A health evaluation system for power distribution stations based on multi-source information

Abstract

The invention relates to the technical field of distribution station operation status monitoring, and discloses a distribution station health evaluation system based on multi-source information, comprising a sensor unit, a data processing unit, a data analysis unit, and a data display unit. The invention can comprehensively obtain the operation status information of the distribution station, and improve the accuracy and reliability of the health evaluation; through the partial discharge recognition algorithm and the specific data structure processing, a clear and accurate data basis is provided for the subsequent score analysis; the ultra-high frequency information, ultrasonic information, transient ground voltage information, temperature information, and humidity information on the switch cabinet are scored and calculated respectively, and the influence of various factors on the health of the switch cabinet is considered, so that the comprehensive health score is more scientific and reasonable; the data analysis results are displayed to relevant personnel in an intuitive manner through the data display unit, so that the operation and maintenance personnel can understand the operation status of the distribution station in time, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution station operation status monitoring, and in particular to a power distribution station building health evaluation system based on multi-source information. Background Art

[0002] With the rapid development of social economy, the demand for electricity is growing. As a vital component of the power transmission and distribution network, the state of the distribution station has a significant impact on the safe operation of the power grid. In the traditional distribution station operation status monitoring, it is mostly based on the evaluation of a single electrical parameter, but this method has obvious limitations. A single electrical parameter can often only reflect the characteristics of a certain aspect of the distribution station, and it is difficult to make a more comprehensive assessment of the overall status of the distribution station. For example, relying solely on a single parameter such as voltage or current, it is impossible to accurately judge the comprehensive health status of the equipment in the distribution station and the potential risk of failure.

[0003] In addition, the switch cabinet in the power distribution station is one of the key equipment, and its operating status is directly related to the reliability of the power distribution station. Traditional monitoring methods make it difficult to conduct detailed health assessments of each switch cabinet, and fail to promptly detect potential problems such as partial discharge, abnormal temperature, and excessive humidity inside the switch cabinet. At the same time, there is also a lack of comprehensive and effective means to monitor the environmental conditions in the power distribution station, such as smoke, access control, and flooding.

[0004] In summary, in order to ensure the safe and stable operation of the power grid, there is an urgent need for an operating status evaluation method that can accurately and comprehensively reflect the health of distribution substations based on multi-source information. Summary of the invention

[0005] The purpose of the present invention is to provide a power distribution plant health evaluation system based on multi-source information, which solves the technical problems raised in the background technology.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A health evaluation system for power distribution stations based on multi-source information, including:

[0008] The sensor unit is used to collect the operation data of the power distribution station and then transmit it to the data processing unit and the data analysis unit;

[0009] The data processing unit is used to pre-process the operation data collected by the sensor unit; and transmit the pre-processing result to the data analysis unit;

[0010] A data analysis unit, used to perform score analysis on the operation data collected and processed by the sensor unit and the data processing unit, and then transmit the score analysis results to the data display unit;

[0011] The data display unit is used to display the results obtained by the data analysis unit to relevant personnel in an intuitive manner.

[0012] As a further solution of the present invention: wherein the sensor unit comprises two environmental sensors and two partial discharge sensors arranged on the switch cabinet in the station house; and the environmental sensors comprise a temperature sensor and a humidity sensor, and the partial discharge sensors comprise a UHF sensor and a three-in-one sensor;

[0013] The operation data includes temperature information collected by temperature sensors, humidity information collected by humidity sensors, UHF sensors used to collect UHF information of switch cabinets, and three-in-one sensors used to collect ultrasonic information and transient ground voltage information;

[0014] Among them, a plurality of UHF sensors are arranged on a switch cabinet, and each UHF sensor collects corresponding UHF information.

[0015] As a further solution of the present invention: the pretreatment method is as follows:

[0016] StepA1, on each UHF sensor, obtain n consecutive UHF information of the relevant switch cabinet;

[0017] Step A2, judging each piece of UHF data by using a partial discharge identification algorithm, and obtaining a judgment result of whether the corresponding UHF data is partial discharge data;

[0018] The judgment result includes the partial discharge type and its corresponding probability;

[0019] Step A3, for each sensor, collect n pieces of data to obtain n partial discharge judgment results, correspond the partial discharge type and the corresponding probability one by one to form a dictionary structure, and then form the judgment results of n consecutive pieces of data from different sensors into a two-dimensional list;

[0020] Among them, the partial discharge judgment result is used as the key value of the dictionary structure, and the corresponding probability is used as the value of the dictionary structure;

[0021] The two-dimensional list is as follows:

[0022] ;

[0023] Wherein, i=1, 2, ...n, j=1, 2, ...m, n represents the number of sensors, m represents the number of partial discharge judgment types of data, Indicates the PD judgment type of the jth data of the i-th sensor. When the type is PD, it is represented by the number 1, and when the type is no PD, it is represented by the number 0;

[0024] Step A4: Pre-process the ultrasonic information and transient ground voltage information on the switch cabinet in the manner of Step A1 to Step A3.

[0025] As a further solution of the present invention: the specific method is as follows:

[0026] Step V1. Calculation of the score of UHF information on the switch cabinet

[0027] Get the two-dimensional list obtained by the data processing unit;

[0028] If all key values ​​in the two-dimensional list are 0, that is, all data from all sensors are judged to have no partial discharge, the one-dimensional list with the smallest value mean is taken as the data for score calculation;

[0029] The calculation formula is as follows:

[0030] ;

[0031] in, It is expressed as the score corresponding to the UHF information;

[0032] If the key value in the two-dimensional list is 1, that is, the data collected by the sensor is judged to be partial discharge, the one-dimensional list with the largest value is taken as the data basis for score calculation;

[0033] The calculation formula is as follows:

[0034] ;

[0035] in, Expressed as the score corresponding to the UHF information, Represents the probability of judging that there is no partial discharge data in the one-dimensional list; Represents the probability corresponding to the partial discharge data in the one-dimensional list;

[0036] Step V2. Calculation of the score of ultrasonic information on the switch cabinet

[0037] According to Step V1, the score of ultrasound information is calculated and marked as ;

[0038] Step V3. Calculation of the score of transient ground voltage information on the switch cabinet

[0039] According to Step V1, calculate the score of the transient ground voltage and mark it as ;

[0040] Step V4. Calculation of the score of temperature information on the switch cabinet

[0041] On the temperature sensor, obtain the switch cabinet temperature values ​​of n consecutive switch cabinets of the relevant switch cabinet and record them as ;

[0042] Then through , calculate the mean of n consecutive temperature data, T avg ;

[0043] Then combine the preset temperature optimal value , Temperature alarm upper limit , Temperature alarm lower limit Calculate the temperature score for the switchgear;

[0044] The calculation is as follows:

[0045] ;

[0046] The optimum temperature is , the upper limit of temperature alarm is , the lower limit of temperature alarm is , and it is set separately according to the different types of switch cabinets;

[0047] Step V5. Calculation of humidity score on switch cabinet

[0048] Calculate the humidity score of the switch cabinet according to Step V3;

[0049] It is calculated as follows:

[0050] ;

[0051] In the formula, The real-time humidity uploaded by the humidity sensor. The optimum humidity value is Humidity alarm upper limit, It is the lower limit of humidity alarm;

[0052] Step V6. Calculation of comprehensive health score

[0053] The scores corresponding to the UHF information, ultrasonic information, transient ground voltage information, temperature information, and humidity information on the switchgear obtained from Step V1 to Step V4 are integrated and calculated to obtain the comprehensive health score of the switchgear;

[0054] It is calculated as follows:

[0055] ;

[0056] In the formula, are the preset weight values ​​corresponding to the corresponding factors, It is the comprehensive health score of the switchgear.

[0057] As a further solution of the present invention: the power distribution station is also provided with three kinds of environmental status sensors, which are respectively a smoke sensor, an access control sensor, and a water immersion sensor;

[0058] Among them, the information uploaded by the three environmental status sensors is binary data, and its corresponding value is 1 or 0;

[0059] When the value is 0, it means the status monitored by the sensor is normal;

[0060] When the value is 1, it means that the state monitored by the sensor is abnormal;

[0061] The data analysis unit is also used to perform score analysis on the binary data corresponding to the three environmental state sensors;

[0062] If the three environmental status sensors in the station house contain at least one binary data 0, it means that the monitored state is abnormal, and the station house environmental health score is 0, which is recorded as ;

[0063] If the binary data of the three environmental status sensors in the station house are all 1, it means that there is no abnormality in the station house, and the station house environmental health score is 100, which is recorded as .

[0064] As a further solution of the present invention: the data analysis unit is further used to calculate the total health score of the station house according to the obtained comprehensive health scores of each switch cabinet equipment in the station house and the health score of the station house environment;

[0065] It is calculated as follows:

[0066] ;

[0067] In the formula, Indicates the total health score of the station building. Respectively represent the total health score of each station building, represents the environmental health score of the station house, and m represents the number of switchgear equipment in the station house.

[0068] As a further solution of the present invention: also include:

[0069] The tracking and analysis unit is used to track the state of the switch cabinet according to the value changes of various sensors on each switch cabinet within a specified period of time, and obtain the growth index based on the growth tracking;

[0070] Among them, the growth index includes three data types. Each data type is calculated to obtain three growth indicators, which are: normal value, warning value, and alarm value;

[0071] The data types are: UHF information collected by UHF sensors, ultrasonic information collected by three-in-one sensors, and transient ground voltage information.

[0072] As a further solution of the present invention: the growth tracking method is as follows:

[0073] StepH1. Compose the maximum values ​​of the information collected by multiple sensors of the same type within a period of time into a maximum value list, as shown below:

[0074] ;

[0075] In the formula, A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0076] A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0077] A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0078] Among them, n represents the number of corresponding sensors;

[0079] StepH2. Calculate the mean of each maximum value list and standard deviation , the corresponding screening threshold is calculated according to the mean and variance of each information, as follows:

[0080] ;

[0081] In the formula, The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0082] The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0083] The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0084] StepH3. For each maximum value list and filtering threshold of each information, retain the data in the list that is less than the filtering threshold to form a new maximum value list, as shown below:

[0085] ;

[0086] In the formula, Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0087] Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0088] Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0089] StepH4, then calculate the mean of each new maximum value list and standard deviation , and then three thresholds are obtained based on the mean and standard deviation: normal value, warning value, and alarm value;

[0090] The three values ​​are calculated as follows:

[0091] ;

[0092] As a further solution of the present invention: wherein, the normal value, the warning value, and the alarm value are used for horizontal comparison between different switch cabinets in the same time period, and for comparison of change trends of the same switch cabinet in different time periods.

[0093] Beneficial effects of the present invention:

[0094] The present invention collects multi-source information through multiple sensors, including temperature sensors, humidity sensors, UHF sensors, three-in-one sensors, smoke sensors, access control sensors, water immersion sensors and other environmental status sensors, which can comprehensively reflect the operating status of distribution station rooms and switch cabinets and improve the accuracy of health evaluation.

[0095] The present invention processes and analyzes different types of sensor data in a targeted manner. For example, it calculates scores for ultra-high frequency information, ultrasonic information, transient ground voltage information, temperature information, and humidity information, respectively, and comprehensively considers multiple factors such as electrical and environmental factors, making health evaluation more comprehensive and objective.

[0096] The present invention calculates the scores of ultra-high frequency information, ultrasonic information and transient ground voltage information, judges whether partial discharge exists and the probability of partial discharge, and adopts different calculation formulas to accurately reflect the influence of these key electrical parameters on the health of the switch cabinet.

[0097] In the present invention, the score calculation of the temperature information and the humidity information is combined with the preset optimal value, the upper limit and the lower limit of the alarm, so that the score is more scientific and reasonable, and the potential harm of abnormal temperature and humidity to the switch cabinet can be discovered in time.

[0098] The present invention calculates the comprehensive health score by integrating the scores of various factors and setting corresponding weight values, which can comprehensively consider the contribution of various factors to the comprehensive health of the switch cabinet and provide a scientific basis for maintenance and management.

[0099] The present invention performs score analysis on the binary data of three environmental status sensors, namely, smoke sensors, access control sensors, and water immersion sensors, and can timely discover abnormal conditions in the station environment. When one sensor monitoring status is abnormal, the station environment health score is 0, thereby increasing the attention paid to the safety of the station environment.

[0100] The present invention combines the station house environment health score with the comprehensive health score of the switch cabinet equipment to calculate the total station house health score, making the overall health evaluation of the station house more comprehensive and helping to take timely measures to ensure the safe and stable operation of the station house.

[0101] In the present invention, the tracking and analysis unit performs growth tracking on the switch cabinet state according to the value changes of various sensors on each switch cabinet within a specified time period, and calculates three growth indicators, namely normal value, warning value and alarm value, to provide a basis for horizontal comparison between different switch cabinets within the same time period and comparison of change trends of the same switch cabinet in different time periods.

[0102] The present invention can timely discover the changing trend of the operating status of the switch cabinet, warn of potential problems in advance, help to take preventive maintenance measures, and improve the reliability and stability of the distribution station.

[0103] In summary, the health evaluation system of distribution substation based on multi-source information has many beneficial effects, such as comprehensive and accurate health assessment, scientific and reasonable score calculation method, correlation between environmental status monitoring and health, growth tracking and comparative analysis, etc., which can provide strong guarantee for the safe and stable operation of distribution substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] The present invention will be further described below in conjunction with the accompanying drawings.

[0105] Figure 1 The system block diagram of the power distribution station health evaluation system based on multi-source information of the present invention.

[0106] Figure 2 It is a flow chart of a distribution station health evaluation system based on multi-source information of the present invention. DETAILED DESCRIPTION

[0107] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0108] Embodiment 1

[0109] See also Figure 1 and Figure 2 As shown, the present invention is a power distribution station health evaluation system based on multi-source information, comprising:

[0110] Sensor unit, used to collect operating data of the power distribution station;

[0111] The sensor unit includes two environmental sensors and two partial discharge sensors installed on the switch cabinet in the station house; the environmental sensors include temperature sensors and humidity sensors, and the partial discharge sensors include ultra-high frequency sensors and three-in-one sensors;

[0112] The operation data includes temperature information collected by temperature sensors, humidity information collected by humidity sensors, UHF sensors used to collect UHF information (UHF) of switch cabinets, and three-in-one sensors used to collect ultrasonic information (AA) and transient earth voltage information (TEV);

[0113] In this embodiment, a plurality of UHF sensors are arranged on a switch cabinet, and each UHF sensor collects corresponding UHF information;

[0114] A data processing unit, used for pre-processing the operation data collected by the sensor unit;

[0115] The preprocessing method is as follows:

[0116] StepA1, on each UHF sensor, obtain n consecutive UHF information of the relevant switch cabinet;

[0117] Step A2, judging each piece of UHF data by using a partial discharge identification algorithm, and obtaining a judgment result of whether the corresponding UHF data is partial discharge data;

[0118] The judgment result includes the partial discharge type and its corresponding probability;

[0119] Step A3, for each sensor, collect n pieces of data to obtain n partial discharge judgment results, correspond the partial discharge type and the corresponding probability one by one to form a dictionary structure, and then form the judgment results of n consecutive pieces of data from different sensors into a two-dimensional list;

[0120] Among them, the partial discharge judgment result is used as the key value of the dictionary structure, and the corresponding probability is used as the value of the dictionary structure;

[0121] The two-dimensional list is as follows:

[0122] ;

[0123] Wherein, i=1, 2, ...n, j=1, 2, ...m, n represents the number of sensors, m represents the number of partial discharge judgment types of data, Indicates the PD judgment type of the jth data of the i-th sensor. When the type is PD, it is represented by the number 1, and when the type is no PD, it is represented by the number 0;

[0124] Step A4, pre-processing the ultrasonic information and transient ground voltage information on the switch cabinet according to the method from Step A1 to Step A3;

[0125] A data analysis unit, used for performing score analysis on the operation data;

[0126] The specific method is as follows:

[0127] Step V1. Calculation of the score of UHF information on the switch cabinet

[0128] Get the two-dimensional list obtained by the data processing unit;

[0129] If all key values ​​in the two-dimensional list are 0, that is, all data from all sensors are judged to have no partial discharge, the one-dimensional list with the smallest value mean is taken as the data for score calculation;

[0130] The calculation formula is as follows:

[0131] ;

[0132] in, It is expressed as the score corresponding to the UHF information;

[0133] For example:

[0134] The partial discharge judgment results of the data collected by multiple UHF sensors on a switch cabinet device are all no partial discharge, as shown below:

[0135] ;

[0136] In the two-dimensional list, the probability mean corresponding to all judgment results in the second sublist is the smallest, and its probability is 0.742;

[0137] Then through Get the score corresponding to the UHF information;

[0138] If the key value in the two-dimensional list is 1, that is, the data collected by the sensor is judged to be partial discharge, the one-dimensional list with the largest value is taken as the data basis for score calculation;

[0139] The calculation formula is as follows:

[0140] ;

[0141] in, Expressed as the score corresponding to the UHF information, Represents the probability of judging that there is no partial discharge data in the one-dimensional list; Represents the probability corresponding to the partial discharge data in the one-dimensional list;

[0142] For example:

[0143] The partial discharge judgment results of the data collected by multiple UHF sensors on a switch cabinet device show partial discharge, as shown below:

[0144] ;

[0145] In the two-dimensional list, the key=1 in the last element of the first sublist has the largest probability, which is 0.95.

[0146] Then through

[0147] ;

[0148] Get the score corresponding to the UHF information;

[0149] Step V2. Calculation of the score of ultrasonic information on the switch cabinet

[0150] According to Step V1, the score of ultrasound information is calculated and marked as ;

[0151] Step V3. Calculation of the score of transient ground voltage information on the switch cabinet

[0152] According to Step V1, calculate the score of the transient ground voltage and mark it as ;

[0153] Step V4. Calculation of the score of temperature information on the switch cabinet

[0154] On the temperature sensor, obtain the switch cabinet temperature values ​​of n consecutive switch cabinets of the relevant switch cabinet and record them as ;

[0155] Then through , calculate the mean of n consecutive temperature data, T avg ;

[0156] Then combine the preset temperature optimal value , Temperature alarm upper limit , Temperature alarm lower limit Calculate the temperature score for the switchgear;

[0157] The calculation is as follows:

[0158] ;

[0159] The optimum temperature is , the upper limit of temperature alarm is , the lower limit of temperature alarm is , and it is set separately according to the different types of switch cabinets;

[0160] For example:

[0161] If the optimal temperature value is preset on the switch cabinet equipment , temperature alarm upper limit , lower limit of temperature ;

[0162] The real-time temperature list uploaded is T=[35,36,29,30,38], and the average temperature is ;

[0163] but ;

[0164] According to the calculation formula ;

[0165] Get the final score of temperature health;

[0166] Step V5. Calculation of humidity score on switch cabinet

[0167] Calculate the humidity score of the switch cabinet according to Step V3;

[0168] It is calculated as follows:

[0169] ;

[0170] In the formula, The real-time humidity uploaded by the humidity sensor. The optimum humidity value is Humidity alarm upper limit, It is the lower limit of humidity alarm;

[0171] Step V6. Calculation of comprehensive health score

[0172] The scores corresponding to the UHF information, ultrasonic information, transient ground voltage information, temperature information, and humidity information on the switchgear obtained from Step V1 to Step V4 are integrated and calculated to obtain the comprehensive health score of the switchgear;

[0173] It is calculated as follows:

[0174] ;

[0175] In the formula, are the preset weight values ​​corresponding to the corresponding factors, It is the comprehensive health score of the switchgear;

[0176] For example:

[0177] If the scores corresponding to the health of UHF, ultrasonic, transient ground voltage, temperature, and humidity and their corresponding preset weight values ​​are as follows:

[0178] ;

[0179] According to the calculation formula ;

[0180] Calculate the overall health score of the switchgear;

[0181] The data display unit is used to display the results obtained by the data analysis unit to relevant personnel in an intuitive manner.

[0182] This embodiment collects the operating data of the distribution station through multiple sensors, can comprehensively obtain the operating status information of the distribution station, and improves the accuracy and reliability of the health evaluation; performs detailed data preprocessing on the ultra-high frequency sensor, ultrasonic information, and transient ground voltage information, and provides a clear and accurate data basis for subsequent score analysis through partial discharge recognition algorithm and specific data structure processing; scores are calculated for the ultra-high frequency information, ultrasonic information, transient ground voltage information, temperature information, and humidity information on the switch cabinet, respectively, and considers the influence of multiple factors on the health of the switch cabinet, so that the comprehensive health score is more scientific and reasonable; the data analysis results are displayed to relevant personnel in an intuitive manner through the data display unit, which is convenient for operation and maintenance personnel to understand the operating status of the distribution station in a timely manner, thereby improving operation and maintenance efficiency.

[0183] Embodiment 2

[0184] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from that of the first embodiment only in that:

[0185] The power distribution station is also equipped with three types of environmental status sensors, namely smoke sensor, access control sensor, and water immersion sensor;

[0186] Among them, the information uploaded by the three environmental status sensors is binary data, and its corresponding value is 1 or 0;

[0187] When the value is 0, it means the status monitored by the sensor is normal;

[0188] When the value is 1, it means that the state monitored by the sensor is abnormal;

[0189] A data analysis unit, used for performing score analysis on binary data corresponding to three environmental state sensors;

[0190] If the three environmental status sensors in the station house contain at least one binary data 0, it means that the monitored state is abnormal, and the station house environmental health score is 0, which is recorded as ;

[0191] If the binary data of the three environmental status sensors in the station house are all 1, it means that there is no abnormality in the station house, and the station house environmental health score is 100, which is recorded as ;

[0192] This embodiment adds three environmental status sensors: smoke sensor, access control sensor, and water immersion sensor, which further enriches the monitoring content of the distribution station building and can detect environmental abnormalities in a timely manner. The binary data uploaded by the three environmental status sensors are simple and intuitive, which is convenient for quickly judging whether the station building environment is normal, improves the detection efficiency of abnormal situations, and determines the station building environmental health score based on the binary data, providing an important basis for comprehensive evaluation of the health of the station building.

[0193] Embodiment 3

[0194] As the third embodiment of the present invention, when the present application is implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is only in this embodiment;

[0195] The total health score of the station building is calculated based on the comprehensive health scores of each switchgear device in the station building and the health score of the station building environment.

[0196] It is calculated as follows:

[0197] ;

[0198] In the formula, Indicates the total health score of the station building. Respectively represent the total health score of each station building, represents the environmental health score of the station house, and m represents the number of switchgear equipment in the station house;

[0199] For example:

[0200] Assuming that the water immersion sensor in the station environment sensor is abnormal, and the other two sensors are normal, the station environment health score is ;

[0201] Assume that there are 5 switchgear devices in the station house, and their comprehensive health scores are as follows:

[0202] ;

[0203] According to the calculation formula ;

[0204] Calculate the total station building health score.

[0205] This embodiment combines the comprehensive health scores of each switch cabinet equipment obtained in Embodiment 1 and the station building environment health scores obtained in Embodiment 2 to calculate the total station building health score, thereby achieving a comprehensive assessment of the overall health of the station building. It comprehensively considers the operating status of the switch cabinet and the station building environmental factors, making the station building health assessment more comprehensive and accurate.

[0206] Embodiment 4

[0207] As the fourth embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the second embodiment and the third embodiment, the difference between the present embodiment and the first embodiment, the second embodiment and the third embodiment is that the present embodiment further includes:

[0208] Tracking and analysis unit, used to track the status of switch cabinets according to the value changes of various sensors on each switch cabinet within a specified period of time;

[0209] Growth indicators include three data types, and three growth indicators are calculated for each data type;

[0210] Among them, the growth indicators are: normal value, warning value, and alarm value;

[0211] The data types are: UHF information collected by UHF sensor, ultrasonic information collected by three-in-one sensor, and transient ground voltage information;

[0212] Growth tracking is as follows:

[0213] StepH1. Compose the maximum values ​​of the information collected by multiple sensors of the same type within a period of time into a maximum value list, as shown below:

[0214] ;

[0215] In the formula, A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0216] A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0217] A maximum value list consisting of multiple UHF sensors collecting UHF information of the switch cabinet, and The corresponding These are the maximum values ​​collected by multiple UHF sensors in turn;

[0218] Among them, n represents the number of corresponding sensors;

[0219] StepH2. Calculate the mean of each maximum value list and standard deviation , the corresponding screening threshold is calculated according to the mean and variance of each information, as follows:

[0220] ;

[0221] In the formula, The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0222] The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0223] The maximum value list The mean and standard deviation calculated from the n largest values; For The corresponding screening threshold;

[0224] StepH3. For each maximum value list and filtering threshold of each information, retain the data in the list that is less than the filtering threshold to form a new maximum value list, as shown below:

[0225] ;

[0226] In the formula, Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0227] Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0228] Collecting UHF information of switch cabinets for multiple UHF sensors to form a new maximum value list;

[0229] StepH4, then calculate the mean of each new maximum value list and standard deviation , and then three thresholds are obtained based on the mean and standard deviation: normal value, warning value, and alarm value;

[0230] The three values ​​are calculated as follows:

[0231] ;

[0232] The three thresholds calculated above are updated and calculated every month;

[0233] Based on the three thresholds calculated by each device, a horizontal comparison is made between different switch cabinets in the same time period, and a comparison of the change trends of the same switch cabinet in different time periods is made.

[0234] For example:

[0235] Assume that within a period of time, the maximum value list of the collected UHF sensor information is as follows:

[0236] ;

[0237] And calculate the mean of the maximum value list , standard deviation Calculate the screening threshold ;

[0238] After threshold screening, the new maximum value list is: ;

[0239] The mean of the new maximum value list , standard deviation According to the calculation formula

[0240] ;

[0241] Then obtain the normal value, warning value and alarm value;

[0242] In this embodiment,

[0243] The normal value is used as a benchmark to measure the normal operation of the switch cabinet. In daily operation, if the data collected by various sensors of the switch cabinet are within the normal value range, it indicates that the switch cabinet is in a stable and normal operation state, and the various indicators of the equipment are within a reasonable range and the operation is reliable.

[0244] The normal value provides a clear judgment standard for operation and maintenance personnel to quickly determine whether the equipment is working normally. When the data is within the normal value range, the operation and maintenance personnel do not need to take special maintenance measures, but only need to perform routine monitoring and inspections;

[0245] When comparing different switch cabinets horizontally, the normal value can be used as a reference to help determine whether the operating differences between the switch cabinets are within the normal range; if the sensor data of different switch cabinets in the same time period fluctuate around the normal value and the fluctuation amplitude is small, it means that the operating status of each switch cabinet is relatively consistent and there is no obvious abnormality;

[0246] In the comparison of the changing trends of the same switch cabinet in different time periods, the normal value can be used to determine whether the operating status of the switch cabinet remains stable; if the sensor data of the switch cabinet in different time periods always fluctuates around the normal value, it means that the operating status of the switch cabinet has not changed significantly and the equipment performance is stable.

[0247] The warning value plays an early warning role. When the data collected by various sensors on the switch cabinet are close to the warning value, it indicates that there may be potential problems or abnormal conditions in the switch cabinet, which needs to attract the attention of the operation and maintenance personnel;

[0248] The warning value provides an early warning information for the operation and maintenance personnel so that they can take corresponding preventive measures in time. For example, when the sensor data is close to the warning value, the operation and maintenance personnel can increase the monitoring frequency of the switch cabinet, conduct more detailed inspections and analyses, find the possible root causes of the problem, and take corresponding maintenance measures to prevent the problem from further deteriorating.

[0249] When comparing different switch cabinets horizontally, the warning value can help determine which switch cabinets may have potential risks. If the sensor data of a switch cabinet frequently approaches or exceeds the warning value, while the data of other switch cabinets are relatively stable, then the switch cabinet may have special operating conditions or potential fault hazards, which need to be paid special attention and checked;

[0250] In the comparison of the change trend of the same switch cabinet in different time periods, the warning value can be used to determine whether the operating status of the switch cabinet shows an abnormal change trend. If the sensor data of the switch cabinet in a certain period of time gradually approaches the warning value, it means that the operating status of the switch cabinet may be changing, and it is necessary to further analyze the cause and take corresponding measures.

[0251] The alarm value is a clear alarm message. When the data collected by various sensors on the switch cabinet reaches or exceeds the alarm value, it indicates that there is a serious problem or fault in the switch cabinet and emergency measures need to be taken immediately.

[0252] The alarm value provides an emergency alarm information for the operation and maintenance personnel so that they can take prompt action to prevent the fault from expanding. For example, when the sensor data exceeds the alarm value, the operation and maintenance personnel should immediately stop the operation of the switch cabinet and conduct a comprehensive inspection and maintenance to ensure the safety of the equipment and system.

[0253] When comparing different switch cabinets horizontally, the alarm value can be used to quickly determine which switch cabinets are in a serious fault state. If the sensor data of a switch cabinet reaches or exceeds the alarm value, while the data of other switch cabinets are relatively normal, then the switch cabinet needs to be immediately fault-handled to avoid a greater impact on the entire system;

[0254] In the comparison of the change trend of the same switch cabinet in different time periods, the alarm value can be used to judge the severity of the switch cabinet failure. If the sensor data of the switch cabinet in a certain time period suddenly reaches or exceeds the alarm value, it means that the switch cabinet may have a serious failure and needs to be repaired and restored as soon as possible.

[0255] This embodiment performs growth tracking on the switch cabinet status through the tracking and analysis unit, and can timely discover the changing trend of the switch cabinet operation status, providing strong support for early warning and fault handling, and calculates three growth indicators of normal value, warning value, and alarm value, which correspond to different operation states respectively, to provide clear judgment standards and action guidelines for operation and maintenance personnel, and through horizontal comparison between different switch cabinets in the same time period and comparison of changing trends of the same switch cabinet in different time periods, it is possible to better discover abnormal conditions and potential problems of the switch cabinet, thereby improving the pertinence and effectiveness of operation and maintenance.

[0256] Embodiment 5

[0257] As the fifth embodiment of the present invention, when the present application is specifically implemented, compared with the first, second, third and fourth embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second, third and fourth embodiments.

[0258] This embodiment combines and implements the solutions of Embodiment 1, Embodiment 2, Embodiment 3, and Embodiment 4, giving full play to the advantages of each embodiment, achieving comprehensive, accurate, and real-time evaluation and tracking of the health of the distribution station, and providing operation and maintenance personnel with more comprehensive and accurate information, which helps to improve operation and maintenance efficiency, reduce the risk of equipment failure, and ensure the safe and stable operation of the distribution station.

[0259] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0260] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A health evaluation system for power distribution stations based on multi-source information. It is characterized in that include: The sensor unit is used to collect the operation data of the power distribution station and then transmit it to the data processing unit and the data analysis unit; The sensor unit includes two environmental sensors and two partial discharge sensors arranged on the switch cabinet in the station house; the environmental sensors include a temperature sensor and a humidity sensor, and the partial discharge sensors include a UHF sensor and a three-in-one sensor; The operation data includes temperature information collected by temperature sensors, humidity information collected by humidity sensors, UHF sensors used to collect UHF information of switch cabinets, and three-in-one sensors used to collect ultrasonic information and transient ground voltage information; Among them, a plurality of UHF sensors are arranged on a switch cabinet, and each UHF sensor collects corresponding UHF information; The data processing unit is used to pre-process the operation data collected by the sensor unit; and transmit the pre-processing result to the data analysis unit; The preprocessing method is as follows: StepA1, on each UHF sensor, obtain n consecutive UHF information of the relevant switch cabinet; Step A2, judging each piece of UHF data by using a partial discharge identification algorithm, and obtaining a judgment result of whether the corresponding UHF data is partial discharge data; The judgment result includes the partial discharge type and its corresponding probability; Step A3, for each sensor, collect n pieces of data to obtain n partial discharge judgment results, correspond the partial discharge type and the corresponding probability one by one to form a dictionary structure, and then form the judgment results of n consecutive pieces of data from different sensors into a two-dimensional list; Among them, the partial discharge judgment result is used as the key value of the dictionary structure, and the corresponding probability is used as the value of the dictionary structure; The two-dimensional list is as follows: ； Wherein, i=1, 2, ...n, j=1, 2, ...m, n represents the number of sensors, m represents the number of partial discharge judgment types of data, Indicates the PD judgment type of the jth data of the i-th sensor. When the type is PD, it is represented by the number 1, and when the type is no PD, it is represented by the number 0; Step A4, pre-processing the ultrasonic information and transient ground voltage information on the switch cabinet according to the method from Step A1 to Step A3; A data analysis unit, used to perform score analysis on the operation data collected and processed by the sensor unit and the data processing unit, and then transmit the score analysis results to the data display unit; The scoring analysis is as follows: Step V1. Calculation of the score of UHF information on the switch cabinet Get the two-dimensional list obtained by the data processing unit; If all key values ​​in the two-dimensional list are 0, that is, all data from all sensors are judged to have no partial discharge, the one-dimensional list with the smallest value mean is taken as the data for score calculation; The calculation formula is as follows: ； in, It is expressed as the score corresponding to the UHF information; If the key value in the two-dimensional list is 1, that is, the data collected by the sensor is judged to be partial discharge, the one-dimensional list with the largest value is taken as the data basis for score calculation; The calculation formula is as follows: ； in, Expressed as the score corresponding to the UHF information, Represents the probability of judging that there is no partial discharge data in the one-dimensional list; Represents the probability corresponding to the partial discharge data in the one-dimensional list; Step V2. Calculation of the score of ultrasonic information on the switch cabinet According to Step V1, the score of ultrasound information is calculated and marked as ; Step V3. Calculation of the score of transient ground voltage information on the switch cabinet According to Step V1, calculate the score of the transient ground voltage and mark it as ; Step V4. Calculation of the score of temperature information on the switch cabinet On the temperature sensor, obtain the switch cabinet temperature values ​​of n consecutive switch cabinets of the relevant switch cabinet and record them as ; Then through , calculate the mean of n consecutive temperature data, T avg ; Then combine the preset temperature optimal value , Temperature alarm upper limit , Temperature alarm lower limit Calculate the temperature score for the switchgear; The calculation is as follows: ； The optimum temperature is , the upper limit of temperature alarm is , the lower limit of temperature alarm is , and it is set separately according to the different types of switch cabinets; Step V5. Calculation of humidity score on switch cabinet Calculate the humidity score of the switch cabinet according to Step V3; It is calculated as follows: ； In the formula, The real-time humidity uploaded by the humidity sensor. The optimum humidity value is Humidity alarm upper limit, It is the lower limit of humidity alarm; Step V6, comprehensive health score calculation The scores corresponding to the UHF information, ultrasonic information, transient ground voltage information, temperature information, and humidity information on the switchgear obtained from Step V1 to Step V4 are integrated and calculated to obtain the comprehensive health score of the switchgear; It is calculated as follows: ； In the formula, are the preset weight values ​​corresponding to the corresponding factors, It is the comprehensive health score of the switchgear; The data display unit is used to display the results obtained by the data analysis unit to relevant personnel in an intuitive manner.

2. According to the multi-source information-based health evaluation system of power distribution station in claim 1, It is characterized in that The power distribution station is also equipped with three types of environmental status sensors, namely smoke sensor, access control sensor, and water immersion sensor; Among them, the information uploaded by the three environmental status sensors is binary data, and its corresponding value is 1 or 0; When the value is 0, it means the status monitored by the sensor is normal; When the value is 1, it means that the state monitored by the sensor is abnormal; The data analysis unit is also used to perform score analysis on the binary data corresponding to the three environmental state sensors; If the three environmental status sensors in the station house contain at least one binary data 0, it means that the monitored state is abnormal, and the station house environmental health score is 0, which is recorded as ; If the binary data of the three environmental status sensors in the station house are all 1, it means that there is no abnormality in the station house, and the station house environmental health score is 100, which is recorded as .

3. According to the multi-source information-based health evaluation system of power distribution station in claim 2, It is characterized in that The data analysis unit is also used to calculate the total health score of the station house based on the obtained comprehensive health scores of each switch cabinet device in the station house and the health score of the station house environment; It is calculated as follows: ； In the formula, Indicates the total health score of the station building. Respectively represent the total health score of each station building, represents the environmental health score of the station house, and m represents the number of switchgear equipment in the station house.

4. According to the multi-source information-based health evaluation system of power distribution station in claim 1, It is characterized in that Also includes: The tracking and analysis unit is used to track the state of the switch cabinet according to the value changes of various sensors on each switch cabinet within a specified period of time, and obtain the growth index based on the growth tracking; Among them, the growth index includes three data types. Each data type is calculated to obtain three growth indicators, which are: normal value, warning value, and alarm value; The data types are: UHF information collected by UHF sensors, ultrasonic information collected by three-in-one sensors, and transient ground voltage information.

Images