node of the scenario device combination, and the node of the scenario device combination transmits scenario response associated data to the node of the device process combination.

[0042] The direction of data interaction is determined according to the logical order of resource interaction. The “SF001D” node of the equipment process combination transmits the opening status data of the water guiding mechanism to the “LC001D” node of the process scenario combination; the “LC001D” node of the process scenario combination transmits the execution result data of the lubrication system inspection step to the “CJ001D” node of the scenario equipment combination; the “CJ001D” node of the scenario equipment combination transmits the trigger signal data of the emergency stop scenario to the “SF001D” node of the equipment process combination.

[0043] Step S1275: Based on the correspondence between each associated node and the training demand information, set the association identifier for each connection relationship. Configure the first association identifier for the connection relationship directly corresponding to the training focus topic direction information, configure the second association identifier for the connection relationship directly corresponding to the training capability target information, and configure the third association identifier for the connection relationship directly corresponding to the training target characteristic information.

[0044] For example, step S12751: Analyze the training focus theme information in the training needs information and extract the core keywords, which reflect the core content and key areas of the training.

[0045] The training focus and direction information in the training needs information were analyzed, and the core keyword was "hydro turbine generator unit start-up procedure".

[0046] Step S12752: By traversing all the connection relationships in the multi-source resource association node network, identify the correspondence between the resource content and the core keywords corresponding to each connection relationship, and filter out the connection relationships that directly correspond to the resource content and the core keywords.

[0047] By traversing all connections in the multi-source resource association node network, the resource content corresponding to the connection between the "SF001D" node of the equipment process combination and the "LC001D" node of the process scenario combination is identified as the "start water guiding mechanism" step, which directly corresponds to the core keyword "hydro turbine generator set start-up process operation". This connection is then selected.

[0048] Step S12753: Configure a first association identifier for the selected connection relationship. The first association identifier includes the focus topic direction code and the corresponding core keyword identifier. The correspondence between the connection relationship and the training focus topic direction information is determined through the first association identifier.

[0049] Configure the first association identifier for the selected connection relationship, set the focus topic direction code to "T1", the core keyword identifier to "K1", and the first association identifier to "T1K1".

[0050] Step S12754: Analyze the training capability objective information in the training needs information, and extract the capability requirement keywords in the training capability objective information. The capability requirement keywords reflect the capability standards and skill levels that the training needs to achieve.

[0051] The training capability objectives information in the training needs information were analyzed, and the keyword for capability requirements was "accurately execute emergency shutdown operations".

[0052] Step S12755: Traverse all connections in the multi-source resource association node network, identify the correspondence between resource content and capability requirement keywords corresponding to the connection, and filter out the connection relationships that directly correspond to resource content and capability requirement keywords.

[0053] Traverse all connections in the multi-source resource association node network, identify the resource content corresponding to the connection between the "CJ001D" node of the scene device combination and the "SF001D" node of the device process combination as "emergency shutdown operation", which directly corresponds to the capability requirement keyword "accurately execute emergency shutdown operation", and filter out this connection.

[0054] Step S12756: Configure a second association identifier for the selected connection relationship. The second association identifier includes the capability target code and the corresponding capability requirement keyword identifier. The correspondence between the connection relationship and the training capability target information is determined through the second association identifier.

[0055] Configure a second association identifier for the selected connection relationship, set the capability target code to "N1", set the capability requirement keyword identifier to "M1", and set the second association identifier to "N1M1".

[0056] Step S12757: Analyze the training target characteristic information in the training demand information, and extract the target attribute keywords in the training target characteristic information. The target attribute keywords reflect the job type, skill base and learning characteristics of the training target.

[0057] The training needs information was analyzed to extract the training target characteristics, and the target attribute keyword was "operations and maintenance novice".

[0058] Step S12758: Traverse all connections in the multi-source resource association node network, identify the correspondence between resource content and object attribute keywords corresponding to the connection, and filter out the connection relationships that directly correspond to resource content and object attribute keywords.

[0059] Traverse all connections in the multi-source resource association node network, identify the resource content corresponding to the connection of the "SF002J" node (lubricating oil pressure monitoring node and lubricating oil system inspection step node) of the equipment process combination, which is "inspecting the lubricating oil system". This step is suitable for operation and maintenance novices to learn and directly corresponds to the object attribute keyword "operation and maintenance novices". Filter out this connection.

[0060] Step S12759: Configure a third association identifier for the selected connection relationship. The third association identifier includes the object feature code and the corresponding object attribute keyword identifier. The correspondence between the connection relationship and the training object feature information is determined through the third association identifier.

[0061] Configure a third association identifier for the selected connection relationship, set the object feature code to "O1", the object attribute keyword identifier to "P1", and the third association identifier to "O1P1".

[0062] Step S127510: Supplement the identification configuration for the unfiltered connection relationships, and configure the fourth association identifier. The fourth association identifier contains a general association code, which is used to identify the connection relationship that indirectly corresponds to the training requirement information.

[0063] Configure a fourth association identifier for the unfiltered connection relationships, and set the general association code to "U1".

[0064] Step S127511: Establish a mapping index between association identifiers and training demand information. The mapping index includes association identifier codes, corresponding training demand keywords, and connection relationship identifiers. The mapping index enables the querying and matching of association identifiers and training demand information.

[0065] Establish a mapping index between associated identifiers and training requirement information. The index content includes the associated identifier code "T1K1" corresponding to the training requirement keyword "hydro turbine generator start-up procedure" and the connection relationship identifier "SF001D-LC001D", the associated identifier code "N1M1" corresponding to the training requirement keyword "accurate execution of emergency shutdown operation" and the connection relationship identifier "CJ001D-SF001D", the associated identifier code "O1P1" corresponding to the training requirement keyword "maintenance novice" and the connection relationship identifier "SF002J", and the associated identifier code "U1" corresponding to the training requirement keyword "general content" and the connection relationship identifiers that have not been filtered.

[0066] Step S1276: Construct a node connection relationship matrix. The node connection relationship matrix includes node identifiers, corresponding connected node identifiers, data interaction directions, and association identifiers. The matrix presents the association status of each node in a visual way.

[0067] Construct a node connection matrix, which includes the node identifier "SF001D" connected to node identifier "LC001D", the data interaction direction "SF001D→LC001D" and the associated identifier "T1K1"; the node identifier "LC001D" connected to node identifier "CJ001D", the data interaction direction "LC001D→CJ001D" and the associated identifier "U1"; the node identifier "CJ001D" connected to node identifier "SF001D", the data interaction direction "CJ001D→SF001D" and the associated identifier "N1M1"; the node identifier "SF002J" connected to node identifier "LC002J", the data interaction direction "SF002J→LC002J" and the associated identifier "O1P1", etc.

[0068] Step S1277: Based on the node connection relationship matrix, a visual model of the multi-source resource associated node network is generated using a graphical modeling method. The visual model is used to display the location distribution, connection path, data flow direction and association identifier of each node.

[0069] A visual model is generated using a graphical modeling approach based on the node connection matrix. In the visual model, node identifier "SF001D" is located on the left, node identifier "LC001D" in the middle, node identifier "CJ001D" on the right, node identifier "SF002J" in the lower left, and node identifier "LC002J" in the lower center. Nodes are connected by lines, with the direction of data interaction marked on the lines, and association markers next to the nodes.

[0070] Step S1278: Verify the connectivity of the multi-source resource association node network, check for the existence of isolated nodes and broken connections, supplement isolated nodes with associated resources to establish connections, and repair the association logic between nodes in broken connections to keep the multi-source resource association node network in a complete and connected state.

[0071] Verify the connectivity of the multi-source resource association node network. Inspection revealed that node identifier "SF003J" (stator voltage monitoring node) was not connected to other nodes, making it an isolated node. Supplement associated resources by establishing a connection between this node and the "Check Stator Voltage" step node in the core resources of the workflow, repairing broken connections, and ensuring the multi-source resource association node network remains fully connected.

[0072] Step S128: Configure a real-time scheduling protocol for the multi-source resource association node network. The real-time scheduling protocol specifies the format, timing and fault-tolerant processing logic of data interaction between nodes. Based on the real-time scheduling protocol and the multi-source resource association node network, a dynamic collaborative architecture is constructed that runs through the core resources of equipment operation, the core resources of work process and the core resources of scenario response.

[0073] A real-time scheduling protocol is configured for the multi-source resource association node network. The data interaction format is specified as XML, and the timing specification requires that data from the device process combination node must be transmitted before data from the process scenario combination node. The fault tolerance logic specification specifies that if data transmission fails, it should be retransmitted three times; if it still fails, the error information should be recorded and an alarm should be triggered. Based on this real-time scheduling protocol and the multi-source resource association node network, a dynamic collaborative architecture is constructed.

[0074] Step S130: Construct a multi-directional interaction link based on the dynamic collaborative architecture, wherein the multi-directional interaction link realizes real-time linkage between the presentation of the simulation training scenario and the feedback of training behavior.

[0075] Step S131: Analyze the multi-source resource association node network of the dynamic collaborative architecture, extract the output data type, data transmission rate and data interaction requirements of each association node, and determine the data source access requirements of the simulation training scenario presentation module based on the output data type, data transmission rate and data interaction requirements.

[0076] The multi-source resource association node network of the dynamic collaborative architecture is analyzed. The output data types of each association node are extracted as device status data, process execution data, and scenario trigger data. The data transmission rate is a specified number of data transmissions per second, and the data interaction requirements are real-time data transmission with no latency. Based on the above information, the data source access requirements for the simulation training scenario presentation module are determined to be: support for XML format data access, a data transmission rate that meets the specified number of data transmissions per second, and support for real-time data interaction.

[0077] Step S132: Based on the data source access requirements, construct a scene presentation data receiving interface. The scene presentation data receiving interface supports real-time access, parsing, and format conversion of the output data of each associated node in the dynamic collaborative architecture, so that the accessed data is consistent with the processing requirements of the scene presentation module.

[0078] A scene presentation data receiving interface is constructed based on data source access requirements. This interface supports real-time access to output data from various associated nodes in a dynamic collaborative architecture. The accessed data is parsed in XML format and converted into a format supported by the scene presentation module, ensuring that the accessed data is consistent with the processing requirements of the scene presentation module.

[0079] Step S133: Analyze the training behavior types generated during the training process. The training behavior types include equipment operation behavior, process selection behavior, scenario response behavior, and parameter adjustment behavior. For each type of training behavior, determine its data collection dimension, collection frequency, and data storage format.

[0080] Analyze the types of training behaviors generated during the training process. Data collection dimensions for equipment operation behavior include the name of the operated equipment, operation time, and operation result, with collection frequency at each operation and data storage format in JSON format. Data collection dimensions for process selection behavior include the name of the selected process, selection time, and selection result, with collection frequency at each selection and data storage format in JSON format. Data collection dimensions for scenario response behavior include the name of the responded scenario, response time, and response result, with collection frequency at each response and data storage format in JSON format. Data collection dimensions for parameter adjustment behavior include the name of the adjusted parameter, parameter value before adjustment, parameter value after adjustment, and adjustment time, with collection frequency at each adjustment and data storage format in JSON format.

[0081] Step S134: Based on the data collection requirements of training behavior, construct a training behavior data collection interface. The training behavior data collection interface supports real-time capture, classification and storage, and format standardization processing of various types of training behavior data, so that the collected data can be identified and processed by the dynamic collaborative architecture.

[0082] A training behavior data collection interface is constructed based on the data collection requirements of training behavior. This interface supports real-time capture of data on equipment operation behavior, process selection behavior, scenario response behavior, and parameter adjustment behavior. The captured data is categorized and stored according to behavior type, and the stored data is standardized and converted into XML format supported by the dynamic collaborative architecture, enabling the collected data to be recognized and processed by the dynamic collaborative architecture.

[0083] Step S135: Construct a data transfer and processing unit. The data transfer and processing unit establishes connections with the scene presentation data receiving interface and the training behavior data collection interface, respectively, receives resource interaction data transmitted by the scene presentation data receiving interface, and simultaneously receives standardized training behavior data transmitted by the training behavior data collection interface.

[0084] Step S1351: Construct the hardware architecture of the data transfer and processing unit, adopt a multi-core processing component as the data processing core, configure a high-speed cache component for temporary storage of data to be processed, configure dual data input interfaces to connect to the scene presentation data receiving interface and the training behavior data acquisition interface respectively, and configure the data output interface to connect to the dynamic collaborative architecture.

[0085] The hardware architecture of the data transfer and processing unit is constructed, using a multi-core processing component as the core of data processing, configuring a high-speed cache component for temporary storage of data to be processed, configuring dual data input interfaces to connect to the scene presentation data receiving interface and the training behavior data acquisition interface respectively, and configuring a data output interface to connect to the dynamic collaborative architecture.

[0086] Step S1352: Construct the software processing logic of the data transfer processing unit. First, start the data receiving thread and listen to the data transmission status of the scene presentation data receiving interface and the training behavior data collection interface. When a data transmission request is detected, establish a data transmission channel.

[0087] The software processing logic of the data transfer and processing unit is constructed by first starting the data receiving thread, and simultaneously monitoring the data transmission status of the scene presentation data receiving interface and the training behavior data collection interface. When a data transmission request is detected, a data transmission channel is established.

[0088] Step S1353: Through the dual-channel data input interface, synchronously receive resource interaction data transmitted from the scenario presentation data receiving interface and standardized training behavior data transmitted from the training behavior data collection interface, store the received resource interaction data in the first storage area of ​​the cache component, and store the standardized training behavior data in the second storage area of ​​the cache component.

[0089] Through dual data input interfaces, the system synchronously receives resource interaction data transmitted from the scenario presentation data receiving interface and standardized training behavior data transmitted from the training behavior data collection interface. The received resource interaction data is stored in the first storage area of ​​the cache component, and the standardized training behavior data is stored in the second storage area of ​​the cache component.

[0090] Step S1354: Start the data preprocessing thread to perform format verification and redundant data removal on the resource interaction data in the first storage area to maintain the integrity and validity of the resource interaction data. Perform data classification and time-series sorting on the standardized training behavior data in the second storage area to maintain the orderliness and readability of the training behavior data.

[0091] The data preprocessing thread is started to perform format verification on the resource interaction data in the first storage area, remove redundant data, and maintain the integrity and validity of the resource interaction data; the standardized training behavior data in the second storage area is classified by behavior type and sorted by time order to maintain the orderliness and readability of the training behavior data.

[0092] Step S1355: Construct a data association mapping thread. Based on the multi-source resource association node network information of the dynamic collaborative architecture, establish association mapping rules between resource interaction data and standardized training behavior data. The association mapping rules define the correspondence between device status data in resource interaction data and device operation data in training behavior data, the correspondence between process execution data and process selection data, and the correspondence between scenario adaptation data and scenario response data.

[0093] A data association mapping thread is constructed, and association mapping rules are established based on the network information of multi-source resource association nodes in a dynamic collaborative architecture. The rules define the correspondence between equipment status data in resource interaction data and equipment operation data in training behavior data as follows: "Water guide mechanism open status" in equipment status data corresponds to "Open water guide mechanism operation" in equipment operation data; the correspondence between process execution data and process selection data is as follows: "Check lubricating oil system step execution result" in process execution data corresponds to "Select check lubricating oil system process" in process selection data; the correspondence between scenario adaptation data and scenario response data is as follows: "Abnormal scenario trigger signal" in scenario adaptation data corresponds to "Abnormal scenario response operation" in scenario response data.

[0094] Step S1356: Based on the association mapping rules, perform association matching processing on the preprocessed resource interaction data and standardized training behavior data to generate data association matching results. The data association matching results include successfully matched data pairs, data identifiers of failed matches, and unmatched data items.

[0095] Based on association mapping rules, the preprocessed resource interaction data and standardized training behavior data are matched. The "water diversion mechanism activation status" data in the resource interaction data is matched with the "water diversion mechanism activation operation" data in the training behavior data to generate successfully matched data pairs; data that cannot be matched is marked, generating a data failure flag; data for which no corresponding match is found is recorded, generating an unmatched data item.

[0096] Step S1357: Start the data integration output thread, integrate and encapsulate the successfully matched data pairs in the data association matching results, generate integrated data according to the format required by the real-time scheduling protocol of the dynamic collaborative architecture, record and mark the data identifiers of the failed matches and the unmatched data items, and generate a data processing log.

[0097] Start the data integration and output thread to integrate and encapsulate successfully matched data pairs, and generate integrated data in XML format according to the real-time scheduling protocol requirements of the dynamic collaborative architecture; record and mark data that failed to match and unmatched data items, and generate data processing logs.

[0098] Step S1358: Transmit the integrated data to the dynamic collaborative architecture through the data output interface, and store the data processing log to the local storage component. This enables the data transfer and processing unit to handle the entire process of receiving, preprocessing, associating and matching, integrating and outputting resource interaction data and training behavior data, as well as logging.

[0099] Through the data output interface, the integrated data is transmitted to the dynamic collaborative architecture, while the data processing logs are stored in the local storage component, realizing the full-process processing of the data transfer and processing unit.

[0100] Step S136: Based on the real-time scheduling protocol of the dynamic collaborative architecture, construct the linkage logic of the data transfer processing unit. The linkage logic defines the matching rules, response timing and feedback path of resource interaction data and training behavior data, so as to realize the dynamic linkage of resource interaction data driving scene presentation and training behavior data adjusting resource interaction in reverse.

[0101] The real-time scheduling protocol based on a dynamic collaborative architecture constructs the linkage logic of the data transfer and processing unit. Matching rules define that the device status data in the resource interaction data must completely match the device operation data in the training behavior data; response timing defines that the time when the scenario driven by the resource interaction data is presented must precede the time when the training behavior data adjusts the resource interaction; feedback path defines the path for the training behavior data to adjust the resource interaction as training behavior data → data transfer and processing unit → dynamic collaborative architecture → resource interaction data adjustment.

[0102] Step S137: Integrate the scene presentation data receiving interface, training behavior data collection interface, data transfer processing unit and linkage logic to form a multi-directional interactive link. The multi-directional interactive link realizes real-time data flow and linkage response between the simulation training scene presentation and training behavior feedback through the data transfer processing unit.

[0103] The system integrates the scene presentation data receiving interface, the training behavior data collection interface, the data transfer and processing unit, and the linkage logic to form a multi-directional interactive link. This multi-directional interactive link realizes real-time data flow and linkage response between the simulated training scene presentation and training behavior feedback through the data transfer and processing unit.

[0104] Step S140: Based on the dynamic collaborative architecture and multi-directional interaction links, generate an adaptive simulation training scenario that integrates collaborative content from multiple sources of training core resources.

[0105] Step S141: Receive preset training demand information, which includes training target characteristic information, training ability target information, training focus theme direction information, and training duration planning information.

[0106] The system receives pre-set training needs information, with the target audience being "new maintenance personnel," the training capability objective being "mastering the start-up procedure and emergency shutdown operation of the hydro-generator unit," the training focus being "start-up procedure of the hydro-generator unit," and the training duration being "the prescribed duration."

[0107] Step S142: Based on training demand information, obtain a subset of equipment resources that match the training target characteristics and training capability objectives from the equipment operation core resources of the multi-source training core resource pool through resource filtering operations; obtain a subset of process resources that match the training focus topic direction information and training duration planning information from the operation process core resources; and obtain a subset of scenario resources that match the training capability objectives and training focus topic direction information from the scenario response core resources.

[0108] Resource selection is based on training needs information. From the core equipment operation resources, a subset of equipment resources suitable for "new maintenance personnel" and "mastering the start-up and emergency shutdown procedures of hydro-generator units" is obtained, including resources related to equipment such as the water guide mechanism and lubrication system. From the core operation process resources, a subset of process resources suitable for "start-up procedures of hydro-generator units" and "training duration is the specified duration" is obtained, including resources related to steps such as "checking the lubrication system," "activating the excitation system," and "starting the water guide mechanism." From the core scenario response resources, a subset of scenario resources suitable for "mastering the start-up and emergency shutdown procedures of hydro-generator units" and "start-up procedures of hydro-generator units" is obtained, including resources related to abnormal scenarios and emergency shutdown scenarios.

[0109] Step S143: Import the device resource subset, process resource subset, and scenario resource subset into the multi-source resource association node network of the dynamic collaborative architecture, perform resource collaborative association processing through a real-time scheduling protocol, and generate a resource collaborative combination scheme based on the attribute information and execution information of each resource subset. The resource collaborative combination scheme determines the association method, interaction sequence, and presentation identifier of each resource subset.

[0110] The equipment resource subset, process resource subset, and scenario resource subset are imported into a multi-source resource association node network of a dynamic collaborative architecture, and resource collaborative association processing is performed through a real-time scheduling protocol. Based on the attribute information of the equipment resource subset, the execution information of the process resource subset, and the adaptation information of the scenario resource subset, a resource collaborative combination scheme is generated. This resource collaborative combination scheme determines that the association method of each resource subset is as follows: the equipment resource subset and the process resource subset are associated through the "activate the water guiding mechanism" step, and the process resource subset and the scenario resource subset are associated through abnormal scenarios. The interaction sequence is that the equipment resource subset data is transmitted first, the process resource subset data is transmitted later, and the scenario resource subset data is transmitted last. The presentation identifier is that the display ratio of equipment resource content is a specified ratio, the display ratio of process resource content is a specified ratio, and the display ratio of scenario resource content is a specified ratio.

[0111] Step S144: Through the scene presentation data receiving interface of the multi-directional interactive link, the resource collaboration combination scheme is transmitted to the simulation training scene presentation module, and the basic framework of the initial simulation training scene is constructed based on the resource collaboration combination scheme, the presentation order of each link of the scene is configured, and the display ratio of each resource content is determined.

[0112] The resource collaboration and combination scheme is transmitted to the simulation training scenario presentation module through a multi-directional interactive link scenario presentation data receiving interface. The scenario presentation module constructs the basic framework of the initial simulation training scenario based on the resource collaboration and combination scheme. This framework includes an equipment display area, a process display area, and a scenario display area. The presentation order of each stage of the scenario is configured as follows: first, equipment resource content is displayed; then, process resource content is displayed; and finally, scenario resource content is displayed. The display proportions of each resource content are determined as follows: equipment resource content displays a specified proportion, process resource content displays a specified proportion, and scenario resource content displays a specified proportion.

[0113] Step S145: Start the initial simulation training scenario. Through the training behavior data acquisition interface of the multi-directional interactive link, collect the first stage training behavior data of the trainees in the initial simulation training scenario in real time. The first stage training behavior data includes equipment operation behavior data, process selection behavior data, scenario response behavior data and parameter adjustment behavior data.

[0114] The initial simulation training scenario is initiated, and training behavior data collection interfaces via a multi-directional interactive link are used to collect the first phase of training behavior data from the trainees in real time. Equipment operation behavior data includes the time and results of the trainees operating the water guiding mechanism; process selection behavior data includes the time and results of the trainees selecting the "Check Lubricating Oil System" process; scenario response behavior data includes the response time and results of the trainees to abnormal scenarios; and parameter adjustment behavior data includes the time and values ​​of the trainees adjusting the lubricating oil pressure parameters before and after adjustment.

[0115] Step S146: The first-stage training behavior data is transmitted to the dynamic collaborative architecture through the data transfer processing unit of the multi-directional interactive link. The dynamic collaborative architecture, based on the real-time scheduling protocol, matches and analyzes the first-stage training behavior data with the resource collaborative combination scheme, and identifies the adaptation differences between the initial simulation training scenario and the training demand information. The adaptation differences include resource content adaptation differences, presentation order adaptation differences, and display ratio adaptation differences.

[0116] The training behavior data from the first phase is transmitted to the dynamic collaboration architecture via a data transfer and processing unit. Based on a real-time scheduling protocol, the dynamic collaboration architecture matches and analyzes the first-phase training behavior data with resource collaboration combinations. It identifies the following discrepancies: insufficient emergency shutdown scenario content in the scenario resource content; a discrepancy in presentation order due to the process resource content display order not matching the trainees' learning order; and a discrepancy in display proportion due to an excessively high proportion of equipment resource content displayed.

[0117] Step S147: Based on the adaptation differences, adjust the combination ratio of device resource subset, process resource subset and scene resource subset, optimize the association method, interaction sequence and presentation identifier of resource collaboration combination scheme, and generate optimized resource collaboration combination scheme.

[0118] Step S1471: Analyze the resource content adaptation differences in the adaptation differences, identify resource items in the equipment resource subset, process resource subset and scenario resource subset that do not match the training requirements information, and count the number and proportion of mismatched resource items in each resource subset.

[0119] The differences in resource content adaptation are analyzed to identify insufficient emergency shutdown scenario content in the scenario resource subset, which are identified as mismatched resource items. The proportion of these mismatched resource items in the scenario resource subset is calculated as a specified ratio.

[0120] Step S1472: Based on the statistical results of mismatched resource items, adjust the combination ratio of each resource subset, increase the proportion of resource items that match the training requirements information in the corresponding subset, reduce or remove mismatched resource items, so that the content of the equipment resource subset, process resource subset and scenario resource subset is highly consistent with the training requirements information.

[0121] Based on the statistical results, the combination ratio of each resource subset was adjusted to increase the proportion of emergency shutdown scenario content in the scenario resource subset and reduce the proportion of resource items in the equipment resource subset that do not match the training needs information, so that the content of each resource subset is highly consistent with the training needs information.

[0122] Step S1473: For the adaptation differences in presentation order, identify the links with unreasonable timing by analyzing the interaction sequence of the initial resource collaboration combination scheme and the cognitive patterns and operating habits of the trainees.

[0123] Analyzing the interaction sequence of the initial resource collaboration scheme and its compatibility with the trainees' cognitive patterns and operational habits, it was found that the process resource content display sequence of "checking the lubrication system", "putting into the excitation system", and "starting the water guiding mechanism" did not match the trainees' learning sequence, indicating that the sequence was unreasonable.

[0124] Step S1474: Based on cognitive patterns and operational habits, optimize the interaction sequence of the resource collaboration combination scheme, adjust the presentation order of unreasonable links, and make the presentation order of equipment operation, process execution and scenario response conform to the learning logic of the trainees.

[0125] Based on the cognitive patterns and operational habits of the trainees, the interaction sequence of the resource collaboration scheme was optimized. The display order of process resource content was adjusted to "put on the excitation system", "check the lubrication system" and "start the water guiding mechanism", so that the presentation order conforms to the learning logic of the trainees.

[0126] Step S1475: For the adaptation differences in display ratio, analyze the correspondence between the presentation identifiers of the initial resource collaboration combination scheme and the training focus theme information, and identify resource content with unreasonable ratio allocation.

[0127] By analyzing the correspondence between the presentation identifiers of the initial resource collaboration combination scheme and the training focus theme information, it was found that the proportion of equipment resource content displayed was too high, indicating an unreasonable allocation of resource content.

[0128] Step S1476: Based on the training focus topic information, adjust the presentation identifier of the resource collaboration combination scheme, increase the display ratio of resource items corresponding to the training focus topic content, increase their presentation frequency and display duration in the simulation training scenario, and adjust the display ratio of non-focus topic content.

[0129] Based on the training focus on the theme of "operational process of starting up hydro-generator units", the presentation of resource collaboration schemes is adjusted to increase the proportion of process resource content in the display, increase its presentation frequency and duration in the simulation training scenario, and reduce the proportion of equipment resource content in the display.

[0130] Step S1477: Optimize the association method of resource collaboration combination scheme. Based on the adjusted combination ratio, interaction sequence and presentation identifier, redefine the association logic of device resource subset, process resource subset and scenario resource subset, strengthen the association strength between focused theme resource items and weaken the association between non-focused theme resource items.

[0131] Based on the adjusted combination ratio, interaction sequence, and presentation identifiers, the association method of the resource collaboration combination scheme is optimized. The association logic between the equipment resource subset and the process resource subset is redefined so that the equipment resource subset is associated with the process resource subset through the "putting the excitation system into operation" step, thereby strengthening the association between the process resource subset and the scenario resource subset and weakening the association between the equipment resource subset and the scenario resource subset.

[0132] Step S148: Through the scene presentation data receiving interface of the multi-directional interactive link, the optimized resource collaboration combination scheme is transmitted to the simulation training scene presentation module. Based on the optimized resource collaboration combination scheme, the scene presentation module updates the basic framework, presentation order and display ratio of the initial simulation training scene, and generates an adaptive simulation training scene that integrates the collaborative content of multi-source training core resources.

[0133] The optimized resource collaboration scheme is transmitted to the simulation training scenario presentation module via a multi-directional interactive data receiving interface. Based on the optimized scheme, the scenario presentation module updates the basic framework of the initial simulation training scenario, adjusting the layout of the equipment display area, process display area, and scenario display area; updating the presentation order to first display process resource content, then equipment resource content, and finally scenario resource content; and updating the display proportions to a specified percentage for each of the three resource content categories, generating an adaptive simulation training scenario.

[0134] For example, step S149: extract the update feature information of each core resource in the multi-source training core resource pool. The update feature information includes parameter change information of the equipment operation core resource, step adjustment information of the operation process core resource, and condition update information of the scenario response core resource.

[0135] Extract update feature information of each core resource in the multi-source training core resource pool. The parameter change information of the equipment operation core resource is the change of the water guide mechanism opening voltage parameter; the step adjustment information of the operation process core resource is that the "check lubrication system" step is changed to the "check lubrication system and cooling system" step; the condition update information of the scenario response core resource is that the abnormal scenario trigger condition is changed to lubrication pressure being lower than the specified value for a specified duration.

[0136] Step S1410: Based on the updated feature information, a resource update monitoring unit is constructed. The resource update monitoring unit captures the changes of each core resource in the multi-source training core resource pool in real time and generates resource update notification information.

[0137] A resource update monitoring unit is constructed based on update feature information. This unit captures changes in each core resource within the multi-source training core resource pool in real time. When it detects changes in parameters of core resources for equipment operation, adjustments to steps of core resources for work processes, or updates to conditions of core resources for scenario response, it generates resource update notification information.

[0138] Step S1411: The resource update notification information is transmitted to the dynamic collaborative architecture through the data relay processing unit of the multi-directional interaction link. The dynamic collaborative architecture parses the changes in the resource update notification information based on the real-time scheduling protocol.

[0139] The resource update notification information is transmitted to the dynamic collaborative architecture through the data relay processing unit of the multi-directional interactive link. The dynamic collaborative architecture, based on the real-time scheduling protocol, parses the changes in the resource update notification information, such as changes in the opening voltage parameter of the water guide mechanism, the adjustment of the "check lubricating oil system" step to the "check lubricating oil system and cooling system" step, and the change of the abnormal scenario trigger condition to lubricating oil pressure being lower than the specified value for a specified duration.

[0140] Step S1412: Based on the parsed changes, adjust the connection relationship and data interaction direction of the multi-source resource association node network, and update the association method and interaction sequence of the resource collaborative combination scheme.

[0141] Based on the changes analyzed, the connection relationships of the multi-source resource association node network are adjusted, establishing a connection between the "Inspect Lubricating Oil System" step node and the "Inspect Cooling System" step node; the data interaction direction is adjusted so that the data from the "Inspect Cooling System" step node is transmitted to the process scenario combination node; the association method of the resource collaboration combination scheme is updated so that the equipment resource subset and the process resource subset are associated through the "Inspect Lubricating Oil System and Cooling System" step, and the interaction sequence is that the process resource subset data is transmitted first, followed by the equipment resource subset data.

[0142] Step S1413: Through the scene presentation data receiving interface of the multi-directional interactive link, the updated resource collaboration combination scheme is transmitted to the simulation training scene presentation module, and the basic framework, presentation order and display ratio of the adaptive simulation training scene are adjusted based on the updated resource collaboration combination scheme to achieve real-time synchronization between resource updates and scene presentation.

[0143] The updated resource collaboration scheme is transmitted to the simulation training scenario presentation module via a multi-directional interactive link's scenario presentation data receiving interface. Based on the updated scheme, the scenario presentation module adjusts the basic framework of the adaptive simulation training scenario, adding a cooling system display area; adjusting the presentation order to first display the "Inspect the Lubricating Oil System and Cooling System" step; and adjusting the display proportion to ensure that the "Inspect the Lubricating Oil System and Cooling System" step accounts for a specified percentage, achieving real-time synchronization between resource updates and scenario presentation.

[0144] Step S1414: Collect training behavior data of trainees in the adaptive simulation training scenario after resource update, and compare and analyze the training behavior data with the training behavior data before resource update to identify adaptation differences after scenario adjustment.

[0145] Collect training behavior data of trainees after resource updates, including the time and results of trainees operating the cooling system; compare and analyze this data with the training behavior data before the resource update to identify the adaptation difference after the scenario adjustment as the trainees' lack of proficiency in the operation of the "inspecting the lubrication system and cooling system" step.

[0146] Step S1415: Based on the identified adaptation differences, further optimize the presentation identifier and association logic of the resource collaboration combination scheme, so that the adaptive simulation training scenario can continuously adapt to the updates and changes of multi-source training core resources.

[0147] Based on the identified adaptation differences, the presentation of resource collaboration combination schemes is further optimized to increase the display ratio of the "Inspect Lubricating Oil System and Cooling System" step content; the association logic is optimized to strengthen the association strength between the "Inspect Lubricating Oil System and Cooling System" step node and the equipment resource subset, so that the adaptive simulation training scenario can continuously adapt to the updates and changes of multi-source training core resources.

[0148] Step S150: Collect feedback optimization data during the operation of the adaptive simulation training scenario, iteratively adjust the scheduling parameters of the dynamic collaborative architecture and the linkage rules of the multi-directional interaction links to form a multi-source collaborative simulation training closed loop.

[0149] Step S151: During the operation of the adaptive simulation training scenario, resource interaction data of each associated node is collected through the real-time scheduling protocol of the dynamic collaborative architecture. The resource interaction data includes interaction data between equipment resources and process resources, interaction data between process resources and scenario resources, and interaction data between scenario resources and equipment resources.

[0150] During the operation of the adaptive simulation training scenario, resource interaction data of each associated node is collected through a real-time scheduling protocol of a dynamic collaborative architecture. The interaction data between equipment resources and process resources consists of the interaction between the water guide mechanism's open status data and the execution result data of the "open water guide mechanism" step; the interaction data between process resources and scenario resources consists of the interaction between the execution result data of the "check lubrication system and cooling system" step and the abnormal scenario trigger data; and the interaction data between scenario resources and equipment resources consists of the interaction between emergency shutdown scenario trigger data and the water guide mechanism's closed status data. Simultaneously, the collected resource interaction data undergoes privacy protection processing, employing encryption algorithms to encrypt and store the data, preventing data leakage.

[0151] Step S152: Through the training behavior data acquisition interface of the multi-directional interactive link, synchronously collect the full training behavior data of the trainees in each stage of the adaptive simulation training scenario. The full training behavior data includes equipment operation behavior data, process selection behavior data, scenario response behavior data and parameter adjustment behavior data at each stage.

[0152] Through a multi-directional interactive training behavior data collection interface, training behavior data of trainees throughout the entire training process is collected synchronously. Equipment operation behavior data includes the time and results of trainees operating the water guiding mechanism and cooling system; process selection behavior data includes the time and results of trainees selecting the "Check Lubrication System and Cooling System" process; scenario response behavior data includes the response time and results of trainees to abnormal scenarios and emergency shutdown scenarios; parameter adjustment behavior data includes the time and values ​​before and after trainees adjusting the opening voltage and lubrication pressure parameters of the water guiding mechanism. Simultaneously, the collected training behavior data undergoes privacy protection processing, employing de-identification technology to anonymize sensitive information in the data to prevent privacy leaks.

[0153] Step S153: Obtain feedback evaluation data of the trainees after completing the adaptive simulation training scenario through data collection operations. The feedback evaluation data includes data on the rationality of resource content, data on the adaptability of scenario presentation, data on the timeliness of interactive response, and data on training effect satisfaction.

[0154] Feedback and evaluation data from trainees were obtained through data collection operations. Data on the reasonableness of resource content indicates that trainees considered the steps of "inspecting the lubrication system and cooling system" to be reasonable; data on the suitability of scenario presentation indicates that trainees considered the sequence of scenario presentation to be suitable for their learning logic; data on the timeliness of interactive response indicates that trainees considered the interactive response to be timely; and data on training effectiveness satisfaction indicates that trainees were satisfied with the training effect.

[0155] Step S154: Integrate resource interaction data, full-process training behavior data, and feedback evaluation data to form a feedback optimization data set, wherein the feedback optimization data set includes data identifiers, data sources, data content, and data relationships.

[0156] Integrate resource interaction data, training behavior data, and feedback evaluation data to form a feedback optimization data set. Data is identified by sequentially arranged identifiers; data sources include the dynamic collaborative architecture, training behavior data collection interfaces, and data collection operations; data content includes specific information for each data point; and data relationships include the association between resource interaction data and training behavior data, and the association between training behavior data and feedback evaluation data.

[0157] Step S155: Analyze the feedback optimization data set, extract the scheduling parameter operation data in the real-time scheduling protocol of the dynamic collaborative architecture, and identify the parameter items that need to be adjusted in the scheduling parameters based on the scheduling parameter operation data. The scheduling parameter operation data includes transmission bandwidth usage data, data transmission delay data, node response speed data, and data fault tolerance processing result data.

[0158] The feedback optimization dataset was analyzed to extract scheduling parameter operation data from the real-time scheduling protocol of the dynamic collaborative architecture. Transmission bandwidth usage data represents the specified percentage of bandwidth utilization; data transmission latency data represents the specified duration of data transmission latency; node response speed data represents the specified node response speed; and data fault tolerance processing result data represents successful data transmission after three retransmissions following a failed transmission. Based on this data, the transmission bandwidth parameter was identified as the scheduling parameter requiring adjustment.

[0159] Step S156: Based on the identification results, adjust the transmission bandwidth allocation parameters of the dynamic collaborative architecture, allocate higher transmission bandwidth to the associated nodes corresponding to the data transmission delay data, adjust the node response order parameters, arrange the response order of associated nodes according to the frequency of resource interaction, adjust the data fault tolerance processing logic parameters, and improve the recovery path after data loss.

[0160] Based on the identification results, the transmission bandwidth allocation parameters of the dynamic collaborative architecture are adjusted to allocate higher transmission bandwidth to the associated nodes corresponding to the data transmission delay data; the node response order parameters are adjusted to arrange the response order of associated nodes according to the frequency of resource interaction, placing nodes with frequent resource interaction at the front; the data fault tolerance processing logic parameters are adjusted to improve the recovery path after data loss and add data backup nodes.

[0161] Step S157: Analyze the feedback optimization data set, extract the linkage rule operation data of the multi-directional interaction link, and identify the rule items that need to be optimized in the linkage rules based on the linkage rule operation data. The linkage rule operation data includes data matching accuracy data, linkage response time data, and feedback adjustment effective data.

[0162] The feedback optimization dataset is analyzed to extract the operational data of the linkage rules in the multi-directional interaction chain. Data matching accuracy data represents a specified percentage of data matching accuracy, linkage response time data represents a specified linkage response time, and feedback adjustment effectiveness data represents a specified percentage of feedback adjustment effectiveness. Based on this data, the rules requiring optimization in the linkage rules are identified as data matching rules and linkage response timing rules.

[0163] Step S158: Based on the identification results, perform optimization operations on the linkage rules of the multi-directional interaction link. The optimization operations include data matching rule optimization, linkage response timing rule optimization, and feedback adjustment rule optimization.

[0164] Step S1581: Based on the analysis of the data items that failed to match in the feedback optimization data set, identify the reasons for the matching failure. The reasons include inconsistent data formats, inconsistent data identifiers, and unclear association logic. According to the identified reasons, perform the following revision operations: When the reason is inconsistent data formats, revise the format matching standard in the data matching rules to achieve format uniformity between training behavior data and resource interaction data; when the reason is inconsistent data identifiers, revise the data identifier matching rules to maintain consistency in the identifier coding rules of the two types of data; when the reason is unclear association logic, improve the association logic matching clauses to clarify the association conditions and judgment criteria for different types of data. At the same time, perform key feature extraction and verification logic addition operations to extract key feature information from the training behavior data and resource interaction data, establish secondary matching verification logic based on the key feature information, and add the verification logic to the data matching rules for secondary matching when the first matching fails.

[0165] Based on the analysis of data items that failed to match in the feedback optimization dataset, the reasons for the matching failures were identified as inconsistent data formats, inconsistent data identifiers, and unclear association logic. When the reason was inconsistent data formats, the format matching standard in the data matching rules was revised to unify the formats of training behavior data and resource interaction data to XML format. When the reason was inconsistent data identifiers, the data identifier matching rules were revised to maintain consistency in the identifier encoding rules for the two types of data. When the reason was unclear association logic, the association logic matching clauses were improved to clarify the association conditions and judgment criteria for different types of data. Simultaneously, key feature information, such as operation time and operation results, was extracted from the training behavior data and resource interaction data. A secondary matching verification logic was established based on this key feature information and added to the data matching rules.

[0166] Step S1582: Based on the analysis of the linkage response duration data in the feedback optimization dataset, identify the links whose response duration exceeds a set duration threshold. These links include data transmission links, data processing links, and rule execution links. According to the identified links, perform the following adjustment operations: For the data transmission link, optimize the data transmission path to reduce the number of relay nodes in the data transmission process; for the data processing link, optimize the data processing logic to improve data processing efficiency; for the rule execution link, adjust the rule execution order to prioritize the execution of the core linkage logic.

[0167] Based on the analysis of the response duration data in the feedback optimization dataset, the stages where the response duration exceeds the set threshold are identified as data transmission stages and data processing stages. For the data transmission stage, the data transmission path is optimized to reduce intermediate nodes in the data transmission process; for the data processing stage, the data processing logic is optimized to improve data processing efficiency; for the rule execution stage, the rule execution order is adjusted to prioritize the execution of core linkage logic.

[0168] Step S1583: Based on the analysis of valid feedback adjustment data in the feedback optimization dataset, identify the reasons for ineffective adjustments. These reasons include adjustments deviating from requirements, adjustments not matching the scenario, and adjustments being made at inappropriate times. Based on the identified reasons, perform the following improvements: When the reason is that the adjustment direction deviates from requirements, improve the adjustment direction determination logic in the feedback adjustment rules to accurately determine the adjustment direction by combining training needs information and training behavior data; when the reason is that the adjustment magnitude does not match the scenario, optimize the adjustment magnitude setting logic in the feedback adjustment rules to dynamically adjust the adjustment magnitude according to changes in the scenario; when the reason is that the adjustment timing is inappropriate, adjust the adjustment timing trigger conditions in the feedback adjustment rules to determine the optimal adjustment timing based on data interaction frequency and the rate of scenario change.

[0169] Based on the analysis of valid feedback adjustment data in the feedback optimization dataset, the reasons for ineffective adjustments were identified as follows: the adjustment direction deviated from the requirements, and the adjustment magnitude did not conform to the scenario. When the reason was that the adjustment direction deviated from the requirements, the logic for determining the adjustment direction in the feedback adjustment rules was improved to accurately determine the adjustment direction by combining training needs information and training behavior data. When the reason was that the adjustment magnitude did not conform to the scenario, the logic for setting the adjustment magnitude in the feedback adjustment rules was optimized to dynamically adjust the adjustment magnitude according to changes in the scenario. When the reason was that the adjustment timing was unreasonable, the triggering conditions for the adjustment timing in the feedback adjustment rules were adjusted to determine the optimal adjustment timing based on the data interaction frequency and the rate of change in the scenario.

[0170] Step S1584: After optimizing the data matching rules, linkage response timing rules, and feedback adjustment rules, the optimized rule logics are integrated to form the optimized multi-directional interactive link linkage rules.

[0171] After optimizing the data matching rules, the linkage response timing rules, and the feedback adjustment rules, the optimized rule logics are integrated to form the optimized multi-directional interactive link linkage rules.

[0172] For example, step S159: Construct a feedback data classification unit, which divides the feedback optimization data set into resource interaction data, training behavior data and evaluation feedback data based on the data source and data type.

[0173] A feedback data classification unit is constructed, which divides the feedback optimization data set into resource interaction data, training behavior data, and evaluation feedback data based on data source and data type. Resource interaction data is collected from the dynamic collaboration architecture, training behavior data is collected from the training behavior data collection interface, and evaluation feedback data is obtained from data collection operations.

[0174] Step S1510: Configure personalized analysis logic for each type of data. Resource interaction data adopts node association analysis logic, training behavior data adopts time series association analysis logic, and evaluation feedback data adopts dimensional decomposition analysis logic.

[0175] Personalized analysis logic is configured for each type of data. Resource interaction data uses node association analysis logic to analyze the interaction relationships between related nodes; training behavior data uses time-series association analysis logic to analyze the temporal sequence of training behaviors; evaluation and feedback data uses dimensional decomposition analysis logic to analyze from dimensions such as the rationality of resource content and the adaptability of scenario presentation.

[0176] Step S1511: Through the personalized analysis logic of the feedback data classification unit, extract the key influencing factors in each type of data. The key influencing factors include the node transmission factor of resource interaction data, the operation adaptation factor of training behavior data, and the satisfaction influencing factor of evaluation feedback data.

[0177] By employing personalized analysis logic within the feedback data classification units, key influencing factors are extracted from each data category. For resource interaction data, the key influencing factor is the node transmission factor; for training behavior data, the key influencing factor is the operational adaptation factor; and for evaluation feedback data, the key influencing factor is the satisfaction factor.

[0178] Step S1512: Based on the key influencing factors, construct an optimization priority determination unit. The optimization priority determination unit combines the correlation between the key influencing factors and the simulation training effect to set the optimization order of dynamic collaborative architecture scheduling parameters and multi-directional interactive link linkage rules.

[0179] Based on key influencing factors, an optimization priority determination unit is constructed. This unit, considering the correlation between key influencing factors and simulation training effectiveness, sets the optimization order of dynamic collaborative architecture scheduling parameters and multi-directional interaction link linkage rules as follows: first optimize the multi-directional interaction link linkage rules, then optimize the dynamic collaborative architecture scheduling parameters.

[0180] Step S1513: According to the set optimization order, adjust the transmission bandwidth allocation parameters, node response sequence parameters, and data fault tolerance processing logic parameters of the dynamic collaborative architecture, and optimize the data matching rules, linkage response timing rules, and feedback adjustment rules of the multi-directional interactive links.

[0181] According to the set optimization order, adjust the transmission bandwidth allocation parameters, node response sequence parameters, and data fault tolerance processing logic parameters of the dynamic collaborative architecture, and optimize the data matching rules, linkage response timing rules, and feedback adjustment rules of the multi-directional interactive links.

[0182] Step S1514: Import the adjusted scheduling parameters and optimized linkage rules into the system, start a new round of adaptive simulation training scenario operation, and collect feedback optimization data during this round of operation.

[0183] Import the adjusted scheduling parameters and optimized linkage rules into the system, start a new round of adaptive simulation training scenario operation, and collect feedback optimization data during this round of operation.

[0184] Step S1515: Compare the changes in key influencing factors in the new round of feedback optimization data with those in the previous round of feedback optimization data to identify differences in optimization effects.

[0185] By comparing the changes in key influencing factors in the new round of feedback optimization data with those in the previous round of feedback optimization data, the differences in optimization effect were identified as improved data matching accuracy and shortened linkage response time.

[0186] Step S1516: Based on the identified differences in optimization effects, adjust the judgment logic of the optimization priority determination unit, and repeat the data classification, factor extraction, priority setting, parameter adjustment and effect verification process to achieve continuous improvement in the efficiency of multi-source collaborative simulation training closed-loop optimization.

[0187] Based on the differences in the optimization effects identified, the judgment logic of the optimization priority determination unit is adjusted, and the processes of data classification, factor extraction, priority setting, parameter adjustment and effect verification are repeatedly executed to achieve continuous improvement in the efficiency of multi-source collaborative simulation training closed-loop optimization.

[0188] In one exemplary embodiment, a system for constructing a multi-source collaborative hydropower station simulation training system is provided. This system can be a terminal, a server, etc., and its internal structure diagram can be as follows: Figure 2As shown, the multi-source collaborative hydropower station simulation training system includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, near-field communication, or other technologies. When the computer program is executed by the processor, it implements a method for constructing a multi-source collaborative hydropower station simulation training system. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, or a button, trackball, or touchpad set on the shell of the multi-source collaborative hydropower station simulation training system. It can also be an external keyboard, touchpad, or mouse, etc.

[0189] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for constructing a hydropower station simulation training system based on multi-source collaboration, characterized in that, The method includes: Integrate the core resources of multi-source training for hydropower stations to form a multi-source training core resource pool, which includes core resources for equipment operation, core resources for work processes, and core resources for scenario response. A dynamic collaborative architecture is constructed for each resource within the multi-source training core resource pool. This dynamic collaborative architecture carries the real-time data interaction and associated scheduling between the resources. A multi-directional interaction link based on the aforementioned dynamic collaborative architecture is constructed to realize the dynamic linkage of resource interaction data-driven scenario presentation and training behavior data-driven resource interaction; the multi-directional interaction link realizes real-time linkage between simulated training scenario presentation and training behavior feedback. Based on the aforementioned dynamic collaborative architecture and multi-directional interaction links, an adaptive simulation training scenario integrating collaborative content from multiple sources of training core resources is generated. This includes: receiving preset training requirement information and acquiring subsets of equipment resources, process resources, and scenario resources based on the training requirement information; generating a resource collaboration combination scheme based on the attribute and execution information of each resource subset; collecting first-stage training behavior data and matching and analyzing the first-stage training behavior data with the resource collaboration combination scheme to identify adaptation differences between the initial simulation training scenario and the training requirement information, including resource content adaptation differences, presentation order adaptation differences, and display ratio adaptation differences; adjusting the combination ratio of the equipment resource subset, process resource subset, and scenario resource subset based on the adaptation differences, optimizing the association method, interaction sequence, and presentation identifier of the resource collaboration combination scheme, and generating an optimized resource collaboration combination scheme; and updating the basic framework, presentation order, and display ratio of the initial simulation training scenario based on the optimized resource collaboration combination scheme to generate an adaptive simulation training scenario integrating collaborative content from multiple sources of training core resources. The adaptive simulation training scenario dynamically adjusts the resource presentation content and method based on the training behavior data. The system collects feedback optimization data during the operation of the adaptive simulation training scenario, iteratively adjusts the scheduling parameters of the dynamic collaborative architecture and the linkage rules of the multi-directional interaction links, and forms a multi-source collaborative simulation training closed loop.

2. The method for constructing a hydropower station simulation training system based on multi-source collaboration as described in claim 1, characterized in that, The construction of the dynamic collaborative architecture for each resource within the multi-source training core resource pool includes: Extract the resource attribute information of the core resources for equipment operation within the multi-source training core resource pool. The resource attribute information includes equipment structural feature information, equipment operating status information, equipment operation specification information, and equipment association and adaptation information. Extract the process execution information of the core resources of the work process in the multi-source training core resource pool. The process execution information includes work step decomposition information, step connection logic information, process execution standard information and process association constraint information. Extract scene adaptation information from the scene response core resources in the multi-source training core resource pool. The scene adaptation information includes scene triggering condition information, scene response action information, scene transition logic information, and scene associated device information. The system identifies the associated nodes by linking the resource attribute information of the core resources for equipment operation with the process execution information of the core resources for the work process. Based on the correspondence between equipment operation specification information and work step decomposition information, it determines the direct associated nodes between the equipment and the process. Based on the adaptation relationship between equipment operation status information and process execution standard information, it determines the indirect associated nodes between the equipment and the process. The process execution information of the core resources of the work process and the scenario adaptation information of the core resources of the scenario response are used to identify the associated nodes. Based on the correspondence between the step connection logic information and the scenario triggering condition information, the direct associated nodes between the process and the scenario are determined, and based on the adaptation relationship between the process association constraint information and the scenario transformation logic information, the indirect associated nodes between the process and the scenario are determined. The system identifies the associated nodes by linking the scene adaptation information of the core resources for scene response with the resource attribute information of the core resources for device operation. Based on the correspondence between scene response action information and device operation specification information, the system determines the direct associated nodes between the scene and the device. Based on the adaptation relationship between scene-associated device information and device-associated adaptation information, the system determines the indirect associated nodes between the scene and the device. Based on all directly and indirectly related nodes, a multi-source resource association node network is constructed. The multi-source resource association node network includes the connection relationship of each node, the direction of data interaction, and the association identifier. The association identifier is set based on the correspondence between the node and the training requirement information. A real-time scheduling protocol is configured for the multi-source resource association node network. The real-time scheduling protocol specifies the format, timing and fault-tolerant processing logic of data interaction between nodes. Based on the real-time scheduling protocol and the multi-source resource association node network, a dynamic collaborative architecture is constructed that runs through the core resources of equipment operation, the core resources of work process and the core resources of scenario response.

3. The method for constructing a hydropower station simulation training system based on multi-source collaboration as described in claim 2, characterized in that, The construction of a multi-directional interaction link based on the dynamic collaborative architecture includes: The multi-source resource association node network of the dynamic collaborative architecture is analyzed, and the output data type, data transmission rate and data interaction requirements of each association node are extracted. Based on the output data type, data transmission rate and data interaction requirements, the data source access requirements of the simulation training scenario presentation module are determined. Based on the data source access requirements, a scene presentation data receiving interface is constructed. The scene presentation data receiving interface supports real-time access, parsing, and format conversion of the output data of each associated node in the dynamic collaborative architecture, so that the accessed data is consistent with the processing requirements of the scene presentation module. The training behavior types generated during the training process are analyzed, including equipment operation behavior, process selection behavior, scenario response behavior and parameter adjustment behavior. For each type of training behavior, the data collection dimension, collection frequency and data storage format are determined. Based on the data collection requirements of training behavior, a training behavior data collection interface is constructed. The training behavior data collection interface supports real-time capture, classified storage and format standardization of various training behavior data, so that the collected data can be identified and processed by the dynamic collaborative architecture. A data transfer and processing unit is constructed, which is connected to the scene presentation data receiving interface and the training behavior data collection interface respectively. The data transfer and processing unit receives resource interaction data transmitted by the scene presentation data receiving interface and standardized training behavior data transmitted by the training behavior data collection interface. Based on a real-time scheduling protocol with a dynamic collaborative architecture, a linkage logic for a data transfer and processing unit is constructed. The linkage logic defines the matching rules, response timing, and feedback path for resource interaction data and training behavior data, thereby realizing dynamic linkage where resource interaction data drives scenario presentation and training behavior data adjusts resource interaction in reverse. The system integrates the scene presentation data receiving interface, the training behavior data collection interface, the data transfer and processing unit, and the linkage logic to form a multi-directional interactive link. The multi-directional interactive link realizes real-time data flow and linkage response between the simulation training scene presentation and the training behavior feedback through the data transfer and processing unit.

4. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 2, characterized in that, The adaptive simulation training scenario, which integrates collaborative content from multiple sources of core training resources, is generated based on the dynamic collaborative architecture and multi-directional interaction links, including: Receive preset training demand information, which includes training target characteristic information, training ability target information, training focus theme direction information, and training duration planning information; Based on training demand information, a subset of equipment resources that match the training target characteristics and training capability objectives are obtained from the equipment operation core resources of the multi-source training core resource pool through resource filtering operations; a subset of process resources that match the training focus theme direction information and training duration planning information are obtained from the operation process core resources; and a subset of scenario resources that match the training capability objectives and training focus theme direction information are obtained from the scenario response core resources. The device resource subset, process resource subset, and scenario resource subset are imported into the multi-source resource association node network of the dynamic collaborative architecture. Resource collaborative association processing is performed through a real-time scheduling protocol. Based on the attribute information and execution information of each resource subset, a resource collaborative combination scheme is generated. The resource collaborative combination scheme determines the association method, interaction sequence, and presentation identifier of each resource subset. Through the scene presentation data receiving interface of the multi-directional interactive link, the resource collaboration combination scheme is transmitted to the simulation training scene presentation module. The scene presentation module constructs the basic framework of the initial simulation training scene based on the association method in the resource collaboration combination scheme, configures the presentation order of each link of the scene based on the interaction sequence, and determines the display ratio of each resource content based on the presentation identifier. The initial simulation training scenario is launched, and the training behavior data collection interface of the multi-directional interactive link is used to collect the first stage training behavior data of the trainees in the initial simulation training scenario in real time. The first stage training behavior data includes equipment operation behavior data, process selection behavior data, scenario response behavior data and parameter adjustment behavior data. The training behavior data of the first stage is transmitted to the dynamic collaborative architecture through the data transfer and processing unit of the multi-directional interactive link. The dynamic collaborative architecture, based on the real-time scheduling protocol, matches and analyzes the training behavior data of the first stage with the resource collaborative combination scheme, and identifies the adaptation differences between the initial simulation training scenario and the training demand information. The adaptation differences include resource content adaptation differences, presentation order adaptation differences, and display ratio adaptation differences. Based on adaptation differences, the combination ratio of device resource subsets, process resource subsets and scenario resource subsets is adjusted, the association method, interaction sequence and presentation identifier of resource collaboration combination scheme are optimized, and an optimized resource collaboration combination scheme is generated. The scene presentation module updates the basic framework, presentation order, and display ratio of the initial simulation training scene based on the optimized resource collaboration combination scheme, and generates an adaptive simulation training scene that integrates collaborative content of multi-source training core resources. The adaptive simulation training scene dynamically adjusts the resource presentation content and method based on training behavior data.

5. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 2, characterized in that, The process of collecting feedback optimization data during the operation of the adaptive simulation training scenario, iteratively adjusting the scheduling parameters of the dynamic collaborative architecture and the linkage rules of the multi-directional interaction links to form a multi-source collaborative simulation training closed loop includes: During the operation of the adaptive simulation training scenario, the resource interaction data of each associated node is collected through the real-time scheduling protocol of the dynamic collaborative architecture. The resource interaction data includes the interaction data between equipment resources and process resources, the interaction data between process resources and scenario resources, and the interaction data between scenario resources and equipment resources. Through the training behavior data collection interface of the multi-directional interactive link, the training behavior data of the trainees in each stage of the adaptive simulation training scenario is collected synchronously. The training behavior data includes equipment operation behavior data, process selection behavior data, scenario response behavior data and parameter adjustment behavior data at each stage. The data collection process obtains feedback evaluation data from trainees after they complete an adaptive simulation training scenario. This feedback evaluation data includes data on the rationality of resource content, the adaptability of scenario presentation, the timeliness of interactive response, and the satisfaction with training effectiveness. Integrate resource interaction data, full-process training behavior data, and feedback evaluation data to form a feedback optimization data set, which includes data identifiers, data sources, data content, and data relationships; The feedback optimization data set is analyzed, and the scheduling parameter operation data in the real-time scheduling protocol of the dynamic collaborative architecture is extracted. Based on the scheduling parameter operation data, the parameter items that need to be adjusted in the scheduling parameters are identified. The scheduling parameter operation data includes transmission bandwidth usage data, data transmission delay data, node response speed data, and data fault tolerance processing result data. Based on the identification results, the transmission bandwidth allocation parameters of the dynamic collaborative architecture are adjusted to allocate corresponding transmission bandwidth to the associated nodes corresponding to the data transmission delay data. The node response order parameters are adjusted to arrange the response order of associated nodes according to the frequency of resource interaction. The data fault tolerance processing logic parameters are adjusted to improve the recovery path after data loss. The feedback optimization data set is analyzed, the linkage rule operation data of the multi-directional interaction link is extracted, the linkage rule operation data is run based on the linkage rule, and the rule items that need to be optimized in the linkage rule are identified. The linkage rule operation data includes data matching accuracy data, linkage response time data, and feedback adjustment effective data. Based on the identification results, optimization operations are performed on the linkage rules of the multi-directional interaction link. The optimization operations include data matching rule optimization, linkage response timing rule optimization, and feedback adjustment rule optimization. The adjusted scheduling parameters and optimized linkage rules are re-imported into the dynamic collaborative architecture and multi-directional interaction link, and the data collection, parsing, adjustment, and optimization process is repeated to form a multi-source collaborative simulation training closed loop.

6. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 4, characterized in that, The construction of a multi-source resource association node network based on all directly and indirectly associated nodes includes: Perform node classification and labeling operations to classify all directly related nodes and indirectly related nodes and label the resource type combination corresponding to each node. The resource type combination includes equipment process combination, process scenario combination and scenario equipment combination. A unique node identifier is assigned to the associated nodes of each resource type combination. The node identifier includes the resource type code, node sequence number and association type identifier. The node identifier enables the differentiation and management of each associated node. Based on the resource attribute information, process execution information and scenario adaptation information of each associated node, the connection relationship between nodes is determined. The nodes of the device process combination and the nodes of the process scenario combination are connected based on process resources. The nodes of the process scenario combination and the nodes of the scenario device combination are connected based on scenario resources. The nodes of the scenario device combination and the nodes of the device process combination are connected based on device resources. Based on the logical order of resource interaction, the data interaction direction of each connection relationship is determined. The node of the device process combination transmits device status associated data to the node of the process scenario combination, the node of the process scenario combination transmits process execution associated data to the node of the scenario device combination, and the node of the scenario device combination transmits scenario response associated data to the node of the device process combination. Based on the correspondence between each associated node and training demand information, perform the association identifier setting operation, configure the first association identifier for the connection relationship directly corresponding to the training focus topic direction information, configure the second association identifier for the connection relationship directly corresponding to the training capability target information, and configure the third association identifier for the connection relationship directly corresponding to the training target characteristic information. Construct a node connection relationship matrix, which includes node identifiers, corresponding connected node identifiers, data interaction directions, and association identifiers, and presents the relationship between each node in a visual matrix form; Based on the node connection relationship matrix, a graphical modeling method is used to generate a visualization model of a multi-source resource associated node network. The visualization model is used to display the location distribution, connection path, data flow direction and association identifier of each node. Verify the connectivity of the multi-source resource association node network, check for the existence of isolated nodes and broken connections, supplement isolated nodes with associated resources to establish connections, and repair the association logic between nodes in broken connections to maintain the complete connectivity of the multi-source resource association node network.

7. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 3, characterized in that, The data transfer and processing unit is constructed, and it establishes connections with both the scene presentation data receiving interface and the training behavior data collection interface. It receives resource interaction data transmitted from the scene presentation data receiving interface and standardized training behavior data transmitted from the training behavior data collection interface, including: The hardware architecture of the data transfer and processing unit is constructed, using a multi-core processing component as the data processing core, configuring a high-speed cache component for temporary storage of data to be processed, configuring dual data input interfaces to connect to the scene presentation data receiving interface and the training behavior data collection interface respectively, and configuring a data output interface to connect to the dynamic collaborative architecture. The software processing logic of the data transfer and processing unit is constructed by first starting the data receiving thread, and simultaneously monitoring the data transmission status of the scene presentation data receiving interface and the training behavior data collection interface. When a data transmission request is detected, a data transmission channel is established. Through dual data input interfaces, the system synchronously receives resource interaction data transmitted from the scenario presentation data receiving interface and standardized training behavior data transmitted from the training behavior data collection interface. The received resource interaction data is stored in the first storage area of ​​the cache component, and the standardized training behavior data is stored in the second storage area of ​​the cache component. Start the data preprocessing thread to perform format verification and redundant data removal on the resource interaction data in the first storage area to maintain the integrity and validity of the resource interaction data; and perform data classification and time-series sorting on the standardized training behavior data in the second storage area to maintain the orderliness and readability of the training behavior data. A data association mapping thread is constructed. Based on the network information of multi-source resource association nodes in the dynamic collaborative architecture, association mapping rules are established between resource interaction data and standardized training behavior data. The association mapping rules define the correspondence between device status data in resource interaction data and device operation data in training behavior data, the correspondence between process execution data and process selection data, and the correspondence between scenario adaptation data and scenario response data. Based on the association mapping rules, the preprocessed resource interaction data and standardized training behavior data are associated and matched to generate data association matching results. The data association matching results include successfully matched data pairs, data identifiers of failed matches, and unmatched data items. Start the data integration and output thread, integrate and encapsulate the successfully matched data pairs in the data association and matching results, generate integrated data according to the format required by the real-time scheduling protocol of the dynamic collaborative architecture, record and mark the data identifiers of the failed matches and the unmatched data items, and generate data processing logs. Through the data output interface, the integrated data is transmitted to the dynamic collaborative architecture, while the data processing logs are stored in the local storage component. This enables the data transfer and processing unit to handle the entire process of receiving, preprocessing, associating and matching, integrating and outputting resource interaction data and training behavior data, as well as logging.

8. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 4, characterized in that, The process involves adjusting the combination ratios of device resource subsets, process resource subsets, and scene resource subsets based on adaptation differences, optimizing the association methods, interaction sequences, and presentation identifiers of the resource collaboration combination scheme, and generating an optimized resource collaboration combination scheme, including: The resource content adaptation differences in the adaptation differences are analyzed to identify resource items in the equipment resource subset, process resource subset and scenario resource subset that do not match the training requirements information, and the number and proportion of mismatched resource items in each resource subset are counted. Based on the statistical results of mismatched resource items, the combination ratio of each resource subset is adjusted to increase the proportion of resource items that match the training needs information in the corresponding subset, and to reduce or remove mismatched resource items, so that the content of the equipment resource subset, process resource subset and scenario resource subset is highly consistent with the training needs information. To address the differences in presentation order adaptation, we analyzed the interaction sequence of the initial resource collaboration scheme and its compatibility with the cognitive patterns and operational habits of the trainees, identifying the links with unreasonable timing. Based on cognitive patterns and operational habits, the interaction sequence of resource collaboration combination schemes is optimized, and the presentation order of unreasonable steps is adjusted so that the presentation order of equipment operation, process execution and scenario response conforms to the learning logic of the trainees. To address the differences in display proportion among adaptation discrepancies, we analyzed the correspondence between the presentation identifiers of the initial resource collaboration combination scheme and the training focus theme information, and identified resource content with unreasonable proportion allocation. Based on the training focus topic information, adjust the presentation labels of resource collaboration combination schemes, increase the display ratio of resource items corresponding to the training focus topic content, increase their presentation frequency and display duration in the simulation training scenario, and adjust the display ratio of non-focus topic content. Optimize the association method of resource collaboration combination scheme. Based on the adjusted combination ratio, interaction sequence and presentation identifier, redefine the association logic of device resource subset, process resource subset and scenario resource subset, strengthen the association strength between focused theme resource items, and adjust the association between non-focused theme resource items. By integrating and adjusting the combination ratios, optimizing the interaction sequence, adjusting the presentation identifiers, and redefining the association logic, an optimized resource collaboration combination scheme is generated.

9. The method for constructing a hydropower station simulation training system based on multi-source collaboration according to claim 5, characterized in that, Based on the identification results, the linkage rules of the multi-directional interaction link are optimized. The optimization operation includes data matching rule optimization, linkage response timing rule optimization, and feedback adjustment rule optimization. Based on the analysis of data items that failed to match in the feedback optimization dataset, the reasons for the matching failure were identified. These reasons included inconsistent data formats, inconsistent data identifiers, and unclear association logic. According to the identified reasons, the following revision operations were performed: when the reason was inconsistent data formats, the format matching standard in the data matching rules was revised to achieve format uniformity between training behavior data and resource interaction data; when the reason was inconsistent data identifiers, the data identifier matching rules were revised to maintain consistency in the identifier coding rules of the two types of data. When the reason is unclear association logic, improve the association logic matching clauses to clarify the association conditions and judgment criteria for different types of data; at the same time, perform key feature extraction and verification logic addition operations, extract key feature information from training behavior data and resource interaction data, establish secondary matching verification logic based on key feature information, and add the verification logic to the data matching rules for secondary matching when the first matching fails. Based on the analysis of the linkage response time data in the feedback optimization dataset, the links in which the response time exceeds the set time threshold are identified. These links include data transmission links, data processing links, and rule execution links. According to the identified links, the following adjustment operations are performed: for the data transmission link, the data transmission path is optimized to reduce the number of relay nodes in the data transmission process; for the data processing link, the data processing logic is optimized to improve data processing efficiency. For the rule execution phase, the rule execution order is adjusted to prioritize the execution of core linkage logic; Based on the analysis of valid feedback adjustment data in the feedback optimization dataset, the reasons for ineffective adjustments are identified. These reasons include adjustments deviating from requirements, adjustments not matching the scenario, and adjustments being made at inappropriate times. According to the identified reasons, the following improvements are implemented: When the reason is that the adjustment direction deviates from requirements, the adjustment direction determination logic in the feedback adjustment rules is improved to accurately determine the adjustment direction by combining training needs information and training behavior data; when the reason is that the adjustment magnitude does not match the scenario, the adjustment magnitude setting logic in the feedback adjustment rules is optimized to dynamically adjust the adjustment magnitude based on changes in the scenario; when the reason is that the adjustment timing is inappropriate, the adjustment timing trigger conditions in the feedback adjustment rules are adjusted to determine the optimal adjustment timing based on data interaction frequency and the rate of scenario change. After optimizing the data matching rules, the linkage response timing rules, and the feedback adjustment rules, the optimized rule logics are integrated to form the optimized multi-directional interactive link linkage rules.

10. A system for constructing a multi-source collaborative hydropower station simulation training system, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the method for constructing a multi-source collaborative hydropower station simulation training system according to any one of claims 1 to 9 by executing the machine-executable instructions.

Images