An intensive power distribution intelligent operation and maintenance host that can be used in unattended power distribution rooms

Abstract

The present invention relates to the field of big data processing technology, and in particular to an intensive power distribution intelligent operation and maintenance host that can be used for unattended power distribution rooms, including a patrol cycle setting module, a patrol task execution module, a real-time data monitoring and analysis module, an abnormality identification and filtering module, and an abnormal feature automatic extraction module; by dividing the equipment type, the patrol cycle is set differently and dynamically adjusted; by generating patrol tasks and assigning them to patrol personnel, the task management process is simplified and the problem tracing is facilitated; by real-time monitoring of the operating status of the equipment, and processing and analyzing, a data source is provided for subsequent abnormal identification; by identifying abnormal operating status, the pertinence and efficiency of abnormal processing are improved; by in-depth analysis of abnormal data, abnormal features are extracted, and timely feedback is provided to optimize the patrol strategy. The present invention is used to solve the technical problems of low patrol quality and unstable operation of unattended power distribution rooms.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to an intensive power distribution intelligent operation and maintenance host that can be used in an unmanned power distribution room. Background Art

[0002] Big data processing technology refers to a collection of technologies and tools used to process and analyze large-scale data sets, usually involving technologies in fields such as distributed systems, data mining, machine learning, and artificial intelligence. It aims to extract meaningful information and insights from massive data, emphasizing the complexity, real-time nature and potential value of data.

[0003] With the continuous advancement of technology and the continuous expansion of application fields, the power industry is also developing steadily. However, the distribution room is located at the key node of the power grid and is responsible for the distribution and transmission of electric energy. Since these distribution rooms are often unattended, the following problems exist: the equipment inspection method is single and the quality is not high. Many inspectors of unattended distribution rooms still use traditional methods and lack professional detection equipment and tools, resulting in low inspection quality and easy neglect of key electrical components and environmental impacts; lack of effective inspection management, the inspection work of unattended distribution rooms lacks effective management; lack of stability, the distribution room needs to operate stably for a long time, and is prone to abnormalities and failures, thereby reducing operating efficiency. To this end, the present invention proposes an intensive distribution intelligent operation and maintenance host that can be used for unattended distribution rooms. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the background technology and to propose an intensive power distribution intelligent operation and maintenance host that can be used in an unmanned power distribution room.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: An intensive power distribution intelligent operation and maintenance host that can be used in unattended power distribution rooms, comprising: a patrol cycle setting module, a patrol task execution module, a real-time data monitoring and analysis module, an abnormality identification and filtering module, and an abnormality feature automatic extraction module; The patrol cycle setting module is used to automatically classify equipment into different categories according to the preset equipment importance standards; use the fault records in the historical operation data to perform statistical and computational analysis to evaluate the fault mode and frequency of each equipment category; set the corresponding patrol cycle for each type of equipment based on the data evaluation results; and dynamically adjust the set patrol cycle in combination with real-time monitoring data and abnormal events; The patrol task execution module is used to create patrol tasks, assign the generated patrol tasks to patrol personnel for execution, and manage the execution status; The real-time data monitoring and analysis module is used to monitor the operating status of the equipment in real time during the inspection cycle; it is responsible for capturing, processing and analyzing the various operating parameters of the equipment and obtaining the monitoring data set; The anomaly identification and filtering module is used to perform quantitative analysis on the monitoring data set, automatically identify and filter out abnormal operating conditions that deviate from the normal range, and obtain an abnormal indicator set; The abnormal feature automatic extraction module is used to process and analyze the abnormal indicator set, extract abnormal features from it, record the identified abnormal events, and feed back to the patrol cycle setting module.

[0006] Furthermore, the process of the patrol cycle setting module automatically classifying the equipment into different categories according to the preset equipment importance standard includes: Devices are divided into different categories based on their function and purpose , i.e. key equipment , important equipment And general equipment Among them, key equipment refers to the equipment with the greatest impact on the operation of the distribution room, important equipment refers to the equipment with a medium impact on the operation of the distribution room, and general equipment refers to the equipment with the least impact on the operation of the distribution room.

[0007] Furthermore, the patrol cycle setting module uses the fault records in the historical operation data to perform statistical and computational analysis to evaluate the failure mode and frequency of each equipment category, including: Define a weight value for each category of equipment , , indicating the quantitative value of the importance of this type of equipment; Collect the operating time of each type of equipment from the historical data of the intensive power distribution intelligent operation and maintenance host and number of failures , where n represents the month of historical data obtained; Calculate the mean time between failures for each type of equipment and failure rate : , , where Indicates the average time between equipment failures in historical data month n; Combined with the failure rate and importance weight, the risk assessment of the intensive power distribution intelligent operation and maintenance host is carried out: ;in, Represents the risk assessment value.

[0008] Furthermore, the patrol cycle setting module sets a corresponding patrol cycle for each type of equipment based on the data evaluation results, and dynamically adjusts the patrol cycle in combination with real-time monitoring data and abnormal events. The process includes: Set patrol cycle : , where k represents a constant, The weight value defined for each category of equipment, is the mean time between failures for each type of equipment, is the risk assessment value; According to the real-time monitoring data of the equipment and the abnormal event record information, a dynamic adjustment mechanism is established: if the real-time monitored equipment status data exceeds the normal range or the feedback information of the abnormal feature automatic extraction module is received, the adjustment factor Increase, otherwise decrease; thus get the adjusted patrol cycle ;in, Decisions are made based on deviations of real-time monitoring data from the normal range.

[0009] Furthermore, the patrol task execution module creates patrol tasks, assigns the generated patrol tasks to patrol personnel for execution, and manages the execution status, including: For patrol cycle Generate patrol tasks : Determine the patrol period for each device category ; According to the patrol cycle and the current time , calculate the next patrol time point ;like , then a patrol task is generated , indicating that the scheduled patrol time has been exceeded, i.e. , and Updated to ;in, Indicates the time point of the last inspection of device category C, which is used to calculate the starting point of the next inspection cycle. When the inspection task is completed, Updated to current time , to reflect the latest inspection time; Combined with the importance weight of the equipment category, each patrol task is arranged in the order of priority attention or execution to obtain the patrol priority. : ; Get patrol task collection And the patrol personnel set R, each patrol task Have corresponding skills , each patrol officer r∈R has his own skills and current availability status ; Finding the Allocation Matrix , so that for each patrol task m there is a patrol officer r that satisfies and ;in, is a binary variable, indicating whether patrol officer r is assigned to patrol task m, i.e., the patrol task assignment result. It means that if and only if the patroller r is assigned to patrol task m, otherwise ; Maximize the coverage Z of the patrol task: , where Indicates the patrol task number. Indicates the total number of patrol tasks, Indicates the patrol officer's number. Indicates the total number of patrol officers; Among them, the following constraints are met: , where (1) means that each patrol task can only be performed by one patrol officer; (2) means that each patrol officer only performs one patrol task; (3) means that the patrol officer's skills match the patrol task requirements; where is the indicator function, if Include , then returns 1, otherwise returns 0; (4) represents the patrol personnel availability check; (5) represents duality; Track and record the execution of patrol tasks, including patrol task start time, execution progress and completion status, and upload them to the data center.

[0010] Furthermore, the real-time data monitoring and analysis module monitors the operating status of the equipment in real time, captures and processes and analyzes various operating parameters of the equipment, and the process of obtaining the monitoring data set includes: Determine the time range for monitoring and monitor data according to the set time period, including the start and end time of monitoring; Use sensor components to measure current, voltage, temperature and humidity; use power meters and energy metering equipment to calculate the energy efficiency ratio, that is, the ratio of energy converted per unit time to energy consumed; The current and voltage are regarded as power parameters D, the temperature and humidity are regarded as environmental parameters H, and the energy efficiency ratio is processed and analyzed as the energy efficiency parameter N; the specific analysis formula is as follows: , where Represents comprehensive evaluation parameter index; Indicates the average value of the power parameter; Indicates the optimal value of the operating environment; Indicates the average value of energy efficiency parameters; Represents adjustment parameters, which are used to adjust the degree of influence when each parameter deviates from the average value or optimal value; The comprehensive evaluation parameter indicators of all monitoring time periods are integrated to form a monitoring data set.

[0011] Furthermore, the anomaly identification and filtering module performs quantitative analysis on the monitoring data set, automatically identifies and filters out abnormal operating conditions that deviate from the normal range. The process of obtaining the abnormal indicator set includes: Extract the values ​​of comprehensive evaluation parameter indicators of the monitoring data set and conduct quantitative analysis; , where is the normality index, which is used to reflect the closeness of the equipment status to normal operation; h is the offset; is a scalar parameter, indicating a threshold interval; when hour, The value is 0, indicating that the device status is abnormal; when hour, It increases linearly, indicating that the equipment status tends to be normal; when hour, A value of 1 indicates that the device is in normal state; According to the quantitative analysis results, the comprehensive evaluation parameter indicators corresponding to the abnormal equipment status are obtained and marked as an abnormal indicator set.

[0012] Furthermore, the abnormal feature automatic extraction module processes and analyzes the abnormal indicator set, extracts abnormal features therefrom, records the identified abnormal events, and feeds back to the patrol cycle setting module. The process includes: The skewness formula is used to analyze whether the data distribution of the abnormal indicator set is symmetrical; the skewness formula is as follows: , where represents the skewness value, which is an indicator used to measure the degree of asymmetry of the data distribution of the abnormal indicator set, describing the direction and degree of skewness of the data distribution of the abnormal indicator set around its mean; b represents the total number of data points in the abnormal indicator set; i represents the number of the data point in the abnormal indicator set; xi represents the i-th data point in the abnormal indicator set; represents the mean of the abnormal indicator set, that is, ; It represents the standard deviation of the abnormal indicator set, which is used to measure the degree of dispersion between the data points in the abnormal indicator set and their mean, that is, ; Represents the process of normalizing each data point in the anomaly indicator set; When analyzing the skewness calculation results, when the skewness is greater than 0, the skewness is positive, which means that the data distribution of the abnormal indicator set is skewed to the right; when the skewness is less than 0, the skewness is negative, which means that the data distribution of the abnormal indicator set is skewed to the left; The kurtosis formula is used to analyze the sharpness of the data distribution of the abnormal indicator set; the kurtosis formula is as follows: , where Represents the kurtosis value, which is an indicator used to measure the sharpness or flatness of the data distribution of the abnormal indicator set; When analyzing the kurtosis calculation results, when the kurtosis is greater than 0, it is a peak state, which means that the data distribution of the abnormal indicator set is sharper than the normal distribution; when the kurtosis is less than 0, it is a flat peak state, which means that the data distribution of the abnormal indicator set is flatter than the normal distribution; According to the analysis results of skewness and kurtosis, the abnormal features are extracted. If the skewness of the abnormal indicator set is positive and the kurtosis is high, it means that there are many abnormal high values ​​and the abnormal values ​​are concentrated; if the skewness of the abnormal indicator set is negative and the kurtosis is low, it means that there are few abnormal values ​​and the distribution is relatively uniform. Based on the analyzed high-value or low-value abnormal features, use a database to record information about abnormal events; wherein the information about abnormal events recorded includes timestamp, data value, parameter type, and abnormal attributes; The abnormal event information is fed back to the patrol cycle setting module to dynamically adjust the patrol cycle for subsequent optimization management.

[0013] Compared with the existing technology, the present invention provides an intensive power distribution intelligent operation and maintenance host and method that can be used in an unattended power distribution room, which has the following advantages: 1. The present invention automatically divides the equipment in the power distribution room into different categories, which facilitates differentiated operation and maintenance management in the future; statistical and computational analysis are performed by using the fault records in the historical operation data to evaluate the fault mode and its frequency of occurrence; and a reasonable inspection cycle is set for each type of equipment and dynamically adjusted to avoid waste of resources caused by excessive maintenance; 2. The present invention creates specific inspection tasks according to the inspection plan generated by the inspection cycle setting module, and assigns them to corresponding inspection personnel to execute, thereby ensuring the standardization and timeliness of the inspection work; by continuously monitoring the operating status of the equipment during the inspection cycle, processing and analyzing various operating parameters, and obtaining monitoring data sets, data support is provided for subsequent abnormal identification and evaluation; 3. The present invention identifies abnormal operating conditions that deviate from the normal range by quantitatively analyzing the monitoring data set; automatically filters abnormal operating conditions by setting a reasonable threshold algorithm; and further improves the operation and maintenance level by extracting abnormal features and recording abnormal events.

[0014] To sum up, the present invention can carry out comprehensive data analysis and precise monitoring according to actual conditions, optimize resource allocation, and make various modules cooperate and work together to constitute the core functions of the intensive power distribution intelligent operation and maintenance host. It improves the operation and maintenance efficiency and management level of the unmanned distribution room through automation and intelligent means, ensuring the efficient and stable operation of the subsequent intensive power distribution intelligent operation and maintenance host that can be used for unmanned distribution rooms. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a module diagram of an intensive power distribution intelligent operation and maintenance host that can be used in an unmanned power distribution room proposed by the present invention. DETAILED DESCRIPTION

[0016] 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 implementation regulations described 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.

[0017] Reference Figure 1 , an intensive power distribution intelligent operation and maintenance host that can be used in unmanned power distribution rooms, the system includes a patrol cycle setting module, a patrol task execution module, a real-time data monitoring and analysis module, an abnormality identification and filtering module, and an abnormality feature automatic extraction module; The patrol cycle setting module is used to automatically classify equipment into different categories according to the preset equipment importance standards; use the fault records in the historical operation data to perform statistical and computational analysis to evaluate the fault mode and frequency of each equipment category; set the corresponding patrol cycle for each type of equipment based on the data evaluation results; and dynamically adjust the set patrol cycle in combination with real-time monitoring data and abnormal events; Among them, the inspection cycle refers to the remote or automated inspection of the power distribution room at a certain time interval (such as daily, weekly, monthly, etc.) to monitor the operating status of the equipment, discover potential problems and deal with them in a timely manner; the setting of the inspection cycle is an important part of operation and maintenance management, ensuring that the power distribution room can be monitored and managed in a timely and effective manner even when there is no real-time presence of personnel; The patrol task execution module is used to create patrol tasks, assign the generated patrol tasks to patrol personnel for execution, and manage the execution status; The real-time data monitoring and analysis module is used to monitor the operating status of the equipment in real time during the inspection cycle; it is responsible for capturing, processing and analyzing the various operating parameters of the equipment and obtaining the monitoring data set; The anomaly identification and filtering module is used to perform quantitative analysis on the monitoring data set, automatically identify and filter out abnormal operating conditions that deviate from the normal range, and obtain an abnormal indicator set; The abnormal feature automatic extraction module is used to process and analyze the abnormal indicator set, extract abnormal features from it, record the identified abnormal events, and feed back to the patrol cycle setting module.

[0018] It should be noted that the application object of an intensive distribution intelligent operation and maintenance host that can be used for an unmanned distribution room in an embodiment of the present invention can be an unmanned distribution room in the power industry, and can be used to monitor the operating status of a group of power equipment in real time. Specifically, it can be used to comprehensively analyze and accurately evaluate various operating data of the power equipment group through big data and Internet of Things technology to identify potential faults, and optimize resource allocation by adjusting the patrol cycle, thereby improving operation and maintenance efficiency and energy utilization, and ensuring the stable operation of the distribution room and the entire power system; among them, the intensive distribution intelligent operation and maintenance host, as the core equipment of the unmanned distribution room, can have a very complex and diverse composition to meet the needs of comprehensive, efficient and intelligent operation and maintenance of the distribution room; the component devices of the intensive distribution intelligent operation and maintenance host mainly include a patrol cycle setting module, a patrol task execution module, a real-time data monitoring and analysis module, an abnormality identification and filtering module, and an abnormal feature automatic extraction module.

[0019] The patrol cycle setting module automatically divides the equipment into different categories according to the preset equipment importance standards; uses the fault records in the historical operation data to perform statistical and computational analysis to evaluate the failure mode and frequency of each equipment category; sets the corresponding patrol cycle for each type of equipment based on the data evaluation results; and dynamically adjusts the set patrol cycle in combination with real-time monitoring data and abnormal events. The steps include: Step 101: Classify devices into different categories based on their functions and uses , i.e. key equipment , important equipment And general equipment Among them, key equipment refers to the equipment with the highest degree of impact on the operation of the power distribution room, important equipment refers to the equipment with a medium degree of impact on the operation of the power distribution room, and general equipment refers to the equipment with the least degree of impact on the operation of the power distribution room; In step 101, the equipment involved includes but is not limited to transformers, high-voltage switchgear, capacitor supplement cabinets, DC panels, lighting and ventilation equipment, etc.; the transformer is the core equipment in the distribution room, which is used to convert the high-voltage electric energy of the power grid into low-voltage electric energy for users to use, and is classified as key equipment; the high-voltage switchgear is used to receive and distribute the high-voltage electric energy in the power grid, and to control and protect the circuit, and is classified as key equipment; the lighting and ventilation equipment are used to provide the necessary working environment and safety protection, and are classified as general equipment; the DC panel is the DC power supply equipment in the distribution room, which provides DC power for the control, protection, monitoring and other equipment in the power system, and is classified as important equipment; the capacitor supplement cabinet is used to The key equipment refers to the equipment that has a vital impact on the normal operation of the power distribution room. Once a fault or failure occurs, it will directly lead to the paralysis of the intensive power distribution intelligent operation and maintenance host or a serious accident. The important equipment refers to the equipment that has a significant impact on the operation of the power distribution room. When a fault occurs, it will reduce the operating efficiency of the intensive power distribution intelligent operation and maintenance host or increase the operation and maintenance cost, but will not directly lead to the paralysis of the intensive power distribution intelligent operation and maintenance host. The general equipment refers to the equipment that has a small impact on the operation of the power distribution room. When a fault occurs, it usually does not cause a serious impact on the overall operation of the intensive power distribution intelligent operation and maintenance host. Step 102: Define a weight value for each category of equipment , , indicating the quantitative value of the importance of this type of equipment; Step 103: Collect the operating time of each type of equipment from the historical data of the intensive power distribution intelligent operation and maintenance host and number of failures , where n represents the month of historical data obtained; Step 104: Calculate the mean time between failures for each type of equipment and failure rate : , , where Indicates the average time between equipment failures in historical data month n; Step 105: Based on the failure rate and importance weight, a risk assessment is performed on the intensive power distribution intelligent operation and maintenance host: ;in, represents the risk assessment value; Step 106: Set patrol cycle : , where k is a constant. The weight value defined for each category of equipment, is the mean time between failures for each type of equipment, is the risk assessment value; Step 107: Establish a dynamic adjustment mechanism based on the real-time monitoring data of the device and the abnormal event record information: if the real-time monitored device status data exceeds the normal range or the feedback information of the abnormal feature automatic extraction module is received, the adjustment factor Increase, otherwise decrease; thus get the adjusted patrol cycle ;in, Decisions are made based on deviations of real-time monitoring data from the normal range.

[0020] The patrol task execution module creates patrol tasks, assigns the generated patrol tasks to patrol personnel for execution, and manages the execution status, including the following steps: Step 201: For patrol cycle Generate patrol tasks : Determine the patrol period for each device category ; According to the patrol cycle and the current time , calculate the next patrol time point ;like , then a patrol task is generated , indicating that the scheduled patrol time has been exceeded, i.e. , and Updated to ;in, Indicates the time point of the last inspection of device category C, which is used to calculate the starting point of the next inspection cycle. When the inspection task is completed, Updated to current time , to reflect the latest inspection time; Step 202: Combine the importance weights of the equipment categories and arrange each patrol task in the order of priority attention or execution to obtain the patrol priority. : ; Step 203: Get patrol task set And the patrol personnel set R, each patrol task Have corresponding skills , each patrol officer r∈R has his own skills and current availability status ; In step 203, availability indicates that the patrol personnel R is able and willing to perform the assigned patrol task within a specific time period. In the process of patrol task allocation, the assessment of patrol personnel availability is crucial, which helps to ensure that tasks can be performed by personnel with sufficient ability and willingness, thereby improving the efficiency and quality of task completion; at the same time, through the assessment of availability, potential problems such as staff shortages or insufficient resources can be discovered and resolved in a timely manner, providing a strong guarantee for the smooth progress of tasks; Step 204: Find the allocation matrix , so that for each patrol task m there is a patrol officer r that satisfies and ;in, is a binary variable, indicating whether patrol officer r is assigned to patrol task m, i.e., the patrol task assignment result. It means that if and only if the patroller r is assigned to patrol task m, otherwise ; Step 205: Maximize the coverage Z of the patrol task: , where Indicates the patrol task number. Indicates the total number of patrol tasks, Indicates the patrol officer's number. Indicates the total number of patrol officers; In step 205, the following constraints are met: , where (1) means that each patrol task can only be performed by one patrol officer; (2) means that each patrol officer can only perform one patrol task; (3) means that the patrol officer's skills match the patrol task requirements; where is the indicator function, if Include , then returns 1, otherwise returns 0; (4) represents the patrol personnel availability check; (5) represents duality; Step 206: Track and record the patrol task execution status, including patrol task start time, execution progress and completion status, and upload to the data center.

[0021] The real-time data monitoring and analysis module monitors the operating status of the equipment in real time during the inspection cycle. It is responsible for capturing, processing and analyzing the various operating parameters of the equipment. The steps to obtain the monitoring data set include: Step 301, determine the time range for monitoring, and perform data monitoring according to the set time period, including the start time and end time of monitoring; Step 302: Use the sensor assembly to measure current, voltage, temperature and humidity; calculate the energy efficiency ratio, that is, the ratio of the energy converted to the energy consumed per unit time, through the power meter and the electric energy metering equipment; Step 303: current and voltage are regarded as power parameters D, temperature and humidity are regarded as environmental parameters H, and energy efficiency ratio is regarded as energy efficiency parameter N for processing and analysis; the specific analysis formula is as follows: , where Represents comprehensive evaluation parameter index; Indicates the average value of the power parameter; Indicates the optimal value of the operating environment; Indicates the average value of energy efficiency parameters; Represents adjustment parameters, which are used to adjust the degree of influence when each parameter deviates from the average value or optimal value; Step 304: Integrate the comprehensive evaluation parameter indicators of all monitoring time periods to form a monitoring data set.

[0022] The anomaly identification and filtering module performs quantitative analysis on the monitoring data set, automatically identifies and filters out abnormal operating conditions that deviate from the normal range. The steps for obtaining the abnormal indicator set include: Step 401: extract the values ​​of comprehensive evaluation parameter indicators of the monitoring data set and perform quantitative analysis; , where is the normality index, which is used to reflect the closeness of the equipment status to normal operation. The higher the value, the more normal the equipment status is, and the lower the value, the deviation of the equipment status from normal operation. h is the offset, which is an average value or optimal operating point calculated based on historical data, or a theoretical value set in combination with expected performance. In practical applications, m needs to be adjusted according to specific circumstances to ensure that it can accurately reflect the normal operating status of the equipment. It is a scalar parameter, which represents a threshold interval, i.e., tolerance, used to determine the range within which the change of the device status is considered acceptable; Step 402: hour, The value is 0, indicating that the device status is abnormal; when hour, It increases linearly, indicating that the equipment status tends to be normal; when hour, A value of 1 indicates that the device is in normal state; Step 403: According to the quantitative analysis result, the comprehensive evaluation parameter index corresponding to the abnormal device status is obtained and marked as an abnormal index set.

[0023] The abnormal feature automatic extraction module is used to process and analyze the abnormal indicator set, extract abnormal features from it, record the identified abnormal events, and provide feedback to the patrol cycle setting module. The steps include: Step 501: Use the skewness formula to analyze whether the data distribution of the abnormal indicator set is symmetrical; wherein the skewness formula is as follows: , where represents the skewness value, which is an indicator used to measure the degree of asymmetry of the data distribution of the abnormal indicator set, describing the direction and degree of skewness of the data distribution of the abnormal indicator set around its mean; b represents the total number of data points in the abnormal indicator set; i represents the number of the data point in the abnormal indicator set; xi represents the i-th data point in the abnormal indicator set; represents the mean of the abnormal indicator set, that is, ; It represents the standard deviation of the abnormal indicator set, which is used to measure the degree of dispersion between the data points in the abnormal indicator set and their mean, that is, ; Represents the process of normalizing each data point in the anomaly indicator set to have zero mean and unit standard deviation, which is used to eliminate the effect of data scale on skewness calculation; Step 502, when analyzing the skewness calculation result, when the skewness is greater than 0, the skewness is positive, which means that the data distribution of the abnormal indicator set is skewed to the right, that is, most of the data values ​​are concentrated on the left side of the mean, while a few larger data values ​​are located on the right side of the mean, indicating that there are more extreme high value anomalies (such as the environment where the device is located is overheated, the device current is too large, etc.); when the skewness is less than 0, the skewness is negative, which means that the data distribution of the abnormal indicator set is skewed to the left, that is, most of the data values ​​are concentrated on the right side of the mean, while a few smaller data values ​​are located on the left side of the mean, indicating that there are more extreme low value anomalies (such as the humidity of the environment where the device is located is too low, the device voltage is too low, etc.); when the skewness is close to 0, it means that the data distribution is relatively symmetrical and there is no obvious skewness; Step 503: Use the kurtosis formula to analyze the sharpness of the data distribution of the abnormal indicator set; wherein the kurtosis formula is as follows: , where Represents the kurtosis value, which is an indicator used to measure the sharpness or flatness of the data distribution of the abnormal indicator set; Step 504, when analyzing the kurtosis calculation result, when the kurtosis is greater than 0, it is a peak state, which means that the data distribution of the abnormal indicator set is sharper than the normal distribution, that is, there are more extreme values ​​(data points far from the mean) and fewer intermediate values; when the kurtosis is less than 0, it is a flat peak state, which means that the data distribution of the abnormal indicator set is flatter than the normal distribution, that is, there are fewer extreme values ​​and more intermediate values; when the kurtosis is close to 0, it means that the data distribution is close to the normal distribution, that is, there is no significant peak or flat peak phenomenon; Step 505: extract abnormal features based on the analysis results of skewness and kurtosis. If the skewness of the abnormal indicator set is positive and the kurtosis is high, it means that there are many abnormal high values ​​and the abnormal values ​​are concentrated; if the skewness of the abnormal indicator set is negative and the kurtosis is low, it means that there are few abnormal values ​​and the distribution is relatively uniform. Step 506: Based on the analyzed high-value or low-value abnormal features, use a database to record information about the abnormal event; In step 506, the information of the abnormal event is recorded including a timestamp, a data value, a parameter type, and an abnormal attribute; Step 507: Feedback the abnormal event information to the patrol cycle setting module to dynamically adjust the patrol cycle for subsequent optimization management.

[0024] In the embodiment of the present invention, by dividing the equipment into different categories, using the fault records in the historical operation data, evaluating the fault mode and frequency of each equipment category, and providing a basis for formulating the inspection strategy; by setting a reasonable inspection cycle for each type of equipment based on the fault assessment results, ensuring the effective allocation of resources, reducing unnecessary inspection work, thereby improving the operation and maintenance efficiency and reducing costs; by dynamically adjusting the inspection cycle to adapt to the changes in the equipment status, improving the inspection efficiency; by creating specific inspection tasks, assigning the generated inspection tasks to the corresponding inspection personnel for execution, clarifying the inspection responsibilities, and facilitating the timely discovery and correction of problems in the inspection process; by real-time monitoring of the operating status of the equipment during the inspection cycle, providing data support for abnormal identification and inspection cycle adjustment; by quantitatively analyzing the monitoring data set, identifying abnormal operating states that deviate from the normal range, and reducing manual intervention; by processing and analyzing the abnormal indicator set, refining the abnormal characteristics, recording abnormal events and feeding back relevant information to the inspection cycle setting module, it is helpful to optimize the inspection cycle setting and abnormal handling strategy, and form a closed-loop management. In summary, the example of the present invention solves the problems of low inspection quality and unstable operation of unmanned distribution rooms. In actual situations, more data and context information may be needed to make specific decisions and optimization plans.

[0025] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0026] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0027] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0028] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0029] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0030] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0031] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0032] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room, characterized in that: It includes patrol cycle setting module, patrol task execution module, real-time data monitoring and analysis module, abnormality identification and filtering module and abnormal feature automatic extraction module; The patrol cycle setting module is used to automatically classify equipment into different categories according to the preset equipment importance standards; Use the fault records in the historical operation data to conduct statistical and computational analysis to evaluate the failure mode and frequency of each equipment category; based on the data evaluation results, set the corresponding inspection cycle for each type of equipment; Combine real-time monitoring data and abnormal events to dynamically adjust the set patrol cycle; The patrol task execution module is used to create patrol tasks, assign the generated patrol tasks to patrol personnel for execution, and manage the execution status; The real-time data monitoring and analysis module is used to monitor the operating status of the equipment in real time during the inspection cycle; it is responsible for capturing, processing and analyzing the various operating parameters of the equipment and obtaining the monitoring data set; The anomaly identification and filtering module is used to perform quantitative analysis on the monitoring data set, automatically identify and filter out abnormal operating conditions that deviate from the normal range, and obtain an abnormal indicator set; The abnormal feature automatic extraction module is used to process and analyze the abnormal indicator set, extract abnormal features from it, record the identified abnormal events, and feed back to the patrol cycle setting module.

2. According to claim 1, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The patrol cycle setting module automatically divides the equipment into different categories according to the preset equipment importance standards, including: Devices are divided into different categories based on their function and purpose , i.e. key equipment , important equipment And general equipment Among them, key equipment refers to the equipment with the greatest impact on the operation of the distribution room, important equipment refers to the equipment with a medium impact on the operation of the distribution room, and general equipment refers to the equipment with the least impact on the operation of the distribution room.

3. According to claim 2, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The patrol cycle setting module uses the fault records in the historical operation data to perform statistical and computational analysis to evaluate the failure mode and frequency of each equipment category. The process includes: Define a weight value for each category of equipment , , indicating the quantitative value of the importance of this type of equipment; Collect the operating time of each type of equipment from the historical data of the intensive power distribution intelligent operation and maintenance host and number of failures , where n represents the month of historical data obtained; Calculate the mean time between failures for each type of equipment and failure rate : , , where Indicates the average time between equipment failures in historical data month n; Combined with the failure rate and importance weight, the risk assessment of the intensive power distribution intelligent operation and maintenance host is carried out: ;in, Represents the risk assessment value.

4. According to claim 3, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The patrol cycle setting module sets the corresponding patrol cycle for each type of equipment based on the data evaluation results, and dynamically adjusts the patrol cycle in combination with real-time monitoring data and abnormal events. The process includes: Set patrol cycle : , where k represents a constant, The weight value defined for each category of equipment, is the mean time between failures for each type of equipment, is the risk assessment value; According to the real-time monitoring data of the equipment and the abnormal event record information, a dynamic adjustment mechanism is established: if the real-time monitored equipment status data exceeds the normal range or the feedback information of the abnormal feature automatic extraction module is received, the adjustment factor Increase, otherwise decrease; thus get the adjusted patrol cycle ;in, Decisions are made based on deviations of real-time monitoring data from the normal range.

5. According to claim 4, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The patrol task execution module creates patrol tasks, assigns the generated patrol tasks to patrol personnel for execution, and manages the execution status, including the following processes: For patrol cycle Generate patrol tasks : Determine the patrol period for each device category ; According to the patrol cycle and the current time , calculate the next patrol time point ;like , then a patrol task is generated , indicating that the scheduled patrol time has been exceeded, i.e. , and Updated to ;in, Indicates the time point of the last inspection of device category C, which is used to calculate the starting point of the next inspection cycle. When the inspection task is completed, Updated to current time , to reflect the latest inspection time; Combined with the importance weight of the equipment category, each patrol task is arranged in the order of priority attention or execution to obtain the patrol priority. : ； Get patrol task collection and the patrol personnel set R, each patrol task Have corresponding skills , each patrol officer r∈R has his own skills and current availability status ; Finding the Allocation Matrix , so that for each patrol task m there is a patrol officer r that satisfies and ;in, is a binary variable, indicating whether patrol officer r is assigned to patrol task m, i.e., the patrol task assignment result. It means that if and only if the patroller r is assigned to patrol task m, otherwise ; Maximize the coverage Z of the patrol task: , where Indicates the patrol mission number. Indicates the total number of patrol tasks, Indicates the patrol officer's number. Indicates the total number of patrol officers; Among them, the following constraints are met: , where (1) means that each patrol task can only be performed by one patrol officer; (2) means that each patrol officer can only perform one patrol task; (3) means that the patrol officer's skills match the patrol task requirements; where is the indicator function, if Include , then returns 1, otherwise returns 0; (4) represents the patrol personnel availability check; (5) represents duality; Track and record the execution of patrol tasks, including patrol task start time, execution progress and completion status, and upload them to the data center.

6. According to claim 1, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The real-time data monitoring and analysis module monitors the operating status of the equipment in real time, captures and processes the various operating parameters of the equipment for analysis. The process of obtaining the monitoring data set includes: Determine the time range for monitoring and monitor data according to the set time period, including the start and end time of monitoring; Use sensor components to measure current, voltage, temperature and humidity; use power meters and energy metering equipment to calculate the energy efficiency ratio, that is, the ratio of energy converted per unit time to energy consumed; The current and voltage are regarded as power parameters D, the temperature and humidity are regarded as environmental parameters H, and the energy efficiency ratio is processed and analyzed as the energy efficiency parameter N; the specific analysis formula is as follows: , where Represents comprehensive evaluation parameter index; Indicates the average value of the power parameter; Indicates the optimal value of the operating environment; Indicates the average value of energy efficiency parameters; Represents adjustment parameters, which are used to adjust the degree of influence when each parameter deviates from the average value or optimal value; The comprehensive evaluation parameter indicators of all monitoring time periods are integrated to form a monitoring data set.

7. The intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room according to claim 6 is characterized by: The anomaly identification and filtering module conducts quantitative analysis on the monitoring data set, automatically identifies and filters out abnormal operating conditions that deviate from the normal range. The process of obtaining the abnormal indicator set includes: Extract the values ​​of comprehensive evaluation parameter indicators of the monitoring data set and conduct quantitative analysis; , where is the normality index, which is used to reflect the closeness of the equipment status to normal operation; h is the offset; is a scalar parameter, indicating a threshold interval; when hour, The value is 0, indicating that the device status is abnormal; when hour, It increases linearly, indicating that the equipment status tends to be normal; when hour, A value of 1 indicates that the device is in normal state; According to the quantitative analysis results, the comprehensive evaluation parameter indicators corresponding to the abnormal equipment status are obtained and marked as an abnormal indicator set.

8. According to claim 1, an intensive power distribution intelligent operation and maintenance host that can be used in an unattended power distribution room is characterized in that: The abnormal feature automatic extraction module processes and analyzes the abnormal indicator set, extracts abnormal features from it, records the identified abnormal events, and feeds back to the patrol cycle setting module. The process includes: The skewness formula is used to analyze whether the data distribution of the abnormal indicator set is symmetrical; the skewness formula is as follows: , where represents the skewness value, which is an indicator used to measure the degree of asymmetry of the data distribution of the abnormal indicator set, describing the direction and degree of skewness of the data distribution of the abnormal indicator set around its mean; b represents the total number of data points in the abnormal indicator set; i represents the number of the data point in the abnormal indicator set; xi represents the i-th data point in the abnormal indicator set; represents the mean of the abnormal indicator set, that is, ; It represents the standard deviation of the abnormal indicator set, which is used to measure the degree of dispersion between the data points in the abnormal indicator set and their mean, that is, ; Represents the process of normalizing each data point in the anomaly indicator set; When analyzing the skewness calculation results, when the skewness is greater than 0, the skewness is positive, which means that the data distribution of the abnormal indicator set is skewed to the right; when the skewness is less than 0, the skewness is negative, which means that the data distribution of the abnormal indicator set is skewed to the left; The kurtosis formula is used to analyze the sharpness of the data distribution of the abnormal indicator set; the kurtosis formula is as follows: , where Represents the kurtosis value, which is an indicator used to measure the sharpness or flatness of the data distribution of the abnormal indicator set; When analyzing the kurtosis calculation results, when the kurtosis is greater than 0, it is a peak state, which means that the data distribution of the abnormal indicator set is sharper than the normal distribution; when the kurtosis is less than 0, it is a flat peak state, which means that the data distribution of the abnormal indicator set is flatter than the normal distribution; According to the analysis results of skewness and kurtosis, the abnormal features are extracted. If the skewness of the abnormal indicator set is positive and the kurtosis is high, it means that there are many abnormal high values ​​and the abnormal values ​​are concentrated; if the skewness of the abnormal indicator set is negative and the kurtosis is low, it means that there are few abnormal values ​​and the distribution is relatively uniform. Based on the analyzed high-value or low-value abnormal features, use a database to record information about abnormal events; wherein the information about abnormal events recorded includes timestamp, data value, parameter type, and abnormal attributes; The abnormal event information is fed back to the patrol cycle setting module to dynamically adjust the patrol cycle for subsequent optimization management.

Images