A big data-based intelligent dispatching system for power grid operation and maintenance

Abstract

The present invention relates to the technical field of power dispatching and management, and specifically to an intelligent dispatching system for power grid operation and maintenance based on big data. The system includes: a data acquisition module, an anomaly identification module, a state classification module, a trend prediction module, and a path planning module. In the present invention, by real-time acquisition of dynamic data of power grid equipment, the state monitoring and fault diagnosis of power equipment are optimized, the abnormal state of the equipment is detected in real time based on voltage data and the fault time node is identified, the accuracy and efficiency of fault diagnosis are improved, and the voltage phase offset value and temperature gradient rise rate of the equipment are combined to timely judge the state of the equipment, monitor the risk of equipment overheating, and improve the reliability and safety of the power grid system. By predicting the aging status of equipment, optimizing the maintenance strategy, reducing the risk of equipment outage, and utilizing task cluster path planning and resource scheduling, the efficient execution of operation and maintenance tasks is ensured, and the efficiency of power grid operation and maintenance and the rationality of resource allocation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power dispatching management, and in particular to a big data-based intelligent dispatching system for power grid operation and maintenance. Background Art

[0002] The technical field of power dispatching and management includes the real-time dispatching, monitoring, operation and maintenance management of power production, transmission and electricity consumption during the production and operation of the power system. The core content of this technical field includes unified dispatching, control and management of power grid operation status monitoring, power load regulation, power distribution and transmission, and related equipment maintenance, so as to achieve the safety, stability and reliability of power grid system operation. Specifically, it involves the scheduling of power grid operation and maintenance, real-time monitoring and fault diagnosis, processing of dispatching instructions and various technical matters, so as to achieve a comprehensive grasp of the power grid operation status and coordinated control of multiple links of power production, transmission and distribution, so as to ensure the safety and stability of power supply.

[0003] Among them, the big data-based power grid operation and maintenance intelligent dispatching system refers to the collection of multi-dimensional data such as the operating status of power equipment, historical fault records, load changes, and the processing of feature extraction, cluster analysis, distribution modeling, etc. on the data to establish the judgment logic and dispatching rules of the operation and maintenance status, support the dynamic allocation of dispatching tasks and the optimization of the response process. The technical matters targeted by the system cover multiple links such as data source interface access, data cache processing, task priority setting, work order generation mechanism, and dispatching path planning. It also uses data warehouse technology to classify and clean the original data, and supports the condition matching of the dispatching decision logic module and the logical execution of the dispatching process control module.

[0004] Traditional power grid operation and maintenance intelligent dispatching and management technology lacks the timeliness of real-time monitoring of power grid operation and fault response. When faced with equipment failures or emergencies, it lacks sufficient intelligent dispatching and decision-making capabilities. It relies on static data collection and analysis methods, and it is difficult to obtain and analyze the dynamic data of equipment in real time. As a result, when the power load changes and equipment fails, the response time is long, affecting the stability of the power grid. The fault diagnosis and processing mechanism relies on manual intervention and lacks automation and intelligent judgment capabilities, resulting in low fault handling efficiency, leading to scheduling delays or wrong decisions. It is impossible to dynamically adjust operation and maintenance tasks according to real-time data, and scheduling is often based on preset templates. It is impossible to flexibly adjust task priorities and work resource configuration according to changes in equipment status, resulting in the formulation of maintenance plans often lagging behind actual needs. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a big data-based intelligent dispatching system for power grid operation and maintenance.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: A big data-based power grid operation and maintenance intelligent dispatching system includes:

[0007] The data acquisition module acquires grid operation data, extracts the current amplitude, voltage fluctuation rate, and active power change of multiple grid devices, analyzes the volatility of each data in real time, calculates the variation range of the operation data, adjusts the data sampling frequency, and obtains the power parameter data set;

[0008] The anomaly identification module calls the power parameter data set, extracts the voltage monitoring data sequence of multiple power grid devices, calculates the voltage change slope, and calculates the slope difference of the voltage curve in consecutive time periods, detects abnormal voltage data and abnormal power equipment, identifies abnormal time nodes, and obtains abnormal data location records;

[0009] The status classification module detects the voltage phase offset value and temperature gradient rise rate of the power equipment in real time based on the abnormal data location record and the power parameter data set, analyzes the equipment status, and obtains the equipment status classification level;

[0010] Based on the equipment status classification level, the trend prediction module extracts the leakage current and operating voltage of the equipment in real time, calculates the insulation degradation factor of the equipment, and evaluates the aging status of the equipment in combination with the temperature gradient rise rate of the equipment. It also calculates the remaining life cycle of the equipment and obtains the maintenance trigger time window.

[0011] As a further solution of the present invention, the power parameter data set includes an equipment voltage waveform data set, leakage current detection data, and an equipment operating temperature data set. The abnormal data location record is specifically an abnormal time node, abnormal voltage data, and abnormal power equipment. The equipment status classification level is specifically the equipment health status level, voltage phase offset value, and temperature gradient rise rate. The maintenance trigger time window is specifically the remaining life cycle of the equipment, insulation degradation factor, and maintenance trigger time.

[0012] As a further solution of the present invention, the data acquisition module includes:

[0013] The power parameter extraction submodule obtains grid operation data by extracting the current amplitude, voltage fluctuation rate, and active power change data of multiple grid devices, combining the device number and time stamp to obtain the device operation characteristic data;

[0014] The load variation analysis submodule calls the equipment operation characteristic data and uses the formula:

[0015] ;

[0016] Calculate the data fluctuation determination value within each sliding window period and obtain the variation amplitude parameter;

[0017] in, is the total number of samples in the sampling window, is the data point index, For the The value of the current amplitude data point, is the average value of the current amplitude, For the The value of the active power change data point, is the average value of active power change, For the The value of the voltage fluctuation rate data point, is the average value of voltage fluctuation rate, is the data fluctuation determination value;

[0018] The sampling frequency control submodule calls the variation amplitude parameter, adjusts the data acquisition frequency in real time according to the variation amplitude of the equipment operation data, and obtains the voltage waveform, leakage current, and operating temperature data of multiple operating devices to construct a power parameter data set.

[0019] As a further solution of the present invention, the abnormality identification module includes:

[0020] The voltage data extraction submodule calls the power parameter data set, extracts the voltage value of each power device in the power grid at multiple time points, and obtains the voltage monitoring data sequence by combining the device number and the timestamp;

[0021] The voltage slope calculation submodule calls the voltage monitoring data sequence, calculates the voltage change slope of the device in each time period based on the voltage difference between adjacent moments, and calculates the slope difference of consecutive time periods to obtain the voltage slope difference;

[0022] The abnormal node identification submodule calls the voltage slope difference, detects abnormal voltage data in real time, marks abnormal power events in combination with the device number and timestamp, and obtains abnormal data location records.

[0023] As a further solution of the present invention, the status classification module includes:

[0024] The phase shift detection submodule calls the abnormal data location record and power parameter data set, extracts the absolute value of the phase difference between each cycle voltage waveform and the standard sine wave according to the voltage waveform sequence, calculates the sliding window mean of the phase difference of multiple consecutive cycles, calculates the sliding average of the absolute value of the cycle phase difference, combines it with the identified operating temperature data, calculates the temperature gradient rise rate, and obtains the state input parameter set;

[0025] The state judgment calculation submodule calls the state input parameter set to calculate the temperature rise increment and voltage fluctuation intensity of adjacent cycles, combined with the real-time active power of the equipment, using the formula:

[0026] ;

[0027] Calculate the comprehensive judgment value of the state;

[0028] in, Indicates the comprehensive judgment value of the status, Indicates the voltage phase offset value, represents the temperature gradient value, Indicates the real-time active power of the device. Indicates the temperature rise increment in adjacent cycles, Indicates the voltage fluctuation intensity of the current cycle;

[0029] The risk level classification submodule identifies the device status based on the comprehensive status judgment value and combines the preset status scoring interval to match the device status label in real time and establish the device status classification level.

[0030] As a further solution of the present invention, the trend prediction module includes:

[0031] The insulation degradation extraction submodule calls the equipment status classification level, calls the leakage current and operating voltage data of the power equipment, obtains the average leakage current and the average voltage amplitude, and obtains the insulation degradation factor value by analyzing the leakage current change rate and the voltage amplitude change trend in combination with the voltage deviation direction;

[0032] The aging status assessment submodule extracts the periodic temperature gradient change based on the insulation degradation factor value, obtains the temperature increase and time span of multiple cycles, and calculates the temperature rise rate and voltage deviation ratio fluctuation level in combination with the equipment voltage fluctuation parameters using the formula:

[0033] ;

[0034] Calculate the equipment aging trend offset and perform an average evaluation of the fluctuation amplitude of consecutive cycles to obtain a comprehensive aging status indicator;

[0035] in, Indicates the comprehensive index of aging status, Indicates the Cycle leakage current, represents the temperature gradient, Indicates the operating voltage deviation value, Indicates the temperature rise change value, represents the period time span, Indicates the number of monitoring cycles, The index number of the monitoring period;

[0036] The life cycle calculation submodule retrieves the standard life benchmark parameters of each device based on the comprehensive aging status indicators, calculates the remaining life cycle of the device in combination with the current time node, and obtains the maintenance trigger time window.

[0037] As a further embodiment of the present invention, the system further comprises:

[0038] The path planning module calls the abnormal data location record and maintenance trigger time window, builds an operation and maintenance work order based on the type, location information, and required tool type of the abnormal equipment, calculates the similarity of the job attributes of multiple work orders, and plans the task cluster path based on the geographical coordinates of the equipment to obtain the power grid operation and maintenance scheduling parameters;

[0039] The power grid operation and maintenance scheduling parameters specifically include operation and maintenance work order construction records, task cluster paths, and job attribute similarity.

[0040] As a further solution of the present invention, the path planning module includes:

[0041] The operation and maintenance work order construction submodule constructs an operation and maintenance work order based on the abnormal data location record and the maintenance trigger time window, the type of abnormal equipment, location information, and required tool type, and obtains an operation and maintenance work order list;

[0042] The job attribute similarity calculation submodule extracts the job attributes of each work order based on the operation and maintenance work order list, including tool requirements, voltage level, and job risk level, using the formula:

[0043] ;

[0044] Calculate the similarity of job attributes between multiple work orders;

[0045] in, Representative work order and work orders The similarity value of Representative work order In the The value of the job attribute, Representative work order In the The value of the job attribute, For work orders The mean value over all job attributes, For work orders The mean value over all job attributes, is the total number of job attributes, is the index of the job attribute;

[0046] The task cluster path planning submodule plans the task cluster path based on the similarity of the job attributes, combined with the geographical coordinates of the equipment, the priority of the task and the resource requirements, and obtains the power grid operation and maintenance scheduling path parameters.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by collecting dynamic data of power grid equipment in real time, the status monitoring and fault diagnosis of power equipment are optimized, the abnormal status of equipment is detected in real time and the fault time node is identified according to voltage data, the accuracy and efficiency of fault diagnosis are improved, and the voltage phase offset value and temperature gradient rise rate of the equipment are combined to timely judge the status of the equipment, monitor the risk of equipment overheating, and improve the reliability and safety of the power grid system. By predicting the aging status of equipment, optimizing the maintenance strategy, reducing the risk of equipment outage, and utilizing task cluster path planning and resource scheduling, the efficient execution of operation and maintenance tasks is ensured, and the power grid operation and maintenance efficiency and the rationality of resource allocation are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a system flow chart of the present invention;

[0050] Figure 2 This is a flow chart of the data acquisition module of the present invention;

[0051] Figure 3 This is a flow chart of the abnormality identification module of the present invention;

[0052] Figure 4 This is a flow chart of the state classification module of the present invention;

[0053] Figure 5 This is a flow chart of the trend prediction module of the present invention;

[0054] Figure 6 This is a flow chart of the path planning module of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0057] See also Figure 1 , a big data-based intelligent dispatching system for power grid operation and maintenance includes:

[0058] The data acquisition module acquires grid operation data, extracts the current amplitude, voltage fluctuation rate, and active power change of multiple grid devices, analyzes the volatility of each data in real time, calculates the variation range of the operation data, adjusts the data sampling frequency, and obtains the power parameter data set;

[0059] The anomaly identification module calls the power parameter data set, extracts the voltage monitoring data sequence of multiple power grid devices, calculates the voltage change slope, and calculates the slope difference of the voltage curve in consecutive time periods, detects abnormal voltage data and abnormal power equipment, identifies abnormal time nodes, and obtains abnormal data location records;

[0060] The status classification module detects the voltage phase offset value and temperature gradient rise rate of the power equipment in real time based on the abnormal data location record and the power parameter data set, analyzes the equipment status, and obtains the equipment status classification level;

[0061] Based on the equipment status classification level, the trend prediction module extracts the leakage current and operating voltage of the equipment in real time, calculates the insulation degradation factor of the equipment, and evaluates the aging status of the equipment in combination with the temperature gradient rise rate of the equipment. It also calculates the remaining life cycle of the equipment and obtains the maintenance trigger time window;

[0062] The path planning module calls on abnormal data location records and maintenance trigger time windows. Based on the type, location information, and required tool type of the abnormal equipment, it constructs operation and maintenance work orders and calculates the similarity of job attributes of multiple work orders. Combined with the geographic coordinates of the equipment, it plans the task cluster path and obtains the power grid operation and maintenance scheduling parameters.

[0063] The power parameter data set includes the equipment voltage waveform data set, leakage current detection data, and equipment operating temperature data set. The abnormal data location records are specifically abnormal time nodes, abnormal voltage data, and abnormal power equipment. The equipment status classification level is specifically the equipment health status level, voltage phase offset value, and temperature gradient rise rate. The maintenance trigger time window is specifically the equipment remaining life cycle, insulation degradation factor, and maintenance trigger time. The power grid operation and maintenance scheduling parameters are specifically the operation and maintenance work order construction record, task cluster path, and job attribute similarity.

[0064] See also Figure 2 , the data acquisition module includes:

[0065] The power parameter extraction submodule obtains grid operation data by extracting the current amplitude, voltage fluctuation rate, and active power change data of multiple grid devices, combining the device number and time stamp to obtain the device operation characteristic data;

[0066] First, the current amplitude, voltage fluctuation rate, and active power change data are extracted from each power grid device and recorded in combination with the device number and timestamp. This module collects the electrical parameters of the device by periodically monitoring the device to form the operating characteristic data of the device. For each device, the current amplitude, voltage fluctuation rate, and active power change will be recorded as a time series to form a device characteristic data set. In practical applications, assuming that the current amplitude of device A at a certain moment is 10A, the voltage fluctuation rate is 5V, and the active power change is 2kW, these data are used to describe the operating status of the device at that point in time. In this way, each device can generate an electric parameter data set, which contains information such as the device number, timestamp, current amplitude, voltage fluctuation rate, and active power change. The formula is used:

[0067] ;

[0068] A data set of power parameters of computing equipment, wherein: For the Current amplitude data points, For the Voltage fluctuation rate data points, For the Active power change data points. Assuming that the current amplitude of device A is 10A, the voltage fluctuation rate is 5V, and the active power change is 2kW, after substituting into the formula, the power parameter data set is obtained:

[0069] ;

[0070] The results show that the power parameter data set of the device includes current amplitude of 10A, voltage fluctuation rate of 5V and active power variation of 2kW, which will provide basic data for subsequent analysis.

[0071] The load variation analysis submodule calls the equipment operation characteristic data and uses the formula:

[0072] ;

[0073] Calculate the data fluctuation determination value within each sliding window period and obtain the variation amplitude parameter;

[0074] in, is the total number of samples in the sampling window, is the data point index, For the The value of the current amplitude data point, is the average value of the current amplitude, For the The value of the active power change data point, is the average value of active power change, For the The value of the voltage fluctuation rate data point, is the average value of voltage fluctuation rate, is the data fluctuation determination value;

[0075] In the load variation analysis submodule, the system uses the equipment operation characteristic data obtained from the data acquisition submodule to further analyze the changes in the current amplitude, voltage fluctuation rate, and active power change. The system performs difference processing on these data according to the time window, and evaluates the volatility of the equipment status by calculating the fluctuation judgment value of the data in each sliding window. For each sliding window, the system calculates the difference between the current amplitude, active power change, and voltage fluctuation rate, and calculates the fluctuation judgment value based on the formula. Assuming that within a sliding window period, the current amplitude changes by 5A, the active power change changes by 0.5kW, and the voltage fluctuation rate changes by 1V, use the formula:

[0076] ;

[0077] Assume that within a sliding window, the current amplitude changes by 5A, the active power changes by 0.5kW, and the voltage fluctuation rate changes by 1V. The average values ​​of the current amplitude, power, and voltage fluctuation rate within the window are 10A, 2kW, and 5V, respectively. Substitute these values ​​into the following formula for calculation:

[0078] ;

[0079] ;

[0080] The calculation results show that the fluctuation determination value is 1.45. By comparing this value with the set threshold, the system can further evaluate the status change trend of the equipment, thereby providing a basis for sampling frequency adjustment and equipment maintenance.

[0081] The sampling frequency control submodule calls the variation amplitude parameter and adjusts the data collection frequency in real time according to the variation amplitude of the equipment operation data. It also obtains the voltage waveform, leakage current, and operating temperature data of multiple operating devices to construct a power parameter data set.

[0082] In the sampling frequency control submodule, the system adjusts the frequency of data collection according to the variation amplitude parameter. The size of the variation amplitude determines the volatility of the equipment's operating status. When the fluctuation is large, the system will increase the sampling frequency to capture changes in the equipment status in real time. The system compares the variation amplitude parameter with the set threshold. If the fluctuation exceeds the set threshold, the sampling frequency will increase; if the fluctuation is less than the threshold, the current frequency will be maintained. Assuming that the variation amplitude of device A is 1.45 and the threshold is set to 1.0, the system will adjust the sampling period according to this difference. Assuming that the original sampling period is 10 seconds, the system will adjust the sampling period to 1.5 times the original, to 7 seconds. At this time, the system will update the power parameter data set according to the sampling period. Use the formula:

[0083] ;

[0084] Calculate the new sampling period, where is the new sampling period, is the original sampling period, is the variation range, To set the threshold, assume the original sampling period is 10 seconds, the variation is 1.45, and the threshold is 1.0. Substitute the formula for calculation:

[0085] ;

[0086] Calculations show that the new sampling period is 24.5 seconds. Based on this sampling frequency, the system adjusts and acquires voltage waveforms, leakage current, and operating temperature data from multiple operating devices, ultimately constructing a power parameter dataset.

[0087] See also Figure 3 , the anomaly recognition module includes:

[0088] The voltage data extraction submodule calls the power parameter data set to extract the voltage value of each power device in the power grid at multiple time points, and combines the device number and timestamp to obtain the voltage monitoring data sequence;

[0089] The voltage data extraction submodule begins by extracting the voltage values ​​of grid devices at different time points from the power parameter dataset. These voltage values ​​are labeled and organized according to device number and timestamp for use in subsequent analysis. Specifically, the voltage data extraction submodule obtains a voltage sequence from the operating data of each grid device. These data points can span multiple time periods and devices. For example, the voltage value of device A in a certain time period is 230V, and the voltage value of device B is 234V. These voltage values ​​are classified according to device number and timestamp, ultimately forming a voltage monitoring data sequence. This data sequence contains not only voltage values, but also other grid operating data such as current amplitude and power data, providing a complete data source for subsequent voltage change analysis. In this way, the system can provide voltage data for each device at each monitoring time point, generating a voltage monitoring data sequence for further analysis.

[0090] The voltage slope calculation submodule calls the voltage monitoring data sequence, calculates the voltage change slope of the device in each time period based on the voltage difference between adjacent moments, and calculates the slope difference of consecutive time periods to obtain the voltage slope difference;

[0091] The voltage slope calculation submodule calculates the voltage change slope of the device in each time period based on the voltage monitoring data sequence. By calculating the ratio of the voltage difference of each pair of adjacent time points to the time interval, the speed of voltage change is obtained. For example, at time point and The voltage change is , and the time interval is , the system calculates the voltage change slope For the next time point pair, the system will continue to use the same method to calculate the slope and summarize the slope values ​​of each time period. The formula is:

[0092] ;

[0093] Calculate the voltage change slope, where is the voltage change slope, is the voltage value at two time points, are the timestamps of two time points. Assuming the voltage data is 230V, 234V, and 233V, with a time interval of 1 second, substitute the formula to calculate the slope:

[0094] ;

[0095] The calculation results show that the voltage change slope is 4V / s. This calculation method is continued to be applied to other data points in the voltage monitoring data sequence to generate voltage change slope data.

[0096] The abnormal node identification submodule uses the voltage slope difference to detect abnormal voltage data in real time, combines the device number and timestamp, marks abnormal power events, and obtains abnormal data location records;

[0097] The abnormal node identification submodule identifies abnormal event nodes in the voltage change process based on the voltage slope difference. The system determines whether there is an abnormal event based on the sudden change in the voltage change slope. Specifically, when the voltage change slope suddenly changes, for example, the voltage slope suddenly jumps from the normal 1V / s to 10V / s, the system marks this time point as an abnormal node. When identifying abnormal nodes, the system calculates the voltage slope difference for consecutive time periods and monitors whether abnormal fluctuations occur. If the slope difference is found to be greater than the preset threshold, the system will mark the period as an abnormal node and record it. The formula is:

[0098] ;

[0099] Calculate the voltage slope difference, where is the voltage slope difference, For the The voltage slope of the time period, is the voltage slope of the previous time period. Assuming that the voltage slope is 1V / s in a certain period and 10V / s in the next period, substitute it into the formula for calculation:

[0100] ;

[0101] The calculation results show that the voltage slope difference is 9V / s, exceeding the preset threshold, and the system marks that time point as an abnormal node. Through this process, the system can identify abnormal event nodes in the power grid and generate abnormal data location records.

[0102] See also Figure 4 , the status classification module includes:

[0103] The phase offset detection submodule uses abnormal data location records and power parameter data sets to extract the absolute phase difference between each cycle voltage waveform and the standard sine wave based on the voltage waveform sequence. It then calculates the sliding window mean of the phase difference for multiple consecutive cycles, calculates the sliding average of the absolute phase difference of each cycle, and combines this with the identified operating temperature data to calculate the temperature gradient rise rate and obtain the state input parameter set.

[0104] After calling the abnormal data location record and power parameter data set, the complete voltage waveform sequence of the target power equipment within the unit cycle is first extracted, and its zero crossing points are numbered to mark the phase structure of each cycle signal. The relative phase offset is calculated by comparing the zero crossing position within the sampling period with the standard sine wave, and the absolute value of the phase difference of each cycle is obtained by full-cycle interpolation calculation, thereby forming a phase difference sequence of continuous cycles. Subsequently, the average phase offset is calculated in sequence with every 5 cycles as a sliding window. The same sliding processing operation is performed on the temperature data, the temperature difference between adjacent cycles is extracted and the average temperature rise rate is calculated, and then the two are integrated to form a set of equipment status input parameters. In order to quantify the stability of the phase offset, the following formula is set:

[0105] ;

[0106] Calculate the average phase offset of the sliding window, where is the average phase offset value, For the Periodic measured phase value, is the ideal sine wave phase value, is the number of sliding window periods.

[0107] set up: , , , , , ,

[0108] Substitute into the calculation:

[0109] ,

[0110] The calculation results show that the average phase offset value of the device in the current sliding cycle is 4.1 degrees. Combined with the temperature rise rate, it forms a state input parameter set for subsequent state judgment.

[0111] To further observe the phase offset trend, the sampling period can be continuously scrolled to construct a phase sliding curve, and the offset rising mutation point can be marked for temperature coupling comparison.

[0112] The state judgment calculation submodule calls the state input parameter set to calculate the temperature rise increment and voltage fluctuation intensity of adjacent cycles, combined with the real-time active power of the equipment, using the formula:

[0113] ;

[0114] Calculate the comprehensive judgment value of the state;

[0115] in, Indicates the comprehensive judgment value of the status, Indicates the voltage phase offset value, represents the temperature gradient value, Indicates the real-time active power of the device. Indicates the temperature rise increment in adjacent cycles, Indicates the voltage fluctuation intensity of the current cycle;

[0116] Based on the obtained state input parameter set, the voltage phase offset, voltage fluctuation intensity, and the comprehensive impact value between active power and temperature rise index are further calculated. First, the real-time active power value of the equipment in a continuous time period is extracted. , temperature rise gradient , Voltage fluctuation intensity of the current cycle and the temperature rise increment of adjacent cycles , the comprehensive status scoring formula is as follows:

[0117] ;

[0118] Used to calculate the comprehensive judgment value of the device status in the current cycle, where: is the comprehensive judgment value of the state, is the phase offset value, is the real-time active power, is the voltage fluctuation intensity, is the temperature gradient, is the temperature rise increment;

[0119] set up , , , , , substitute into the calculation:

[0120] ;

[0121] The calculation result is a comprehensive status judgment value of 33.27, which is used as a scoring reference for the next level classification process;

[0122] After the execution of this submodule is completed, the device status is digitally determined and expressed to provide input conditions for status level classification.

[0123] The risk level classification submodule identifies the equipment status and matches the equipment status tag in real time based on the comprehensive status judgment value and the preset status scoring interval to establish the equipment status classification level;

[0124] After invoking the comprehensive status judgment values ​​obtained by the previous module, an index table of corresponding device numbers is first established to identify the devices to which each status value belongs. During the status grading phase, the system pre-configures a set of status scoring intervals. These intervals are based on factors such as device type, voltage level, and operating environment. These intervals are generally divided into four levels, representing device operating conditions ranging from excellent to high risk. These scoring intervals should be determined in conjunction with grid operating standards and engineering practice to ensure representativeness of the assessment. Based on the standard interval boundaries, the comprehensive status judgment values ​​are matched against all level boundary values. When the status value is below the lowest boundary value, the system automatically classifies the device as Level I, indicating stable operation. If the value is in the second level range, it is classified as Level II, indicating a slight trend of instability. Devices in the third level range are classified as Level III, requiring regular inspections to monitor operational trends. When the status value reaches or exceeds the highest range value, the device is classified as Level IV, indicating significant temperature rise excursions or voltage fluctuations, requiring early inclusion in the key monitoring list and proactive maintenance intervention. During the classification process, each status value must be assigned a unique level label and structured with data such as the device ID number, timestamp, and device type to form a complete data record. This record is stored in the status level database and subsequently accessed by system modules such as visualization, trend tracking, and maintenance task scheduling. After the classification process is complete, the system simultaneously generates a list of device operating status categories, grouping and summarizing them by level. This facilitates operations and maintenance managers to formulate subsequent intervention plans based on risk priority, thereby completing the unified classification of all target device statuses and obtaining the device status classification level.

[0125] See also Figure 5 , the trend forecast module includes:

[0126] The insulation degradation extraction submodule uses the equipment status classification level, the leakage current and operating voltage data of the power equipment, and obtains the average leakage current and average voltage amplitude. By analyzing the leakage current change rate and voltage amplitude change trend, combined with the voltage deviation direction, the insulation degradation factor value is obtained;

[0127] In the insulation degradation extraction submodule, the system first retrieves the status classification level of the power equipment and obtains the data of leakage current and operating voltage. By analyzing these data, the system can calculate the average value of the leakage current and the average value of the voltage amplitude. Next, by analyzing the trend of the leakage current change rate and the voltage amplitude change, the system can obtain preliminary signals about the degradation of the equipment's insulation materials. Specifically, when the leakage current changes greatly, it means that the insulation performance of the equipment is gradually degrading; and the trend of voltage fluctuation can help confirm the directionality of this degradation, such as the degree to which the voltage deviates from the normal value and its persistence. Combining these two data, the insulation degradation factor value is finally calculated. This value reflects the health level of the equipment's insulation status and can be used to support decision-making for equipment maintenance. For example, in a monitoring cycle, assuming that the leakage current change rate is 5% and the voltage fluctuation amplitude is 2%, the system will derive a certain degradation factor by combining these two parameters. Use the formula:

[0128] ;

[0129] Calculate the insulation degradation factor, where is the insulation degradation factor, is the average value of the leakage current, is the average value of the voltage amplitude. Assume , , substitute the set value into the calculation:

[0130] ;

[0131] The calculation results show that the device's insulation degradation factor is 0.91%. This low value indicates that the device's insulation performance is healthy and that no serious degradation has occurred during operation. The system then uses this value to conduct a device health assessment and predict subsequent maintenance needs.

[0132] The aging status assessment submodule extracts the periodic temperature gradient change based on the insulation degradation factor value, obtains the temperature increase and time span of multiple cycles, and calculates the temperature rise rate and voltage deviation ratio fluctuation level in combination with the equipment voltage fluctuation parameters using the formula:

[0133] ;

[0134] Calculate the equipment aging trend offset and perform an average evaluation of the fluctuation amplitude of consecutive cycles to obtain a comprehensive aging status indicator;

[0135] in, Indicates the comprehensive index of aging status, Indicates the Cycle leakage current, represents the temperature gradient, Indicates the operating voltage deviation value, Indicates the temperature rise change value, represents the period time span, Indicates the number of monitoring cycles, The index number of the monitoring period;

[0136] In the aging status assessment submodule, the system further calculates the temperature rise increment and time span in multiple cycles based on the extracted insulation degradation factor value. By extracting the temperature change data within the cycle, the system can determine whether the equipment is at risk of overheating. Combined with the voltage fluctuation parameters, the relationship between the temperature rise rate and the voltage fluctuation is calculated to understand the impact of the equipment's heating conditions on aging. For example, when the voltage fluctuation of the equipment intensifies, the rate of temperature rise will also accelerate, ultimately leading to accelerated aging of the equipment. In this way, the system can obtain a comprehensive indicator of the aging status of the equipment, which is used to evaluate the health status of the equipment in different cycles. Assuming that the temperature rise change of the equipment in the first cycle is 3°C and the voltage fluctuation is 5%, the temperature rise rate can be calculated and the aging process of the equipment can be inferred. The formula is used:

[0137] ;

[0138] set up 5 means that 5 cycles of data are used for calculation, and IL is , unit is A, TG (temperature gradient) is , unit is ℃, UV (voltage deviation value) is , the unit is V, (temperature rise change) is , unit is ℃, (Time span) is , in hours. Calculation process:

[0139] For period 1 ( ):

[0140] ;

[0141] ;

[0142] ;

[0143] For period 2 ( ):

[0144] ;

[0145] ;

[0146] ;

[0147] For period 3 ( ):

[0148] ;

[0149] ;

[0150] ;

[0151] ;

[0152] ;

[0153] ;

[0154] For period 5 ( ):

[0155] ;

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] The aging status comprehensive index DA is 1.810191016. This result shows that in the past five cycles, the comprehensive aging status value of the equipment is 1.81, indicating that the health of the equipment is good or requires further monitoring.

[0161] The life cycle calculation submodule retrieves the standard life benchmark parameters of each device based on the comprehensive aging status indicators, calculates the remaining life cycle of the device in combination with the current time node, and obtains the maintenance trigger time window;

[0162] In the life cycle calculation submodule, the system calculates the current service life of the equipment based on the comprehensive indicators of aging status and the standard life parameters of the equipment type. It then calculates the remaining operating cycle of the equipment based on the current accumulated operating time and outputs the maintenance trigger time window. First, the system calls the standard life parameters of each equipment. For example, the standard life of a large transformer is set to 36,000 hours, and obtains the actual operating time of the equipment. Through the comprehensive indicators of aging status, the system calculates the remaining operating cycle of the equipment based on the current accumulated operating time. Mapping the lifespan consumption multiples in the current unit time forms the basis for calculating acceleration or deceleration compared to the normal aging rate. Specifically, the system multiplies the running time by the lifespan acceleration rate represented by the aging factor at the current moment, calculates the current equivalent lifespan consumption, and then subtracts the equivalent lifespan consumption from the total lifespan consumption to obtain the remaining lifespan. The formula used is:

[0163] ;

[0164] Calculate the remaining life cycle, where is the remaining life cycle of the equipment, is the standard life cycle of the equipment, The current cumulative running time of the device. It is a comprehensive indicator of aging status. is the equipment aging gain coefficient. Set , , , , substitute the set value into the calculation:

[0165] ;

[0166] The calculation results show that the remaining life cycle of the equipment is 19,200 hours. Based on this value and the operation plan, the system sets a reasonable maintenance trigger time window.

[0167] See also Figure 6 , the path planning module includes:

[0168] The operation and maintenance work order construction submodule constructs an operation and maintenance work order based on the abnormal data location records and maintenance trigger time window, the type of abnormal equipment, location information, and required tool type, and obtains the operation and maintenance work order list;

[0169] In the maintenance work order generation submodule, the system first extracts relevant data based on the aforementioned abnormal data location records and maintenance trigger time windows, identifies the time point when the equipment fault occurred, and locates the fault type and location. Using this information, the system accurately identifies the specific equipment in the power grid requiring maintenance and the specific fault details for each device. The system then automatically generates maintenance work orders based on the type and location of the faulty equipment and the nature of the maintenance task. These work orders include the device's location, fault type, required repair tools, work time, and priority. Maintenance personnel can quickly access detailed information about the maintenance task through work orders, improving work efficiency. For example, if a transformer in the power grid fails, the system automatically generates a work order based on its location and fault type, including a description of the fault, repair requirements, required tools, and repair time. If a device experiences abnormal voltage fluctuations and requires insulation inspection, the system specifies the required tools as an "insulation tester" and a "voltage tester" and dispatches personnel to the designated location to conduct equipment inspection and repair, as specified in the work order. During this process, the generation of maintenance work orders ensures timely and accurate execution of repair work, improving maintenance efficiency and reducing the probability of operational errors. Ultimately, all generated work orders are assigned to the maintenance team according to priority, ensuring stable system operation and preparing for subsequent work. The final result is a list of maintenance work orders.

[0170] The job attribute similarity calculation submodule extracts the job attributes of each work order based on the operation and maintenance work order list, including tool requirements, voltage level, and job risk level, using the formula:

[0171] ;

[0172] Calculate the similarity of job attributes between multiple work orders;

[0173] in, Representative work order and work orders The similarity value of Representative work order In the The value of the job attribute, Representative work order In the The value of the job attribute, For work orders The mean value over all job attributes, For work orders The mean value over all job attributes, is the total number of job attributes, is the index of the job attribute;

[0174] During the execution of this submodule, it is first necessary to extract the job attributes of each work order from the aforementioned operation and maintenance work order list. The main job attributes include tool requirements, voltage level, and job risk level. For each pair of work orders, the system calculates the difference between them in each job attribute, and then derives the similarity value between the two work orders. The core of this process is to convert the job attribute differences of each pair of work orders into a comparable similarity score through standardized calculation, which reflects the similarity of the tasks. Using the similarity value, the system can reasonably allocate resources, optimize the order of task execution, and improve efficiency by minimizing resource waste. The formula used is:

[0175] ;

[0176] To calculate the similarity of operations, assume that the operation attributes of work order A and work order B are: work order A, tool requirement level 2, voltage level 10kV, risk level high; work order B, tool requirement level 3, voltage level 10kV, risk level medium. The calculation process is as follows:

[0177] ,

[0178] ,

[0179] ,

[0180] Get the similarity of job attributes between multiple work orders.

[0181] The task cluster path planning submodule plans the task cluster path based on the similarity of job attributes, combined with the geographical coordinates of the equipment, the priority of the task and the resource requirements, and obtains the grid operation and maintenance scheduling path parameters;

[0182] During the execution of this submodule, the system first divides the tasks into different clusters through cluster analysis based on the similarity of the job attributes calculated above, combined with information such as the geographical coordinates, task priority, and required resources of each task. Tasks within each cluster usually have similar job requirements and geographical locations, so they can be completed together to improve resource utilization and save time. During the cluster analysis process, the system considers multiple factors, including the urgency of the task, the tools required for maintenance, the execution time of the task, etc. These factors work together to ensure that the task cluster can be optimized and scheduled according to the actual situation. The cluster analysis formula is used:

[0183] ;

[0184] in, is the distance measure between task X and task Y, and For tasks X and Y in The value of the job attribute, is the total number of job attributes. Using a clustering analysis algorithm, the system clusters tasks, ensuring that tasks with high priority and high similarity are physically close together. This allows multiple tasks to be completed simultaneously within the same area, reducing transportation time and frequent switching operations. Assuming the attributes of Task A and Task B in the task cluster are: Task A is at position (3, 4) with a high priority, and Task B is at position (5, 6) with a medium priority, the calculation process is:

[0185] ;

[0186] Based on this distance metric, the system further assigns Task A and Task B to different task clusters (if their job attributes and priorities match). After calculating the task distance metric, the system proceeds to path planning, sorting and scheduling tasks based on the distance metric and job priorities. This ensures that tasks are executed along the most efficient path, optimizes resource allocation, and reduces unnecessary time waste. In this way, the system ensures that jobs are executed in order of priority while minimizing resource waste and execution time. Obtain the task cluster path parameters.

[0187] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A big data-based intelligent dispatching system for power grid operation and maintenance, characterized by: The system comprises: The data acquisition module acquires grid operation data, extracts the current amplitude, voltage fluctuation rate, and active power change of multiple grid devices, analyzes the volatility of each data in real time, calculates the variation range of the operation data, adjusts the data sampling frequency, and obtains the power parameter data set; The anomaly identification module calls the power parameter data set, extracts the voltage monitoring data sequence of multiple power grid devices, calculates the voltage change slope, and calculates the slope difference of the voltage curve in consecutive time periods, detects abnormal voltage data and abnormal power equipment, identifies abnormal time nodes, and obtains abnormal data location records; The status classification module detects the voltage phase offset value and temperature gradient rise rate of the power equipment in real time based on the abnormal data location record and the power parameter data set, analyzes the equipment status, and obtains the equipment status classification level; Based on the equipment status classification level, the trend prediction module extracts the leakage current and operating voltage of the equipment in real time, calculates the insulation degradation factor of the equipment, and evaluates the aging status of the equipment in combination with the temperature gradient rise rate of the equipment. It also calculates the remaining life cycle of the equipment and obtains the maintenance trigger time window; The trend prediction module includes: The insulation degradation extraction submodule calls the equipment status classification level, calls the leakage current and operating voltage data of the power equipment, obtains the average leakage current and the average voltage amplitude, and obtains the insulation degradation factor value by analyzing the leakage current change rate and the voltage amplitude change trend in combination with the voltage deviation direction; The aging status assessment submodule extracts the periodic temperature gradient change based on the insulation degradation factor value, obtains the temperature increase and time span of multiple cycles, and calculates the temperature rise rate and voltage deviation ratio fluctuation level in combination with the equipment voltage fluctuation parameters using the formula: ； Calculate the equipment aging trend offset and perform an average evaluation of the fluctuation amplitude of consecutive cycles to obtain a comprehensive aging status indicator; in, Indicates the comprehensive index of aging status, Indicates the Cycle leakage current, represents the temperature gradient, Indicates the operating voltage deviation value, Indicates the temperature rise change value, represents the period time span, Indicates the number of monitoring cycles, The index number of the monitoring period; The life cycle calculation submodule retrieves the standard life benchmark parameters of each device based on the comprehensive aging status indicators, calculates the current service life of the device, combines the current accumulated operating time, calculates the remaining operating cycle of the device, and obtains the maintenance trigger time window.

2. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 1 is characterized in that: The power parameter data set includes an equipment voltage waveform data set, leakage current detection data, and an equipment operating temperature data set. The abnormal data location record specifically includes abnormal time nodes, abnormal voltage data, and abnormal power equipment. The equipment status classification level specifically includes equipment health status level, voltage phase offset value, and temperature gradient rise rate. The maintenance trigger time window specifically includes the remaining life cycle of the equipment, insulation degradation factor, and maintenance trigger time.

3. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 1 is characterized in that: The data acquisition module includes: The power parameter extraction submodule obtains grid operation data by extracting the current amplitude, voltage fluctuation rate, and active power change data of multiple grid devices, combining the device number and time stamp to obtain the device operation characteristic data; The load variation analysis submodule calls the equipment operation characteristic data and uses the formula: ； Calculate the data fluctuation determination value within each sliding window period and obtain the variation amplitude parameter; in, is the total number of samples in the sampling window, is the data point index, For the The value of the current amplitude data point, is the average value of the current amplitude, For the The value of the active power change data point, is the average value of active power change, For the The value of the voltage fluctuation rate data point, is the average value of voltage fluctuation rate, is the data fluctuation determination value; The sampling frequency control submodule calls the variation amplitude parameter, adjusts the data acquisition frequency in real time according to the variation amplitude of the equipment operation data, and obtains the voltage waveform, leakage current, and operating temperature data of multiple operating devices to construct a power parameter data set.

4. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 3 is characterized in that: The abnormality identification module includes: The voltage data extraction submodule calls the power parameter data set, extracts the voltage value of each power device in the power grid at multiple time points, and obtains the voltage monitoring data sequence by combining the device number and the timestamp; The voltage slope calculation submodule calls the voltage monitoring data sequence, calculates the voltage change slope of the device in each time period based on the voltage difference between adjacent moments, and calculates the slope difference of consecutive time periods to obtain the voltage slope difference; The abnormal node identification submodule calls the voltage slope difference, detects abnormal voltage data in real time, marks abnormal power events in combination with the device number and timestamp, and obtains abnormal data location records.

5. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 4 is characterized in that: The status classification module includes: The phase shift detection submodule calls the abnormal data location record and power parameter data set, extracts the absolute value of the phase difference between each cycle voltage waveform and the standard sine wave according to the voltage waveform sequence, calculates the sliding window mean of the phase difference of multiple consecutive cycles, calculates the sliding average of the absolute value of the cycle phase difference, combines it with the identified operating temperature data, calculates the temperature gradient rise rate, and obtains the state input parameter set; The state judgment calculation submodule calls the state input parameter set to calculate the temperature rise increment and voltage fluctuation intensity of adjacent cycles, combined with the real-time active power of the equipment, using the formula: ； Calculate the comprehensive judgment value of the state; in, Indicates the comprehensive judgment value of the status, Indicates the voltage phase offset value, represents the temperature gradient value, Indicates the real-time active power of the device. Indicates the temperature rise increment in adjacent cycles, Indicates the voltage fluctuation intensity of the current cycle; The risk level classification submodule identifies the device status based on the comprehensive status judgment value and combines the preset status scoring interval to match the device status label in real time and establish the device status classification level.

6. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 1 is characterized in that: The system further comprises: The path planning module calls the abnormal data location record and maintenance trigger time window, builds an operation and maintenance work order based on the type, location information, and required tool type of the abnormal equipment, calculates the similarity of the job attributes of multiple work orders, and plans the task cluster path based on the geographical coordinates of the equipment to obtain the power grid operation and maintenance scheduling parameters; The power grid operation and maintenance scheduling parameters specifically include operation and maintenance work order construction records, task cluster paths, and job attribute similarity.

7. The big data-based intelligent dispatching system for power grid operation and maintenance according to claim 6 is characterized in that: The path planning module includes: The operation and maintenance work order construction submodule constructs an operation and maintenance work order based on the abnormal data location record and the maintenance trigger time window, the type of abnormal equipment, location information, and required tool type, and obtains an operation and maintenance work order list; The job attribute similarity calculation submodule extracts the job attributes of each work order based on the operation and maintenance work order list, including tool requirements, voltage level, and job risk level, using the formula: ； Calculate the similarity of job attributes between multiple work orders; in, Representative work order and work orders The similarity value of Representative work order In the The value of the job attribute, Representative work order In the The value of the job attribute, For work orders The mean value over all job attributes, For work orders The mean value over all job attributes, is the total number of job attributes, is the index of the job attribute; The task cluster path planning submodule plans the task cluster path based on the similarity of the job attributes, combined with the geographical coordinates of the equipment, the priority of the task and the resource requirements, and obtains the power grid operation and maintenance scheduling path parameters.

Images