Multi-level state characteristic decomposition diagnosis system and method for power distribution network transformer

Abstract

The invention discloses a multi-level state characteristic decomposition diagnosis system and method for a power distribution network transformer, and relates to the technical field of transformer diagnosis, influence data needing to be monitored of the transformer are obtained through a large database, multi-level state characteristic layers are divided based on the influence data, each state characteristic layer comprises corresponding observation data, and the observation data are stored in a database; and generating corresponding stability indexes and entropy weights for the state feature layers according to the observation data, performing weighted fusion on the stability indexes of all the state feature layers in the transformer to obtain a comprehensive feature value of the transformer, performing abnormality diagnosis on the transformer based on the comprehensive feature value, and generating a corresponding management strategy in combination with an abnormality diagnosis result. The diagnosis system can more comprehensively reflect different influence factors of the operation of the transformer by constructing a multi-level state feature layer, and the careful degree of monitoring and the accuracy of diagnosis are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer diagnosis, and in particular to a multi-level state feature decomposition diagnosis system and method for a transformer in a distribution network. Background Art

[0002] As an important part of the power system, distribution transformers are responsible for converting high voltage into low voltage suitable for users, providing stable electricity for homes, factories and commercial places. The operating environment of distribution transformers is complex and is easily affected by load fluctuations, ambient temperature changes, aging losses and external factors. The diagnostic system is mainly used to monitor and analyze the operating status of distribution transformers to ensure the safe and stable operation of transformers.

[0003] The prior art has the following defects:

[0004] The existing diagnostic system only focuses on a single dimension or a few status characteristics, and the assessment of the transformer status is not comprehensive enough. In addition, the variability and uncertainty of the characteristic data are often ignored during data processing, resulting in the health assessment of the transformer status being mostly qualitative analysis, which is difficult to achieve accurate quantification, thereby reducing the accuracy and comprehensiveness of the transformer status diagnosis.

[0005] Based on this, the present invention proposes a multi-level state feature decomposition diagnosis system and method for distribution network transformers. By constructing a multi-level state feature layer, the different influencing factors of transformer operation can be more comprehensively reflected, thereby improving the level of monitoring and the accuracy of diagnosis. Summary of the invention

[0006] The purpose of the present invention is to provide a distribution network transformer multi-level state feature decomposition diagnosis system and method to solve the shortcomings of the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a multi-level state feature decomposition diagnosis method for a distribution network transformer, the diagnosis method comprising the following steps:

[0008] The diagnostic system obtains the impact data that needs to be monitored by the transformer through a large database. The impact data represents the data that affects the safe and stable operation of the transformer. Based on the impact data, multiple levels of state feature layers are divided, and each level of state feature layer includes corresponding observation data.

[0009] Generate corresponding stability index and entropy weight for the state feature layer based on the observed data;

[0010] After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. The corresponding management strategy is generated based on the abnormal diagnosis result and sent to the transformer management platform.

[0011] In a preferred embodiment, generating a corresponding stability index for the state characteristic layer based on the observed data includes the following steps:

[0012] Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data;

[0013] The stable value of the component is calculated based on the probability of small observation data, the probability of normal observation data and the probability of large observation data. The expression is: In the formula, W is the stability value, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. The calculation expression of the stability index of the state characteristic layer is:

[0014] Where SW is the stability index, n is the number of components included in the state feature layer, and W i is the stability value of the i-th component. The larger the stability index is, the higher the overall stability of the state characteristic layer during the operation of the transformer.

[0015] In a preferred embodiment, generating corresponding entropy weights for the state feature layer based on the observed data includes the following steps:

[0016] Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data;

[0017] The weight of the component is calculated based on the probability of small observation data, the probability of average observation data, and the probability of large observation data. The expression is:

[0018] H=-(p(x1)log(p(x1))+p(x2)log(p(x2))+p(x3)log(p(x3))); Eq.

[0019] In it, H is the weight, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. Since the state feature layer includes multiple components, the weights of multiple components are summed to obtain the entropy weight of the state feature layer. The expression is:

[0020] In the formula, SH is the entropy weight, n is the number of components included in the state feature layer, and H i is the weight of the ith component.

[0021] In a preferred embodiment, after weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive feature value of the transformer is obtained, which includes the following steps:

[0022] After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the expression is: In the formula, tz s is the comprehensive eigenvalue, m is the number of state feature layers in the transformer, SW i is the stability index of the i-th state feature layer, SH i is the entropy weight of the i-th state feature layer.

[0023] In a preferred embodiment, abnormality diagnosis of a transformer based on the comprehensive characteristic value includes the following steps:

[0024] The comprehensive characteristic value is compared with the preset health threshold. The health threshold is used to diagnose whether the transformer has abnormalities. If the comprehensive characteristic value is greater than or equal to the health threshold, it is diagnosed that the transformer does not have abnormalities. If the comprehensive characteristic value is less than the health threshold, it is diagnosed that the transformer has abnormalities.

[0025] In a preferred embodiment, the diagnostic system obtains the impact data that needs to be monitored for the transformer through a large database, including the following steps:

[0026] The diagnostic system obtains the impact data that the transformer needs to monitor through a large database, including temperature data, resistance data, current data, and vibration data;

[0027] The multi-level state characteristic layer is divided based on the impact data, the temperature data is divided into the temperature state characteristic layer, the resistance data is divided into the resistance state characteristic layer, the current data is divided into the current state characteristic layer, and the vibration data is divided into the vibration state characteristic layer.

[0028] In a preferred embodiment, each state characteristic layer includes corresponding observation data, the observation data of the temperature state characteristic layer includes winding temperature, cooling oil temperature and core temperature, the observation data of the resistance state characteristic layer includes winding resistance, bushing resistance and contact resistance, the observation data of the current state characteristic layer includes winding current and load current, and the observation data of the vibration state characteristic layer includes winding vibration, core vibration and oil pump vibration.

[0029] The multi-level state feature decomposition diagnosis system of distribution network transformers includes data collection module, parameter generation module and abnormality diagnosis module;

[0030] Data collection module: Obtain the impact data that needs to be monitored for the transformer through a large database. The impact data represents the data that affects the safe and stable operation of the transformer. Multi-level state feature layers are divided based on the impact data, and each state feature layer includes corresponding observation data;

[0031] Parameter generation module: Generates corresponding stability index and entropy weight for the state feature layer based on the observed data;

[0032] Abnormal diagnosis module: After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. The corresponding management strategy is generated based on the abnormal diagnosis result, and the management strategy is sent to the transformer management platform.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0034] The present invention obtains the influencing data that the transformer needs to monitor through a large database, divides the multi-level state feature layer based on the influencing data, and each state feature layer includes corresponding observation data. According to the observation data, the corresponding stability index and entropy weight are generated for the state feature layer. After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the transformer is abnormally diagnosed based on the comprehensive characteristic value, and the corresponding management strategy is generated in combination with the abnormal diagnosis result. By constructing a multi-level state feature layer, the diagnostic system can more comprehensively reflect the different influencing factors of the transformer operation, and improve the meticulousness of monitoring and the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0038] Example 1: Please refer to Figure 1 As shown, the multi-level state feature decomposition diagnosis method of the distribution network transformer described in this embodiment includes the following steps:

[0039] The diagnostic system obtains the influencing data that needs to be monitored for the transformer through a large database. The influencing data represents the data that has an impact on the safe and stable operation of the transformer. Based on the influencing data, a multi-level state feature layer is divided, and each state feature layer includes corresponding observation data (for example, when the influencing data is temperature data, the divided state feature is a temperature feature layer, and the temperature feature layer includes observation data such as winding temperature and oil temperature). According to the observation data, a corresponding stability index and entropy weight are generated for the state feature layer (the larger the stability index, the more stable the state feature layer, and the smaller the impact on the stable operation of the transformer; the larger the entropy weight, the greater the uncertainty of the state feature layer). After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. In combination with the abnormal diagnosis results, a corresponding management strategy is generated, and the management strategy is sent to the transformer management platform.

[0040] This application obtains the influencing data that needs to be monitored for the transformer through a large database, divides the multi-level state feature layer based on the influencing data, and each state feature layer includes corresponding observation data. According to the observation data, the corresponding stability index and entropy weight are generated for the state feature layer. After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the transformer is abnormally diagnosed based on the comprehensive characteristic value, and the corresponding management strategy is generated in combination with the abnormal diagnosis results. By constructing a multi-level state feature layer, the diagnostic system can more comprehensively reflect the different influencing factors of the transformer operation, improve the meticulousness of monitoring and the accuracy of diagnosis.

[0041] Embodiment 2: The diagnostic system obtains the impact data that needs to be monitored for the transformer through a large database, where the impact data represents data that has an impact on the safe and stable operation of the transformer, and divides the multi-level state feature layer based on the impact data, including the following steps:

[0042] The diagnostic system obtains the impact data that the transformer needs to monitor through a large database, including temperature data, resistance data, current data, and vibration data;

[0043] The multi-level state characteristic layer is divided based on the impact data, the temperature data is divided into the temperature state characteristic layer, the resistance data is divided into the resistance state characteristic layer, the current data is divided into the current state characteristic layer, and the vibration data is divided into the vibration state characteristic layer.

[0044] The impact data obtained through the big database is used to comprehensively monitor and analyze the status of the transformer. The impact data can be divided into multiple categories (such as temperature data, resistance data, current data, vibration data, etc.), each type of data corresponds to a state feature layer, and each state feature layer contains each observation point under this type of data. The following is an example of a multi-level state feature layer divided according to these data:

[0045] 1) Temperature state characteristic layer:

[0046] Data source: various monitoring data related to temperature in the transformer.

[0047] 1.1) Observational data:

[0048] Winding temperature: monitors the temperature of the winding and reflects the thermal status of the winding.

[0049] Oil temperature: Monitors the temperature of transformer oil, reflecting the effectiveness of the cooling system and the heat dissipation of the transformer.

[0050] Core Temperature: Monitors the temperature of the core to assess whether it is overheating.

[0051] Bushing Temperature: Monitor the temperature of the bushing to assess the insulation condition of the bushing.

[0052] Function of the status feature layer: This layer evaluates the thermal status of the transformer through temperature data. Temperature anomalies may indicate problems such as winding overload, insufficient oil cooling, or core overheating.

[0053] 2) Resistance state characteristic layer:

[0054] Data source: Resistance-related monitoring data, mainly used to detect the health status of transformer windings and insulation.

[0055] 2.2) Observational data:

[0056] Winding Resistance: Monitors the resistance of the winding to detect damage or aging due to overheating or excessive current.

[0057] Insulation resistance: Monitor the insulation resistance of transformer windings, bushings and other components to assess insulation conditions.

[0058] Function of the status feature layer: This layer evaluates the electrical status of the transformer through resistance data. Resistance changes may indicate problems such as winding short circuit, poor contact or insulation aging.

[0059] 3) Current state characteristic layer:

[0060] Data source: Current-related monitoring data, used to assess transformer load conditions and current anomalies.

[0061] 3.3) Observational data:

[0062] Winding current: Monitor the winding current to determine if there is an overload, short circuit or current imbalance.

[0063] Load current: reflects the transformer load condition and is usually used to detect the load change trend.

[0064] Function of the status feature layer: This layer evaluates the current status of the transformer. Excessive current may mean problems such as overload or short circuit, while unbalanced current may indicate system instability.

[0065] 4) Vibration state feature layer:

[0066] Data source: Vibration monitoring data of various components in the transformer, mainly used to evaluate the stability of the transformer mechanical structure.

[0067] 4.4) Observational data:

[0068] Winding vibration: Monitor the vibration of the windings to check for looseness or unevenness.

[0069] Core vibration: Monitor the core for vibration or looseness caused by foreign matter.

[0070] Overall structural vibration: monitors the vibration of the entire transformer structure to assess its mechanical stability.

[0071] Function of the state feature layer: This layer evaluates the mechanical stability of the transformer through vibration data. Abnormal vibration may indicate problems such as loose windings, core damage, or structural instability.

[0072] Each state feature layer includes corresponding observation data (for example, when the influencing data is temperature data, the divided state feature is a temperature feature layer, and the temperature feature layer includes observation data such as winding temperature and oil temperature), including the following steps:

[0073] Each state feature layer includes corresponding observation data. The observation data of the temperature state feature layer includes winding temperature, cooling oil temperature and core temperature. The observation data of the resistance state feature layer includes winding resistance, bushing resistance and contact resistance. The observation data of the current state feature layer includes winding current and load current. The observation data of the vibration state feature layer includes winding vibration, core vibration and oil pump vibration.

[0074] 1. Temperature state characteristic layer observation data:

[0075] Winding temperature: Winding temperature refers to the operating temperature of the transformer winding. Excessive winding temperature may cause aging and damage of the winding insulation material, and may even cause fire or electrical failure. Therefore, winding temperature is a key monitoring data.

[0076] Cooling oil temperature: The temperature of the cooling oil directly affects the cooling effect of the transformer, and thus affects its working efficiency and safety. If the cooling oil temperature is too high, it may indicate a cooling system failure or insufficient oil, and the transformer's heat dissipation capacity is limited.

[0077] Core temperature: The temperature change of the core reflects the thermal state of the core part of the transformer. If the core temperature is too high, it may be due to abnormal reasons such as overload and short circuit, which may cause the core to be damaged, further affecting the working performance of the transformer.

[0078] Function: The observation data of the temperature state characteristic layer is used to monitor the thermal condition of the transformer. If the temperature of a part is too high (such as winding temperature, oil temperature, etc.), it means that the part may be faulty or need maintenance.

[0079] For example: If the winding temperature reaches 90°C, the cooling oil temperature is 85°C, and the core temperature is close to 80°C, it may mean that the cooling oil temperature rises quickly and the cooling effect decreases. It is necessary to check the oil level and cooling system.

[0080] 2. Resistance state characteristic layer observation data:

[0081] Winding Resistance: Winding resistance is used to monitor the health of the windings. Low or high resistance may indicate deterioration of the winding insulation or a short circuit.

[0082] Bushing resistance: The resistance of the bushing is a monitoring of the insulation performance of the transformer bushing. The change in resistance reflects whether the insulation material of the bushing is aging or has breakdown.

[0083] Contact Resistance: The electrical resistance of a tap changer or other mechanical contact. Poor contact can result in increased resistance, creating a risk of overheating or electrical fire.

[0084] Function: The observation data of the resistance state characteristic layer is mainly used to evaluate the electrical health of the transformer. Abnormal changes in resistance values ​​may indicate electrical faults such as winding insulation problems and bushing aging.

[0085] For example: If the winding resistance fluctuates greatly and the bushing resistance continues to rise, this may indicate aging of the insulation system or the presence of partial discharges.

[0086] A gradual increase in contact resistance may indicate a problem with the tap changer contact point, which may cause unstable current in the transformer.

[0087] 3. Current state characteristic layer observation data:

[0088] Winding Current: The current in the transformer windings can help determine the load and whether an overload has occurred. Excessive winding current can be a sign of an overload, or the cause of a short circuit or poor contact.

[0089] Load current: The load current reflects the actual load of the transformer. Under normal circumstances, the load current should match the rated load of the transformer. If the load current is too large, it may mean that the transformer is overloaded or the load is unevenly distributed.

[0090] Function: The current state characteristic layer is used to monitor the load condition and current fluctuation of the transformer. Excessive or uneven current may cause equipment damage or failure.

[0091] For example: If the winding current is continuously higher than the rated value and the load current fluctuates greatly, it may indicate that the transformer is facing an overload risk or the load distribution is uneven, and the load needs to be adjusted or shut down for inspection as soon as possible. If the winding current is inconsistent with the load current, it may indicate that there is an imbalance inside the transformer, and the winding needs to be checked for damage or poor contact.

[0092] 4. Observation data of vibration state characteristic layer:

[0093] Winding vibration: Winding vibration data can help determine if the winding is loose or damaged. Abnormal vibration may be a sign of loose, damaged or other mechanical problems inside the transformer.

[0094] Core Vibration: Vibration monitoring of the core is used to detect whether there are mechanical problems or magnetic saturation. Excessive vibration may cause damage to the core structure and affect the performance of the transformer.

[0095] Oil pump vibration: Oil pump vibration monitoring can determine whether the cooling system is operating properly. Abnormal oil pump vibration may indicate that there is a fault in the oil pump or that the oil flow is not smooth, which may lead to reduced cooling effect.

[0096] Purpose: The vibration status signature layer is used to assess the mechanical health of the transformer. Excessive or irregular vibrations usually indicate mechanical failure or loose components.

[0097] For example: If the detected amplitude of the winding vibration suddenly increases and the core vibration also shows large fluctuations, it may indicate that there is a mechanical structure problem with the transformer, such as a loose core or a mechanical failure in the winding. Increased oil pump vibration may be a warning signal of oil pump failure, and it is necessary to check the operating status of the oil pump and whether the oil flow is smooth.

[0098] Generate the corresponding entropy weight for the state feature layer based on the observed data, including the following steps:

[0099] Each state feature layer includes corresponding observation data. The observation data of the temperature state feature layer includes winding temperature, cooling oil temperature and core temperature. The observation data of the resistance state feature layer includes winding resistance, bushing resistance and contact resistance. The observation data of the current state feature layer includes winding current and load current. The observation data of the vibration state feature layer includes winding vibration, core vibration and oil pump vibration.

[0100] Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data;

[0101] The weight of the component is calculated based on the probability of small observation data, the probability of average observation data, and the probability of large observation data. The expression is:

[0102] H=-(p(x1)log(p(x1))+p(x2)log(p(x2))+p(x3)log(p(x3))); Eq.

[0103] In it, H is the weight, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. Since the state feature layer includes multiple components, the weights of multiple components are summed to obtain the entropy weight of the state feature layer. The expression is:

[0104] In the formula, SH is the entropy weight, n is the number of components included in the state feature layer, and H i is the weight of the i-th component. The larger the entropy weight of the state feature layer, the greater the uncertainty of the state feature layer, that is, the greater the impact on the transformer.

[0105] In order to better illustrate the above solution, this application gives the following examples:

[0106] Taking the winding temperature in the temperature state characteristic layer as an example, the winding temperature usually has a preset standard temperature range (T min ~T max ), if the current temperature of the winding is within the standard temperature range, it is recorded as standard observation data; if the current temperature of the winding is less than the first temperature threshold T min , it is recorded as a smaller observation data. If the current temperature of the winding is greater than the second temperature threshold T max , it is recorded as larger observation data;

[0107] For example, the transformer winding temperature preset first temperature threshold is 85 degrees Celsius, the second temperature threshold is 105 degrees Celsius, and when the current winding temperature is greater than or equal to 85 degrees Celsius and less than or equal to 105 degrees Celsius, it is recorded as general observation data, and so on;

[0108] The method for generating observation data for the resistance state characteristic layer and the current state characteristic layer is the same as that for the temperature state characteristic layer, and will not be introduced one by one in this application.

[0109] Among them, the method of obtaining the observation data of the vibration state characteristic layer is different from that of the temperature state characteristic layer. This is because in the transformer diagnosis process, the vibration amplitude of the component is usually as small as possible. Therefore, taking the core vibration in the vibration state characteristic layer as an example, a first vibration threshold and a second vibration threshold are preset. If the current vibration of the core is less than or equal to the first vibration threshold, it indicates that there is no vibration abnormality and is recorded as small observation data. If the current vibration of the core is greater than the first vibration threshold and less than or equal to the second vibration threshold, it indicates that there is slight vibration and is recorded as general observation data. If the current vibration of the core is greater than the second vibration threshold, it indicates that there is severe vibration and is recorded as large observation data.

[0110] The duration of each occurrence of general observation data is summed up to obtain the duration of general observation data, the duration of each occurrence of smaller observation data is summed up to obtain the duration of smaller observation data, and the duration of each occurrence of larger observation data is summed up to obtain the duration of larger observation data.

[0111] Generating a corresponding stability index for the state feature layer based on the observed data includes the following steps:

[0112] Each state feature layer includes corresponding observation data. The observation data of the temperature state feature layer includes winding temperature, cooling oil temperature and core temperature. The observation data of the resistance state feature layer includes winding resistance, bushing resistance and contact resistance. The observation data of the current state feature layer includes winding current and load current. The observation data of the vibration state feature layer includes winding vibration, core vibration and oil pump vibration.

[0113] Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum up the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data.

[0114] The stable value of the component is calculated based on the probability of small observation data, the probability of normal observation data and the probability of large observation data. The expression is: In the formula, W is the stability value, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. The calculation expression of the stability index of the state characteristic layer is:

[0115] Where SW is the stability index, n is the number of components included in the state feature layer, and W i is the stability value of the i-th component. The larger the stability index is, the higher the overall stability of the state characteristic layer during the operation of the transformer.

[0116] The calculation formula of the component stability value is only applicable to the temperature state characteristic layer, the resistance state characteristic layer and the current state characteristic layer. For the vibration state characteristic layer, the calculation expression of the component stability value is: Where W is the stable value, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. This is because in the vibration state characteristic layer, the vibration of the component is usually as small as possible.

[0117] After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the transformer is diagnosed abnormally based on the comprehensive characteristic value. The corresponding management strategy is generated in combination with the abnormal diagnosis result, and the management strategy is sent to the transformer management platform, including the following steps:

[0118] After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the expression is: In the formula, tz s is the comprehensive eigenvalue, m is the number of state feature layers in the transformer, SW i is the stability index of the i-th state feature layer, SH i is the entropy weight of the i-th state feature layer. The larger the comprehensive eigenvalue is, the better the overall health state of the surface transformer is.

[0119] Compare the comprehensive characteristic value with the preset health threshold. The health threshold is used to diagnose whether the transformer is abnormal. If the comprehensive characteristic value is greater than or equal to the health threshold, it is diagnosed that the transformer is not abnormal. If the comprehensive characteristic value is less than the health threshold, it is diagnosed that the transformer is abnormal.

[0120] When the transformer is diagnosed to be abnormal, the corresponding management strategies are generated, including:

[0121] If the combined anomaly is due to overload or unbalanced load, take load adjustment measures immediately to transfer the load from the affected transformer to the standby equipment or other healthy equipment through the load sharing system.

[0122] If the load is too large and the transformer is in an overload state, the load cut-off protection mechanism should be activated to suspend or reduce the load operation to prevent the temperature from continuing to rise and the equipment from being damaged by overload.

[0123] If the assessment results show that the combined abnormalities have posed a significant threat to the health of the transformer (for example, both temperature and resistance abnormalities occur, which may lead to insulation aging or internal short circuits), an emergency shutdown operation should be performed and a comprehensive inspection should be carried out.

[0124] Depending on the type of abnormality, the abnormal transformer can be isolated to avoid affecting the entire distribution network.

[0125] If the transformer cannot resume normal operation, the backup transformer or backup power supply should be started to ensure the stability of the power supply system.

[0126] Based on the diagnosis results, the generated management strategy should respond quickly, accurately locate the cause of the abnormality, and take practical measures. By dispatching loads, testing equipment, starting backup plans or performing maintenance, transformer failures can be avoided as much as possible and the impact on the system can be reduced. Reasonable management strategies can help improve the operating safety of transformers, extend their service life, and reduce maintenance costs.

[0127] Embodiment 3: The multi-level state feature decomposition diagnosis system of the distribution network transformer described in this embodiment includes a data collection module, a parameter generation module, and an abnormality diagnosis module;

[0128] Data collection module: Obtain the influencing data that needs to be monitored for the transformer through a large database. The influencing data represents the data that has an impact on the safe and stable operation of the transformer. Multi-level state feature layers are divided based on the influencing data. Each state feature layer includes corresponding observation data (for example, when the influencing data is temperature data, the divided state feature is a temperature feature layer, and the temperature feature layer includes observation data such as winding temperature and oil temperature). The multi-level state feature layer and the corresponding observation data are sent to the parameter generation module;

[0129] Parameter generation module: Generates the corresponding stability index and entropy weight for the state feature layer based on the observed data (the larger the stability index, the more stable the state feature layer, and the smaller the impact on the stable operation of the transformer; the larger the entropy weight, the greater the uncertainty of the state feature layer). The stability index and entropy weight are sent to the abnormal diagnosis module;

[0130] Abnormal diagnosis module: After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. The corresponding management strategy is generated based on the abnormal diagnosis result, and the management strategy is sent to the transformer management platform.

[0131] 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 in the formula are set by technicians in this field according to actual conditions.

[0132] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0133] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-level state feature decomposition diagnosis method for distribution network transformers, characterized by: The diagnostic method comprises the following steps: The diagnostic system obtains the impact data that needs to be monitored by the transformer through a large database. The impact data represents the data that affects the safe and stable operation of the transformer. Based on the impact data, multiple levels of state feature layers are divided, and each level of state feature layer includes corresponding observation data. Generate corresponding stability index and entropy weight for the state feature layer based on the observed data; After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. The corresponding management strategy is generated based on the abnormal diagnosis result and sent to the transformer management platform.

2. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 1 is characterized in that: Generating a corresponding stability index for the state feature layer based on the observed data includes the following steps: Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data; The stable value of the component is calculated based on the probability of small observation data, the probability of normal observation data and the probability of large observation data. The expression is: In the formula, W is the stability value, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. The calculation expression of the stability index of the state characteristic layer is: Where SW is the stability index, n is the number of components included in the state feature layer, and W i is the stability value of the i-th component. The larger the stability index is, the higher the overall stability of the state characteristic layer during the operation of the transformer.

3. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 2 is characterized in that: Generate the corresponding entropy weight for the state feature layer based on the observed data, including the following steps: Obtain the duration of occurrence of small observation data, general observation data and large observation data of any component in the state feature layer observation data, sum the duration of occurrence of small observation data, general observation data and large observation data to obtain the total duration, divide the duration of occurrence of small observation data by the total duration to obtain the probability of small observation data, divide the duration of occurrence of general observation data by the total duration to obtain the probability of general observation data, and divide the duration of occurrence of large observation data by the total duration to obtain the probability of large observation data; The weight of the component is calculated based on the probability of small observation data, the probability of average observation data, and the probability of large observation data. The expression is: H=-(p(x1)log(p(x1))+p(x2)log(p(x2))+p(x3)log(p(x3))); Eq. In it, H is the weight, p(x1) is the probability of small observation data, p(x2) is the probability of general observation data, and p(x3) is the probability of large observation data. Since the state feature layer includes multiple components, the weights of multiple components are summed to obtain the entropy weight of the state feature layer. The expression is: In the formula, SH is the entropy weight, n is the number of components included in the state feature layer, and H i is the weight of the ith component.

4. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 3 is characterized in that: After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive feature value of the transformer is obtained, including the following steps: After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and the expression is: In the formula, tz s is the comprehensive eigenvalue, m is the number of state feature layers in the transformer, SW i is the stability index of the i-th state feature layer, SH i is the entropy weight of the i-th state feature layer.

5. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 4 is characterized in that: The abnormal diagnosis of transformer based on comprehensive characteristic values ​​includes the following steps: The comprehensive characteristic value is compared with the preset health threshold. The health threshold is used to diagnose whether the transformer has abnormalities. If the comprehensive characteristic value is greater than or equal to the health threshold, it is diagnosed that the transformer does not have abnormalities. If the comprehensive characteristic value is less than the health threshold, it is diagnosed that the transformer has abnormalities.

6. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 5 is characterized in that: The diagnostic system obtains the impact data that needs to be monitored on the transformer through a large database, including the following steps: The diagnostic system obtains the impact data that the transformer needs to monitor through a large database, including temperature data, resistance data, current data, and vibration data; The multi-level state characteristic layer is divided based on the impact data, the temperature data is divided into the temperature state characteristic layer, the resistance data is divided into the resistance state characteristic layer, the current data is divided into the current state characteristic layer, and the vibration data is divided into the vibration state characteristic layer.

7. The multi-level state feature decomposition diagnosis method for distribution network transformer according to claim 6 is characterized in that: Each state feature layer includes corresponding observation data. The observation data of the temperature state feature layer includes winding temperature, cooling oil temperature and core temperature. The observation data of the resistance state feature layer includes winding resistance, bushing resistance and contact resistance. The observation data of the current state feature layer includes winding current and load current. The observation data of the vibration state feature layer includes winding vibration, core vibration and oil pump vibration.

8. A multi-level state feature decomposition diagnosis system for distribution network transformers, used to implement the diagnosis method according to any one of claims 1 to 7, characterized in that: It includes data collection module, parameter generation module and abnormality diagnosis module; Data collection module: Obtain the impact data that needs to be monitored for the transformer through a large database. The impact data represents the data that affects the safe and stable operation of the transformer. Multi-level state feature layers are divided based on the impact data, and each state feature layer includes corresponding observation data; Parameter generation module: Generates corresponding stability index and entropy weight for the state feature layer based on the observed data; Abnormal diagnosis module: After weighted fusion of the stability indexes of all state feature layers in the transformer, the comprehensive characteristic value of the transformer is obtained, and abnormal diagnosis of the transformer is performed based on the comprehensive characteristic value. The corresponding management strategy is generated based on the abnormal diagnosis result, and the management strategy is sent to the transformer management platform.

Images