Power plant equipment dismounting simulation management system and method based on BIM

Abstract

The invention discloses a BIM-based power plant equipment dismounting simulation management system and method, and relates to the related field of equipment dismounting simulation management, and the system comprises a building module which is used for building a BIM after the data collection of power plant equipment; the recording module is used for executing real-time operation recording and establishing an operation record data set and a response data set; the first detection module is used for carrying out dismounting credible detection on the operation record data set; the second detection module is used for carrying out response conflict detection on the response data set by utilizing the conflict channel; the fusion authentication module is used for performing time sequence correlation analysis on the first dismounting simulation detection result and the second dismounting simulation detection result to generate a fusion authentication result; and the management module is used for carrying out dismounting simulation management. The technical problem that safety and accuracy of disassembly and assembly operation are difficult to comprehensively and accurately assess in existing equipment disassembly and assembly management is solved, and the technical effect of comprehensively and accurately assessing safety and accuracy of disassembly and assembly operation is achieved.

Description

Technical Field

[0001] This application relates to the field of equipment disassembly and assembly simulation management, and particularly to a BIM-based power plant equipment disassembly and assembly simulation management system and method. Background Art

[0002] In the maintenance and management of power plant equipment, ensuring the accuracy and safety of the disassembly and assembly process is of crucial importance. Incorrect disassembly and assembly operations may not only cause equipment damage but also lead to safety accidents, posing a serious threat to the normal operation of the power plant and the safety of personnel. Currently, the main method to solve the problems of the accuracy and safety of power plant equipment disassembly and assembly is to rely on traditional drawings and on-site experience for disassembly and assembly operations. Due to insufficient details or untimely updates of the drawings, it is difficult for operators to accurately understand the equipment structure and disassembly and assembly steps. On-site experience is limited by the personal abilities and experience levels of operators and lacks unified standards and standardized guidance. These problems may lead to misoperations during the disassembly and assembly process, increasing the risks of equipment damage and safety.

[0003] In the current related technologies, there are technical problems in the disassembly and assembly management of power plant equipment, such as it being difficult to comprehensively and accurately evaluate the safety and accuracy of disassembly and assembly operations. Summary of the Invention

[0004] This application provides a BIM-based power plant equipment disassembly and assembly simulation management system and method. By collecting data on power plant equipment, including equipment parameters and installation space data, establishing a BIM model based on these data, when the user starts to perform a simulated disassembly and assembly operation, the operation process is recorded in real time to generate an operation record data set, and the response data set of the BIM model is synchronously updated. The operation record data set is analyzed to detect the rationality and credibility of the disassembly and assembly operation, generating a first disassembly and assembly simulation detection result. Conflict channels are set based on the BIM model to perform conflict detection on the response data set to identify potential disassembly and assembly conflicts, generating a second disassembly and assembly simulation detection result. The first and second disassembly and assembly simulation detection results are subjected to temporal correlation analysis, comprehensively considering the temporal logic and conflict situations of the disassembly and assembly operation, generating a fusion authentication result. According to the fusion authentication result, technical means such as managing the disassembly and assembly simulation process are adopted to achieve the technical effect of comprehensively and accurately evaluating the safety and accuracy of disassembly and assembly operations.

[0005] The present application provides a BIM-based disassembly and assembly simulation management system for power plant equipment, including: a building module, configured to build a BIM model after collecting data of power plant equipment, where the data collection includes collecting equipment parameter data and installation space data; a recording module, configured to perform real-time operation recording when the user starts to execute disassembly and assembly simulation, and establish an operation record data set and a response data set of the BIM model; a first detection module, configured to perform disassembly and assembly credibility detection on the operation record data set to generate a first disassembly and assembly simulation detection result; a second detection module, configured to set a conflict channel based on the BIM model, perform response conflict detection on the response data set using the conflict channel, and establish a second disassembly and assembly simulation detection result; a fusion authentication module, configured to perform time-series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result; a management module, configured to perform disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

[0006] In a possible implementation manner, the first detection module includes: a disassembly and assembly simulation module, configured to perform disassembly and assembly simulation of power plant equipment using the BIM model to establish a disassembly and assembly simulation set; a disassembly and assembly sequence constraint building module, configured to build disassembly and assembly sequence constraints according to the disassembly and assembly simulation set, where the disassembly and assembly sequence constraints include floating sequence constraints and fixed sequence constraints; a disassembly and assembly credibility detection module, configured to perform disassembly and assembly credibility detection on the operation record data set through the disassembly and assembly sequence constraints to generate a sequence simulation detection result; a disassembly and assembly time node parsing module, configured to parse disassembly and assembly time nodes of the operation record data set to establish a disassembly and assembly window for components; a window length distribution evaluation module, configured to perform window length distribution evaluation of the disassembly and assembly window for components to generate a window simulation detection result; a first disassembly and assembly simulation detection result generation module, configured to generate a first disassembly and assembly simulation detection result according to the sequence simulation detection result and the window simulation detection result.

[0007] In a possible implementation manner, the disassembly and assembly credibility detection module includes: a floating component positioning module, configured to position floating components according to the floating sequence constraints; a first credibility detection standard generation module, configured to obtain the component criticality of floating components and generate a first credibility detection standard according to the component criticality; a second credibility detection standard generation module, configured to obtain the component collision risk level of floating components and generate a second credibility detection standard according to the collision risk level; a floating component disassembly and assembly credibility detection module, configured to perform disassembly and assembly credibility detection of floating components using the first credibility detection standard and the second credibility detection standard to establish the sequence simulation detection result.

[0008] In a possible implementation manner, the window length distribution evaluation module includes: a component calibration disassembly time establishment module, configured to establish the minimum disassembly granularity of components, perform simulation disassembly of the BIM model according to the minimum disassembly granularity, and establish the component calibration disassembly time; a standard component time allocation ratio establishment module, configured to establish a standard component time allocation ratio according to the component calibration disassembly time; a ratio distribution evaluation module, configured to perform ratio distribution evaluation of the component disassembly and assembly windows by using the standard component time allocation ratio, and generate a ratio distribution evaluation result; a component disassembly and assembly evaluation result establishment module, configured to perform one-by-one window comparison of the component disassembly and assembly windows by using the component calibration disassembly time, and establish a component disassembly and assembly evaluation result; a window simulation detection result generation module, configured to generate a window simulation detection result according to the ratio distribution evaluation result and the component disassembly and assembly evaluation result.

[0009] In a possible implementation manner, the second detection module includes: a first conflict sub-channel construction module, configured to establish a fixed space constraint according to the installation space data, and construct a first conflict sub-channel based on the fixed space constraint; a second conflict sub-channel establishment module, configured to obtain the device component structure according to the BIM model, establish a fixed component constraint according to the device component structure, and establish a second conflict sub-channel by using the fixed component constraint; a conflict channel establishment module, configured to set a dynamic conflict sub-channel, where the dynamic conflict sub-channel is dynamically updated based on the response data set, and establish a conflict channel by using the first conflict sub-channel, the second conflict sub-channel, and the dynamic conflict sub-channel to complete response conflict detection.

[0010] In a possible implementation manner, the fusion authentication module includes: a time series alignment module, configured to perform time series alignment on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result; a delayed correlation search module, configured to extract a reference comparison node from the first disassembly and assembly simulation detection result, and perform a delayed correlation search on the second disassembly and assembly simulation detection result mapped by time series alignment to establish a search matching result; a detection cross-validation module, configured to perform detection cross-validation by using the search matching result to establish the fusion authentication result.

[0011] In a possible implementation manner, the management module includes: a personal profile creation module, configured to create a personal profile of a user; a disassembly and assembly weak data generation module, configured to generate disassembly and assembly weak data according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result; a personal profile update module, configured to update the disassembly and assembly weak data to the personal profile for disassembly and assembly simulation management of the user.

[0012] In a possible implementation manner, the personal profile update module includes: a periodic intensive training plan generation module, configured to generate a periodic intensive training plan according to the disassembly and assembly weak data and user data, and establish a timing feedback node; a periodic intensive training detection module, configured to perform periodic intensive training detection of a user at the timing feedback node, and establish a detection data set; a reinforcement compensation module, configured to generate a reinforcement compensation by using the detection data set, optimize the periodic intensive training plan based on the reinforcement compensation, and perform user management according to the optimized periodic intensive training plan.

[0013] In a possible implementation manner, the system further includes: a training module, configured to activate voice guidance and operation guidance when a user starts to perform simulation training, and perform training prompt management of the user by using the voice guidance and the operation guidance.

[0014] In a possible implementation manner, the training module includes: a warning correction module, configured to identify an operation deviation between an actual operation of a user and an operation guidance, establish a correction guidance based on the operation deviation, and report an operation anomaly warning.

[0015] This application further provides a BIM-based disassembly and assembly simulation management method for power plant equipment, including: after data collection of power plant equipment, establishing a BIM model, where the data collection includes equipment parameter data collection and installation space data collection; when a user starts to perform simulation disassembly and assembly, performing real-time operation recording, establishing an operation record data set and a response data set of the BIM model; performing disassembly and assembly credibility detection on the operation record data set to generate a first disassembly and assembly simulation detection result; setting a conflict channel based on the BIM model, performing response conflict detection on the response data set by using the conflict channel, and establishing a second disassembly and assembly simulation detection result; performing time series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result; and performing disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

[0016] A BIM-based power plant equipment disassembly and assembly simulation management system and method proposed in this application, after collecting data on power plant equipment, establishes a BIM model through an establishment module. The data collection includes the collection of equipment parameter data and installation space data. When the user starts to perform the simulation of disassembly and assembly, the recording module executes real-time operation records, establishes an operation record data set and a response data set of the BIM model. The first detection module performs disassembly and assembly credibility detection on the operation record data set to generate a first disassembly and assembly simulation detection result. Based on the BIM model, the second detection module sets a conflict channel, uses the conflict channel to perform response conflict detection on the response data set, and establishes a second disassembly and assembly simulation detection result. The fusion authentication module performs time-series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result. The management module performs disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result. It achieves the technical effect of comprehensively and accurately evaluating the safety and accuracy of disassembly and assembly operations. Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of this application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in sequence. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0018] Figure 1 It is a schematic structural diagram of a BIM-based power plant equipment disassembly and assembly simulation management system provided by an embodiment of this application.

[0019] Figure 2 It is a schematic flowchart of a BIM-based power plant equipment disassembly and assembly simulation management method provided by an embodiment of this application.

[0020] Description of the reference numerals: establishment module 10, recording module 20, first detection module 30, second detection module 40, fusion authentication module 50, management module 60. Detailed Embodiments

[0021] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the specific embodiments of this application.

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be construed as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0023] In the following description, reference is made to "some embodiments", which describe subsets of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first / second" are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0024] The embodiments of this application provide a BIM-based disassembly and assembly simulation management system for power plant equipment, as Figure 1 shown. The system includes:

[0025] A building module 10, configured to establish a BIM model after collecting data of power plant equipment. The data collection includes collection of equipment parameter data and installation space data.

[0026] Specifically, through on-site measurement, referring to equipment manuals, or data provided by equipment manufacturers, physical and performance parameters such as the size, weight, material, and interface information of power plant equipment are collected. These parameters are input into the system using professional data collection software or tools. Technologies such as three-dimensional laser scanners or drone aerial photography are used to accurately scan the equipment installation area to obtain three-dimensional point cloud data of the site. The point cloud data is imported into BIM software, and a three-dimensional model of the installation space is generated through software processing. In the BIM software, a three-dimensional model of the power plant equipment is created based on the collected equipment parameters and installation space data. By adjusting the scale, position, and orientation of the model, the model is ensured to be consistent with the actual situation. Attribute information of the equipment, such as name, model, manufacturer, etc., is added.

[0027] A recording module 20, configured to perform real-time operation recording when the user starts to execute the simulation disassembly and assembly, and establish an operation record data set and a response data set of the BIM model.

[0028] Specifically, when the user conducts disassembly and assembly simulation through a virtual reality (VR) or augmented reality (AR) interface, the system captures the user's operation actions in real time. The operation actions are converted into a data form, and information such as the time, type (such as rotation, movement, connection, etc.), and operation object of each operation step is recorded. According to the user's operations, the system updates the state of the BIM model in real time and records the changes in the model during disassembly and assembly, such as the movement of components and the change of connection states.

[0029] The first detection module 30 is used to perform disassembly and assembly credibility detection on the operation record data set and generate a first disassembly and assembly simulation detection result.

[0030] Specifically, by analyzing the operation record data set through algorithms, it is checked whether the disassembly and assembly sequence meets the requirements of the equipment manual (an official document containing information such as equipment operation, maintenance, disassembly, and assembly), whether the disassembly and assembly time allocation is reasonable, whether there are overly long stagnant times or unnecessary repeated operations, and whether there are operations that may cause damage or safety hazards. For example, a topological sorting algorithm based on graph theory is used, combined with the disassembly and assembly sequence constraints in the equipment manual, to analyze the operation sequence in the operation record data set and determine whether it meets the preset disassembly and assembly sequence requirements. A sliding window algorithm is used to analyze the time series in the operation record data set to identify whether there are overly long stagnant times or unnecessary repeated operations. Combining the safety specifications in the equipment manual, a rule engine algorithm is used to analyze the operation record data set to identify operations that may cause damage or safety hazards. According to the detection results, a report containing information such as the rationality of the disassembly and assembly sequence, the efficiency of time allocation, and the identification of weak points is generated.

[0031] Furthermore, the present application provides a specific implementation method. In this implementation method, the first detection module 30 includes: a disassembly and assembly simulation module for using the BIM model to perform disassembly and assembly simulation of power plant equipment and establishing a disassembly and assembly simulation set; a disassembly and assembly sequence constraint establishment module for establishing disassembly and assembly sequence constraints according to the disassembly and assembly simulation set, where the disassembly and assembly sequence constraints include floating sequence constraints and fixed sequence constraints; a disassembly and assembly credibility detection module for performing disassembly and assembly credibility detection on the operation record data set through the disassembly and assembly sequence constraints and generating a sequence simulation detection result; a disassembly and assembly time node parsing module for parsing the disassembly and assembly time nodes of the operation record data set and establishing a component disassembly and assembly window; a window length distribution evaluation module for performing window length distribution evaluation on the component disassembly and assembly window and generating a window simulation detection result; and a first disassembly and assembly simulation detection result generation module for generating a first disassembly and assembly simulation detection result according to the sequence simulation detection result and the window simulation detection result.

[0032] Specifically, by using the established BIM model, the disassembly and assembly process of equipment is simulated through virtual simulation technology, and virtual disassembly and assembly operations are performed on power plant equipment. Record the components, tools, operation sequence, and relevant physical parameters (such as force, displacement, time, etc.) involved in each disassembly and assembly operation. Establish a disassembly and assembly simulation set, which contains all possible disassembly and assembly schemes and their corresponding operation sequences and physical parameters.

[0033] Analyze each disassembly and assembly scheme in the disassembly and assembly simulation set to extract the operation sequence. The operation sequence refers to the order of component disassembly and assembly. For example, first disassemble component A, then disassemble component B, and finally disassemble component C. Disassembly and assembly order constraints are divided into floating order constraints and fixed order constraints. Floating order constraints allow the disassembly and assembly order of components to be adjusted within a certain range, that is, for some components, their disassembly and assembly order can be adjusted within a certain range, but other fixed order constraints cannot be violated. For example, either component A or component B can be disassembled first, but they must both be completed before disassembling component C. Fixed order constraints require disassembly and assembly to be carried out in a specific order. Fixed order constraints are based on equipment manuals or industry specifications to determine that certain components must be disassembled and assembled in a specific order. For example, the equipment manual stipulates that component B must be disassembled before component A, and this order is fixed and cannot be changed.

[0034] For example, the disassembly and assembly simulation set of a certain power plant equipment contains the following two disassembly and assembly schemes: Scheme 1: A → B → C → D, Scheme 2: B → A → C → D. By analyzing the operation sequence, the following disassembly and assembly order constraints can be extracted: Fixed order constraint: C must be disassembled before D. Floating order constraint: The disassembly and assembly order of A and B can be interchanged, but must be completed before C.

[0035] Compare the actual disassembly and assembly operation records (operation record data set) performed by the user with the disassembly and assembly order constraints. Check whether each step in the operation record data set meets the requirements of the disassembly and assembly order constraints. Generate an order simulation detection result, indicating which operations violate the constraints and which operations are compliant.

[0036] For each component, extract the start and end time points of its disassembly and assembly from the operation record data set. For example, record the start time of component A's disassembly as T1 and the end time as T2. Based on the extracted time nodes, establish a disassembly and assembly window for each component, indicating the time range required for the disassembly and assembly of the component. Record the disassembly and assembly windows of all components to form a component disassembly and assembly window set.

[0037] For example, the operation record dataset is shown in Table 1. By analyzing the operation record dataset, the disassembly and assembly time nodes of each component can be extracted: the disassembly and assembly time nodes of component A: start time T1, completion time T2. The disassembly and assembly time nodes of component B: start time T3, completion time T4. Further establish disassembly and assembly windows: A: [T1, T2]; B: [T3, T4].

[0038] Table 1: Operation record dataset

[0039] Operation time Operation type Operation object T1 Start disassembly A T2 Complete disassembly A T3 Start disassembly B T4 Complete disassembly B

[0040] Calculate the length of the disassembly and assembly window for each component, that is, the difference between the completion time and the start time. For example, the window length of component A is T2 - T1. Conduct statistical analysis on the window lengths of all components, and calculate statistical indicators such as the average value, maximum value, and minimum value. By comparing the window lengths of each component, identify the components with overly long disassembly and assembly times. These components may be bottlenecks or lengthy processes during disassembly and assembly, generate window simulation detection results, indicating which components have overly long disassembly and assembly times and which components have relatively reasonable disassembly and assembly times.

[0041] For example, the disassembly and assembly windows are shown in Table 2. Through statistical analysis: average window length: (5 + 10 + 3 + 8) / 4 = 6.5 minutes, maximum window length: 10 minutes (component B), minimum window length: 3 minutes (component C). According to the analysis results, it can be identified that component B has the longest disassembly and assembly time and may be a bottleneck or lengthy process during disassembly and assembly.

[0042] Table 2: Component disassembly and assembly windows

[0043] Component Disassembly and assembly window Window length A [T1,T2] T2 - T1 = 5 minutes B [T3,T4] T4 - T3 = 10 minutes C [T5,T6] T6 - T5 = 3 minutes D [T7,T8] T8 - T7 = 8 minutes

[0044] Integrate the sequential simulation detection results and the window simulation detection results to generate the first disassembly and assembly simulation detection results. The results include an evaluation of the compliance of the disassembly and assembly sequence, an analysis of the reasonableness of the disassembly and assembly time, and possible improvement suggestions. This implementation method ensures that the actual disassembly and assembly operations performed by users meet the requirements of the equipment manual or industry specifications through the disassembly and assembly sequence constraint establishment module and the disassembly and assembly credibility detection module, avoiding incorrect or illegal operations. Through the disassembly and assembly time node parsing module and the window length distribution evaluation module, identify bottlenecks or lengthy processes during disassembly and assembly, providing data support for optimizing the disassembly and assembly time allocation. These steps and modules work together to enable the BIM-based power plant equipment disassembly and assembly simulation management system to provide users with more accurate and reliable disassembly and assembly simulation results, thereby providing strong technical support for the maintenance, repair, and upgrade of power plant equipment.

[0045] In a possible implementation, the disassembly and assembly trust detection module includes: a floating component positioning module for positioning floating components according to the floating sequence constraint; a first trust detection standard generation module for obtaining the component criticality of floating components and generating a first trust detection standard according to the component criticality; a second trust detection standard generation module for obtaining the component collision risk level of floating components and generating a second trust detection standard according to the collision risk level; and a floating component disassembly and assembly trust detection module for performing disassembly and assembly trust detection of floating components by using the first trust detection standard and the second trust detection standard to establish the sequential simulation detection result.

[0046] Specifically, obtain the defined floating sequence constraints from the disassembly and assembly sequence constraint establishment module. These constraints describe which components can adjust their sequences within a certain range during disassembly and assembly. Using the component information in the BIM model, identify all components that meet the floating sequence constraints, i.e., floating components. Assign a unique identifier to each floating component for reference in subsequent steps.

[0047] Extract the attribute information of components from the equipment manual, historical maintenance records, data provided by the equipment manufacturer, and the BIM model, including the importance, functional complexity, and maintenance frequency of the components. Score the components according to their functional importance in the equipment (high scores for critical components and low scores for non-critical components). Score the components according to their functional complexity (high scores for components with complex functions and low scores for simple components). Score the components according to their historical maintenance frequency (high scores for components with high maintenance frequencies and low scores for low frequencies). Perform a weighted sum of the above indicators to obtain the comprehensive criticality score of each component. According to the scoring results, set a criticality threshold for judging the credibility of components during disassembly and assembly. For example, components with scores higher than the threshold are considered high-criticality components and need to strictly follow the disassembly and assembly sequence and operation specifications.

[0048] For example, in a power plant equipment, there are three floating components A, B, and C, and their attribute information is shown in Table 3. Set the weights as follows: importance weight 0.4, functional complexity weight 0.3, and maintenance frequency weight 0.3. Calculate the comprehensive criticality score: Component A: 8×0.4 + 7×0.3 + 6×0.3 = 7.1; Component B: 5×0.4 + 4×0.3 + 3×0.3 = 4.1; Component C: 9×0.4 + 8×0.3 + 7×0.3 = 8.1. Set the criticality threshold as 6.0. Then: The criticality scores of components A and C are higher than the threshold and belong to high-criticality components. The criticality score of component B is lower than the threshold and belongs to low-criticality components.

[0049] Table 3: Component criticality attribute information

[0050] Component Importance score Functional complexity score Maintenance frequency score A 8 7 6 B 5 4 3 C 9 8 7

[0051] Extract the geometry, material properties, functional importance and other information of the components from the BIM model. Score the components according to their shape complexity (components with complex shapes are more likely to collide and have high scores). Score the components according to the brittle properties of the materials (components with brittle materials have high collision sensitivity and high scores). Score the components according to their functional importance (key functional components have high collision sensitivity and high scores). Weighted sum the above indicators to obtain the collision sensitivity score of each component. According to the scoring results, the components are divided into different collision risk levels, such as low risk, medium risk and high risk. The level division here is based on the tolerance of the components to collision, that is, the more collision-sensitive the components are, the higher their risk level. For each collision risk level, set a risk threshold, which represents the maximum collision risk allowed at that level, and is used to determine whether the disassembly and assembly operation is safe. This threshold is set based on industry experience, safety specifications and specific requirements of the components to ensure that the disassembly and assembly operations do not exceed the tolerance range of the components. Among them, collision sensitivity refers to the sensitivity of the components to collision during the disassembly and assembly process, that is, the degree of damage that the components may suffer after collision.

[0052] For example, the attribute information of floating components A, B, and C is shown in Table 4. The weights are set as follows: geometry weight 0.3, material attribute weight 0.3, and function importance weight 0.4. Calculate the collision sensitivity score: component A: 7×0.3+6×0.3+8×0.4=7.1; component B: 4×0.3+5×0.3+5×0.4=4.7; component C: 9×0.3+7×0.3+9×0.4=8.4. According to the scoring results, the collision risk level is divided into: high risk: score greater than or equal to 8.0 (component C); medium risk: score between 6.0 and 7.9 (component A); low risk: score less than 6.0 (component B).

[0053] Table 4: Component collision risk attribute information

[0054]

[0055]

[0056] Based on the operation record data set, analyze the user's operation sequence, operation time, and whether there is a collision risk for each floating component. Apply the first trusted detection standard to check whether the operation exceeds the criticality threshold of the component (for example, whether the high-criticality component is operated correctly). Apply the second trusted detection standard to check whether the operation exceeds the collision risk threshold of the component (for example, whether the high-risk component collides). According to the above standards, determine whether the disassembly and assembly operation is reliable, and generate sequential simulation detection results, indicating which disassembly and assembly operations are reliable and which are not, and give corresponding explanations and suggestions.

[0057] For example, the operation record dataset is shown in Table 5. According to the previous evaluation results: Components A and C are high-criticality components, and Component C is a high-collision-risk component. Apply the first trusted detection criterion to check whether the operation sequence meets the criticality requirements. Components A and C are high-criticality components and the disassembly and assembly sequence needs to be strictly followed. The user operation sequence is A → B → C, which meets the requirements. Apply the second trusted detection criterion to check whether the operation exceeds the collision risk threshold. Component C collides during disassembly, which is a high-risk operation and does not meet the requirements. Generate the sequence simulation detection results: Component A: The operation is trusted. Component B: The operation is trusted. Component C: The operation is not trusted (collision occurs, exceeding the collision risk threshold). The final detection result indicates that there is an untrusted operation when the user disassembles Component C, and it is recommended to re-plan the disassembly and assembly steps to avoid the collision risk.

[0058] Table 5: Operation record dataset

[0059] Operation time Operation type Operation object Operation result [T1,T2] Disassembly A Successful [T3,T4] Disassembly B Successful [T5,T6] Disassembly C Collision

[0060] Through the application of the first trusted detection criterion and the second trusted detection criterion, this implementation method ensures that the disassembly and assembly operations not only meet the requirements of the equipment manual or industry specifications, but also avoid potential safety risks and performance problems. These steps and modules work together to enable the BIM-based disassembly and assembly simulation management system for power plant equipment to provide users with more accurate and reliable disassembly and assembly simulation results, thereby helping users formulate more reasonable and efficient disassembly and assembly strategies and reducing the risks and costs during the disassembly and assembly process.

[0061] In a possible implementation manner, the window length distribution evaluation module includes: a component calibration disassembly time establishment module for establishing the minimum disassembly granularity of a component, performing simulation disassembly of the BIM model according to the minimum disassembly granularity, and establishing the component calibration disassembly time; a standard component time allocation ratio establishment module for establishing a standard component time allocation ratio according to the component calibration disassembly time; a ratio distribution evaluation module for using the standard component time allocation ratio to perform ratio distribution evaluation of the component disassembly and assembly window and generating a ratio distribution evaluation result; a component disassembly and assembly evaluation result establishment module for using the component calibration disassembly time to perform one-by-one window comparison of the component disassembly and assembly window and establishing a component disassembly and assembly evaluation result; and a window simulation detection result generation module for generating a window simulation detection result according to the ratio distribution evaluation result and the component disassembly and assembly evaluation result.

[0062] Specifically, based on the physical characteristics, functional independence, and feasibility of disassembly operations of components, determine the minimum disassembly granularity of each component, that is, the smallest unit that cannot be further subdivided during the disassembly process. For example, check the physical connection methods of components (such as bolt connection, welding, riveting, etc.). If a component is combined with other parts through irreversible or complex connection methods, it needs to be regarded as a whole. Then, use the BIM model to simulate disassembly and record the disassembly time of each component according to the minimum disassembly granularity. Based on the calibrated disassembly time of the components, calculate the proportion of the disassembly time of each component in the total disassembly time, and establish a standard component time allocation ratio to evaluate the balance of the disassembly process. Compare the difference between the proportion of the disassembly time of each component in the actual disassembly process and the standard component time allocation ratio, evaluate the proportion distribution of the component disassembly window, and assess whether the proportion of the disassembly time of each component in the actual disassembly process meets the expected standard component time allocation ratio.

[0063] Use the calibrated disassembly time of the components to compare each component of the component disassembly window one by one, and evaluate the disassembly efficiency and quality of each component, including checking whether the disassembly time exceeds the expectation, whether the disassembly process is smooth, etc. Combining the evaluation results of the proportion distribution and the component disassembly evaluation results, generate a window simulation detection result, which is a comprehensive score or rating used to reflect the overall efficiency and quality of the disassembly process. This implementation method can identify bottlenecks and potential problems in the disassembly process through the proportion distribution evaluation and the component disassembly evaluation results, and more accurately reflect the efficiency and quality of the disassembly process.

[0064] The second detection module 40 is used to set a conflict channel based on the BIM model, use the conflict channel to perform response conflict detection on the response data set, and establish a second disassembly simulation detection result.

[0065] Specifically, preset possible conflict areas or paths in the BIM model, such as component interference caused by narrow space, overlapping movement trajectories, etc. Use the conflict channel to analyze the response data set and check whether physical conflicts or space limitations will occur during the disassembly process. Identify and record the location, cause, and potential consequences of the conflict. According to the detection results, generate a report containing information such as the conflict location, cause, and consequences.

[0066] In a possible implementation, the second detection module 40 includes: a first conflict sub-channel building module, configured to establish a fixed space constraint according to installation space data, and build a first conflict sub-channel based on the fixed space constraint; a second conflict sub-channel establishing module, configured to obtain the structure of device components according to the BIM model, establish a fixed component constraint according to the structure of the device components, and establish a second conflict sub-channel by using the fixed component constraint; a conflict channel building module, configured to set a dynamic conflict sub-channel, where the dynamic conflict sub-channel is dynamically updated based on the response data set, and build a conflict channel by using the first conflict sub-channel, the second conflict sub-channel, and the dynamic conflict sub-channel, so as to complete response conflict detection.

[0067] Specifically, according to the installation space data (the space information required for the installation of power plant equipment, including dimensions, positions, layouts, etc.), determine the space limitations and constraint conditions during the installation of power plant equipment. These constraint conditions include equipment dimensions, installation positions, surrounding obstacles, etc. Use these constraint conditions to build the first conflict sub-channel, which represents the possible conflict areas of the equipment in the fixed space.

[0068] Obtain the structural information of the device components through the BIM model, including component dimensions, shapes, connection relationships, etc. According to this information, establish a fixed component constraint, that is, the constraint conditions formed by the components in the device that cannot be moved or changed in position. Use these fixed component constraints to build the second conflict sub-channel, which represents the possible conflict areas between the internal components of the device.

[0069] Set a dynamic conflict sub-channel, which is dynamically updated based on the response data set. The response data set contains the operations performed by the user during the simulated disassembly and assembly process and the real-time feedback of the BIM model. The dynamic conflict sub-channel can reflect the conflict situation during the disassembly and assembly process in real time. Combine the first conflict sub-channel, the second conflict sub-channel, and the dynamic conflict sub-channel to build a complete conflict channel. This conflict channel is used for comprehensive response conflict detection. This implementation method establishes a comprehensive and accurate conflict detection mechanism by combining fixed space constraints, fixed component constraints, and dynamic response data, which helps to discover and solve potential conflict problems in a timely manner during the disassembly and assembly simulation process.

[0070] The fusion authentication module 50 is configured to perform a sequential correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result, and generate a fusion authentication result.

[0071] Specifically, the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result are correlated in chronological order to check the logical coherence and consistency during the disassembly and assembly process, ensuring the rationality and feasibility of the disassembly and assembly steps. By integrating the two detection results, a fusion certification result is generated, which includes information such as the rationality of the disassembly and assembly sequence, the efficiency of time allocation, the identification of weak points, conflict detection, and proposed improvement measures.

[0072] In a possible implementation manner, the fusion certification module 50 includes: a time series alignment module, configured to perform time series alignment on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result; a delayed correlation search module, configured to extract reference comparison nodes from the first disassembly and assembly simulation detection result and perform a delayed correlation search on the second disassembly and assembly simulation detection result mapped through time series alignment to establish a search matching result; and a detection cross-verification module, configured to use the search matching result to perform detection cross-verification and establish the fusion certification result.

[0073] Specifically, through steps such as timestamp synchronization and time interval adjustment, the timestamps in the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result are compared and calibrated to ensure that they are consistent in the time dimension.

[0074] Key reference comparison nodes are extracted from the first disassembly and assembly simulation detection result. These nodes are important events or turning points during the disassembly and assembly process, such as the disassembly of core components or high-risk components, key steps or dependency points in the disassembly and assembly sequence, etc. They are mapped to the second disassembly and assembly simulation detection result through time series alignment for a delayed correlation search, that is, to find events corresponding to or associated with the reference comparison nodes in the second disassembly and assembly simulation detection result and record the matching situations of these events. Taking the disassembly of component C as an example, the first detection result shows that its disassembly time is too long, and the second detection result finds that there is a spatial conflict between component C and component D during disassembly. This indicates that the long disassembly time of component C is not an operation problem but due to the spatial conflict. Such inconsistent detection results reveal potential operation path problems, and it is necessary to optimize the disassembly path of component C or adjust its spatial relationship with other components to improve the disassembly and assembly efficiency and avoid conflicts.

[0075] Using the search matching results obtained by the delayed association search module, cross-verify the first disassembly and assembly simulation detection results and the second disassembly and assembly simulation detection results, including evaluating the accuracy, consistency, integrity, etc. of the matching results. Through cross-verification, further confirm the relevance and reliability between the two detection results. This implementation method can ensure that the first disassembly and assembly simulation detection results and the second disassembly and assembly simulation detection results are consistent in the time dimension through steps such as time series alignment, delayed association search, and detection cross-verification, and the relevance and reliability between the two are further confirmed, which helps to improve the accuracy and reliability of the entire disassembly and assembly simulation management system, thereby guiding the optimization of the subsequent disassembly and assembly process and improving the disassembly and assembly efficiency and quality.

[0076] The management module 60 is used to perform disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

[0077] Specifically, according to the disassembly and assembly simulation detection results and the fusion authentication result, optimize and adjust the disassembly and assembly plan. Formulate a detailed disassembly and assembly plan, including time, personnel, tools, steps, etc. Archive and save all data during the disassembly and assembly simulation process (including operation records, detection results, authentication reports, etc.). Provide a convenient query function to facilitate users to consult relevant data and information at any time. In the embodiment of the present application, data collection is performed on power plant equipment, including equipment parameters and installation space data. Based on these data, a BIM model is established. When the user starts to perform the simulation disassembly and assembly operation, the operation process is recorded in real time to generate an operation record data set, and the response data set of the BIM model is synchronously updated. Analyze the operation record data set to detect the rationality and credibility of the disassembly and assembly operation, and generate the first disassembly and assembly simulation detection result. Set conflict channels based on the BIM model to perform conflict detection on the response data set to identify potential disassembly and assembly conflicts, and generate the second disassembly and assembly simulation detection result. Perform time series correlation analysis on the first and second disassembly and assembly simulation detection results, comprehensively consider the time series logic and conflict situation of the disassembly and assembly operation, generate the fusion authentication result, and manage the disassembly and assembly simulation process according to the fusion authentication result and other technical means, achieving the technical effect of comprehensively and accurately evaluating the safety and accuracy of the disassembly and assembly operation.

[0078] In a possible implementation manner, the management module 60 includes: a personal profile creation module for creating a user's personal profile; a disassembly and assembly weak data generation module for generating disassembly and assembly weak data according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result; and a personal profile update module for updating the disassembly and assembly weak data to the personal profile for the disassembly and assembly simulation management of the user.

[0079] Specifically, when the user first uses the system, the system creates an independent personal profile through the user registration information (such as name, ID, permissions, etc.). This profile is a database record that stores the user's personal information, learning progress, disassembly and assembly simulation scores, etc., and is used to track the user's disassembly and assembly simulation learning and management.

[0080] Based on the first disassembly and assembly simulation test results (such as incorrect disassembly and assembly sequence, time node issues), the second disassembly and assembly simulation test results (such as spatial conflicts, component collisions), and the fusion authentication results (such as timing mismatches, cross-verification failures), the system, through algorithm analysis, identifies the weak links in the user's disassembly and assembly simulation and generates disassembly and assembly weak data (weak points or error points during the user's disassembly and assembly process). For example, a rule-based expert system algorithm is adopted, combined with the disassembly and assembly specifications in the equipment manual and historical maintenance data, to analyze the user's operation record data set. According to the preset rule library, this algorithm identifies common error patterns in the user's operations (such as incorrect disassembly and assembly sequence, excessive operation time, collision risks, etc.). The specific implementation is as follows: Extract information such as disassembly and assembly sequence, operation specifications, and safety requirements from the equipment manual, and combine with historical maintenance data to form a set of rule libraries. For example, the rule library contains fixed sequence rules such as "Component B must be disassembled before component A" and time constraint rules such as "The disassembly time of component C shall not exceed 10 minutes". Match the user's operation record data set with the rule library to identify operations that violate the rules. For example, if the user disassembles component A without first disassembling component B, the rule match is triggered, and this operation is recorded as an incorrect disassembly and assembly sequence. According to the rule match results, generate disassembly and assembly weak data, including error types (such as sequence error, time overrun, collision risk, etc.), occurrence frequency, specific operation steps, and other information. At the same time, use the clustering analysis algorithm to classify the user's operation data and identify operation weak links with similar characteristics, so as to generate detailed disassembly and assembly weak data. The specific implementation is as follows: Normalize the user's operation record data set and extract key features such as operation time, operation sequence, operation object, etc. Use the K-Means clustering algorithm to divide the user's operation data into multiple clusters. Each cluster represents an operation mode. For example, one cluster may contain all operations with excessive disassembly time, and another cluster may contain all operations with incorrect disassembly and assembly sequences. Analyze the characteristics of each cluster to identify operation weak links with similar characteristics. For example, if most operations in a certain cluster have a disassembly time exceeding 10 minutes, it is considered that the operations represented by this cluster have a weak link of time overrun. Combine the clustering results with data such as the user's learning progress and historical scores to further refine the weak data. For example, for users with a slower learning progress, focus on their weak links of time overrun in operations; for users who make mistakes frequently, focus on their weak links of incorrect disassembly and assembly sequences. Combine the preliminary weak data generated by the rule-based expert system algorithm with the results of the clustering analysis algorithm to generate the final disassembly and assembly weak data. For example, if the rule match finds that the user has an incorrect sequence when disassembling component A, and the clustering analysis finds that the user's operation time when disassembling component A is generally long, then both the sequence error and time overrun issues will be recorded in the final weak data.By adding new records or updating existing records in the database, disassembling and assembling weak data (such as error types, occurrence frequencies, severity levels, etc.) is updated to the user's personal profile for subsequent tracking and evaluation. This implementation method realizes the comprehensive tracking and management of the user's disassembly and assembly simulation learning by creating a personal profile, generating disassembly and assembly weak data, and updating the personal profile, so as to provide the user with a personalized learning path and training suggestions, and help the user better master the disassembly and assembly skills of power plant equipment.

[0081] In a possible implementation, the personal profile update module includes: a periodic intensive training plan generation module, configured to generate a periodic intensive training plan according to the disassembly and assembly weak data and user data, and establish a time-series feedback node; a periodic intensive training detection module, configured to perform periodic intensive training detection on the user at the time-series feedback node and establish a detection data set; a reinforcement compensation module, configured to generate reinforcement compensation by using the detection data set, optimize the periodic intensive training plan based on the reinforcement compensation, and perform user management according to the optimized periodic intensive training plan.

[0082] Specifically, collect and analyze the user's disassembly and assembly weak data (such as common disassembly and assembly errors, inaccurate time node control, etc.) and user data (such as learning progress, historical scores, etc.). Based on this data, use an algorithm to generate a personalized periodic intensive training plan, including the content, difficulty, frequency of training, and the goals of each training stage. For example, use a genetic algorithm to optimize the training plan, and continuously iterate to generate a better training plan by simulating the natural selection process. The specific implementation is as follows: generate an initial population of training plans according to the user data and disassembly and assembly weak data. Each training plan includes parameters such as training content, difficulty, frequency, and goals. Define a fitness function to evaluate the quality of each training plan. The fitness function takes into account the user's learning progress, historical scores, and weak link factors. For example, if a training plan can effectively improve the user's performance in terms of disassembly and assembly sequence errors, its fitness is relatively high. Through genetic operations such as selection, crossover, and mutation, continuously iterate to generate a better training plan. The selection operation selects excellent training plans according to the fitness function; the crossover operation exchanges some parameters of two training plans; the mutation operation randomly changes some parameters to introduce new mutations. After multiple generations of iteration, finally generate an optimized periodic intensive training plan. This plan can dynamically adjust the training content and difficulty according to the user's weak links and learning progress.

[0083] Meanwhile, the Bayesian network algorithm is combined to infer and analyze user data, predict the performance of users in subsequent training, and thus customize personalized training content and progress for each user. The specific implementation is as follows: A Bayesian network model is constructed based on user data and disassembly and assembly weak data. Nodes in the model include the learning progress, historical scores, weak links, etc. of users, as well as the probability relationships between these nodes. The Bayesian network is used to infer and analyze user data to predict the performance of users in subsequent training. For example, according to the current learning progress and historical scores of users, the improvement probability in terms of incorrect disassembly and assembly sequence is predicted. According to the results of the inference and analysis, personalized training content and progress are customized for each user. For example, if the predicted improvement probability of a user in terms of incorrect disassembly and assembly sequence is low, the difficulty and frequency of relevant training content are increased; if a user performs well in terms of exceeding the time limit, the relevant training content is appropriately reduced. The optimized solution generated by the genetic algorithm is combined with the inference and analysis results of the Bayesian network to generate the final cycle reinforcement training plan. For example, if the genetic algorithm recommends increasing the difficulty of a certain training content, and the Bayesian network predicts that the user has a high improvement probability in this content, both aspects of the suggestions will be considered in the final training plan. Meanwhile, time series feedback nodes are established, which are used to monitor and evaluate the progress of users in each training stage.

[0084] At the time series feedback nodes, cycle reinforcement training detection is performed on users, including a series of tests or simulated disassembly and assembly tasks, which are used to evaluate the progress and remaining problems of users during training. The detection results of users are collected to generate a detection data set. Based on the detection data set, the performance and existing problems of users in training are analyzed to generate reinforcement compensation, which includes additional training content, targeted guidance or suggestions, and adjustment of the training plan. The cycle reinforcement training plan is optimized according to the reinforcement compensation to ensure that users can more effectively improve their disassembly and assembly skills in the next training. The optimized training plan is used to guide the subsequent learning and management of users. This implementation method generates a personalized training plan that meets the needs of users by collecting and analyzing the disassembly and assembly weak data and user data of users, ensuring the effectiveness and pertinence of training. By setting time series feedback nodes, the progress of users during training is tracked and evaluated in real time, and reinforcement compensation and optimized training plans are generated based on the detection data set, which can compensate and improve the deficiencies of users in training in a targeted manner, thereby further improving the disassembly and assembly skills of users.

[0085] In a possible implementation manner, the system further includes: a training module, configured to activate voice guidance and operation guidance when the user starts to perform simulation training, and use the voice guidance and the operation guidance to manage the training prompts of the user.

[0086] Specifically, when the user starts the simulation training mode, the training module will automatically activate the built-in voice guidance system. This system will provide real-time voice prompts and guidance according to the user's training progress and current operations. Among them, the voice guidance is generated through text-to-speech technology and is the audio information used to guide the user's operations. In addition to the voice guidance, the training module will also generate detailed operation guides according to the user's training content and current steps. These guides are presented in the form of text, pictures or animations on the user interface to help the user more intuitively understand the operation steps and precautions. This implementation method can help the user master the disassembly and assembly skills faster, reduce errors and repeated operations, and thus improve the training efficiency by providing real-time voice guidance and operation guides.

[0087] In a possible implementation manner, the training module includes: a warning and correction module, which is used to identify the operation deviation between the user's actual operation and the operation guide, establish a correction guide based on the operation deviation, and report an operation anomaly warning.

[0088] Specifically, the warning and correction module monitors the user's actual operation in real time and compares it with the operation guide provided by the training module. By comparing the differences between the two, the operation deviation of the user is identified. Once the operation deviation is identified, the warning and correction module generates corresponding correction guides according to the type and degree of the deviation. These guides are presented in the form of text, pictures or voice to help the user understand where the deviation is and guide them to perform the correct operation. In addition to generating correction guides, the warning and correction module will also report an operation anomaly warning to the user through the system interface or voice prompt, etc., to attract the user's attention and prompt them to correct the deviation in time. After the user provides a correction operation, the warning and correction module will compare and evaluate the user's operation again to ensure the correction effect. If there are still problems with the corrected operation, the module will repeat the above steps until the user fully masters the correct operation method. This implementation method can timely discover and correct the user's operation deviation by monitoring and comparing the user's actual operation with the operation guide in real time, thereby improving the quality and effect of the simulation training.

[0089] In the above text, reference is made to Figure 1 The BIM-based power plant equipment disassembly and assembly simulation management system according to the embodiments of the present invention has been described in detail. Next, reference will be made to Figure 2 Describe the BIM-based power plant equipment disassembly and assembly simulation management method according to the embodiments of the present invention.

[0090] The BIM-based power plant equipment disassembly and assembly simulation management method according to the embodiments of the present invention is used to solve the technical problem that it is difficult to comprehensively and accurately evaluate the safety and accuracy of disassembly and assembly operations in the existing equipment disassembly and assembly management, and achieve the technical effect of comprehensively and accurately evaluating the safety and accuracy of disassembly and assembly operations.

[0091] The BIM-based disassembly and assembly simulation management method for power plant equipment includes: after collecting data on power plant equipment, a BIM model is established. The data collection includes the collection of equipment parameter data and installation space data. When the user starts to perform the simulation of disassembly and assembly, real-time operation records are executed, and an operation record data set and a response data set of the BIM model are established. The operation record data set is subjected to disassembly and assembly credibility detection to generate a first disassembly and assembly simulation detection result. Conflict channels are set based on the BIM model, and response conflict detection of the response data set is performed using the conflict channels to establish a second disassembly and assembly simulation detection result. Temporal correlation analysis is performed on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result. Disassembly and assembly simulation management is carried out according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

[0092] Among them, the operation record data set is subjected to disassembly and assembly credibility detection to generate a first disassembly and assembly simulation detection result, which can further include: using the BIM model to perform disassembly and assembly simulation of power plant equipment to establish a disassembly and assembly simulation set; establishing disassembly and assembly sequence constraints according to the disassembly and assembly simulation set, and the disassembly and assembly sequence constraints include floating sequence constraints and fixed sequence constraints; performing disassembly and assembly credibility detection on the operation record data set through the disassembly and assembly sequence constraints to generate a sequence simulation detection result; analyzing the disassembly and assembly time nodes of the operation record data set to establish a disassembly and assembly window for components; performing an evaluation of the window length distribution of the disassembly and assembly window for components to generate a window simulation detection result; generating a first disassembly and assembly simulation detection result according to the sequence simulation detection result and the window simulation detection result.

[0093] Among them, performing disassembly and assembly credibility detection on the operation record data set through the disassembly and assembly sequence constraints to generate a sequence simulation detection result can further include: positioning floating components according to the floating sequence constraints; obtaining the component criticality of the floating components, and generating a first credibility detection standard according to the component criticality; obtaining the component collision risk level of the floating components, and generating a second credibility detection standard according to the collision risk level; performing disassembly and assembly credibility detection on the floating components using the first credibility detection standard and the second credibility detection standard to establish the sequence simulation detection result.

[0094] Among them, the evaluation of the window length distribution of the component disassembly and assembly window can further include: establishing the minimum disassembly granularity of the component, performing simulation disassembly of the BIM model according to the minimum disassembly granularity, and establishing the calibrated disassembly time of the component; establishing the standard component time allocation ratio according to the calibrated disassembly time of the component; using the standard component time allocation ratio to evaluate the proportional distribution of the component disassembly and assembly window, and generating a proportional distribution evaluation result; using the calibrated disassembly time of the component to perform one-by-one window comparison of the component disassembly and assembly window, and establishing a component disassembly and assembly evaluation result; generating a window simulation detection result according to the proportional distribution evaluation result and the component disassembly and assembly evaluation result.

[0095] Among them, based on the BIM model, a conflict channel is set, and the response conflict detection of the response data set is performed using the conflict channel to establish a second disassembly and assembly simulation detection result, which can further include: establishing a fixed space constraint according to the installation space data, and building a first conflict sub-channel with the fixed space constraint; obtaining the equipment component structure according to the BIM model, establishing a fixed component constraint according to the equipment component structure, and using the fixed component constraint to establish a second conflict sub-channel; setting a dynamic conflict sub-channel, which is dynamically updated based on the response data set, and using the first conflict sub-channel, the second conflict sub-channel, and the dynamic conflict sub-channel to establish a conflict channel to complete the response conflict detection.

[0096] Among them, performing time-series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result can further include: performing time-series alignment on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result; extracting a reference comparison node from the first disassembly and assembly simulation detection result, and performing delayed correlation search on the second disassembly and assembly simulation detection result mapped by time-series alignment to establish a search matching result; using the search matching result to perform detection cross-verification to establish the fusion authentication result.

[0097] Among them, according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result, disassembly and assembly simulation management can be further included: creating a personal profile for the user; generating disassembly and assembly weak data according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result; updating the disassembly and assembly weak data to the personal profile to perform disassembly and assembly simulation management for the user.

[0098] Among them, updating the disassembly and assembly weak data to the personal file may further include: generating a periodic intensive training plan according to the disassembly and assembly weak data and user data, and establishing a time-series feedback node; performing periodic intensive training detection of the user at the time-series feedback node, and establishing a detection data set; generating an intensive compensation by using the detection data set, optimizing the periodic intensive training plan based on the intensive compensation, and performing user management according to the optimized periodic intensive training plan.

[0099] Among them, the method may further include: when the user starts to perform the simulation training, activating the voice guidance and operation guidance, and using the voice guidance and the operation guidance to perform the training prompt management of the user.

[0100] Among them, using the voice guidance and the operation guidance to perform the training prompt management of the user may further include: identifying the operation deviation between the actual operation of the user and the operation guidance, establishing a correction guidance based on the operation deviation, and reporting an operation exception warning.

[0101] The BIM-based power plant equipment disassembly and assembly simulation management system provided by the embodiments of the present invention can execute the BIM-based power plant equipment disassembly and assembly simulation management method provided by any embodiment of the present invention, and has the corresponding function modules and beneficial effects for executing the method.

[0102] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included various modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0103] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to the design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A BIM-based disassembly and assembly simulation management system for power plant equipment, characterized in that The system includes: A building module, which is used to establish a BIM model after collecting data of power plant equipment. The data collection includes collecting equipment parameter data and installation space data; A recording module, which is used to perform real-time operation recording when the user starts to execute the simulated disassembly and assembly, and establish an operation record data set and a response data set of the BIM model; A first detection module, which is used to perform disassembly and assembly credibility detection on the operation record data set to generate a first disassembly and assembly simulation detection result; A second detection module, which is used to set a conflict channel based on the BIM model, perform response conflict detection on the response data set by using the conflict channel, and establish a second disassembly and assembly simulation detection result; A fusion authentication module, which is used to perform time-series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result; A management module, which is used to perform disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

2. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 1, characterized in that The first detection module includes: A disassembly and assembly simulation module, which is used to perform disassembly and assembly simulation of power plant equipment by using the BIM model to establish a disassembly and assembly simulation set; A disassembly and assembly sequence constraint establishment module, which is used to establish disassembly and assembly sequence constraints according to the disassembly and assembly simulation set. The disassembly and assembly sequence constraints include floating sequence constraints and fixed sequence constraints; A disassembly and assembly credibility detection module, which is used to perform disassembly and assembly credibility detection on the operation record data set through the disassembly and assembly sequence constraints to generate a sequence simulation detection result; A disassembly and assembly time node analysis module, which is used to analyze the disassembly and assembly time nodes of the operation record data set to establish a component disassembly and assembly window; A window length distribution evaluation module, which is used to perform window length distribution evaluation of the component disassembly and assembly window to generate a window simulation detection result; A first disassembly and assembly simulation detection result generation module, which is used to generate a first disassembly and assembly simulation detection result according to the sequence simulation detection result and the window simulation detection result.

3. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 2, wherein, The disassembly and assembly credibility detection module includes: A floating component positioning module, which is used to position floating components according to the floating sequence constraints; A first credibility detection standard generation module, which is used to obtain the component criticality of floating components and generate a first credibility detection standard according to the component criticality; A second credibility detection standard generation module, which is used to obtain the component collision risk level of floating components and generate a second credibility detection standard according to the collision risk level; A floating component disassembly and assembly credibility detection module, which is used to perform disassembly and assembly credibility detection of floating components by using the first credibility detection standard and the second credibility detection standard to establish the sequence simulation detection result.

4. The BIM-based disassembly and assembly simulation management system for power plant equipment according to claim 2, wherein The window length distribution evaluation module includes: A component calibration disassembly time establishment module, which is used to establish the minimum disassembly granularity of components, perform simulated disassembly of the BIM model according to the minimum disassembly granularity, and establish component calibration disassembly time; A standard component time allocation ratio establishment module, which is used to establish a standard component time allocation ratio according to the component calibration disassembly time; A ratio distribution evaluation module, which is used to perform ratio distribution evaluation of the component disassembly and assembly window by using the standard component time allocation ratio to generate a ratio distribution evaluation result; The component disassembly and assembly evaluation result establishment module is used to compare each window of the component disassembly time with the component installation and disassembly window one by one by using the calibrated disassembly time of the component, and establish the component disassembly and assembly evaluation result; The window simulation detection result generation module is used to generate the window simulation detection result according to the proportional distribution evaluation result and the component disassembly and assembly evaluation result.

5. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 1, wherein The second detection module includes: The first conflict sub-channel construction module is used to establish fixed space constraints according to the installation space data, and construct the first conflict sub-channel with the fixed space constraints; The second conflict sub-channel establishment module is used to obtain the equipment component structure according to the BIM model, establish fixed component constraints according to the equipment component structure, and establish the second conflict sub-channel by using the fixed component constraints; The conflict channel establishment module is used to set a dynamic conflict sub-channel, the dynamic conflict sub-channel is dynamically updated based on the response data set, and the conflict channel is established by using the first conflict sub-channel, the second conflict sub-channel, and the dynamic conflict sub-channel to complete the response conflict detection.

6. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 1, characterized in that The fusion authentication module includes: The time series alignment module is used to perform time series alignment on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result; The delayed correlation search module is used to extract the reference comparison nodes from the first disassembly and assembly simulation detection result, and perform a delayed correlation search on the second disassembly and assembly simulation detection result mapped by time series alignment to establish a search matching result; The detection cross-validation module is used to perform detection cross-validation by using the search matching result to establish the fusion authentication result.

7. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 1, wherein The management module includes: The personal profile creation module is used to create the user's personal profile; The disassembly and assembly weak data generation module is used to generate disassembly and assembly weak data according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result; The personal profile update module is used to update the disassembly and assembly weak data to the personal profile for the disassembly and assembly simulation management of the user.

8. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 7, wherein The personal profile update module includes: The periodic intensive training plan generation module is used to generate a periodic intensive training plan according to the disassembly and assembly weak data and the user data, and establish a time series feedback node; The periodic intensive training detection module is used to perform periodic intensive training detection on the user at the time series feedback node to establish a detection data set; The reinforcement compensation module is used to generate reinforcement compensation by using the detection data set, optimize the periodic intensive training plan based on the reinforcement compensation, and perform user management according to the optimized periodic intensive training plan.

9. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 1, wherein The system further includes: The training module is used to activate the voice guidance and operation guidance when the user starts to perform the simulation training, and perform training prompt management on the user by using the voice guidance and the operation guidance.

10. The BIM-based power plant equipment disassembly and assembly simulation management system according to claim 9, wherein, The training module includes: The warning correction module is used to identify the operation deviation between the user's actual operation and the operation guidance, establish a correction guidance based on the operation deviation, and report an operation anomaly warning.

11. The BIM-based disassembly and assembly simulation management method for power plant equipment is characterized in that, The method is implemented by executing the BIM-based power plant equipment disassembly and assembly simulation management system according to any one of claims 1-10. The method includes: After collecting data on power plant equipment, a BIM model is established. The data collection includes the collection of equipment parameter data and installation space data; When the user starts to perform simulated disassembly and assembly, real-time operation records are executed, and an operation record data set and a response data set of the BIM model are established; Perform disassembly and assembly credibility detection on the operation record data set to generate a first disassembly and assembly simulation detection result; Set a conflict channel based on the BIM model, and use the conflict channel to perform response conflict detection on the response data set to establish a second disassembly and assembly simulation detection result; Perform time-series correlation analysis on the first disassembly and assembly simulation detection result and the second disassembly and assembly simulation detection result to generate a fusion authentication result; Perform disassembly and assembly simulation management according to the first disassembly and assembly simulation detection result, the second disassembly and assembly simulation detection result, and the fusion authentication result.

Images