Electric power intelligent monitoring system based on multi-device cooperative linkage and operation and maintenance method

Abstract

The invention discloses an electric power intelligent monitoring system based on multi-device cooperative linkage and an operation and maintenance method, and belongs to the technical field of electric power intelligent monitoring and operation and maintenance. Radiation data and historical decay records are collected through a sensor, a linear regression algorithm is adopted to fit and establish an energy spectrum purity attenuation model, and the dose loss proportion is calculated in real time; carrying out dynamic compensation on beam intensity and irradiation time based on the proportion, fusing real-time dose monitoring data by utilizing a Kalman filtering algorithm, and optimizing a beam intensity value to suppress noise interference; the irradiation time is further adjusted according to whether the dose loss exceeds a threshold value or not, and a dynamic compensation combination is formed; the effectiveness of the combination in each stage of the source life cycle is verified through the simulation module, and the verified compensation parameters are updated to the control system in real time, so that closed-loop regulation and control are realized. According to the invention, the whole process of dose output in the irradiation process is accurately and stably controlled, and the consistency and reliability of the irradiation process are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of power intelligent monitoring and operation and maintenance technology, and particularly relates to a power intelligent monitoring system and operation and maintenance method based on multi-device collaborative linkage. Background Technology

[0002] Irradiation processing technology is widely used in materials modification, medical device sterilization, and food preservation. Precise control of its process parameters directly determines product qualification rate and safety, making it a crucial link in ensuring high-quality industrial development. The irradiation process relies on a radiation source to provide high-energy rays, and the process requires the output dose to be stably maintained within a narrow error range to avoid insufficient material performance or excessive damage.

[0003] Current control methods mostly employ fixed parameters or periodic calibration strategies. However, during use, radioactive sources undergo irreversible nuclide decay, causing the radiation spectrum to gradually deviate from its initial state. This change in spectral purity is not uniform and linear but rather accumulates gradually over time, making it impossible for the preset beam intensity and irradiation time combination to consistently match the actual output dose. In long-term operation, the system often requires frequent manual intervention to compensate for dose deviations, increasing operational complexity and uncertainty.

[0004] The attenuation of spectral purity directly leads to a loss of effective dose. This loss varies at different stages of the radioactive source's lifespan, further amplifying the difficulty of dose control. Because changes in purity alter the efficiency of the interaction between radiation and matter, the actual energy deposited into the product under the same beam parameters decreases. This reduction is closely coupled with multiple parameters such as irradiation time and beam intensity, forming a complex dynamic relationship. For example, on a continuously operating irradiation production line, during the several-month cycle from initial loading to nearing the replacement threshold, if parameters are not adjusted in time, the dose of early-stage products may be slightly higher, while later-stage products may exhibit significantly insufficient doses. This makes it difficult to guarantee the consistency of the entire batch and may even trigger quality traceability issues.

[0005] How to establish the correlation between purity changes and dose loss in real time during the continuous decay of the purity of the radioactive source energy spectrum, and dynamically generate a compensation combination of beam intensity and irradiation time accordingly, so that the actual output dose is kept within the process accuracy range throughout the process, has become the key issue for realizing intelligent closed-loop dynamic control of irradiation process parameters. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a power intelligent monitoring system and operation and maintenance method based on multi-device collaborative linkage to overcome the shortcomings of the prior art, so as to realize real-time compensation and optimization of irradiation process parameters.

[0007] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: A method for intelligent power monitoring and operation and maintenance based on multi-device collaborative linkage specifically includes the following steps: Step 1: By deploying a sensor cluster on various heterogeneous power equipment in the power grid, real-time data on the operating status of each device and historical fault records are collected. Time series analysis and association rule mining algorithms are used to construct a power equipment fault propagation model. The model describes the propagation path and influence function relationship of critical equipment faults in a multi-device network. Step 2: Based on the fault propagation model, calculate the deviation between the health status of each device and the baseline status within the current monitoring period to obtain the correlation impact index. The index represents the degree of impact of a single device anomaly on the overall efficiency of the collaboratively operating related device group. Step 3: Obtain the preset values ​​of equipment monitoring priority and inspection cycle under the current power grid operation mode, apply a dynamic adjustment strategy to correct the preset values ​​for the correlation impact index, and determine the preliminary optimized monitoring strategy and inspection plan, aiming to provide early warning of potential cascading failure risks; Step 4: The federated learning framework is used to integrate the preliminary optimization strategies and real-time alarm data from monitoring substations in different regions to obtain a globally collaboratively optimized monitoring strategy. This strategy improves the accuracy of cross-regional linkage analysis while protecting data privacy. Step 5: Based on the globally optimized monitoring strategy, calculate the dynamic allocation scheme of the corresponding operation and maintenance resources. If the correlation impact index exceeds the preset threshold, start preventive maintenance or resource enhancement mode; otherwise, maintain the normal operation and maintenance configuration and generate a multi-device collaborative operation and maintenance instruction set. Step 6: Verify the application effect of the operation and maintenance instruction set under different power grid operating conditions and equipment life cycle stages through the digital twin simulation module, determine whether the verification results meet the system reliability and stability indicators, and output the verified collaborative operation and maintenance scheme. Step 7: The verified collaborative operation and maintenance solution is sent to the local controllers of each device and the regional control center in real time. The system's comprehensive performance feedback data after operation and maintenance is executed and collected to determine whether the entire process is maintained within the safe and stable operating range. The feedback data is then cyclically input into the fault propagation model to achieve intelligent closed-loop operation and maintenance.

[0008] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 1 specifically includes the following steps: Step 1.1: Based on the electrical quantities, temperature, vibration and partial discharge data collected by the sensor cluster, and combined with the equipment ledger and historical fault logs, construct a multi-source heterogeneous time-series database; Step 1.2: Perform data cleaning, alignment, and feature extraction on the time-series database to obtain a standardized sequence of equipment operation features; Step 1.3: Apply time series analysis algorithm to identify the state degradation trend of the equipment itself, and use association rule mining algorithm to analyze the spatiotemporal correlation between different equipment state sequences; Step 1.4: Based on the degradation trend and correlation, construct a directed graph model of fault propagation with devices as nodes and influence relationships as edges, and quantify the propagation probability and influence weight on the edges. Step 1.5: Update the propagation directed graph according to the real-time topology of the power grid, and perform model parameter correction by combining the physical connection relationship of the equipment and the degree of electrical coupling; Step 1.6: When the risk of the critical propagation path predicted by the model exceeds the warning line, a high-risk alarm is triggered and the model parameters are recorded. At the same time, the data acquisition frequency and granularity of the relevant devices are adaptively adjusted.

[0009] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 2 specifically includes the following steps: Step 2.1: Based on the fault propagation model, calculate the cumulative expected impact of the target equipment state deviation along the propagation path on each associated equipment; Step 2.2: Combining the functional importance of the equipment in the power grid with the current load rate, the expected cumulative impact value is weighted to obtain a preliminary correlation impact index; Step 2.3: Compare the preliminary correlation impact index with the historical index for the same period and the preset threshold. If it exceeds the threshold, mark it as a key impact device and generate an impact range report. Step 2.4: For key affected equipment, trace back the main influencing factors of its status deviation to identify whether it is caused by its own degradation, external environment or abnormal interconnection equipment. Step 2.5: Analyze the correlation between the influencing factors and the electrical distance between devices and the control logic dependency, and determine the dominant factors affecting propagation; Step 2.6: If the dominant factor is a specific type of associated anomaly or environmental condition, adjust the monitoring strategy and strengthen the monitoring of the factor and related link devices. Step 2.7: Based on the analysis results, dynamically update the calculation weight and threshold of the correlation impact index to more accurately reflect the system's vulnerable links under the current operating mode.

[0010] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 3 specifically includes the following steps: Step 3.1: Obtain information on the current power grid operation mode, load level, and weather conditions, and determine the corresponding standard monitoring strategy template, including the monitoring frequency, parameter type, and inspection cycle of each device; Step 3.2: Calculate the adjustment coefficients for the monitoring frequency and inspection cycle based on the magnitude and scope of the correlation influence index; Step 3.3: Apply the adjustment coefficient to correct the corresponding value in the standard template to obtain the preliminary optimization strategy at the device level; Step 3.4: Considering the total constraints of operation and maintenance resources, the preliminary optimization strategy is comprehensively optimized to ensure that resource allocation matches the risk level; Step 3.5: If the corrected monitoring frequency or inspection density exceeds the physical limit or economic limit of the equipment, the upper limit value shall be used for amplitude limiting, and additional diagnostic test recommendations shall be triggered. Step 3.6: Generate a preliminary optimization strategy report containing monitoring points, frequencies, parameters, inspection plans, and resource allocations, and push it to relevant operations and maintenance personnel for confirmation or modification.

[0011] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 4 specifically includes the following steps: Step 4.1: Each regional monitoring substation uses its data locally to train and optimize the fault propagation model, generating local model updates and strategy recommendations; Step 4.2: Securely aggregate the uploaded model parameter updates or policy summaries from each sub-site through the federated learning server, instead of the original data. Step 4.3: Using the aggregated global model parameters, evaluate and optimize the preliminary monitoring strategies of each substation to ensure consistency of monitoring strategies for cross-regional boundary devices and optimal global risk. Step 4.4: Integrate real-time cross-regional alarm information and dynamically adjust the focus and response level of collaborative monitoring between adjacent regions; Step 4.5: Distribute the globally optimized monitoring strategy to each substation, and each substation updates and executes its local strategy accordingly. Step 4.6: Continuously evaluate the effectiveness of federated learning and adaptively adjust the aggregation algorithm and participation weights according to changes in the data distribution of each region.

[0012] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 5 specifically includes the following steps: Step 5.1: Based on the key equipment and risk levels determined by the optimized strategy, estimate the types and quantities of resources required, such as maintenance personnel, spare parts, and testing tools. Step 5.2: Based on the current location, availability, and scheduling cost of the resources, formulate a dynamic resource allocation path and schedule; Step 5.3: If the equipment-related impact index exceeds the first-level threshold, a preventive maintenance instruction is generated, such as enhanced inspection, live-line testing, or minor repair. Step 5.4: If the threshold is exceeded, a resource enhancement mode instruction is generated, such as arranging a power outage for maintenance, allocating spare equipment, or sending additional experts for support. Step 5.5: Combine and sort the operation and maintenance instructions for different devices according to spatiotemporal logic and dependency relationships to form an executable collaborative operation and maintenance instruction set; Step 5.6: Simulate the effect of executing the instruction set on improving the reliability of power grid operation, and perform iterative optimization.

[0013] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 6 specifically includes the following steps: Step 6.1: In the digital twin environment, construct a model that is a high-fidelity mapping to the physical power grid, including the device multiphysics model, network topology, and control logic; Step 6.2: Set parameters for different power grid operating conditions and equipment aging stages; Step 6.3: Inject the collaborative operation and maintenance instruction set, and simulate the execution of operation and maintenance operations and their impact on the system; Step 6.4: Collect key indicator data such as system stability, reliability, and power quality during the simulation process; Step 6.5: Analyze the simulation results and evaluate the effectiveness, economy, and potential risks of the operation and maintenance plan; Step 6.6: If the evaluation results do not meet the standards, adjust the timing, scope, or content of the operation and maintenance instructions, and re-simulate until the preset indicators are met. Step 6.7: Output the validated collaborative operation and maintenance solution and simulation evaluation report.

[0014] As a further preferred embodiment of the intelligent power monitoring and operation and maintenance method based on multi-device collaborative linkage of the present invention, step 7 specifically includes the following steps: Step 7.1: Send the operation and maintenance plan instructions to the execution terminal through a secure communication network; Step 7.2: Monitor the execution status of commands and collect equipment status and system-level performance data in real time after maintenance operations; Step 7.3: Analyze the feedback data and assess whether the operation and maintenance effect has met expectations and whether the system risk has been reduced to an acceptable level; Step 7.4: Use the key data, effect evaluation, and environmental factors of this operation and maintenance process as new samples to update the relevant parameters of the fault propagation model; Step 7.5: Use the updated model to conduct a new round of risk assessment and strategy optimization, forming a closed loop of monitoring-analysis-decision-execution-evaluation-learning; Step 7.6: Continuously track the closed-loop operation performance and regularly conduct overall system health assessments and model calibrations.

[0015] A power intelligent monitoring system based on multi-device collaborative linkage includes: The multi-source data acquisition and fusion module is used to collect real-time operating data and historical records of various types of power equipment through a sensor cluster, and to perform preprocessing and fusion. The fault propagation modeling and analysis module is used to build and update equipment fault propagation models using data analysis algorithms, and to calculate equipment health deviation and related impact indices. The monitoring strategy dynamic optimization module is used to dynamically adjust the equipment monitoring priority, frequency and inspection plan based on the correlation impact index and operating mode, and generate a preliminary optimization strategy. The global collaborative learning and decision-making module is used to integrate multi-regional data and strategies using a federated learning framework to generate a globally collaboratively optimized monitoring strategy. The operation and maintenance resource scheduling and instruction generation module is used to calculate the operation and maintenance resource allocation plan based on the optimization strategy, and generate a multi-device collaborative operation and maintenance instruction set according to the risk threshold. The digital twin simulation verification module is used to verify the effectiveness of the operation and maintenance instruction set under different working conditions in a virtual environment and output the verified operation and maintenance solution. The closed-loop execution and learning module is used to issue and monitor the execution of operation and maintenance plans, collect feedback data to update the model, and realize intelligent closed-loop operation and maintenance management.

[0016] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects: This invention first collects radiation data using sensors, then uses linear regression to fit a purity attenuation model to calculate the dose loss ratio. Next, it adjusts the beam intensity based on a compensation formula and uses Kalman filtering to optimize the value and improve stability. Then, it dynamically adjusts the irradiation time according to the loss ratio, forming a compensation combination. Finally, it updates control parameters through simulation verification and real-time feedback, forming a closed-loop control. The core innovation of this invention lies in combining the purity attenuation model with a dynamic compensation mechanism, ensuring that the dose accuracy always meets process requirements, effectively solving the impact of purity attenuation on radiation efficiency, and significantly improving the stability and reliability of the production process. Attached Figure Description

[0017] Figure 1 This is a flowchart of a power intelligent monitoring system and operation and maintenance method based on multi-device collaborative linkage according to the present invention; Figure 2 This is a schematic diagram of a power intelligent monitoring system based on multi-device collaborative linkage according to the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings: 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention. The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. The purpose and effects of the present invention will become clearer. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0019] A power intelligent monitoring and operation and maintenance method based on multi-device collaborative linkage, such as Figure 1 As shown, the specific steps include: Step 1: By deploying a sensor cluster on various heterogeneous power equipment in the power grid, real-time data on the operating status of each device and historical fault records are collected. Time series analysis and association rule mining algorithms are used to construct a power equipment fault propagation model. The model describes the propagation path and influence function relationship of critical equipment faults in a multi-device network. Based on the electrical quantities, temperature, vibration and partial discharge data collected by the sensor cluster, and combined with the equipment ledger and historical fault logs, a multi-source heterogeneous time-series database is constructed. The time-series database is cleaned, aligned, and its features are extracted to obtain a standardized sequence of equipment operation features. Time series analysis algorithms are applied to identify the degradation trend of the equipment itself, and association rule mining algorithms are used to analyze the spatiotemporal correlation between different equipment state sequences; Based on the aforementioned degradation trend and correlation, a directed graph model for fault propagation is constructed with devices as nodes and influence relationships as edges, and the propagation probability and influence weight on the edges are quantified. The propagation directed graph is updated based on the real-time topology of the power grid, and the model parameters are corrected by combining the physical connection relationship of the equipment and the degree of electrical coupling. When the risk of the critical propagation path predicted by the model exceeds the warning line, a high-risk alarm is triggered and the model parameters are recorded. At the same time, the data collection frequency and granularity of the relevant devices are adaptively adjusted.

[0020] Step 2: Based on the fault propagation model, calculate the deviation between the health status of each device and the baseline status within the current monitoring period to obtain the correlation impact index. The index represents the degree of impact of a single device anomaly on the overall efficiency of the collaboratively operating related device group. Based on the fault propagation model, calculate the cumulative expected impact of the target equipment state deviation on each associated equipment along the propagation path; By combining the functional importance of the equipment in the power grid with the current load rate, the cumulative value of the expected impact is weighted to obtain a preliminary correlation impact index; The preliminary correlation impact index is compared with the historical index for the same period and a preset threshold. If it exceeds the threshold, it is marked as a key affected device, and an impact range report is generated. For critically affected equipment, trace back the main influencing factors of its status deviation to identify whether it is caused by its own degradation, external environment or abnormal interconnection equipment; Analyze the correlation between the aforementioned influencing factors and the electrical distance between devices and the dependence of control logic to determine the dominant factors affecting propagation; If the dominant factor is a specific type of associated anomaly or environmental condition, then adjust the monitoring strategy and strengthen the monitoring of that factor and related link devices; Based on the analysis results, the calculation weights and thresholds of the correlation impact index are dynamically updated to more accurately reflect the system's vulnerable links under the current operating mode.

[0021] Step 3: Obtain the preset values ​​of equipment monitoring priority and inspection cycle under the current power grid operation mode, apply a dynamic adjustment strategy to correct the preset values ​​for the correlation impact index, and determine the preliminary optimized monitoring strategy and inspection plan, aiming to provide early warning of potential cascading failure risks; Obtain information on the current power grid operation mode, load level, and weather conditions, and determine the corresponding standard monitoring strategy template, including the monitoring frequency, parameter type, and inspection cycle of each device; Based on the magnitude and scope of the correlation impact index, the adjustment coefficients for the monitoring frequency and inspection cycle are calculated; The adjustment coefficients are applied to correct the corresponding values ​​in the standard template to obtain a preliminary device-level optimization strategy; Considering the total constraints of operation and maintenance resources, the initial optimization strategy is comprehensively optimized to ensure that resource allocation matches the risk level. If the revised monitoring frequency or inspection density exceeds the physical limits or economic limits of the equipment, the upper limit will be used for amplitude limiting, and additional diagnostic test recommendations will be triggered. Generate a preliminary optimization strategy report that includes monitoring points, frequency, parameters, inspection plans, and resource allocation, and push it to relevant operations and maintenance personnel for confirmation or modification.

[0022] Step 4: The federated learning framework is used to integrate the preliminary optimization strategies and real-time alarm data from monitoring substations in different regions to obtain a globally collaboratively optimized monitoring strategy. This strategy improves the accuracy of cross-regional linkage analysis while protecting data privacy. Each regional monitoring substation uses its local data to train and optimize the fault propagation model, generating local model updates and strategy recommendations. The federated learning server coordinates the upload of model parameter updates or policy summaries from various sub-sites, rather than the raw data, for secure aggregation. By utilizing the aggregated global model parameters, the initial monitoring strategies of each substation are evaluated and optimized to ensure consistency of monitoring strategies for cross-regional boundary devices and optimal global risk. Integrate real-time cross-regional alarm information and dynamically adjust the focus and response level of collaborative monitoring between adjacent regions; The globally optimized monitoring strategy is distributed to each substation, and each substation updates and executes its local strategy accordingly. The effectiveness of federated learning is continuously evaluated, and the aggregation algorithm and participation weights are adaptively adjusted according to changes in the data distribution in each region.

[0023] Step 5: Based on the globally optimized monitoring strategy, calculate the dynamic allocation scheme of the corresponding operation and maintenance resources. If the correlation impact index exceeds the preset threshold, start preventive maintenance or resource enhancement mode; otherwise, maintain the normal operation and maintenance configuration and generate a multi-device collaborative operation and maintenance instruction set. Based on the key equipment and risk levels identified by the optimized strategy, estimate the types and quantities of resources required, such as maintenance personnel, spare parts, and testing tools. Based on the current location, availability, and scheduling costs of resources, develop dynamic resource allocation paths and schedules; If the equipment's associated impact index exceeds the first-level threshold, a preventative maintenance instruction will be generated, such as enhanced inspection, live-line testing, or minor repairs. If the threshold is exceeded by a higher level, a resource enhancement mode instruction will be generated, such as arranging a power outage for maintenance, allocating spare equipment, or sending additional experts for support. The operation and maintenance instructions for different devices are combined and sorted according to spatiotemporal logic and dependencies to form an executable collaborative operation and maintenance instruction set; The effect of simulating the execution of the instruction set on improving the reliability of power grid operation is used for iterative optimization.

[0024] Step 6: Verify the application effect of the operation and maintenance instruction set under different power grid operating conditions and equipment life cycle stages through the digital twin simulation module, determine whether the verification results meet the system reliability and stability indicators, and output the verified collaborative operation and maintenance scheme. In a digital twin environment, a model is constructed that maps to the physical power grid with high fidelity, including multi-physics models of devices, network topology, and control logic. Set different power grid operating conditions and equipment aging stage parameters; Inject the collaborative operation and maintenance instruction set to simulate the execution of operation and maintenance processes and their impact on the system; Collect key performance data such as system stability, reliability, and power quality during the simulation process; Analyze the simulation results to evaluate the effectiveness, cost-effectiveness, and potential risks of the operation and maintenance plan; If the evaluation results do not meet the standards, adjust the timing, scope, or content of the operation and maintenance instructions, and re-simulate until the preset indicators are met. Output validated collaborative operation and maintenance solutions and simulation evaluation reports.

[0025] Step 7: The verified collaborative operation and maintenance solution is sent to the local controllers of each device and the regional control center in real time. The system's comprehensive performance feedback data after operation and maintenance is executed and collected to determine whether the entire process is maintained within the safe and stable operating range. The feedback data is then cyclically input into the fault propagation model to achieve intelligent closed-loop operation and maintenance.

[0026] The operation and maintenance plan instructions are sent to the execution terminal through a secure communication network; Monitor command execution status and collect equipment status and system-level performance data in real time after operation and maintenance. Analyze feedback data to assess whether the operation and maintenance effects have met expectations and whether the system risks have been reduced to an acceptable level; The key data, effect evaluation, and environmental factors from this operation and maintenance process will be used as new samples to update the relevant parameters of the fault propagation model. The updated model will be used to conduct a new round of risk assessment and strategy optimization, forming a closed loop of monitoring-analysis-decision-execution-evaluation-learning; Continuously track the closed-loop operation performance and regularly conduct overall system health assessments and model calibrations.

[0027] A power intelligent monitoring system based on multi-device collaborative linkage, such as Figure 2 As shown, it includes: The multi-source data acquisition and fusion module is used to collect real-time operating data and historical records of various types of power equipment through a sensor cluster, and to perform preprocessing and fusion. The fault propagation modeling and analysis module is used to build and update equipment fault propagation models using data analysis algorithms, and to calculate equipment health deviation and related impact indices. The monitoring strategy dynamic optimization module is used to dynamically adjust the equipment monitoring priority, frequency and inspection plan based on the correlation impact index and operating mode, and generate a preliminary optimization strategy. The global collaborative learning and decision-making module is used to integrate multi-regional data and strategies using a federated learning framework to generate a globally collaboratively optimized monitoring strategy. The operation and maintenance resource scheduling and instruction generation module is used to calculate the operation and maintenance resource allocation plan based on the optimization strategy, and generate a multi-device collaborative operation and maintenance instruction set according to the risk threshold. The digital twin simulation verification module is used to verify the effectiveness of the operation and maintenance instruction set under different working conditions in a virtual environment and output the verified operation and maintenance solution. The closed-loop execution and learning module is used to issue and monitor the execution of operation and maintenance plans, collect feedback data to update the model, and realize intelligent closed-loop operation and maintenance management.

[0028] This invention establishes an energy spectrum purity attenuation model, combined with real-time monitoring and Kalman filtering optimization, to achieve dynamic intelligent compensation for beam intensity and irradiation time, effectively suppressing dose deviation caused by radiation source attenuation. The system possesses simulation verification and closed-loop control capabilities, significantly improving the stability, consistency, and automation level of the irradiation process, reducing the frequency of manual intervention, and is suitable for continuous, high-precision irradiation production lines. This invention, through a combination of modeling, compensation, optimization, verification, and closed-loop control, achieves high-precision dynamic control of irradiation process parameters, and has promising prospects for industrial application.

[0029] It will be understood by those skilled in the art that the above descriptions are merely preferred examples of the invention and are not intended to limit the invention. Although the invention has been described in detail with reference to the foregoing examples, those skilled in the art can still modify the technical solutions described in the foregoing examples or make equivalent substitutions for some of the technical features. All modifications and equivalent substitutions made within the spirit and principles of the invention should be included within the scope of protection of the invention. All technical features in this embodiment can be freely combined according to actual needs.

[0030] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. 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. A power intelligent monitoring and operation method based on multi-device cooperative linkage, characterized in that, Specifically comprising the following steps: Step 1, through the sensor cluster deployed on multiple types of heterogeneous power equipment in the power grid, the running state data and historical fault records of each device are collected in real time, a power equipment fault propagation model is constructed by using time series analysis and association rule mining algorithm, and the model describes the propagation path and influence function relationship of key equipment failure in the multi-device network; Step 2, according to the fault propagation model, the deviation of the health state of each device in the current monitoring period from the reference state is calculated to obtain an associated influence index, which represents the influence degree of a single device anomaly on the overall efficiency of the associated device group running cooperatively; Step 3, the preset values of the device monitoring priority and the inspection period under the current power grid operation mode are obtained, the preset values are corrected by applying a dynamic adjustment strategy to the associated influence index, and a preliminary optimized monitoring strategy and inspection plan are determined, aiming to early warning of potential cascading failure risk; Step 4, the preliminary optimized strategy and real-time alarm data from different regional monitoring substations are fused by using a federated learning framework to obtain a globally cooperatively optimized monitoring strategy, which improves the accuracy of cross-regional linkage analysis under the premise of protecting data privacy; Step 5, based on the globally optimized monitoring strategy, a dynamic deployment scheme of the corresponding operation and maintenance resources is calculated, if the associated influence index exceeds a preset threshold, a preventive maintenance or resource enhancement mode is started, otherwise the normal operation and maintenance configuration is maintained, and a multi-device cooperative operation and maintenance instruction set is generated; Step 6, the application effect of the operation and maintenance instruction set under different operation conditions and device life cycle stages of the power grid is verified by a digital twin simulation module, whether the verification result meets the system reliability and stability indicators is judged, and a cooperative operation and maintenance scheme that passes the verification is output; Step 7, the cooperative operation and maintenance scheme that passes the verification is real-time issued to each device local controller and regional control center, the system comprehensive performance feedback data after operation and maintenance is collected, whether the whole process is maintained within the safe and stable operation range is judged, and the feedback data is input into the fault propagation model to realize intelligent closed-loop operation and maintenance. 2.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 1 specifically comprises the following steps: Step 1.1, according to the electrical quantity, temperature, vibration and partial discharge data collected by the sensor cluster, combined with the device account and historical fault log, a multi-source heterogeneous time series database is constructed; Step 1.2, data cleaning, alignment and feature extraction are performed on the time series database to obtain standardized device operation feature sequences; Step 1.3, time series analysis algorithm is applied to identify the state degradation trend of the device itself, and association rule mining algorithm is used to analyze the spatio-temporal correlation between different device state sequences; Step 1.4, based on the degradation trend and correlation, a fault propagation directed graph model is constructed with devices as nodes and influence relationships as edges, and the propagation probability and influence weight of the edges are quantified; Step 1.5, the propagation directed graph is updated according to the real-time topology of the power grid, and the model parameters are corrected combined with the physical connection relationship and electrical coupling degree of the device; Step 1.6, when the model predicts that the key propagation path risk exceeds the warning line, trigger a high-risk alarm and record the model parameters, while adaptively adjusting the data acquisition frequency and granularity of related devices. 3.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 2 specifically comprises the following steps: Step 2.1, based on the fault propagation model, calculate the expected influence cumulative value of the target device state deviation along the propagation path on each associated device; Step 2.2, combined with the functional importance of the device in the power grid and the current load rate, weight the expected influence cumulative value to obtain a preliminary associated influence index; Step 2.3, compare the preliminary associated influence index with the historical index and the preset threshold value, if it exceeds the threshold value, mark it as a key influence device, and generate an influence range report; Step 2.4, for key influence devices, backtrack the main influencing factor data of their state deviation, identify whether it is caused by their own degradation, external environment or interconnection device anomaly; Step 2.5, analyze the relevance of the influencing factors and the electrical distance between the devices, the dependence of the control logic, and determine the dominant factor of influence propagation; Step 2.6, if the dominant factor is a specific type of associated anomaly or environmental condition, adjust the monitoring strategy and strengthen the monitoring of the factor and related link devices; Step 2.7, according to the analysis results, dynamically update the calculation weight and threshold value of the associated influence index to more accurately reflect the system's vulnerable links under the current operating mode. 4.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 3 specifically comprises the following steps: Step 3.1, obtain the current power grid operating mode, load level and weather environment information, determine the corresponding standard monitoring strategy template, including the monitoring frequency, parameter type and inspection cycle of each device; Step 3.2, according to the size and influence range of the associated influence index, calculate the adjustment coefficient of the monitoring frequency and inspection cycle; Step 3.3, apply the adjustment coefficient to modify the corresponding values in the standard template to obtain a preliminary optimization strategy for devices; Step 3.4, considering the total amount of operation and maintenance resources, optimize the preliminary optimization strategy to ensure that the resource allocation matches the risk level; Step 3.5, if the modified monitoring frequency or inspection density exceeds the physical limit or economic limit of the device, use the upper limit value for limiting, and trigger additional diagnostic test suggestions; Step 3.6, generate a preliminary optimization strategy report containing monitoring points, frequency, parameters, inspection plan and resource allocation, and push it to relevant operation and maintenance personnel for confirmation or modification. 5.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 4 specifically comprises the following steps: Step 4.1, each regional monitoring substation uses its data to train and optimize the fault propagation model locally, generating local model updates and strategy suggestions; Step 4.2, through the federal learning server, coordinate the uploading of model parameter updates or strategy summaries, rather than raw data, for safe aggregation; Step 4.3, using the aggregated global model parameters, evaluate and optimize the preliminary monitoring strategies of each substation to ensure consistency of monitoring strategies across regional boundary devices and global risk optimization; Step 4.4, integrate real-time cross-regional alarm information to dynamically adjust the focus and response level of collaborative monitoring between adjacent regions; Step 4.5: The globally optimized monitoring strategy is issued to each substation, and each substation updates its local strategy accordingly. Step 4.6: Continuously evaluate the effectiveness of federated learning and adaptively adjust the aggregation algorithm and participation weight according to changes in regional data distribution. 6.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 5 specifically includes the following steps: Step 5.1: Estimate the required resources such as maintenance personnel, spare parts, and detection tools based on the key devices and risk levels determined by the optimized strategy; Step 5.2: Develop a dynamic resource allocation path and schedule based on the current location, availability, and scheduling cost of resources; Step 5.3: If the device association impact index exceeds the first threshold, generate preventive maintenance instructions such as increased patrols, live detection, or minor repairs; Step 5.4: If it exceeds the higher second threshold, generate resource enhancement mode instructions such as scheduling power-off maintenance, allocating standby equipment, or assigning additional expert support; Step 5.5: Combine and sort the maintenance instructions for different devices according to the spatiotemporal logic and dependency relationships to form an executable set of collaborative maintenance instructions; Step 5.6: Simulate the effectiveness of the instruction set on the reliability of the power grid operation and perform iterative optimization. 7.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 6 specifically includes the following steps: Step 6.1: In the digital twin environment, build a high-fidelity model that maps the physical power grid, including device multi-physical field models, network topology, and control logic; Step 6.2: Set different power grid operation scenarios and device aging stage parameters; Step 6.3: Inject the collaborative maintenance instruction set and simulate the execution of maintenance operations and their impact on the system; Step 6.4: Collect key indicator data such as system stability, reliability, and power quality during the simulation process; Step 6.5: Analyze the simulation results to evaluate the effectiveness, economy, and potential risks of the maintenance plan; Step 6.6: If the evaluation results do not meet the pre-set indicators, adjust the timing, scope, or content of the maintenance instructions and re-simulate until the pre-set indicators are met; Step 6.7: Output the verified collaborative maintenance plan and simulation evaluation report. 8.The power intelligent monitoring and operation method based on multi-device cooperative linkage according to claim 1, characterized in that, The step 7 specifically includes the following steps: Step 7.1: Issue the maintenance plan instructions to the execution terminal through a secure communication network; Step 7.2: Monitor the instruction execution status and collect device state and system-level performance data after maintenance operations in real-time; Step 7.3: Analyze the feedback data to evaluate whether the maintenance effect meets the expectations and whether the system risk has been reduced to an acceptable level; Step 7.4: Use the key data, effect evaluation, and environmental factors from this maintenance process as new samples to update the relevant parameters of the fault propagation model; Step 7.5: Use the updated model to perform a new round of risk assessment and strategy optimization, forming a closed loop of monitoring-analysis-decision-execution-evaluation-learning; Step 7.6: Continuously track the effectiveness of the closed loop and regularly evaluate the overall health of the system and calibrate the model.

9. A power intelligent monitoring system based on multi-device cooperative linkage, characterized in that, The system is used to implement the power intelligent monitoring and maintenance method based on multi-device collaborative linkage as claimed in any one of claims 1 to 8, which includes: A multi-source data acquisition and fusion module is configured to acquire and preprocess and fuse operation data and historical records of multiple types of power equipment in real time through a sensor cluster; A fault propagation modeling and analysis module is configured to construct and update a device fault propagation model using a data analysis algorithm, and to calculate a device health deviation and a correlation influence index; A monitoring strategy dynamic optimization module is configured to dynamically adjust a device monitoring priority, frequency, and inspection plan based on the correlation influence index and operation mode, and to generate a preliminary optimization strategy; A global collaborative learning and decision-making module is configured to fuse multi-region data and strategies using a federated learning framework, and to generate a globally collaborative optimized monitoring strategy; An operation and maintenance resource scheduling and instruction generation module is configured to calculate an operation and maintenance resource allocation scheme based on the optimized strategy, and to generate a multi-device collaborative operation and maintenance instruction set based on a risk threshold; A digital twin simulation verification module is configured to verify the effect of the operation and maintenance instruction set in different working conditions in a virtual environment, and to output a verified operation and maintenance scheme; A closed-loop execution and learning module is configured to issue and monitor the execution of the operation and maintenance scheme, collect feedback data to update the model, and realize intelligent closed-loop operation and maintenance management.

Images