DCS remote cooperative operation and maintenance system based on AR

Abstract

The invention discloses a DCS remote cooperative operation and maintenance system based on AR, and particularly relates to the field of operation and maintenance management, and the system comprises an acquisition module, a parameter mapping module, a resource intelligent matching module, a precise positioning module, an operation synchronization module, a dynamic verification module, an intelligent decision iteration module and a training module. The acquisition module is used for acquiring multi-dimensional parameters and storing the multi-dimensional parameters to a distributed database after performing standardization processing on the multi-dimensional parameters; the parameter mapping module is used for constructing an AR three-dimensional scene model based on spatial positioning data, calculating a scene modeling precision coefficient and dynamically mapping standardized parameters to the model; through cooperative matching degree calculation and cross-terminal AR cooperative interaction, optimal configuration and operation synchronization of operation and maintenance resources are realized, the problems of poor cooperative synchronization and low resource scheduling efficiency in the prior art are solved, the cooperative management efficiency is enhanced, the fault response and handling time is shortened, the operation and maintenance cooperative efficiency is improved, and the user experience is improved. And the real-time cooperation requirement of complex fault handling is met.

Description

Technical Field

[0001] This invention relates to the field of management and maintenance technology, and more specifically, to an AR-based DCS remote collaborative operation and maintenance system. Background Technology

[0002] In the field of industrial production management and control, distributed control systems (DCS) have become a core supporting technology, widely integrating core functions such as production process monitoring, remote resource scheduling, operation and maintenance decision support, and asset performance management to achieve centralized management and full-process operation of dispersed production equipment.

[0003] The advantages of existing DCS remote operation and maintenance technology lie in overcoming geographical limitations, reducing the manpower and time costs of on-site operation and maintenance, and automating some operation and maintenance processes through data analysis capabilities, playing a role in production scheduling optimization and initial allocation of operation and maintenance resources. However, there are still significant shortcomings: First, there is a lack of intuitive interactive platforms. Operation and maintenance personnel can only judge the equipment status through two-dimensional data charts, making it difficult to quickly understand the parameter relationships under complex operating conditions, which limits the accuracy of operation and maintenance decisions and affects the rationality of production resource optimization and allocation. Second, there is poor collaboration synchronization. When multiple operation and maintenance personnel collaborate remotely, there is a delay in the transmission of operation instructions, and data sharing lacks visual linkage, resulting in low collaborative management efficiency and failing to meet the real-time collaboration needs for handling complex faults. Third, there is a disconnect between fault location and adjustment. Existing technologies can only initially identify fault types and cannot achieve precise location by combining equipment spatial structure and real-time parameters. Moreover, adjustment plans lack dynamic verification mechanisms, resulting in poor implementation of operation and maintenance process optimization. Fourth, there is insufficient accumulation and reuse of operation and maintenance data. Historical operation and maintenance experience is not deeply integrated with intelligent decision-making models, leading to prominent issues of repetitive operation and maintenance, wasting operation and maintenance resources, and hindering the improvement of asset performance management.

[0004] To address the shortcomings of existing technologies in intuitive interaction, collaborative synchronization, precise positioning, and data reuse, there is an urgent need for an AR-based DCS remote collaborative operation and maintenance system. This system deeply integrates AR visualization technology with core functions such as data-driven decision-making, collaborative resource scheduling, operation and maintenance process optimization, and asset performance improvement. Through innovative technologies such as multi-dimensional parameter collection, 3D scene modeling, collaborative matching scheduling, and dynamic fault early warning, it constructs a closed-loop operation and maintenance system encompassing "data collection - visualization presentation - collaborative decision-making - precise execution - effect verification." This system solves the pain points of existing technologies and improves the intelligence and efficiency of industrial operation and maintenance. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an AR-based DCS remote collaborative operation and maintenance system, which solves the problems mentioned in the background art through the following solutions.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an AR-based DCS remote collaborative operation and maintenance system, comprising: Data Acquisition Module: Collects multi-dimensional parameters, performs standardization processing, and stores them in a distributed database; Parameter mapping module: Constructs AR 3D scene model based on spatial positioning data, calculates scene modeling accuracy coefficient, and dynamically maps standardized parameters to the model; Resource intelligent matching module: Extracts abnormal parameter features to calculate the fault level, combines personnel attribute parameters to calculate the collaboration matching degree, and allocates the optimal operation and maintenance team; Precise positioning module: Calculates the fault risk index, triggers audible and visual warnings, calculates the precise location coordinates of the fault using a triangulation algorithm, and marks it in the AR scene; Operation synchronization module: The operation and maintenance team accesses the AR collaboration space, calculates the collaboration consistency coefficient, and controls the transmission of operation commands based on the coefficient; Dynamic verification module: Calculates the adjustment execution coefficient based on the fault risk index and the coordination consistency coefficient, determines the adjustment range, and dynamically verifies the adjustment effect; Intelligent Decision Iteration Module: Stores operation and maintenance related data in a blockchain database, calculates the operation and maintenance efficiency improvement coefficient, and optimizes the intelligent decision model; Training module: Constructs an AR virtual operation and maintenance training scenario, calculates the training effectiveness coefficient, and determines the training achievement status based on the coefficient.

[0007] Preferably, the multi-dimensional parameters include equipment operating parameters, operation and maintenance environment parameters, and operation and maintenance personnel attribute parameters; the equipment operating parameters include equipment operating load L, control loop response time T, medium working pressure P, and medium working temperature. The operation and maintenance environment parameters include relative humidity H and equipment vibration frequency F; the operation and maintenance personnel attribute parameters include skill proficiency S and response time K.

[0008] Preferably, the AR 3D scene model is constructed at a 1:1 scale, and the modeling data comes from the physical dimensions, installation location, and pipeline layout data of the DCS equipment obtained by the LiDAR and visual positioning technology of the spatial positioning module; the calculation formula for the scene modeling accuracy coefficient M is as follows: The parameter dynamic mapping uses color gradients and dynamic numerical labels to present parameter changes at corresponding positions in the AR model.

[0009] Preferably, the formula for calculating the fault level G is as follows: The formula for calculating the collaboration matching degree C is as follows: The optimal operation and maintenance team consists of one main operator and two assistant analysts. The team is assigned based on the collaboration matching degree C value ranking result. At the same time, the fault location, parameter anomaly details and personnel division information are pushed to the team through the AR terminal.

[0010] Preferably, the formula for calculating the failure risk index R is as follows: ,in , These represent the equipment's rated operating pressure and rated operating temperature, respectively; the audible and visual warning is triggered when R exceeds a preset threshold; the formula for calculating the precise fault location coordinates (X, Y, Z) is... ,in , as well as The device reference coordinates are indicated; the AR scene markers are highlighted in red to show the fault location.

[0011] Preferably, the AR collaborative space supports real-time synchronization of the main operator's and assistant analyst's screens, and has annotation, ranging, and parameter retrieval functions; the formula for calculating the collaborative consistency coefficient Y is as follows: ,in , E represents the operation delay between the two parties, and E is the data synchronization error. The operation command transmission control rule is that when Y < 0.8, the data transmission priority is adjusted, and when Y ≥ 0.8, the master operator is allowed to send remote control commands. The commands must be encrypted before being transmitted to the DCS actuator.

[0012] Preferably, the formula for calculating the adjustment execution coefficient Z is as follows: The adjustment range is determined by the valve opening adjustment curve and pump frequency adjustment gradient displayed on the AR terminal. The effect needs to be simulated in the AR scene before adjustment. The method for verifying the adjustment effect is: based on the adjustment effect coefficient... Perform verification and judgment, among which , , , , , This represents the corresponding parameters collected after adjustment. The verification and judgment rule is that if U≥0.7, the adjustment is deemed effective. If U<0.7, the Z value is recalculated based on the parameter change trend to generate a secondary adjustment scheme until the requirements are met.

[0013] Preferably, the operation and maintenance related data stored in the blockchain database includes parameter data, collaboration process records, adjustment plans, and adjustment effect coefficient U-values, and the data has the characteristic of being tamper-proof; the operation and maintenance efficiency improvement coefficient The intelligent decision-making model optimization involves performing correlation analysis on historical V, G, and C values, adjusting the parameter thresholds of the collaborative matching algorithm and the fault early warning model, and then integrating the optimized data into the intelligent decision support system.

[0014] Preferably, the AR virtual operation and maintenance training scenario is constructed based on accumulated fault cases and AR 3D models; the training effectiveness coefficient Where A represents the accuracy rate of the trainees' operations. The Q value indicates the operation time; only after the Q value meets the standard can one participate in actual operation and maintenance work. The scenario supports simulating operation and maintenance processes with different fault levels.

[0015] The technical effects and advantages of this invention are as follows: 1. This invention achieves optimized configuration and operation synchronization of operation and maintenance resources through collaborative matching degree calculation and cross-terminal AR collaborative interaction, which solves the problems of poor collaborative synchronization and inefficient resource scheduling in the prior art, enhances collaborative management efficiency, shortens fault response and handling time, improves operation and maintenance collaboration efficiency, and meets the real-time collaboration needs of complex fault handling. 2. This invention achieves early warning and millimeter-level positioning of faults by combining fault risk index calculation and precise positioning algorithm with AR visualization markers. It solves the problems of vague fault positioning and disconnect between adjustment and positioning in the prior art, reduces operation and maintenance costs, improves equipment operation stability, ensures continuous production, and optimizes the implementation effect of operation and maintenance process. 3. This invention achieves the reuse of operation and maintenance experience and the continuous optimization of decision-making models through the accumulation of operation and maintenance data and the iteration of intelligent decision-making. It solves the problems of insufficient data reuse and low decision-making efficiency in the existing technology, forms a closed-loop operation and maintenance system, promotes the transformation of operation and maintenance mode from passive response to proactive early warning, reduces resource waste caused by repeated operation and maintenance, improves asset performance management level, and achieves the goal of cost reduction and efficiency improvement. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall structure of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] As attached Figure 1The illustrated AR-based DCS remote collaborative operation and maintenance system includes a data acquisition module, a parameter mapping module, a resource intelligent matching module, a precise positioning module, an operation synchronization module, a dynamic verification module, an intelligent decision iteration module, and a training module.

[0019] The acquisition module collects multi-dimensional parameters, performs standardized processing, and then stores them in a distributed database. In this embodiment, it should be specifically noted that: the multi-dimensional parameters include equipment operating parameters, operation and maintenance environment parameters, and operation and maintenance personnel attribute parameters; the equipment operating parameters include equipment operating load L, control loop response time T, medium working pressure P, and medium working temperature. The operation and maintenance environment parameters include relative humidity (H) and equipment vibration frequency (F); the operation and maintenance personnel attribute parameters include skill proficiency (S) and response time (K). In industrial operation and maintenance, equipment operating status, environmental conditions, and the capabilities of operation and maintenance personnel are the three core factors affecting the effectiveness of operation and maintenance. Single-dimensional parameters cannot comprehensively cover the information required for operation and maintenance decisions. Parameters lacking standardized processing will lead to subsequent calculation distortion due to differences in units and magnitudes. A fixed sampling frequency is a fundamental prerequisite for ensuring data real-time performance and avoiding parameter lag; therefore, this step is the "data cornerstone" of the entire system operation and is indispensable. Core parameters such as equipment operating load (L) and control loop response time (T) are selected because these parameters directly reflect the operating conditions and control accuracy of core equipment components, aligning with the core focus dimensions of DCS system operation and maintenance. Environmental parameters such as relative humidity (H) and vibration frequency (F) are important external factors leading to equipment failure and must be considered. Parameters such as personnel skill proficiency (S) and response time (K) directly determine the efficiency and quality of operation and maintenance, meeting the core requirements of collaborative resource scheduling. Standardized processing provides a unified benchmark for subsequent cross-dimensional parameter calculations, and the design logic fits the actual industrial scenario. By collecting parameters from multiple dimensions, key information about equipment, environment, and personnel is comprehensively captured, solving the problem of one-sided parameter collection in existing technologies. Standardized processing and fixed sampling frequency ensure the reliability and real-time nature of the data, providing high-quality data support for all core steps such as subsequent modeling, fault analysis, and resource matching, laying the foundation for data-driven decision-making and avoiding decision-making errors due to data defects.

[0020] The parameter mapping module: constructs an AR 3D scene model based on spatial positioning data, calculates the scene modeling accuracy coefficient, and dynamically maps standardized parameters to the model; In this embodiment, it should be specifically noted that: the AR 3D scene model is constructed at a 1:1 scale, and the modeling data comes from the physical dimensions, installation location, and pipeline layout data of the DCS equipment obtained by the LiDAR and visual positioning technology of the spatial positioning module; the calculation formula for the scene modeling accuracy coefficient M is as follows: The dynamic parameter mapping uses color gradients and dynamic numerical labels to present parameter changes at corresponding locations in the AR model. Existing two-dimensional data charts cannot intuitively present the relationship between the spatial structure of equipment and its parameters, making it difficult for maintenance personnel to quickly locate problems. AR 3D modeling can restore the physical form of equipment, and dynamic parameter mapping can bind abstract data to the physical equipment. The combination of these two is the only effective path to solve the pain point of "data visualization" and is a key bridge connecting data and maintenance operations. 1:1 scale modeling ensures consistency between the virtual scene and the actual equipment. LiDAR and visual positioning technologies can accurately acquire equipment size and layout data, providing technical assurance for modeling accuracy. The calculation formula for the scene modeling accuracy coefficient M integrates equipment operating parameters and environmental parameters, quantifying modeling reliability through multi-parameter linkage and avoiding subsequent operational deviations due to model distortion. Mapping methods such as color gradients and dynamic numerical labels conform to human visual perception habits, allowing maintenance personnel to quickly identify abnormal parameter locations. The design logic considers both technical feasibility and ergonomics. By transforming abstract, multi-dimensional parameters into visualized AR scenes, the pain point of intuitive interaction caused by the "disconnect between data and equipment" in existing technologies is solved. The calculation of the accuracy coefficient M ensures the reliability of the model, and the dynamic mapping of parameters realizes the "what you see is what you get" operation and maintenance experience, which significantly improves the efficiency of operation and maintenance personnel in understanding complex working conditions. It provides an intuitive carrier for subsequent fault location and collaborative operation, and strengthens the implementation effect of decision support.

[0021] The intelligent resource matching module extracts abnormal parameter features to calculate the fault level, combines personnel attribute parameters to calculate the collaboration matching degree, and allocates the optimal operation and maintenance team. In this embodiment, it should be specifically noted that the calculation formula for the fault level G is as follows: The formula for calculating the collaboration matching degree C is as follows: The optimal maintenance team consists of one main operator and two assistant analysts. Team allocation is based on the collaboration matching degree C value ranking result. Simultaneously, the fault location, abnormal parameter details, and personnel assignment information are pushed to the team via AR terminals. Complex fault handling requires collaboration from multiple personnel. Existing technologies lack a scientific resource matching mechanism, leading to "personnel-job mismatch," wasting maintenance resources, or delaying fault handling. Intelligent matching based on fault level and personnel capabilities enables optimized resource allocation, a core element in improving collaborative management efficiency, and meets the core requirements of resource scheduling optimization. The calculation formula for fault level G integrates equipment operating parameters and environmental parameters, objectively quantifying the urgency and difficulty of handling the fault, avoiding subjective judgment bias. The collaboration matching degree C combines personnel skill proficiency S and response time K, while introducing a modeling accuracy coefficient M to correct the matching result, ensuring that the matching logic considers both fault difficulty, personnel capabilities, and scenario reliability. The team configuration of one main operator and two assistant analysts conforms to the "decision-execution-assistance" division of labor logic in industrial maintenance. The C value ranking mechanism can quickly select the optimal resources, and the design logic fits the actual collaborative work process. By precisely matching fault levels with personnel capabilities, the problem of inefficient allocation of existing technical collaboration resources was solved; the optimized subgroup division of labor and information push mechanism ensured rapid response and efficient collaboration of the operation and maintenance team, improved collaborative management efficiency, avoided waste of human resources, and shortened fault handling preparation time. The precise positioning module calculates the fault risk index, triggers audible and visual warnings, calculates the precise location coordinates of the fault using a triangulation algorithm, and marks it in the AR scene. In this embodiment, it should be specifically noted that the formula for calculating the fault risk index R is as follows: ,in , These represent the equipment's rated operating pressure and rated operating temperature, respectively; the audible and visual warning is triggered when R exceeds a preset threshold; the formula for calculating the precise fault location coordinates (X, Y, Z) is... ,in , as well as The system represents the equipment's reference coordinates; the AR scene markers highlight the fault location in red. However, existing technologies can only preliminarily identify the fault type, lacking early warning capabilities and offering vague positioning, leading to fault escalation or blind adjustments. Real-time warnings can mitigate risks in advance, while precise positioning provides a clear target for adjustments. The combination of these two is key to addressing the pain point of "passive fault handling" and is the core defense line for ensuring stable equipment operation. The fault risk index R is calculated by comparing real-time and rated parameters of the equipment, combined with operating status and environmental parameters, enabling early detection of fault precursors. The warning logic aligns with the evolution of equipment faults. The triangulation algorithm, combined with AR 3D model coordinates, calculates the fault location coordinates through multi-parameter linkage, achieving millimeter-level positioning accuracy to meet the precise operational needs of industrial maintenance. The red highlighted markers are highly recognizable in the AR scene, quickly guiding maintenance personnel to focus on the fault location. The preset threshold setting provides a clear standard for warnings, and the design logic balances timely warnings with accurate positioning. Real-time fault early warning enables the transformation of the operation and maintenance mode from "passive response" to "proactive early warning", avoiding the risk of fault escalation in advance; millimeter-level precise positioning solves the problem of ambiguous positioning in existing technologies, provides clear targets for subsequent operation and maintenance adjustments, reduces secondary damage to equipment caused by blind operation, ensures production continuity, and optimizes the implementation effect of operation and maintenance processes.

[0022] The operation synchronization module: The operation and maintenance team accesses the AR collaboration space, calculates the collaboration consistency coefficient, and controls the transmission of operation instructions according to the coefficient; In this embodiment, it should be specifically noted that: the AR collaborative space supports real-time synchronization of the main operator's and assistant analyst's screens, and has annotation, ranging, and parameter retrieval functions; the formula for calculating the collaborative consistency coefficient Y is as follows: ,in , The delay between the two parties is represented by E, which is the data synchronization error. The operation command transmission control rule is that when Y < 0.8, the data transmission priority is adjusted, and when Y ≥ 0.8, the main operator is allowed to send remote control commands. The commands must be encrypted before being transmitted to the DCS execution mechanism. In remote collaboration, operation delays and data asynchrony can lead to collaboration chaos. Existing technologies lack a collaboration consistency assessment mechanism, which cannot guarantee operational security. AR collaborative space can achieve screen synchronization, and the collaboration consistency coefficient can quantify the synchronization effect. It is a core technical means to solve the pain point of "poor collaboration synchronization" and a basic guarantee for remote collaborative operation and maintenance. The screen synchronization and annotation functions of AR collaborative space meet the needs of "visual communication" in remote collaboration. The calculation formula of the collaboration consistency coefficient Y integrates operation delay and data synchronization error E, and introduces the modeling accuracy coefficient M to correct the result, which can objectively quantify the level of collaboration synchronization. The command transmission control rule based on the Y value avoids operation errors when synchronization is insufficient and ensures operation efficiency when synchronization is met. Encryption ensures command transmission security. The design logic takes into account both collaboration efficiency and operation security. Cross-terminal AR collaborative interaction enables "real-time linkage" in remote operation and maintenance, solving the problem of poor synchronization in existing technology collaboration; the quantification of the collaboration consistency coefficient and the command control rules ensure the safety and accuracy of collaborative operations, making remote collaboration among multiple personnel as if they were working on-site, significantly improving the efficiency of handling complex faults and strengthening the practical ability of collaborative management.

[0023] The dynamic verification module calculates the adjustment execution coefficient based on the fault risk index and the coordination consistency coefficient, determines the adjustment range, and dynamically verifies the adjustment effect. In this embodiment, it should be specifically noted that the calculation formula for the adjustment execution coefficient Z is as follows: The adjustment range is determined by the valve opening adjustment curve and pump frequency adjustment gradient displayed on the AR terminal. The effect needs to be simulated in the AR scene before adjustment. The method for verifying the adjustment effect is: based on the adjustment effect coefficient... Perform verification and judgment, among which , , , , , The corresponding parameters collected after adjustment are verified. The judgment rule is that if U ≥ 0.7, the adjustment is considered effective. If U < 0.7, the Z value is recalculated based on the parameter change trend to generate a secondary adjustment plan until the requirements are met. In existing technologies, maintenance adjustments are disconnected from fault location and lack a mechanism to verify the adjustment effect, leading to ineffective or excessive adjustments. Adjustment range based on parameter calculation and dynamic verification can achieve a closed loop of "precise adjustment - effect feedback," which is key to solving the pain point of "blind adjustment" and ensuring the effectiveness of maintenance operations. The calculation formula for the adjustment execution coefficient Z integrates the fault risk index R, the coordination consistency coefficient Y, and equipment and environmental parameters. It can dynamically determine the adjustment range based on the severity of the fault and the coordination status, avoiding the limitations of fixed adjustment plans. AR scene simulation of adjustment effects can predict the impact of operations in advance, reducing adjustment risks. The calculation formula for the adjustment effect coefficient U compares the core parameters before and after adjustment, comprehensively quantifying the improvement effect of the adjustment on the equipment operating status and environment. The U value judgment rule provides a clear standard for the effectiveness of the adjustment, and the secondary adjustment mechanism forms a closed-loop optimization. The design logic conforms to the maintenance process of "precise decision-making - verification optimization." The parameter-linked adjustment range calculation solves the problem of blind adjustment, and the dynamic verification mechanism ensures that the adjustment effect meets the standard, avoiding resource waste and equipment wear caused by repeated adjustments; AR scene simulation reduces adjustment risk, improves the accuracy of operation and maintenance operations, optimizes the implementation effect of operation and maintenance processes, and achieves the efficient operation and maintenance goal of "one-time adjustment in place".

[0024] The intelligent decision-making iteration module stores operation and maintenance-related data in a blockchain database, calculates the operation and maintenance efficiency improvement coefficient, and optimizes the intelligent decision-making model. In this embodiment, it should be specifically noted that: the operation and maintenance related data stored in the blockchain database includes parameter data, collaboration process records, adjustment plans, and adjustment effect coefficient U-values, and the data has the characteristic of being tamper-proof; the operation and maintenance efficiency improvement coefficient The intelligent decision-making model optimization involves analyzing the correlation between historical V-values, G-values, and C-values, adjusting the parameter thresholds of the collaborative matching algorithm and the fault early warning model, and then integrating the optimized data into the intelligent decision support system. In existing technologies, historical maintenance data lacks effective accumulation and reuse, leading to repeated handling of similar faults and hindering continuous optimization of the decision-making model. Blockchain storage ensures data security, the efficiency improvement coefficient quantifies maintenance effectiveness, and model iteration enables experience reuse, making it the core solution to the pain point of "insufficient data reuse" and driving continuous upgrades in maintenance models. The immutability of the blockchain database ensures the authenticity and security of maintenance data, providing a reliable foundation for experience reuse. The calculation formula for the maintenance efficiency improvement coefficient V integrates the number of collaborations, adjustment effects, total maintenance time, and synchronization errors, comprehensively quantifying the overall benefits of a single maintenance operation. Based on the correlation analysis of historical V-values, G-values, and C-values, the direction of model optimization can be accurately identified, and adjusting the algorithm and thresholds allows the decision-making model to adapt to different working conditions. The design logic conforms to the intelligent maintenance evolution pattern of "data accumulation - model optimization - decision upgrade." The accumulation of operation and maintenance data enables the digital storage and reuse of historical experience, solving the problem of data waste in existing technologies; the continuous iteration of intelligent decision-making models improves the accuracy of fault identification, resource matching, and adjustment plan generation, promotes the transformation of operation and maintenance mode from "experience-driven" to "data-driven", strengthens the core capabilities of intelligent decision support, and achieves the goals of continuous improvement of operation and maintenance efficiency and cost reduction and efficiency improvement.

[0025] The training module constructs an AR virtual operation and maintenance training scenario, calculates the training effectiveness coefficient, and determines the training achievement status based on the coefficient.

[0026] In this embodiment, it should be specifically noted that: the AR virtual operation and maintenance training scenario is based on accumulated fault cases and AR 3D model construction; the training effectiveness coefficient Where A represents the accuracy rate of the trainees' operations. The Q value represents the operation time; only after meeting the standard can one participate in actual operation and maintenance work. The scenario supports simulating operation and maintenance processes with different fault levels. Currently, operation and maintenance personnel lack real-world emergency drills, leading to insufficient emergency response capabilities. AR virtual training scenarios can simulate real faults, and the training effectiveness coefficient quantifies capability levels, providing an effective path to improve team professional capabilities and ensuring human resource support for the long-term stable operation of the system. Building training scenarios based on real fault cases and AR 3D models maximizes the reproduction of the actual operation and maintenance environment, avoiding the high costs and risks of real equipment drills. The calculation formula for the training effectiveness coefficient Q integrates operation accuracy (A), modeling accuracy coefficient (M), operation time, and fault level (G), comprehensively quantifying the operational capabilities and efficiency of trainees. The Q value qualification rules ensure training quality, and scenario simulations with different fault levels enable tiered training, conforming to the laws of personnel capability improvement. The design logic balances training effectiveness and cost control. AR virtual training addresses the shortcomings of existing technologies in emergency response capabilities, reducing training costs and risks. Quantitative evaluation of training effectiveness ensures that maintenance personnel meet professional standards, and tiered scenario simulations continuously improve the team's practical skills, providing solid human resource support for the long-term stable operation of the DCS system and further enhancing the synergistic efficiency of human resource optimization and maintenance management.

[0027] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An AR-based DCS remote collaborative operation and maintenance system, characterized in that, include: Data Acquisition Module: Collects multi-dimensional parameters, performs standardization processing, and stores them in a distributed database; Parameter mapping module: Constructs AR 3D scene model based on spatial positioning data, calculates scene modeling accuracy coefficient, and dynamically maps standardized parameters to the model; Resource intelligent matching module: Extracts abnormal parameter features to calculate the fault level, combines personnel attribute parameters to calculate the collaboration matching degree, and allocates the optimal operation and maintenance team; Precise positioning module: Calculates the fault risk index, triggers audible and visual warnings, calculates the precise location coordinates of the fault using a triangulation algorithm, and marks it in the AR scene; Operation synchronization module: The operation and maintenance team accesses the AR collaboration space, calculates the collaboration consistency coefficient, and controls the transmission of operation commands based on the coefficient; Dynamic verification module: Calculates the adjustment execution coefficient based on the fault risk index and the coordination consistency coefficient, determines the adjustment range, and dynamically verifies the adjustment effect; Intelligent Decision Iteration Module: Stores operation and maintenance related data in a blockchain database, calculates the operation and maintenance efficiency improvement coefficient, and optimizes the intelligent decision model; Training module: Constructs an AR virtual operation and maintenance training scenario, calculates the training effectiveness coefficient, and determines the training achievement status based on the coefficient.

2. The AR-based DCS remote collaborative operation and maintenance system according to claim 1, characterized in that: The multi-dimensional parameters include equipment operating parameters, maintenance environment parameters, and maintenance personnel attribute parameters; the equipment operating parameters include equipment operating load L, control loop response time T, medium working pressure P, and medium working temperature. The operation and maintenance environment parameters include relative humidity H and equipment vibration frequency F; the operation and maintenance personnel attribute parameters include skill proficiency S and response time K.

3. The AR-based DCS remote collaborative operation and maintenance system according to claim 2, characterized in that: The AR 3D scene model is constructed at a 1:1 scale. The modeling data comes from the physical dimensions, installation location, and pipeline layout data of the DCS equipment obtained by the LiDAR and visual positioning technology of the spatial positioning module. The calculation formula for the scene modeling accuracy coefficient M is as follows: The parameter dynamic mapping uses color gradients and dynamic numerical labels to present parameter changes at corresponding positions in the AR model.

4. The AR-based DCS remote collaborative operation and maintenance system according to claim 2, characterized in that: The formula for calculating the fault level G is as follows: The formula for calculating the collaboration matching degree C is as follows: The optimal operation and maintenance team consists of one main operator and two assistant analysts. The team is assigned based on the collaboration matching degree C value ranking result. At the same time, the fault location, parameter anomaly details and personnel division information are pushed to the team through the AR terminal.

5. The AR-based DCS remote collaborative operation and maintenance system according to claim 2, characterized in that: The formula for calculating the failure risk index R is as follows: ,in , These represent the equipment's rated operating pressure and rated operating temperature, respectively; the audible and visual warning is triggered when R exceeds a preset threshold; the formula for calculating the precise fault location coordinates (X, Y, Z) is... ,in , as well as The device reference coordinates are indicated; the AR scene markers are highlighted in red to show the fault location.

6. The AR-based DCS remote collaborative operation and maintenance system according to claim 5, characterized in that: The AR collaborative space supports real-time synchronization of the main operator's and assistant analyst's screens, and has annotation, ranging, and parameter retrieval functions; the formula for calculating the collaborative consistency coefficient Y is as follows: ,in , E represents the operation delay between the two parties, and E is the data synchronization error. The operation command transmission control rule is that when Y < 0.8, the data transmission priority is adjusted, and when Y ≥ 0.8, the master operator is allowed to send remote control commands. The commands must be encrypted before being transmitted to the DCS actuator.

7. The AR-based DCS remote collaborative operation and maintenance system according to claim 6, characterized in that: The formula for calculating the adjustment execution coefficient Z is as follows: The adjustment range is determined by the valve opening adjustment curve and pump frequency adjustment gradient displayed on the AR terminal. The effect needs to be simulated in the AR scene before adjustment. The method for verifying the adjustment effect is: based on the adjustment effect coefficient... Perform verification and judgment, among which , , , , , This represents the corresponding parameters collected after adjustment. The verification and judgment rule is that if U≥0.7, the adjustment is deemed effective. If U<0.7, the Z value is recalculated based on the parameter change trend to generate a secondary adjustment scheme until the requirements are met.

8. The AR-based DCS remote collaborative operation and maintenance system according to claim 1, characterized in that: The blockchain database stores operation and maintenance related data, including parameter data, collaboration process records, adjustment plans, and adjustment effect coefficients (U-values), and the data is tamper-proof; the operation and maintenance efficiency improvement coefficient... The intelligent decision-making model optimization involves performing correlation analysis on historical V, G, and C values, adjusting the parameter thresholds of the collaborative matching algorithm and the fault early warning model, and then integrating the optimized data into the intelligent decision support system.

9. The AR-based DCS remote collaborative operation and maintenance system according to claim 4, characterized in that: The AR virtual operation and maintenance training scenario is built based on accumulated fault cases and AR 3D models; the training effectiveness coefficient Where A represents the accuracy rate of the trainees' operations. The Q value indicates the operation time; only after the Q value meets the standard can one participate in actual operation and maintenance work. The scenario supports simulating operation and maintenance processes with different fault levels.

Images