Intelligent active operation and maintenance management system based on load monitoring

Abstract

The present invention belongs to the field of operation and maintenance management technology, and specifically is an intelligent active operation and maintenance management system based on load monitoring, including a load online monitoring module, a load analysis module, a fault warning diagnosis module, an operation and maintenance periodic evaluation module and a remote monitoring module; the present invention collects power load data in real time through the load online monitoring module, the load analysis module uses big data analysis technology to extract key information, and the fault warning diagnosis module automatically triggers the fault warning mechanism and performs fault diagnosis based on the analysis result, so as to realize timely discovery and accurate diagnosis of potential faults in the power system, which is helpful to improve the stability and reliability of the power system, and analyzes the power operation and maintenance performance within the detection period through the operation and maintenance periodic evaluation module, and strengthens subsequent operation and maintenance supervision when generating an operation and maintenance periodic poor evaluation signal, which is conducive to ensuring the safe and stable operation of the subsequent power system.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance management, and in particular to an intelligent active operation and maintenance management system based on load monitoring. Background Art

[0002] With the continuous development and complexity of power networks, real-time monitoring and effective management of power loads have become important needs of the power industry. The existing power load operation and maintenance management system is difficult to effectively monitor the power load and timely feedback potential faults, and is unable to accurately evaluate the performance of operation and maintenance cycles and reasonably optimize the management intensity of each period when the operation and maintenance cycle performance is judged to be poor. It is also unable to provide accurate feedback on the subsequent operation and maintenance execution performance. The low level of intelligence is not conducive to ensuring the safe and stable operation of the power system, and the power operation and maintenance management is difficult;

[0003] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent active operation and maintenance management system based on load monitoring, which solves the problems that the prior art is difficult to effectively monitor the power load and promptly feedback potential faults, and is unable to accurately evaluate the operation and maintenance periodic performance and reasonably optimize the management intensity of each time period when it is judged that the operation and maintenance periodic performance is poor, and is unable to provide accurate feedback on subsequent operation and maintenance execution performance, has a low degree of intelligence and is difficult to manage power operation and maintenance.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] Intelligent active operation and maintenance management system based on load monitoring, including load online monitoring module, load analysis module, fault warning diagnosis module, operation and maintenance periodic evaluation module and remote monitoring module;

[0007] The load online monitoring module is used to collect power load data in real time and send the collected power load data to the load analysis module; the load analysis module uses big data analysis technology to process and analyze real-time load data, extract key information and generate corresponding analysis results, and send the analysis results to the fault warning diagnosis module;

[0008] The fault warning and diagnosis module automatically triggers the fault warning mechanism according to the analysis results of the load analysis module, and performs fault diagnosis through the preset diagnosis algorithm, and sends the warning and diagnosis results to the remote monitoring module to notify the operation and maintenance personnel; when a fault occurs, the operation and maintenance personnel make real-time operation adjustments to the power equipment through the remote monitoring module;

[0009] The operation and maintenance periodicity evaluation module analyzes the power operation and maintenance performance within the detection period, generates an operation and maintenance periodicity good evaluation signal or an operation and maintenance periodicity poor evaluation signal through analysis, and sends the operation and maintenance periodicity good evaluation signal or the operation and maintenance periodicity poor evaluation signal to the remote monitoring module. When the remote monitoring module receives the operation and maintenance periodicity poor evaluation signal, it issues a corresponding warning.

[0010] Furthermore, the specific processing and analysis process of the load analysis module is as follows:

[0011] Step 1: Data reception and preprocessing: receiving real-time load data from the load online monitoring module and performing data preprocessing on the received data;

[0012] Step 2: Application of big data analysis technology: Use time series analysis or regression analysis statistical methods to analyze the long-term trend of power load; identify the frequency and amplitude of periodic fluctuations of power load through Fourier transform, wavelet analysis and other methods; automatically identify abnormal load data by setting corresponding thresholds or using machine learning algorithms;

[0013] Step 3: Extract and output key information: Extract key information on load change trends, periodic fluctuations and abnormal conditions, and output the extracted key information in various forms, including data reports, visual charts and early warning information.

[0014] Furthermore, the specific operation process of the fault warning diagnosis module is as follows:

[0015] Step 1: Triggering of the fault warning mechanism: receiving the real-time load data analysis results from the load analysis module, including the key information of load change trends, periodic fluctuations and abnormal conditions;

[0016] The fault warning diagnosis module has built-in preset fault thresholds, which are determined based on historical data, expert experience and the actual operation of the power system. The corresponding analysis results are compared with the preset fault thresholds to determine whether there is a potential fault;

[0017] When a potential fault is determined to exist, the fault warning diagnosis module automatically triggers the fault warning mechanism;

[0018] Step 2: Fault diagnosis: After the fault warning is triggered, collect detailed data related to the fault, including real-time load data, environmental parameters and equipment status;

[0019] The fault warning diagnosis module has built-in multiple preset diagnostic algorithms, which can determine the corresponding diagnostic algorithm for fault analysis; by applying the diagnostic algorithm, the specific type of fault can be identified, and the severity of the fault can be evaluated based on the collected data;

[0020] Step 3: Notification of warning and diagnosis results: Notify the operation and maintenance personnel of the warning and diagnosis results, where the notification information includes the specific type of fault, location, severity and recommended treatment measures.

[0021] Furthermore, the specific operation process of the operation and maintenance periodic evaluation module includes:

[0022] Set a detection cycle, collect the number of times the fault warning mechanism is triggered within the detection cycle and mark it as the fault trigger value, and calculate the time difference between the time when the remote monitoring module receives the corresponding warning and diagnosis results and the time when the operation and maintenance personnel take corresponding adjustment measures to obtain the adjustment duration; mark the number of adjustment durations that exceed the corresponding preset adjustment duration threshold within the detection cycle as the adjustment abnormal detection value, and mark the ratio of the adjustment abnormal detection value to the fault trigger value as the adjustment abnormal measurement value;

[0023] And mark the ratio of the corresponding adjustment time to the corresponding preset adjustment time threshold as the adjustment time measurement value, calculate the average of all adjustment time measurement values ​​within the detection period to obtain the adjustment time analysis value, obtain the operation and maintenance adjustment evaluation value by numerically calculating the adjustment abnormal detection value, the adjustment abnormal measurement value and the adjustment time measurement value, and numerically compare the operation and maintenance adjustment evaluation value with the preset operation and maintenance adjustment evaluation threshold. If the operation and maintenance adjustment evaluation value exceeds the preset operation and maintenance adjustment evaluation threshold, an operation and maintenance periodic poor evaluation signal is generated; if the operation and maintenance adjustment evaluation value does not exceed the preset operation and maintenance adjustment evaluation threshold, an operation and maintenance periodic good evaluation signal is generated.

[0024] Furthermore, the operation and maintenance periodic evaluation module is communicatively connected to the operation and maintenance optimization decision-making module. The operation and maintenance periodic evaluation module sends the operation and maintenance periodic poor evaluation signal to the operation and maintenance optimization decision-making module. The operation and maintenance optimization decision-making module determines the strong control period and the weak control period through analysis, and sends the strong control period and the weak control period to the remote monitoring module, and subsequently strengthens the operation and maintenance supervision and personnel input during the strong control period.

[0025] Furthermore, the specific analysis process of the operation and maintenance optimization decision module is as follows:

[0026] Twelve time periods are set every day, and the duration of each time period is two hours; the number of times the fault warning mechanism is triggered in the corresponding time period of the corresponding date is collected and marked as the time period trigger value, and the time when the fault warning mechanism is triggered is marked as the trigger time, the interval between two adjacent groups of trigger moments is marked as the trigger interval duration, and the number of trigger interval durations that do not exceed the preset trigger interval duration threshold in the corresponding time period of the corresponding date is marked as the trigger short interval value;

[0027] And calculate the average of all trigger interval durations in the corresponding time period on the corresponding date to obtain the trigger interval time measurement value, calculate the trigger risk value by numerically calculating the time period trigger value, the trigger short interval value and the trigger interval time measurement value, calculate the average of all trigger risk values ​​in the corresponding time period within the detection period to obtain the trigger hazard value, compare the trigger hazard value with the preset trigger hazard threshold, and if the trigger hazard value exceeds the preset trigger hazard threshold, the corresponding time period will be marked as a strong control period.

[0028] Further, if the trigger risk value does not exceed the preset trigger risk threshold, the trigger risk value of the corresponding time period of the corresponding date is numerically compared with the preset trigger risk threshold, and if the trigger risk value exceeds the preset trigger risk threshold, the trigger symbol CP-1 is allocated to the corresponding time period of the corresponding date;

[0029] The number of times the trigger symbol CP-1 is assigned to the corresponding time period in the detection cycle is collected and marked as a trigger high risk value, and the excess value of the trigger risk value corresponding to the trigger symbol CP-1 compared with the preset trigger risk threshold is marked as a trigger excess value, and all the trigger excess values ​​of the corresponding time period in the detection cycle are averaged to obtain a trigger excess detection value;

[0030] The time period detailed evaluation value is obtained by numerically calculating the trigger dangerous condition value, the trigger high dangerous value and the trigger over-inspection value, and the time period detailed evaluation value is numerically compared with the preset time period detailed evaluation threshold. If the time period detailed evaluation value exceeds the preset time period detailed evaluation threshold, the corresponding time period is marked as a strong control time period; if the time period detailed evaluation value does not exceed the preset time period detailed evaluation threshold, the corresponding detection time period is marked as a weak control time period.

[0031] Furthermore, the operation and maintenance optimization decision module is communicated with the personnel execution tracking module. The operation and maintenance optimization decision module sends the strong control period and the weak control period to the personnel execution tracking module. The personnel execution tracking module analyzes the execution performance of the operation and maintenance personnel in the next detection cycle, generates an execution tracking abnormality signal or an execution tracking qualified signal through the analysis, and sends the execution tracking abnormality signal or the execution tracking qualified signal to the remote monitoring module. When the remote monitoring module receives the execution tracking abnormality signal, it issues a corresponding warning.

[0032] Furthermore, the specific analysis process of the personnel execution tracking module is as follows:

[0033] The real-time number of on-the-job personnel performing power operation and maintenance is obtained and marked as the on-the-job personnel inspection value, and the historical total operation and maintenance time and the number of historical operation and maintenance errors of the corresponding on-the-job operation and maintenance personnel are collected and marked as the operation and maintenance time table value and the operation and maintenance error table value respectively, and the ratio of the operation and maintenance error table value to the operation and maintenance time table value is marked as the operation and maintenance error inspection value, and the operation and maintenance personnel condition value is obtained by numerically calculating the operation and maintenance time table value and the operation and maintenance error inspection value, and the operation and maintenance personnel condition values ​​of all on-the-job operation and maintenance personnel are averaged to obtain the operation and maintenance personnel evaluation value;

[0034] The execution tracking value is obtained by numerically calculating the inspection value of the on-duty personnel and the evaluation value of the operation and maintenance personnel. If the current period is a strong control period, the preset execution tracking threshold TW1 is allocated to it. If the current period is a weak control period, the preset execution tracking threshold TW2 is allocated to it, and TW1>TW2>0; the execution tracking value is numerically compared with the corresponding preset execution tracking threshold. If the execution tracking value does not exceed the preset execution tracking threshold, it is judged that the corresponding time is in the operation and maintenance inferior table state;

[0035] The duration of each operation and maintenance bad table state in the corresponding detection period is obtained and marked as the operation and maintenance bad table detection value, all the operation and maintenance bad table detection values ​​in the corresponding detection period are summed up to obtain the total operation and maintenance bad table detection value, and the number of operation and maintenance bad table detection values ​​exceeding the preset operation and maintenance bad table detection threshold is marked as the operation and maintenance bad table number detection value, and the operation and maintenance bad table detection value with the largest value is marked as the operation and maintenance bad table amplitude detection value;

[0036] The operation and maintenance execution status value is obtained by numerically calculating the total operation and maintenance fault inspection value, the operation and maintenance fault number inspection value and the operation and maintenance fault amplitude inspection value, and the operation and maintenance execution status value is numerically compared with the preset operation and maintenance execution status threshold. If the operation and maintenance execution status value exceeds the preset operation and maintenance execution status threshold, an execution tracking abnormal signal is generated; if the operation and maintenance execution status value does not exceed the preset operation and maintenance execution status threshold, an execution tracking qualified signal is generated.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. In the present invention, the load online monitoring module collects power load data in real time, the load analysis module uses big data analysis technology to extract key information, and the fault warning diagnosis module automatically triggers the fault warning mechanism and performs fault diagnosis based on the analysis results, so as to realize the timely discovery and accurate diagnosis of potential faults in the power system, which is helpful to improve the stability and reliability of the power system, and the power operation and maintenance performance within the detection period is analyzed by the operation and maintenance periodicity evaluation module, and the subsequent operation and maintenance supervision is strengthened when the operation and maintenance periodicity poor evaluation signal is generated, which is conducive to ensuring the safe and stable operation of the subsequent power system;

[0039] 2. In the present invention, the operation and maintenance periodic poor evaluation signal is sent to the operation and maintenance optimization decision module through the operation and maintenance periodic evaluation module. The operation and maintenance optimization decision module determines the strong control period and the weak control period through analysis, and subsequently strengthens the operation and maintenance supervision and personnel input during the strong control period to ensure the safety of power operation in each subsequent period. The operation and maintenance optimization decision module sends the strong control period and the weak control period to the personnel execution tracking module. The personnel execution tracking module analyzes the execution performance of the operation and maintenance personnel in the next detection cycle, and when the execution tracking abnormal signal is generated, the remote monitoring module issues a corresponding early warning, so as to continue to strengthen the subsequent operation and maintenance personnel arrangement optimization, reduce the difficulty of operation and maintenance management, and further ensure the safe and stable operation of the subsequent power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0041] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0042] Figure 2 This is a system block diagram of Embodiment 2 and Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1: Figure 1 As shown, the intelligent active operation and maintenance management system based on load monitoring proposed in the present invention includes a load online monitoring module, a load analysis module, a fault early warning diagnosis module, an operation and maintenance periodic evaluation module and a remote monitoring module;

[0045] The load online monitoring module is used to collect power load data in real time (including key parameters such as current, voltage, power factor, etc., which can reflect the real-time operation status of the power system), and send the collected power load data to the load analysis module; the load analysis module uses big data analysis technology to process and analyze real-time load data, extract key information and generate corresponding analysis results, and send the analysis results to the fault warning diagnosis module to provide strong support for the operation and maintenance management of the power system; the specific processing and analysis process of the load analysis module is as follows:

[0046] Step 1: Data reception and preprocessing: Receive real-time load data from the load online monitoring module and perform data preprocessing on the received data. The purpose of this step is to eliminate noise, missing values ​​and outliers in the data to ensure the accuracy and reliability of subsequent analysis; data preprocessing includes steps such as removing duplicate data, filling missing values, and correcting errors;

[0047] Step 2: Application of big data analysis technology: Use statistical methods such as time series analysis or regression analysis to analyze the long-term change trend of power load; for example, the change trend of load on different time scales such as day, week, month, and year can be analyzed to predict future load demand;

[0048] Electric load usually has certain periodic fluctuation characteristics, such as daily peaks, daily valleys, seasonal fluctuations, etc. The frequency and amplitude of periodic fluctuations of electric load can be identified through methods such as Fourier transform or wavelet analysis to better understand and predict the fluctuation law of load; abnormal load data can be automatically identified by setting corresponding thresholds or using machine learning algorithms (such as cluster analysis, support vector machines, etc.). These abnormal data mean equipment failure, human error or external events, etc., which need to be handled in time to avoid greater impact on the power system;

[0049] Step 3: Extract and output key information: Extract key information about load change trends, periodic fluctuations and abnormal conditions. This information is of great significance to the operation and maintenance management of the power system and can help operation and maintenance personnel better understand the operating status and potential risks of the power system.

[0050] The extracted key information is output in a variety of forms, such as data reports, visual charts and warning information. These output methods can be customized according to actual needs to meet the needs of different users. For example, operation and maintenance personnel can understand the overall operating status of the power system through data reports, while senior management can more intuitively understand the load change trends and abnormal conditions through visual charts.

[0051] The fault warning and diagnosis module automatically triggers the fault warning mechanism according to the analysis results of the load analysis module, and performs fault diagnosis through the preset diagnostic algorithm, and sends the warning and diagnosis results to the remote monitoring module to notify the operation and maintenance personnel; when a fault occurs, the operation and maintenance personnel make real-time operation adjustments to the power equipment through the remote monitoring module. The fault warning and diagnosis module can realize the timely discovery and accurate diagnosis of potential faults in the power system by automatically triggering the fault warning mechanism and applying the preset diagnostic algorithm, which helps to improve the stability and reliability of the power system and reduce the impact of faults on system operation; the specific operation process of the fault warning and diagnosis module is as follows:

[0052] Step 1: Triggering of fault warning mechanism: receiving real-time load data analysis results from the load analysis module, including key information such as load change trends, periodic fluctuations, and abnormal conditions;

[0053] The fault warning diagnosis module has built-in preset fault thresholds, which are determined based on historical data, expert experience and the actual operation of the power system. The corresponding analysis results are compared with the preset fault thresholds to determine whether there is a potential fault. When it is determined that there is a potential fault, the fault warning diagnosis module automatically triggers the fault warning mechanism.

[0054] Step 2: Fault diagnosis: After the fault warning is triggered, collect detailed data related to the fault, including real-time load data, environmental parameters, and equipment status;

[0055] The fault warning diagnosis module has built-in multiple preset diagnostic algorithms, such as expert system fault diagnosis method, neural network fault diagnosis, etc.; according to the characteristics of the fault, determine the corresponding diagnostic algorithm for fault analysis; by applying the diagnostic algorithm, identify the specific type of fault, such as equipment failure, line failure, human error, etc., and evaluate the severity of the fault based on the collected data, such as minor, medium, severe, etc.;

[0056] Step 3: Notification of warning and diagnosis results: Notify the operation and maintenance personnel of the warning and diagnosis results, where the notification information includes the specific type of fault, location, severity and recommended treatment measures.

[0057] The operation and maintenance periodicity evaluation module analyzes the power operation and maintenance performance within the detection period, generates an operation and maintenance periodicity good evaluation signal or an operation and maintenance periodicity bad evaluation signal through analysis, and sends the operation and maintenance periodicity good evaluation signal or the operation and maintenance periodicity bad evaluation signal to the remote monitoring module. When the remote monitoring module receives the operation and maintenance periodicity bad evaluation signal, it issues a corresponding warning and promptly strengthens the subsequent operation and maintenance supervision, thereby ensuring the safe and stable operation of the subsequent power system; the specific operation process of the operation and maintenance periodicity evaluation module is as follows:

[0058] A detection cycle is set, preferably, the detection cycle is thirty days; the number of times the fault warning mechanism is triggered within the detection cycle is collected and marked as the fault trigger value, and the time difference between the time when the remote monitoring module receives the corresponding warning and diagnosis results and the time when the operation and maintenance personnel take corresponding adjustment measures is calculated to obtain the adjustment time; the adjustment time is numerically compared with the corresponding preset adjustment time threshold, and the number of adjustment times that exceed the corresponding preset adjustment time threshold within the detection cycle is marked as the adjustment abnormal detection value, and the ratio of the adjustment abnormal detection value to the fault trigger value is marked as the adjustment abnormal measurement value;

[0059] and marking the ratio of the corresponding adjustment time to the corresponding preset adjustment time threshold as the adjustment time measurement value, and calculating the average of all the adjustment time measurement values ​​within the detection period to obtain the adjustment time analysis value;

[0060] By formula The adjusted abnormal detection value QN, the adjusted abnormal measurement value QM and the adjusted time measurement value QS are numerically calculated to obtain the operation and maintenance adjustment evaluation value QK, wherein a1, a2, and a3 are preset proportional coefficients with values ​​greater than zero, and a2>a3>a1>0; and the larger the value of the operation and maintenance adjustment evaluation value QK, the less timely the operation and maintenance within the detection period, and the worse the operation and maintenance management performance;

[0061] In addition, the operation and maintenance adjustment evaluation value QK is numerically compared with the preset operation and maintenance adjustment evaluation threshold. If the operation and maintenance adjustment evaluation value QK exceeds the preset operation and maintenance adjustment evaluation threshold, it indicates that the operation and maintenance within the detection period is not timely and the operation and maintenance management performance is poor, then an operation and maintenance periodic poor evaluation signal is generated; if the operation and maintenance adjustment evaluation value QK does not exceed the preset operation and maintenance adjustment evaluation threshold, it indicates that the operation and maintenance within the detection period is timely and the operation and maintenance management performance is good, then an operation and maintenance periodic good evaluation signal is generated.

[0062] Embodiment 2: Figure 2 As shown, the difference between this embodiment and embodiment 1 is that the operation and maintenance periodic evaluation module is communicatively connected to the operation and maintenance optimization decision module, and the operation and maintenance periodic evaluation module sends the operation and maintenance periodic poor evaluation signal to the operation and maintenance optimization decision module. When the operation and maintenance optimization decision module receives the operation and maintenance periodic poor evaluation signal, it determines the strong control period and the weak control period through analysis, and sends the strong control period and the weak control period to the remote monitoring module. Subsequently, the operation and maintenance supervision and personnel input are strengthened during the strong control period, which is conducive to the subsequent operation and maintenance management planning, and improves the rationality and scientificity of the subsequent operation and maintenance management planning scheme, thereby ensuring the safety of power operation in each subsequent period; the specific analysis process of the operation and maintenance optimization decision module is as follows:

[0063] Twelve time periods are set every day, and the duration of each time period is two hours; the number of times the fault warning mechanism is triggered in the corresponding time period of the corresponding date is collected and marked as the time period trigger value, and the time when the fault warning mechanism is triggered is marked as the trigger time, the interval between two adjacent groups of trigger moments is marked as the trigger interval duration, and the number of trigger interval durations that do not exceed the preset trigger interval duration threshold in the corresponding time period of the corresponding date is marked as the trigger short interval value;

[0064] And calculate the average of all trigger interval durations in the corresponding period of the corresponding date to obtain the trigger interval time measurement value, and calculate the trigger value CS, the trigger short interval value CE and the trigger interval time measurement value CR through the formula CF=(up1*CS+up2*CE) / (up3*CR+1.326) to obtain the trigger risk value CF; wherein up1, up2, up3 are preset proportional coefficients, and the values ​​of up1, up2, up3 are all positive numbers; and the larger the value of the trigger risk value CF, the more frequent the faults in the corresponding period of the corresponding date and the more difficult it is to deal with them effectively in time;

[0065] The trigger risk value is obtained by averaging all the trigger risk values ​​in the corresponding time period within the detection cycle, and the trigger risk value is compared with the preset trigger risk threshold. If the trigger risk value exceeds the preset trigger risk threshold, it indicates that the corresponding time period in the detection cycle is difficult to operate and manage preliminarily, and it is necessary to strengthen supervision of the corresponding time period in the future, then the corresponding time period will be marked as a strong control period.

[0066] Furthermore, if the trigger risk value does not exceed the preset trigger risk threshold, the trigger risk value of the corresponding time period of the corresponding date is numerically compared with the preset trigger risk threshold. If the trigger risk value exceeds the preset trigger risk threshold, the trigger symbol CP-1 is allocated to the corresponding time period of the corresponding date;

[0067] The number of times the trigger symbol CP-1 is assigned to the corresponding time period in the detection cycle is collected and marked as a trigger high risk value, and the excess value of the trigger risk value corresponding to the trigger symbol CP-1 compared with the preset trigger risk threshold is marked as a trigger excess value, and all the trigger excess values ​​of the corresponding time period in the detection cycle are averaged to obtain a trigger excess detection value;

[0068] The triggering risk value SW, triggering high risk value SG and triggering over-inspection value SX are numerically calculated by the formula SM=ny2*SG+(ny1*SW+ny3*SX) / 2 to obtain the time period detailed evaluation value SM; among them, ny1, ny2 and ny3 are preset proportional coefficients, ny2>ny3>ny1>0; and the larger the value of the time period detailed evaluation value SM is, the more difficult it is to carry out operation and maintenance management for the corresponding time period in the detection cycle, and the more it is necessary to strengthen supervision for the corresponding time period in the subsequent period;

[0069] The time period detailed evaluation value SM is numerically compared with the preset time period detailed evaluation threshold. If the time period detailed evaluation value SM exceeds the preset time period detailed evaluation threshold, it indicates that the corresponding time period in the detection cycle is difficult to operate and maintain on the whole, and it is necessary to strengthen supervision of the corresponding time period in the future, then the corresponding time period is marked as a strong management time period; if the time period detailed evaluation value SM does not exceed the preset time period detailed evaluation threshold, it indicates that the corresponding time period in the detection cycle is easier to operate and maintain on the whole, then the corresponding detection time period is marked as a weak management time period.

[0070] Embodiment 3: Figure 2 As shown, the difference between this embodiment and embodiment 1 and embodiment 2 is that the operation and maintenance optimization decision module is connected to the personnel execution tracking module in communication, and the operation and maintenance optimization decision module sends the strong control period and the weak control period to the personnel execution tracking module. The personnel execution tracking module analyzes the execution performance of the operation and maintenance personnel in the next detection cycle, generates an execution tracking abnormal signal or an execution tracking qualified signal through analysis, and sends the execution tracking abnormal signal or the execution tracking qualified signal to the remote monitoring module. When the remote monitoring module receives the execution tracking abnormal signal, it issues a corresponding warning, so as to continue to strengthen the subsequent operation and maintenance personnel arrangement optimization, reduce the difficulty of operation and maintenance management, and further ensure the safe and stable operation of the subsequent power system; the specific analysis process of the personnel execution tracking module is as follows:

[0071] The real-time number of on-duty personnel performing power operation and maintenance is obtained and marked as the on-duty personnel inspection value, and the historical total operation and maintenance time and the number of historical operation and maintenance errors of the corresponding on-duty operation and maintenance personnel are collected and marked as the operation and maintenance time table value and the operation and maintenance error table value respectively, and the ratio of the operation and maintenance error table value to the operation and maintenance time table value is marked as the operation and maintenance error inspection value;

[0072] The operation and maintenance personnel condition value RY is obtained by numerically calculating the operation and maintenance time table value RN and the operation and maintenance error detection value RF through the formula RY=c1*RN+c2 / (RF+1.263), where c1 and c2 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the operation and maintenance personnel condition value RY, the stronger the operation and maintenance ability of the corresponding operation and maintenance personnel; the operation and maintenance personnel condition values ​​of all the operation and maintenance personnel on duty are averaged to obtain the operation and maintenance personnel evaluation;

[0073] By formula The execution tracking value YS is obtained by numerically calculating the on-the-job personnel inspection value RP and the operation and maintenance personnel evaluation value RW, where hw1 and hw2 are preset proportional coefficients, and the values ​​of hw1 and hw2 are both positive numbers; and the larger the value of the execution tracking value YS, the better the current operation and maintenance execution status;

[0074] If the current time period is a strong control time period, a preset execution tracking threshold TW1 is allocated to it; if the current time period is a weak control time period, a preset execution tracking threshold TW2 is allocated to it, and TW1>TW2>0; the execution tracking value YS is numerically compared with the corresponding preset execution tracking threshold; if the execution tracking value YS does not exceed the preset execution tracking threshold, indicating that the current operation and maintenance execution status is poor, it is judged that the corresponding moment is in an operation and maintenance inferior table state;

[0075] The duration of each operation and maintenance bad table state in the corresponding detection period is obtained and marked as the operation and maintenance bad table detection value, all the operation and maintenance bad table detection values ​​in the corresponding detection period are summed up to obtain the total operation and maintenance bad table detection value, and the number of operation and maintenance bad table detection values ​​exceeding the preset operation and maintenance bad table detection threshold is marked as the operation and maintenance bad table number detection value, and the operation and maintenance bad table detection value with the largest value is marked as the operation and maintenance bad table amplitude detection value;

[0076] The operation and maintenance execution status value WX is obtained by numerically calculating the total operation and maintenance bad table inspection value WZ, the operation and maintenance bad table number inspection value WK and the operation and maintenance bad table amplitude inspection value WD through the formula WX=rq2*WK+(rq1*WZ+rq3*WD) / rq2, wherein rq1, rq2 and rq3 are preset proportional coefficients, rq2>rq3>rq1>0; and the larger the value of the operation and maintenance execution status value WX, the worse the operation and maintenance execution performance of the corresponding detection period is in general;

[0077] The operation and maintenance execution status value WX is numerically compared with the preset operation and maintenance execution status threshold. If the operation and maintenance execution status value WX exceeds the preset operation and maintenance execution status threshold, it indicates that the operation and maintenance execution performance of the corresponding detection period is poor overall, and an execution tracking abnormal signal is generated; if the operation and maintenance execution status value WX does not exceed the preset operation and maintenance execution status threshold, it indicates that the operation and maintenance execution performance of the corresponding detection period is good overall, and an execution tracking qualified signal is generated.

[0078] The working principle of the present invention is as follows: when in use, the power load data is collected in real time through the load online monitoring module, the load analysis module uses big data analysis technology to process and analyze the real-time load data to extract key information and generate corresponding analysis results, and the fault warning diagnosis module automatically triggers the fault warning mechanism according to the analysis results of the load analysis module and performs fault diagnosis through a preset diagnosis algorithm, so as to realize timely discovery and accurate diagnosis of potential faults in the power system, which helps to improve the stability and reliability of the power system and reduce the impact of faults on the system operation. The power operation and maintenance performance within the detection period is analyzed through the operation and maintenance periodic evaluation module, and an operation and maintenance periodic excellent evaluation signal or an operation and maintenance periodic poor evaluation signal is generated through analysis. When the operation and maintenance periodic poor evaluation signal is generated, the remote monitoring module issues a corresponding warning, and timely strengthens the subsequent operation and maintenance supervision, thereby ensuring the safe and stable operation of the subsequent power system.

[0079] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. Intelligent active operation and maintenance management system based on load monitoring, characterized by: It includes load online monitoring module, load analysis module, fault warning diagnosis module, operation and maintenance periodic evaluation module and remote monitoring module; The load online monitoring module is used to collect power load data in real time and send the collected power load data to the load analysis module; The load analysis module uses big data analysis technology to process and analyze real-time load data, extract key information and generate corresponding analysis results, and send the analysis results to the fault warning diagnosis module; The fault warning and diagnosis module automatically triggers the fault warning mechanism according to the analysis results of the load analysis module, and performs fault diagnosis through the preset diagnosis algorithm, and sends the warning and diagnosis results to the remote monitoring module to notify the operation and maintenance personnel; when a fault occurs, the operation and maintenance personnel make real-time operation adjustments to the power equipment through the remote monitoring module; The operation and maintenance periodicity evaluation module analyzes the power operation and maintenance performance within the detection period, generates an operation and maintenance periodicity good evaluation signal or an operation and maintenance periodicity bad evaluation signal through analysis, and sends the operation and maintenance periodicity good evaluation signal or the operation and maintenance periodicity bad evaluation signal to the remote monitoring module. When the remote monitoring module receives the operation and maintenance periodicity bad evaluation signal, it issues a corresponding warning; The specific operation process of the operation and maintenance periodic evaluation module includes: Set a detection cycle, collect the number of times the fault warning mechanism is triggered within the detection cycle and mark it as the fault trigger value, and calculate the time difference between the time when the remote monitoring module receives the corresponding warning and diagnosis results and the time when the operation and maintenance personnel take corresponding adjustment measures to obtain the adjustment duration; mark the number of adjustment durations that exceed the corresponding preset adjustment duration threshold within the detection cycle as the adjustment abnormal detection value, and mark the ratio of the adjustment abnormal detection value to the fault trigger value as the adjustment abnormal measurement value; and marking the ratio of the corresponding adjustment time to the corresponding preset adjustment time threshold as the adjustment time measurement value, and calculating the average of all the adjustment time measurement values ​​within the detection period to obtain the adjustment time analysis value; By formula The adjusted abnormal detection value QN, the adjusted abnormal measurement value QM and the adjusted time measurement value QS are numerically calculated to obtain the operation and maintenance adjustment evaluation value QK, wherein a1, a2, and a3 are preset proportional coefficients with values ​​greater than zero, and a2>a3>a1>0; the operation and maintenance adjustment evaluation value is numerically compared with the preset operation and maintenance adjustment evaluation threshold. If the operation and maintenance adjustment evaluation value exceeds the preset operation and maintenance adjustment evaluation threshold, an operation and maintenance periodic poor evaluation signal is generated; if the operation and maintenance adjustment evaluation value does not exceed the preset operation and maintenance adjustment evaluation threshold, an operation and maintenance periodic good evaluation signal is generated; The operation and maintenance periodic evaluation module is connected to the operation and maintenance optimization decision module in communication. The operation and maintenance periodic evaluation module sends the operation and maintenance periodic poor evaluation signal to the operation and maintenance optimization decision module. The operation and maintenance optimization decision module determines the strong control period and the weak control period through analysis, and sends the strong control period and the weak control period to the remote monitoring module. Subsequently, the operation and maintenance supervision and personnel input are strengthened during the strong control period. The specific analysis process of the operation and maintenance optimization decision module is as follows: Twelve time periods are set every day, and the duration of each time period is two hours; the number of times the fault warning mechanism is triggered in the corresponding time period of the corresponding date is collected and marked as the time period trigger value, and the time when the fault warning mechanism is triggered is marked as the trigger time, the interval between two adjacent groups of trigger moments is marked as the trigger interval duration, and the number of trigger interval durations that do not exceed the preset trigger interval duration threshold in the corresponding time period of the corresponding date is marked as the trigger short interval value; And calculate the average of all trigger intervals in the corresponding period of the corresponding date to obtain the trigger interval time measurement value, and calculate the trigger value CS, the trigger short interval value CE and the trigger interval time measurement value CR of the period by the formula CF=(up1*CS+up2*CE) / (up3*CR+1.326) to obtain the trigger risk value CF; wherein up1, up2, up3 are preset proportional coefficients, and the values ​​of up1, up2, up3 are all positive numbers; calculate the average of all trigger risk values ​​of the corresponding period in the detection cycle to obtain the trigger risk value, and if the trigger risk value exceeds the preset trigger risk threshold, the corresponding period is marked as a strong control period; If the trigger risk value does not exceed the preset trigger risk threshold, the trigger risk value of the corresponding period of the corresponding date is numerically compared with the preset trigger risk threshold. If the trigger risk value exceeds the preset trigger risk threshold, the trigger symbol CP-1 is allocated to the corresponding period of the corresponding date; The number of times the trigger symbol CP-1 is assigned to the corresponding time period in the detection cycle is collected and marked as a trigger high risk value, and the excess value of the trigger risk value corresponding to the trigger symbol CP-1 compared with the preset trigger risk threshold is marked as a trigger excess value, and all the trigger excess values ​​of the corresponding time period in the detection cycle are averaged to obtain a trigger excess detection value; The trigger dangerous condition value SW, the trigger high dangerous value SG and the trigger over-detection value SX are numerically calculated by the formula SM=ny2*SG+(ny1*SW+ny3*SX) / 2 to obtain the period detailed evaluation value SM; wherein ny1, ny2 and ny3 are preset proportional coefficients, ny2>ny3>ny1>0; if the period detailed evaluation value exceeds the preset period detailed evaluation threshold, the corresponding period is marked as a strong pipe period; if the period detailed evaluation value does not exceed the preset period detailed evaluation threshold, the corresponding detection period is marked as a weak pipe period; The operation and maintenance optimization decision module is connected to the personnel execution tracking module in communication. The operation and maintenance optimization decision module sends the strong control period and the weak control period to the personnel execution tracking module. The personnel execution tracking module analyzes the execution performance of the operation and maintenance personnel in the next detection cycle, generates an execution tracking abnormal signal or an execution tracking qualified signal through analysis, and sends the execution tracking abnormal signal or the execution tracking qualified signal to the remote monitoring module. When the remote monitoring module receives the execution tracking abnormal signal, it issues a corresponding warning; The specific analysis process of the personnel execution tracking module is as follows: The real-time number of on-the-job personnel performing power operation and maintenance is obtained and marked as the on-the-job personnel inspection value, and the historical total operation and maintenance time and the number of historical operation and maintenance errors of the corresponding on-the-job operation and maintenance personnel are collected and marked as the operation and maintenance time table value and the operation and maintenance error table value respectively. The ratio of the operation and maintenance error table value to the operation and maintenance time table value is marked as the operation and maintenance error inspection value. The operation and maintenance time table value RN and the operation and maintenance error inspection value RF are numerically calculated by the formula RY=c1*RN+c2 / (RF+1.263) to obtain the operation and maintenance personnel condition value RY, where c1 and c2 are preset proportional coefficients with values ​​greater than zero. The operation and maintenance personnel condition values ​​of all on-the-job operation and maintenance personnel are averaged to obtain the operation and maintenance personnel evaluation value; By formula The execution tracking value YS is obtained by numerically calculating the on-duty person inspection value RP and the operation and maintenance person evaluation value RW, where hw1 and hw2 are preset proportional coefficients, and the values ​​of hw1 and hw2 are both positive numbers; if the current time period is a strong control time period, the preset execution tracking threshold TW1 is assigned to it; if the current time period is a weak control time period, the preset execution tracking threshold TW2 is assigned to it, and TW1>TW2>0; if the execution tracking value does not exceed the corresponding preset execution tracking threshold, it is judged that the corresponding time is in the operation and maintenance inferior table state; The duration of each operation and maintenance bad table state in the corresponding detection period is obtained and marked as the operation and maintenance bad table detection value, all the operation and maintenance bad table detection values ​​in the corresponding detection period are summed up to obtain the total operation and maintenance bad table detection value, and the number of operation and maintenance bad table detection values ​​exceeding the preset operation and maintenance bad table detection threshold is marked as the operation and maintenance bad table number detection value, and the operation and maintenance bad table detection value with the largest value is marked as the operation and maintenance bad table amplitude detection value; The operation and maintenance execution status value WX is obtained by numerically calculating the total operation and maintenance fault value WZ, the number of operation and maintenance fault values ​​WK and the amplitude of operation and maintenance fault values ​​WD through the formula WX=rq2*WK+(rq1*WZ+rq3*WD) / rq2, wherein rq1, rq2 and rq3 are preset proportional coefficients, rq2>rq3>rq1>0; if the operation and maintenance execution status value exceeds the preset operation and maintenance execution status threshold, an execution tracking abnormal signal is generated; if the operation and maintenance execution status value does not exceed the preset operation and maintenance execution status threshold, an execution tracking qualified signal is generated.

2. The intelligent active operation and maintenance management system based on load monitoring according to claim 1 is characterized in that: The specific processing and analysis process of the load analysis module is as follows: Step 1: Data reception and preprocessing: receiving real-time load data from the load online monitoring module and performing data preprocessing on the received data; Step 2: Application of big data analysis technology: Use time series analysis or regression analysis statistical methods to analyze the long-term change trend of power load; use Fourier transform and wavelet analysis methods to identify the frequency and amplitude of periodic fluctuations of power load; automatically identify abnormal load data by setting corresponding thresholds or using machine learning algorithms; Step 3: Extract and output key information: Extract key information on load change trends, periodic fluctuations and abnormal conditions, and output the extracted key information in various forms.

3. The intelligent active operation and maintenance management system based on load monitoring according to claim 1 is characterized in that: The specific operation process of the fault warning diagnosis module is as follows: Step 1: Triggering the fault warning mechanism: receiving the real-time load data analysis results from the load analysis module; the fault warning diagnosis module has a built-in preset fault threshold, and compares the corresponding analysis results with the preset fault threshold to determine whether there is a potential fault; when it is determined that there is a potential fault, the fault warning diagnosis module automatically triggers the fault warning mechanism; Step 2: Fault diagnosis: After the fault warning is triggered, detailed data related to the fault is collected; the fault warning diagnosis module has built-in multiple preset diagnostic algorithms, and the corresponding diagnostic algorithm is determined for fault analysis; by applying the diagnostic algorithm, the specific type of fault is identified, and the severity of the fault is evaluated based on the collected data; Step 3: Notification of warning and diagnosis results: Notify the operation and maintenance personnel of the warning and diagnosis results.

Images