Intelligent operation and maintenance management and control method and system based on multi-dimensional configuration consistency check

Abstract

The invention relates to the technical field of consistency checking of a multi-dimensional system, in particular to an intelligent operation and maintenance management and control method and system based on multi-dimensional configuration consistency checking, and aims to realize acquisition and intelligent integration of multi-dimensional data and design a multi-dimensional configuration consistency checking model through an intelligent data filtering algorithm. Analyzing configuration deviation and realizing intelligent feedback control and self-optimization; the prediction maintenance technology based on the model can improve the operation and maintenance efficiency, reduce manual intervention, improve the fault prediction precision, accurately diagnose the equipment fault by using the Kalman filtering technology, and avoid the operation and maintenance risk. Through a state updating and checking mechanism, it is ensured that the system state is consistent with observation data, and the reliability and safety of the system are enhanced; the operation and maintenance cost is reduced through remote monitoring and automatic verification, and intelligent operation and maintenance management of distributed equipment is achieved.

Description

Technical Field

[0001] The present invention relates to the field of multi-dimensional data processing verification technology, and in particular to an intelligent operation and maintenance control method and system based on multi-dimensional configuration consistency verification. Background Art

[0002] At present, the remote operation and maintenance technology of power system automation equipment has become quite mature and widely used in various important places such as substations, power plants, and distribution networks, especially in remote or difficult-to-reach areas. Through these systems, remote automatic monitoring and automated operation and maintenance of power equipment have become possible, greatly reducing the dependence on on-site operation and maintenance personnel and improving work efficiency and safety. Typical remote operation and maintenance systems include functions such as remote equipment status monitoring, automatic fault detection and repair. For example, smart substations can obtain the operating status of equipment in real time through sensors and remote communication technology, and automatically detect faults. When the equipment is abnormal, the system will automatically issue an alarm, analyze the cause of the fault through the expert system of the operation and maintenance center, and make maintenance suggestions, thereby reducing the power outage time caused by equipment failure.

[0003] In addition, intelligent fault diagnosis systems are an important part of existing automated operation and maintenance technologies. By analyzing various data during equipment operation, such as voltage, current, temperature, etc., combined with machine learning algorithms and big data analysis technology, these systems can predict possible equipment failures in advance and provide corresponding early warning mechanisms. This technology effectively avoids significant losses caused by sudden equipment failures. By establishing a multi-dimensional equipment operation data model, existing technologies can predict potential equipment failures and make maintenance recommendations, thereby performing preventive maintenance before equipment failures occur.

[0004] Currently, researchers are working on how to improve the intelligence and adaptability of automated operation and maintenance systems. An important research direction is the automated verification technology for intelligent devices. The core of this type of technology is how to ensure the real-time consistency and automated verification of device status, especially the consistency of input and output of devices under automated control. For example, how to design an automated verification algorithm that can perform real-time verification of the control input and output of different nodes in the system to ensure that the control response of the equipment is consistent with expectations. This technology can not only reduce the workload of manual verification, but also improve the operational reliability of the system, especially in complex and rapidly changing scenarios of power systems.

[0005] Existing technologies have laid a solid foundation for the remote operation and maintenance of smart power equipment, and future research will further promote progress in intelligence, automation, collaborative control and safety, ensuring that power system automation equipment can operate continuously, safely and efficiently in more complex and wider application scenarios.

[0006] In summary, the intelligent operation and maintenance control method and system based on multi-dimensional configuration consistency verification is intended to solve the problems of inconsistent equipment status monitoring and control data, low fault prediction accuracy and low operation and maintenance efficiency in the process of remote automated operation and maintenance of power equipment. In the complex distributed power system, due to unstable network conditions and data transmission delays, the actual operating status of the equipment and the control command cannot be verified in real time, which increases the operation and maintenance risk. In addition, the traditional fault prediction method cannot fully consider multi-dimensional data such as equipment status, environmental parameters, and control input, resulting in insufficient prediction accuracy and inability to effectively perform preventive maintenance. Through the multi-dimensional data verification model and intelligent data filtering algorithm proposed in the present invention, the consistency of equipment status and control commands can be ensured, and the accuracy of fault prediction can be improved. At the same time, the present invention reduces the reliance on manual operations through an automated verification mechanism, significantly improves the efficiency and reliability of remote automated operation and maintenance, and is particularly suitable for applications in multi-node distributed power systems, reducing operational risks in equipment operation and maintenance. Summary of the invention

[0007] In view of the above problems existing in the prior art, the present invention is proposed.

[0008] Therefore, the technical problem to be solved by the present invention is to solve the problems of inconsistency between equipment status monitoring and control instructions, insufficient fault prediction accuracy and low operation and maintenance efficiency in the remote automated operation and maintenance process of distributed power systems. Through multi-dimensional data verification models, intelligent data filtering algorithms and automated verification mechanisms, the real-time consistency between equipment status and control inputs is ensured, the accuracy of fault prediction is improved, and manual operations are reduced, which significantly improves the efficiency, reliability and safety of remote automated operation and maintenance, and is particularly suitable for complex multi-node distributed power systems.

[0009] To solve the above technical problems, the present invention provides the following technical solutions, an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification, including: using an intelligent data filtering algorithm to perform multi-dimensional data collection and intelligent integration; designing a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations; based on the verification results, realizing intelligent feedback control and self-optimization mechanism; using predictive maintenance technology based on the multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk control.

[0010] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, wherein: the multi-dimensional data collection collects device status, operating parameters, and environmental data through different devices to grasp the real-time status of device operation; The intelligent integration performs intelligent processing and fusion of the collected multi-dimensional data, integrates the data through an intelligent data filtering algorithm, and eliminates redundancy between data sources.

[0011] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, wherein: the deviation between the multi-dimensional configurations is analyzed by collecting and integrating multi-dimensional data, and a multi-dimensional configuration consistency verification model is used to analyze the deviation between the actual operating status of the equipment and the preset configuration.

[0012] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, wherein: the verification result is obtained by analyzing the multi-dimensional configuration consistency verification model, comparing the multi-dimensional configuration data with the preset standard, determining the potential risks, and serving as the basis for optimization and feedback control; The intelligent feedback control automatically executes control measures and adjusts equipment status and operating parameters according to the verification results; The self-optimization mechanism automatically adjusts the calibration standards and optimizes the operating parameters through data accumulation and continuous learning to achieve self-adaptation.

[0013] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, the predictive maintenance technology is based on a multi-dimensional configuration consistency verification model, and predicts potential failure points of the equipment by analyzing the operation trend and data fluctuation of the equipment, and performs preventive maintenance; The intelligent operation and maintenance risk control, through intelligent operation and maintenance management, uses a multi-dimensional configuration consistency verification model to further diagnose faults and take repair measures for potential fault points monitored by predictive maintenance technology.

[0014] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, wherein: the intelligent data filtering algorithm is improved based on the Kalman filter, including state update equation, measurement update equation, Kalman gain, state prediction update and covariance update; The state update equation is expressed as: , in, Indicates the current time The multidimensional state variables, Indicated in The state variables at time, represents the state transfer matrix, represents the control input, represents the control input matrix, represents process noise; When state transfer occurs, the current device state is predicted according to the state update equation; When a change of more than 10% occurs, it means that the value change exceeds 10% compared with the current state at the previous moment, and the current device state is predicted based on the value change. ;when When it exceeds the preset threshold of 0.05, it indicates that the equipment is disturbed by process noise, and the confidence of the state prediction is reduced; The measurement update equation is expressed as: , in, represents the observed value, represents the observation matrix, represents the measurement noise; When the observation value is obtained, the current device state prediction is adjusted according to the measurement update equation; When it is less than the system preset threshold of 0.01, it indicates that the measurement noise is within the preset range, and the observation value is reliable data. The state prediction is updated based on the observation value. When the element coefficient changes by more than 5%, it indicates that the observation model resets the measurement method, that is, the parameters of the measurement equipment and the measurement method change, and the observation value is associated with the state according to the newly set measurement method; The Kalman gain is expressed as: , in, represents the Kalman gain, represents the state covariance prediction matrix, represents the measurement noise covariance matrix, Represents the observation matrix The transposed matrix of When the forecast error covariance When the Kalman gain exceeds the system preset threshold of 0.01, Increases, indicating that the uncertainty of the system prediction increases, and the state is updated according to the observed value; when the observation noise covariance exceeds the preset threshold of 0.05, the Kalman gain decrease, indicating that the reliability of the observed value decreases, then the system relies on the predicted state; The state prediction update is expressed as: , in, express Combined with the current observation value at the moment The predicted value of the state, express The predicted value of the state at the moment; When the observed value With the predicted value When the difference between the two is greater than the preset threshold of 10%, the system uses the Kalman gain Adjusting the state prediction value , and reduce the difference to within the set error range of 5%; when the Kalman gain When it exceeds the preset threshold of 0.7, the system state update depends on the observed value; The covariance update is expressed as: , in, represents the covariance matrix, represents the identity matrix; When the Kalman gain and the observation matrix The product of satisfies When , the covariance matrix is ​​used to adjust the system prediction error; when When , it indicates that the system's dependence on the observed data reaches 90%, and the covariance matrix When , the uncertainty of the prediction decreases; When , it indicates that the system relies on state prediction, the cosquare matrix remains greater than 90% of the original value, and the prediction error increases by more than 5%.

[0015] As a preferred solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in the present invention, wherein: the multi-dimensional configuration consistency verification model includes a multi-dimensional state estimation formula, a consistency verification formula and a verification adjustment formula; The multidimensional state estimation formula is expressed as: , in, Indicates time The multidimensional state vector of represents the system state vector at the previous moment, represents the state transfer matrix, Indicates The control input influence matrix of dimension, Indicates the current moment The control input of the dimension, represents process noise; The consistency check formula is expressed as: , in, represents the consistency check value at the current moment, Indicates The observation matrix of dimension, represents the observed value of the dimension, Represents the total number of different dimensions in the system; The calibration adjustment formula is expressed as: , in, represents the state covariance matrix, Represents the consistency view mapping matrix between different dimensions, Represents the transpose of the consistency view mapping matrix; When a state transition occurs, the system uses a multidimensional state estimation formula to predict the system state at the current moment; when the control input When the change exceeds 5%, the system automatically adjusts the impact matrix ; When the check value When the preset threshold value exceeds 0.1, it indicates that the configurations of the dimensions are inconsistent. When it is less than 0.05, it means that the deviation between the system state and the observed value is small, and the system configuration consistency is good; When the Kalman gain When it exceeds 0.8, it means that the system is highly dependent on the current observation value, so the system reduces its dependence on the observation value and switches to a state prediction model; when the Kalman gain When it is lower than 0.3, it indicates that the system has low credibility in state prediction, and the system increases its reliance on observations and updates state estimates.

[0016] Another object of the present invention is to provide an intelligent operation and maintenance control system based on multi-dimensional configuration consistency verification, which can obtain device status information in real time and perform automatic verification and filtering of multi-dimensional data during the operation of distributed devices, reduce the occurrence of failures through accurate prediction of the device operation status, and improve the operation and maintenance efficiency and reliability of the system. At the same time, the system can provide early warning of abnormal status and potential risks, realize intelligent fault diagnosis and automatic verification, ensure the stable operation of equipment in a complex operating environment, reduce maintenance costs and improve the overall intelligence level of operation and maintenance management.

[0017] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent operation and maintenance management system based on multi-dimensional configuration consistency verification, comprising: a multi-dimensional data acquisition model, a configuration verification model, a feedback optimization model and a maintenance diagnosis model; The multi-dimensional data collection model uses an intelligent data filtering algorithm to perform multi-dimensional data collection and intelligent integration; The configuration verification model designs a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations; The feedback optimization model realizes intelligent feedback control and self-optimization mechanism based on the verification results; The maintenance diagnosis model adopts predictive maintenance technology based on a multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk management.

[0018] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification as described above are implemented.

[0019] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification as described above are implemented.

[0020] The beneficial effects of the present invention are: improving operation and maintenance efficiency: through intelligent data filtering algorithm and multi-dimensional configuration consistency verification model, real-time monitoring and prediction of equipment status are realized, the frequency and complexity of manual intervention are reduced, and the efficiency of remote automated operation and maintenance is improved.

[0021] Improve the accuracy of fault prediction: The present invention utilizes technologies such as Kalman filtering, combined with multi-dimensional data verification, to accurately predict potential equipment failures, thereby improving the accuracy of fault diagnosis and prediction accuracy, and effectively avoiding operation and maintenance risks caused by inaccurate predictions.

[0022] Enhance the reliability and security of the system: Through the status update and verification mechanism, the present invention can make timely adjustments when the equipment status deviates, ensure the high consistency of the system status and the observed data, ensure the reliability of the operation and maintenance process, and reduce the risk of misoperation.

[0023] Reduce operation and maintenance costs: Through remote real-time monitoring and automated verification, the present invention reduces the need for on-site maintenance personnel, optimizes resource allocation, and reduces the overall cost of operation and maintenance.

[0024] Realize intelligent operation and maintenance management: The present invention integrates multiple automation functions by combining intelligent operation and maintenance control technology, can dynamically adjust system parameters according to the actual operating status, realize intelligent and refined management of distributed equipment, and improve the flexibility and adaptability of the operation and maintenance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0026] Figure 1A flowchart of an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification provided by an embodiment of the present invention.

[0027] Figure 2 An average fault detection diagram of an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification provided by an embodiment of the present invention.

[0028] Figure 3 This is a diagram showing the cumulative downtime of two groups of systems within 30 days of an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification provided by an embodiment of the present invention.

[0029] Figure 4 The accuracy of fault detection in the experimental group of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification provided by an embodiment of the present invention is shown in FIG. Figure 5 A graph of the number of interventions by two groups of workers in an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0031] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification, including: S1: Use intelligent data filtering algorithms to collect and intelligently integrate multi-dimensional data.

[0032] S2: Design a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations.

[0033] S3: Based on the verification results, intelligent feedback control and self-optimization mechanism are realized.

[0034] S4: Use predictive maintenance technology based on a multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk management.

[0035] Among them, the goal of S1 is to establish a real-time data collection system covering multiple dimensions such as equipment status, environmental parameters, and historical operation and maintenance records; and through IoT devices, sensors, and edge computing technology, automatically collect and pre-process operating data from various dimensions and achieve seamless integration of cross-platform data; introduce intelligent data filtering algorithms to filter redundant data in real time, retain only useful information, improve data processing efficiency, and integrate data into a central database to provide accurate basis for subsequent analysis; The goal of S2 is to develop a multi-dimensional consistency verification algorithm to automatically analyze the deviations between multi-dimensional configurations to ensure the accuracy of configuration and actual operation; based on historical data, real-time data and predetermined standard configurations, through a multi-level verification model, dynamically analyze the consistency of configurations. When deviations are found, warnings are immediately issued and optimization suggestions are provided; adaptive algorithms are used to automatically adjust the system verification values ​​to ensure that configuration deviations can be accurately identified and corrected in real time in different scenarios to achieve continuous optimization; S3 is the result of the model based on S2. Its purpose is to adjust the equipment configuration based on the verification results through the automated feedback system to maintain system stability. It also establishes an intelligent feedback adjustment mechanism. The equipment receives feedback from the consistency verification module in real time, automatically adjusts the configuration, optimizes the equipment working status, and avoids configuration conflicts and efficiency losses. It predicts the optimal configuration path of the system based on past operating data, realizes equipment self-adaptation and self-optimization, thereby reducing manual intervention and improving the autonomy and reliability of system operation. S4 is also based on the S2 model. Its purpose is to achieve predictive maintenance of equipment through multi-dimensional data analysis, identify potential faults in advance, comprehensively manage risks in the operation and maintenance system, and ensure the stability and security of the system under multi-dimensional configuration. It adopts model-based predictive maintenance technology, combined with historical data and real-time data analysis, to intelligently diagnose potential equipment failures and provide dynamic maintenance suggestions for equipment to improve system reliability.

[0036] Example 2, reference Figure 1 , is an embodiment of the present invention, which provides an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification, including: multi-dimensional data collection, collecting device status, operating parameters, and environmental data through different devices to grasp the real-time status of device operation; in this way, the real-time status of device operation can be fully grasped, and data support can be provided for subsequent operation and maintenance decisions to ensure that the system has a sufficient information basis; Intelligent integration: intelligently process and fuse the collected multi-dimensional data, integrate data through intelligent data filtering algorithms, eliminate redundancy between data sources, improve data quality, and provide a reliable basis for subsequent analysis, prediction, and decision-making; Verification results: By analyzing the multi-dimensional configuration consistency verification model, the results are obtained, and the multi-dimensional configuration data is compared with the preset standards to determine potential risks, which will serve as the basis for optimization and feedback control. The verification results will serve as the basis for subsequent optimization and adjustment, helping the system to identify configurations that need to be improved or adjusted, and ensuring that the system status fluctuates within a reasonable range. Intelligent feedback control automatically executes control measures and adjusts equipment status and operating parameters based on the verification results. When the verification results show that the system configuration is deviated, the intelligent feedback control will automatically adjust the operating parameters or configuration based on the real-time data of the system to ensure the stability of the system operation. It is an autonomous adjustment mechanism that reduces manual intervention. Self-optimization mechanism, through data accumulation and continuous learning, automatically adjusts the calibration standards and optimizes the operating parameters to achieve self-adaptation; the self-optimization mechanism can adjust the parameter settings based on historical data, calibration results and system feedback without human intervention, and gradually improve the operating efficiency; Predictive maintenance technology is based on a multi-dimensional configuration consistency verification model. It analyzes the operation trend and data fluctuations of the equipment, predicts potential equipment failure points, and performs preventive maintenance. Preventive maintenance aims to prevent equipment failures by discovering problems in advance. It can efficiently manage the operation and maintenance of equipment at different time points. Predictive maintenance is more inclined to preventive measures. Intelligent operation and maintenance control risks. Through intelligent operation and maintenance management, a multi-dimensional configuration consistency verification model is used to further diagnose potential fault points obtained through predictive maintenance technology monitoring, and repair measures are taken. Moreover, measures can be taken before risks occur to reduce the probability of equipment failures and accidents, and improve the overall operating efficiency and safety of the system.

[0037] Furthermore, the intelligent data filtering algorithm is improved based on the Kalman filter, including the state update equation, the measurement update equation, the Kalman gain, the state prediction update, and the covariance update; The state update equation is expressed as: , in, Indicates the current time The multi-dimensional state variables, namely the current device state, include temperature, humidity, voltage, Indicated in The state variable at the moment, that is, the device state at the previous moment, Represents the state transfer matrix, that is, the transfer process from the previous moment to the current state, represents the control input, that is, the system The control variables at all times include adjusting voltage, adding cooling devices and dehumidification devices, represents the control input matrix, which affects the effect of the control input on the state, Represents process noise, i.e., random disturbances in the system, and follows a normal distribution , noise level It can be measured based on historical data; When state transfer occurs, the current device state is predicted according to the state update equation; When a change of more than 10% occurs, it means that the value change exceeds 10% compared with the current state at the previous moment, and the current device state is predicted based on the value change. ;when When it exceeds the preset threshold of 0.05, it indicates that the equipment is disturbed by process noise, and the confidence of the state prediction is reduced; Among them, the 10% change range is usually used to determine whether the state change is significant enough to adjust the system. If the state variable changes within 10%, it means that the system state change is small and can be regarded as noise or normal fluctuations, and there is no need to immediately update the state estimation or adjust the system control. If it exceeds 10%, it means that the system state has changed significantly, and the system needs to intervene to re-estimate or update the state. It is emphasized that changes exceeding the 10% range indicate that the difference between the system state and the expected state exceeds the range of normal fluctuations. The system re-evaluates the current state and makes adjustments based on this difference. By setting a value such as 10%, it can effectively filter out small random disturbances or noise interference to the system, ensuring that the system triggers state updates only when necessary, reducing unnecessary adjustments. The setting of the noise threshold of 0.05 is usually used to determine whether the noise level in the system measurement value exceeds the preset range. If the noise exceeds 0.05, it means that the measurement data may be subject to greater interference and is unreliable, and the system needs to take measures to handle abnormal data. By setting the threshold, the system can ensure that the credibility of the measurement data decreases when the noise is too large, and adjust the accuracy of the state prediction accordingly. Through real-time monitoring of device status (temperature, humidity, voltage), combined with the state transfer matrix and the control input matrix , to predict the status of the equipment; set the initial temperature of the equipment to 45℃. If the temperature continues to rise and exceeds 49.5℃, the threshold value will be converted to (45℃±4.5℃), and the status update mechanism will be triggered. At this time, the system detects abnormal temperature rise, and the cooling device starts to work until it returns to the initial temperature. At the same time, the system humidity is taken into account. When the humidity rises to 60%, automatic dehumidification begins; when the voltage fluctuation exceeds 10%, the equipment load increases, and the system starts to adjust the voltage to ensure that it does not exceed the threshold range of ±10% after adjustment; The measurement update equation is expressed as: , in, Indicates the observed value, i.e. temperature, humidity, voltage, which represents the system's observation data of the real-time status of the device. Represents the observation matrix, which maps the actual state of the device into the observation space. Represents measurement noise, that is, possible interference or error in the observation process, according to the measurement instrument settings, satisfying ; When the observation value is obtained, the current device state prediction is adjusted according to the measurement update equation; When it is less than the system preset threshold of 0.01, it indicates that the measurement noise is within the preset range, and the observation value is reliable data. The state prediction is updated based on the observation value. When the element coefficient changes by more than 5%, it indicates that the observation model resets the measurement method, that is, the parameters of the measurement equipment and the measurement method change, and the observation value is associated with the state according to the newly set measurement method; The threshold is set to 0.01 to determine the size of the measurement noise; if the measurement noise If the value is less than this threshold, it means that the influence of noise is within an acceptable range, the measurement data can be considered reliable, and there is no need to make major adjustments to the state estimation. By setting the threshold, very weak noise can be filtered out to ensure that the system responds only when the noise significantly affects the measurement data, avoiding the system from responding to every tiny change and improving the stability of the system. The 5% setting means that if the observation matrix If the elements of the matrix change by more than 5%, the system judges that there is a significant deviation between the device state and the measurement method, so the measurement method and state estimation model need to be adjusted; the 5% change is usually used as the limit for judging that the configuration of the observation system has changed significantly. When the change of the observation matrix is ​​within 5%, it is considered that the system fluctuates normally. If it exceeds 5%, it means that the system structure or the setting of the measurement device has changed significantly, and the observation type needs to be readjusted; If the coefficient of the observation matrix element changes by more than 5% (the temperature and humidity sensor sensitivity coefficients fluctuate), the system automatically determines that the accuracy of the model has decreased. At this time, the system recalibrates the measurement equipment and updates the observation matrix. When the noise level of the voltage measurement value remains at 0.005V (less than 0.01V), but the voltage coefficient in the observation matrix changes by more than 5%, the system also triggers the adjustment mode to ensure that the final voltage output is within the range of ±10%. The Kalman gain is expressed as: , in, Represents the Kalman gain, which measures the weight of the current prediction and observation, and affects the update equation of the system state. Represents the state covariance prediction matrix, the matrix elements include temperature, humidity and voltage, which is represented in Always The uncertainty of the system state at the moment, and measures the current state The prediction accuracy, the larger the covariance matrix, the greater the prediction error. For temperature control, the initial value is set in the range of 0.1~0.2; It represents the measurement noise covariance matrix, which indicates the size of the noise or error that may exist in the observation process, and measures the uncertainty of the observation data. If the measurement noise is large, the credibility of the observation data is low, and the system should rely more on state prediction. At the same time, it describes the impact of observation noise on the observation value. When the observation data noise is large, the Kalman filter will rely more on state prediction rather than measurement value. In temperature measurement, it is set to 0.01~0.05 according to the sensor accuracy. Represents the observation matrix The transposed matrix of Set to the calibration value of the sensor sensitivity, which is 1.0. In matrix operations, the transposed matrix swaps the rows and columns of the matrix, helping the system to adjust the observation error back to the dimension of the system state, making the state update more accurate; When the forecast error covariance When the Kalman gain exceeds the system preset threshold of 0.01, Increases, indicating that the uncertainty of the system prediction increases, and the state is updated according to the observed value; when the observation noise covariance exceeds the preset threshold of 0.05, the Kalman gain decrease, indicating that the reliability of the observed value decreases, then the system relies on the predicted state; The threshold is set to 0.01, which means that when the prediction error covariance When this value is exceeded, the system considers that the uncertainty of the prediction increases, and its function is to determine whether the prediction error of the system exceeds the acceptable range; when the prediction error exceeds 0.01, it means that the accuracy of the system's state prediction decreases, and the system needs to adjust the Kalman gain so that the subsequent state update depends more on the observed value rather than the predicted value; 0.01 is selected as the threshold to avoid frequent adjustments in practical applications; the threshold is set to 0.05, which means that when the influence of the observation noise covariance exceeds this threshold, the system will consider that the observation noise is too large and affects the reliability of the observation value. When the observation noise exceeds 0.05, the system judges that the quality of the observation data has decreased, and the measurement value may have a large uncertainty; at this time, the system should reduce its reliance on the observation value and rely more on the predicted value to maintain the robustness of the state estimation; the purpose of setting it to 0.05 is to decide whether to trust the current observation data by reasonably distinguishing the sound level, so as to maintain the reliance on the observation value when the noise is small, and reduce the reliance on it when the noise is large; The system monitors the voltage of the equipment in real time through sensors. The fluctuation range is initially set to ±0.05V. If the voltage is stable within the range of 220V±0.05V, the system will continue to monitor through measurement update equations. During operation, the equipment load continues to increase, and the voltage also increases, exceeding the preset range. At the same time, the noise parameter also reaches the critical value. According to the adjusted Kalman gain , and start to dynamically reduce the voltage output load and adjust the voltage to return it to the range of ±0.05V; the system detects temperature and humidity in conjunction with voltage fluctuations. During the voltage fluctuation adjustment period, the temperature and humidity will increase accordingly. Through the prediction model and adjustment feedback, the cooling and dehumidification devices are started to ensure that the temperature returns to the set 45°C and the humidity returns to the range of 60%±2%; The state prediction update is expressed as: , in, express Combined with the current observation value at the moment The state prediction value, that is, the state update value obtained after the latest observation, refers to the temperature, humidity and voltage of the device. express The state prediction value at the moment is based on the previous state information and the system's state transition model. The state prediction value at the moment, that is, the temperature, humidity and voltage predicted based on the system model, is not combined with the observation data at the moment and is only a prediction value; When the observed value With the predicted value When the difference between the two is greater than the preset threshold of 10%, the system uses the Kalman gain Adjusting the state prediction value , and reduce the difference to within the set error range of 5%; when the Kalman gain When it exceeds the preset threshold of 0.7, the system state update depends on the observed value; Among them, when the observed value With the predicted value When the difference between the predicted value and the observed value exceeds the prediction threshold of 10%, the system considers that the prediction error is large and needs to be adjusted. The threshold of 10% is set to ensure that when the error between the predicted value and the observed value exceeds a certain range, the system can respond quickly and make corrections; 10% is selected as the threshold to maintain the prediction accuracy of the system within a certain error range, but at the same time avoid frequent adjustments to smaller fluctuations that affect system stability; after the Kalman gain adjustment, the system adjusts To reduce the error and control the prediction error within 5%, the 5% error range is set to ensure the adjusted state prediction value It can maintain a high consistency with the observed value to ensure the accuracy and reliability of the system; 5% is selected as the final error range, which can not only tolerate small errors in the system but also ensure that the deviation between the prediction and the actual does not affect the operation of the system; when the Kalman gain ,When it exceeds the set threshold of 0.7, it indicates that the system relies more on the observed data for ,status updates.,The purpose of selecting 0.7 as the threshold is that when the credibility of the system ,observation data is high, the system needs to rely more on the observed data rather ,than the predicted value for updating, thus ensuring the effective use of the observed data; The system observes the temperature and humidity of the equipment in real time, and combines the measurement update equation to monitor the humidity and humidity. When the difference between them obtained according to the state observation equation exceeds the preset threshold of 10%, the system adjusts the predicted value through the Kalman gain until the error is identified to be reduced to a reasonable error range of 5%. During this period, the system will trigger the cooling device and adjust the voltage to reduce the load to ensure that the humidity and temperature are within the normal range; the system readjusts the covariance matrix according to the predicted data in the formula to ensure the accuracy of the predicted state; combined with the state prediction update formula, when the system detects that the difference between voltage fluctuation and temperature exceeds the preset threshold of 10%, the system adjusts the Kalman gain according to the data change, reduces the fluctuation error to 5%, triggers the cooling device, and adjusts the voltage while reducing the temperature; The covariance update is expressed as: , in, Represents the covariance matrix, which represents the distribution of the estimation error and is used to adjust the weight of the Kalman gain. Represents the identity matrix, ensuring that the matrix can be standardized without changing. When the partial operation of occurs, the identity matrix ensures that after the subtraction operation, the covariance matrix can still be maintained in the correct dimension and form, and the adjusted system error reflects the balance between the prediction and observation results; when the Kalman gain is large, the subtracted part is large, the system relies more on the observed data for updating, and the adjustment range is large; on the contrary, if If it is smaller, the system relies more on predictions and makes fewer adjustments; When the Kalman gain and the observation matrix The product of satisfies When , the covariance matrix is ​​used to adjust the system prediction error; when When , it indicates that the system's dependence on the observed data reaches 90%, and the covariance matrix When , the uncertainty of the prediction decreases; When , it indicates that the system relies on state prediction, the cosquare matrix remains greater than 90% of the original value, and the prediction error increases by more than 5%; Among them, when , indicating that the system's reliance on the observed data has reached 90%. This is a high reliance value, indicating that the system trusts the accuracy of the observed data more at this time and believes that the observed data is more reliable than the predicted value; therefore, the Kalman gain , will decrease at this time, reducing the reliance on system state prediction and relying more on observations to update the system state; setting 90% as the limit ensures that when the observation data is reliable enough, the system can adaptively adjust its behavior and improve the prediction accuracy; when When , it indicates that the system mainly relies on state prediction, the credibility of observation data is low, and the system believes that the observation data may be affected by greater interference or noise; at this time, the Kalman gain increases so that the system relies more on its own state prediction rather than observation data; this setting is to avoid the system mistakenly relying on these data to make adjustments when the observation data is unreliable, and the threshold is set to 0.1 to ensure that in extreme cases, the system can still obtain stable results from the prediction; this setting is to ensure that when the system relies on state prediction, the covariance matrix Maintain at a high level and maintain the original confidence level; setting it to 90% is to allow a small amount of deviation while maintaining a high system accuracy, ensuring that even if the system relies on predictions, it can still make a high confidence judgment on the state; when the prediction error increases by more than 5%, it indicates that the difference between the observed data and the predicted value is too large, and the system needs to make a larger adjustment of 5% as the threshold in order to balance the sensitivity of prediction accuracy and error adjustment, and avoid frequent adjustments to small errors, but when the error exceeds a certain range, the system should take corresponding measures to correct it; when When the system's predictions match the observed values ​​by 90%, the system can automatically optimize the cooling system to ensure that the temperature and voltage remain within the set range. If the temperature fluctuation continues to rise and exceeds the 10% error range, the system will reduce its dependence on the observed values ​​by lowering the Kalman gain, and readjust the output of the cooling equipment to ensure that the system temperature is reduced and stabilized at the target value. When the humidity sensor detects that the humidity is constantly rising and the deviation of the observed value gradually exceeds 10%, the system uses the Kalman gain to adjust it, setting it to 0.7 and reducing the prediction error to 5%. At this time, the dehumidification device is enabled to adjust the humidity to the threshold range to ensure stable operation of the power equipment.

[0038] Furthermore, the multi-dimensional configuration consistency verification model includes a multi-dimensional state estimation formula, a consistency verification formula, and a verification adjustment formula; The multidimensional state estimation formula is expressed as: , in, Indicates time The multi-dimensional state vector of, including temperature, humidity and voltage, represents the system state vector at the previous moment, Represents the state transfer matrix, which is used to describe the previous state To the current state changes, Indicates The control input influence matrix of dimension, Indicates the current moment The control input of the dimension, represents the process noise, which is assumed to be a normal distribution with zero mean; The consistency check formula is expressed as: , in, Indicates the consistency check value at the current moment, which is used to evaluate the state deviation in different dimensions. Indicates The observation matrix of dimension, represents the observed value of the dimension, Represents the total number of different dimensions in the system; The calibration adjustment formula is expressed as: , in, represents the state covariance matrix, Represents the consistency view mapping matrix between different dimensions, representing the relationship between state and observation, Represents the transpose of the consistency view mapping matrix; When a state transition occurs, the system uses a multidimensional state estimation formula to predict the system state at the current moment; when the control input When the change exceeds 5%, the system automatically adjusts the impact matrix ; When the check value When the preset threshold value exceeds 0.1, it indicates that the configurations of the dimensions are inconsistent. When it is less than 0.05, it means that the deviation between the system state and the observed value is small, and the system configuration consistency is good; When the Kalman gain When it exceeds 0.8, it means that the system is highly dependent on the current observation value, so the system reduces its dependence on the observation value and switches to a state prediction model; when the Kalman gain When it is lower than 0.3, it means that the system has low credibility in state prediction, so the system increases its reliance on observations and updates the state estimate; Among them, when the control input When the change exceeds 5%, it means that the change of the device status has exceeded the acceptable error range, and the system will make adjustments to modify the matrix To reflect this change; 5% as a change threshold is to ensure that the system can capture significant changes without being overly sensitive to slight fluctuations. This setting plays an important role in balancing sensitivity and error control; calibration value When the value exceeds the threshold of 0.1, it indicates that the configurations of the dimensions are inconsistent. 0.1 is used as the threshold to maintain a small error between dimension configurations. This value can ensure the accuracy of the verification model without triggering frequent adjustments due to small errors. The setting of 0.1 ensures that the system can run stably and make appropriate adjustments. When the deviation is less than 0.05, it indicates that the difference between the system state and the observed value is very small. The system can be considered to be consistent in configuration. 0.05 is used as the error range to ensure high consistency between the observed value and the system state and reduce unnecessary adjustments. This value can ensure that the system runs in a highly precise state and avoid frequent adjustments due to small deviations. When When it is greater than 0.8, the system is highly dependent on the observed values, indicating that the observed values ​​are more reliable than the predicted values. 0.8 is a high dependency value, indicating that in most cases, the system should rely more on the observed data rather than the prediction model. This setting ensures that the system will make full use of the real-time data when the observed data is reliable. When it is less than 0.3, it means that the system is less dependent on the observed value and more dependent on the state prediction model; 0.3 is a lower dependency value threshold to ensure that when the observed data is unreliable or noisy, the system relies on its own prediction results to update the state and maintain stability; When the system detects that the temperature rises by more than 5% and the humidity rises by 5% during the equipment status monitoring process, the system will automatically enable the multi-dimensional status prediction model and verification model to ensure that the equipment can still operate stably within the range of changes. The system estimates the future status of the equipment through the status update equation; The system collects all-round data on the temperature, humidity and voltage of the equipment status. For the monitoring of equipment temperature and voltage, the system calculates the consistency check value , to ensure multi-dimensional configuration consistency, when checking the value When it is lower than 0.05, it means that the status configurations of the various dimensions of the equipment are relatively consistent, and the system maintains stable operation; if the temperature fluctuation is within 2%, and the humidity and voltage fluctuations are both less than 1%, the system will not make further adjustments. The system automatically determines that the calibration error is extremely small in this state, and the equipment is running stably; During the operation of the system, if it is detected that the difference between the observed value and the predicted value exceeds 10%, the system will adjust the Kalman gain and covariance matrix to ensure the operating status of the equipment; when it is detected that the voltage fluctuation exceeds 0.1V, the system will use the calibration adjustment formula to automatically correct the state model to ensure the operating status.

[0039] The above is a schematic scheme of an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification in this embodiment. It should be noted that the technical solution of the system of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification belongs to the same concept as the technical solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification mentioned above. The details not described in detail in the technical solution of the intelligent operation and maintenance control system based on multi-dimensional configuration consistency verification in this embodiment can be found in the description of the technical solution of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification mentioned above.

[0040] Embodiment 3 is an embodiment of the present invention, which provides an intelligent operation and maintenance management system based on multi-dimensional configuration consistency verification, including: a multi-dimensional data acquisition model, a configuration verification model, a feedback optimization model and a maintenance diagnosis model; The multi-dimensional data collection model uses an intelligent data filtering algorithm to perform multi-dimensional data collection and intelligent integration; The configuration verification model designs a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations; The feedback optimization model realizes intelligent feedback control and self-optimization mechanism based on the verification results; The maintenance diagnosis model adopts predictive maintenance technology based on a multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk management.

[0041] This embodiment further provides a computing device, which is applicable to the case of an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification, including: Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent operation and maintenance management method based on multi-dimensional configuration consistency verification as proposed in the above embodiment.

[0042] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification as proposed in the above embodiment is implemented.

[0043] The storage medium proposed in this embodiment and the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0044] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0045] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0046] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0047] Example 4, reference Figure 2-Figure 5 , is an embodiment of the present invention. This embodiment provides an intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0048] Experimental setup: Control group: Use the traditional manual operation and maintenance management system.

[0049] Experimental group: Use an intelligent operation and maintenance management system based on multi-dimensional consistency verification, with automatic feedback and predictive maintenance functions.

[0050] Experimental indicators: ①Fault detection time ②Accuracy of fault prediction ③System downtime ④ Efficiency of system updates ⑤Number of times manual intervention is required Experimental steps: Control group: simulates the traditional manual operation and maintenance management system. Monitoring relies on manual inspection and planned maintenance, and fault handling is mainly reactive maintenance.

[0051] Experimental group: simulated intelligent operation and maintenance control system, which can collect equipment data in real time, process data through multi-dimensional verification models, and proactively predict failures based on predictive analysis and perform automatic maintenance.

[0052] Data collection: (1) Record the system running time and downtime of the two groups.

[0053] (2) Record the fault detection and prediction status of the two groups.

[0054] (3) Measure the response time of the two groups in fault handling and system updates.

[0055] Experiment duration: 30 days of uninterrupted operation.

[0056] Experimental data: As shown in Table 1 below: Table 1 Experimental data record table , Chart Description: like Figure 2 As shown in the figure, the fault detection time of the experimental group was about 10 minutes, while the fault detection time of the control group was close to 40 minutes. This shows that the intelligent operation and maintenance system of the experimental group can detect faults in the system faster than the control group, reducing the detection delay by 30 minutes. This efficiency improvement is attributed to the application of intelligent algorithms, which can quickly identify changes in equipment status and respond, avoiding long-term reliance on manual intervention or traditional detection methods.

[0057] Among them, the vertical axis represents time. The blue bar graph represents the fault detection time of the control group, which is about 40 minutes; the yellow bar graph represents the fault detection time of the experimental group, which is about 10 minutes.

[0058] like Figure 3As shown in the figure, the system downtime of the experimental group within 30 days was significantly less than that of the control group. The cumulative downtime of the control group within 30 days was about 10 hours, while that of the experimental group was only about 3 hours. The system downtime of the experimental group showed a relatively small growth trend over time, indicating that the intelligent management system of the experimental group can effectively reduce the number and duration of system downtime, handle faults in a timely manner, and maintain the stable operation of the system.

[0059] Among them, the vertical axis represents the downtime, the horizontal axis represents the number of days, and the yellow line shows the cumulative downtime of the control group system within 30 days, which gradually increases to about 10 hours; the blue line shows the cumulative downtime of the experimental group system within 30 days, and the cumulative downtime is less, about 3 hours.

[0060] like Figure 4 As shown in the figure, the fault prediction accuracy of the experimental group reached 95%, and only 5% of the predictions were inaccurate. This shows that the intelligent operation and maintenance system in the experimental group showed extremely high reliability in predicting equipment failures. Such a high accuracy rate can reduce unnecessary maintenance and downtime, improve the continuous operation capability of the system, and reduce the additional resource consumption caused by false alarms.

[0061] Among them, accurate predictions in the green area accounted for 95%, and inaccurate predictions in the red area accounted for 5%.

[0062] like Figure 5 As shown in the figure, the number of manual interventions in the experimental group was close to 0, while the number of manual interventions in the control group was close to 20. The experimental group required almost no manual intervention during the entire experiment, which shows that the intelligent system in the experimental group has a high level of automation and can deal with most problems autonomously, significantly reducing the frequency and workload of manual intervention. This advantage is particularly important in large-scale systems, helping to reduce labor costs and improve operation and maintenance efficiency.

[0063] Among them, the yellow bar chart indicates the number of manual interventions required by the control group, which is close to 20 times; the blue bar chart indicates the number of manual interventions required by the experimental group, which is less than 2 times.

[0064] From the four charts, the experimental group showed significant advantages in fault detection time, system downtime, fault prediction accuracy, and number of manual interventions. This shows that the intelligent operation and maintenance system of the experimental group has a significant effect in improving operation efficiency, reducing downtime, and reducing dependence on manual intervention. These advantages play an important role in improving the stability and reliability of equipment.

[0065] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification, characterized by: include: Use intelligent data filtering algorithms to collect and intelligently integrate multi-dimensional data; Design a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations; Based on the verification results, intelligent feedback control and self-optimization mechanism are realized; Use predictive maintenance technology based on a multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk management.

2. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 1, characterized in that: The multi-dimensional data collection collects device status, operating parameters, and environmental data from different devices to understand the real-time status of device operation; The intelligent integration performs intelligent processing and fusion of the collected multi-dimensional data, integrates the data through an intelligent data filtering algorithm, and eliminates redundancy between data sources.

3. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 2 is characterized in that: The analysis of the deviation between the multi-dimensional configurations is carried out by collecting and integrating multi-dimensional data and using a multi-dimensional configuration consistency verification model to analyze the deviation between the actual operating state of the equipment and the preset configuration.

4. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 3 is characterized in that: The verification results are obtained by analyzing the multi-dimensional configuration consistency verification model, comparing the multi-dimensional configuration data with the preset standards, determining potential risks, and serving as a basis for optimization and feedback control; The intelligent feedback control automatically executes control measures and adjusts equipment status and operating parameters according to the verification results; The self-optimization mechanism automatically adjusts the calibration standards and optimizes the operating parameters through data accumulation and continuous learning to achieve self-adaptation.

5. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 4 is characterized in that: The predictive maintenance technology is based on a multi-dimensional configuration consistency verification model, and predicts potential equipment failure points by analyzing the equipment's operating trends and data fluctuations, and performs preventive maintenance. The intelligent operation and maintenance risk control, through intelligent operation and maintenance management, uses a multi-dimensional configuration consistency verification model to further diagnose faults and take repair measures for potential fault points monitored by predictive maintenance technology.

6. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 5, characterized in that: The intelligent data filtering algorithm is improved based on the Kalman filter, including a state update equation, a measurement update equation, a Kalman gain, a state prediction update, and a covariance update; The state update equation is expressed as: ， in, Indicates the current time The multidimensional state variables, Indicated in The state variables at time, represents the state transfer matrix, represents the control input, represents the control input matrix, represents process noise; When state transfer occurs, the current device state is predicted according to the state update equation; When a change of more than 10% occurs, it means that the value change exceeds 10% compared with the current state at the previous moment, and the current device state is predicted based on the value change. ;when When it exceeds the preset threshold of 0.05, it indicates that the equipment is disturbed by process noise, and the confidence of the state prediction is reduced; The measurement update equation is expressed as: ， in, represents the observed value, represents the observation matrix, represents the measurement noise; When the observation value is obtained, the current device state prediction is adjusted according to the measurement update equation; When it is less than the system preset threshold of 0.01, it indicates that the measurement noise is within the preset range, and the observation value is reliable data. The state prediction is updated based on the observation value. When the element coefficient changes by more than 5%, it indicates that the observation model resets the measurement method, that is, the parameters of the measurement equipment and the measurement method change, and the observation value is associated with the state according to the newly set measurement method; The Kalman gain is expressed as: ， in, represents the Kalman gain, represents the state covariance prediction matrix, represents the measurement noise covariance matrix, Represents the observation matrix The transposed matrix of When the forecast error covariance When the Kalman gain exceeds the system preset threshold of 0.01, Increases, indicating that the uncertainty of the system prediction increases, and the state is updated according to the observed value; when the observation noise covariance exceeds the preset threshold of 0.05, the Kalman gain decrease, indicating that the reliability of the observed value decreases, then the system relies on the predicted state; The state prediction update is expressed as: ， in, express Combined with the current observation value at the moment The predicted value of the state, express The predicted value of the state at the moment; When the observed value With the predicted value When the difference between the two is greater than the preset threshold of 10%, the system uses the Kalman gain Adjusting the state prediction value , and reduce the difference to within the set error range of 5%; when the Kalman gain When it exceeds the preset threshold of 0.7, the system state update depends on the observed value; The covariance update is expressed as: ， in, represents the covariance matrix, represents the identity matrix; When the Kalman gain and the observation matrix The product of When , the covariance matrix is ​​used to adjust the system prediction error; when When , it indicates that the system's dependence on the observed data reaches 90%, and the covariance matrix When , the uncertainty of the prediction decreases; When , it indicates that the system relies on state prediction, the cosquare matrix remains greater than 90% of the original value, and the prediction error increases by more than 5%.

7. The intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to claim 6 is characterized in that: The multi-dimensional configuration consistency verification model includes a multi-dimensional state estimation formula, a consistency verification formula and a verification adjustment formula; The multidimensional state estimation formula is expressed as: ， in, Indicates time The multidimensional state vector of represents the system state vector at the previous moment, represents the state transfer matrix, Indicates The control input influence matrix of dimension, Indicates the current moment The control input of the dimension, represents process noise; The consistency check formula is expressed as: ， in, represents the consistency check value at the current moment, Indicates The observation matrix of dimension, represents the observed value of the dimension, Represents the total number of different dimensions in the system; The calibration adjustment formula is expressed as: ， in, represents the state covariance matrix, Represents the consistency view mapping matrix between different dimensions, Represents the transpose of the consistency view mapping matrix; When a state transition occurs, the system uses a multidimensional state estimation formula to predict the system state at the current moment; when the control input When the change exceeds 5%, the system automatically adjusts the impact matrix ; When the check value When the preset threshold value exceeds 0.1, it indicates that the configurations of the dimensions are inconsistent. When it is less than 0.05, it means that the deviation between the system state and the observed value is small, and the system configuration consistency is good; When the Kalman gain When it exceeds 0.8, it means that the system is highly dependent on the current observation value, so the system reduces its dependence on the observation value and switches to a state prediction model; when the Kalman gain When it is lower than 0.3, it indicates that the system has low credibility in state prediction, and the system increases its reliance on observations and updates state estimates.

8. A system based on the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification according to any one of claims 1 to 7, characterized in that: include: Multidimensional data acquisition model, configuration verification model, feedback optimization model and maintenance diagnosis model; The multi-dimensional data collection model uses an intelligent data filtering algorithm to perform multi-dimensional data collection and intelligent integration; The configuration verification model designs a multi-dimensional configuration consistency verification model to analyze the deviations between multi-dimensional configurations; The feedback optimization model realizes intelligent feedback control and self-optimization mechanism based on the verification results; The maintenance diagnosis model adopts predictive maintenance technology based on a multi-dimensional configuration consistency verification model to perform preventive maintenance and intelligent operation and maintenance risk management.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent operation and maintenance control method based on multi-dimensional configuration consistency verification described in any one of claims 1 to 7 are implemented.

Images