An intelligent monitoring and fault warning system and method for a transformer

Abstract

The present invention relates to the technical field of transformer monitoring, and specifically to an intelligent monitoring and fault warning system and method for transformers. By setting acquisition parameters, the working data of different acquisition targets of multiple transformers are respectively acquired according to the acquisition parameters, and all the working data are preprocessed to obtain preprocessed data. Then, the qualification rate of each transformer is calculated based on the preprocessed data, and abnormal transformers are screened out according to the qualification rate of the transformers. Finally, the working score of each abnormal transformer is calculated, and fault transformers are screened out according to the working score of the abnormal transformers. This application can detect multiple transformers simultaneously, and screen out fault transformers from multiple transformers based on the working scores of the transformers. Since the working scores are calculated based on different detection items of the transformers, and each detection item has a corresponding weight coefficient, this application can focus on different detection items to screen out fault transformers in a timely manner.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer monitoring, and particularly relates to an intelligent monitoring and fault warning system and method for transformers. Background Art

[0002] ‌A transformer is a device that uses the principle of electromagnetic induction to change the AC voltage. Its main components are the primary coil, secondary coil, and iron core (magnetic core). The main functions of a transformer are: voltage transformation, current transformation, impedance transformation, isolation, voltage stabilization (magnetic saturation transformer), etc. Transformers are basic equipment for power transmission and distribution and are widely used in industries, agriculture, transportation, urban communities, and other fields.

[0003] Chinese Patent with Publication No. CN115268350B discloses a fault warning method and system for a voltage stabilizing transformer. It groups the fault factor set based on the fault phenomenon clustering result to generate a fault factor grouping result, traverses the accessory fault factor set to generate a fault probability list and determines whether it meets the preset fault probability, sorts the fault factors that meet the preset fault probability, and performs warning by matching the associated fault phenomenon clustering result according to the fault factor sorting result. However, in the prior art, only the fault factors are clustered, and no mention is made of how to conduct a detailed inspection for different detection items of the transformer, resulting in the inability to quickly screen out the transformer with the most serious fault situation. Summary of the Invention

[0004] The purpose of the present invention is to address the problems in the background art and propose an intelligent monitoring and fault warning system and method for transformers.

[0005] The technical solution of the present invention:

[0006] On the one hand, the present application provides an intelligent monitoring and fault warning method for transformers, including:

[0007] Set acquisition parameters, and respectively acquire the working data of different acquisition targets of multiple transformers according to the acquisition parameters;

[0008] Preprocess all the working data to obtain preprocessed data;

[0009] Calculate the qualification rate of each transformer based on the preprocessed data, and screen out abnormal transformers according to the qualification rate of the transformers;

[0010] Calculate the working score of each abnormal transformer, and screen out faulty transformers according to the working score of the abnormal transformers.

[0011] Preferably, setting acquisition parameters and respectively acquiring the working data of different acquisition targets of multiple transformers according to the acquisition parameters includes:

[0012] Create a working data table;

[0013] Select a transformer and set acquisition parameters for each acquisition target of the transformer; the acquisition targets include transformer temperature data, transformer voltage data, and transformer oil quality data, and the acquisition parameters include acquisition period and acquisition frequency;

[0014] Collect the working data of multiple acquisition targets respectively according to the acquisition parameters of each acquisition target of the transformer, so as to obtain multiple sub-data groups, and put the multiple sub-data groups into the working data table;

[0015] Return to select a transformer until all transformers are selected, and obtain the working data of each transformer.

[0016] Preferably, preprocess all the working data to obtain preprocessed data, including:

[0017] Randomly select a transformer and all its working data from the working data table;

[0018] Select a sub-data group from all the working data of the transformer, and judge whether each acquisition node of the sub-data group has corresponding acquisition data;

[0019] If there is no corresponding acquisition data for a certain acquisition node in the sub-data group, mark the acquisition node before the acquisition node with corresponding acquisition data as a missing node;

[0020] Copy the acquisition data corresponding to any acquisition node adjacent to the missing node to the missing node to fill the missing node;

[0021] If each acquisition node of the sub-data group has corresponding acquisition data, return to select a sub-data group from all the working data of the transformer until all the sub-data groups of the transformer are selected, and obtain the preprocessed data of the transformer;

[0022] Return to randomly select a transformer and all its working data from the working data table until all transformers are selected, and obtain the preprocessed data of all transformers.

[0023] Preferably, after the step of if there is no corresponding acquisition data for a certain acquisition node in the sub-data group, mark the acquisition node before the acquisition node with corresponding acquisition data as a missing node, it further includes:

[0024] Set a missing threshold;

[0025] Judge whether the number of missing nodes of the sub-data group is greater than or equal to the missing threshold;

[0026] If the number of missing nodes in the sub-data group is greater than or equal to the missing threshold, the transformer corresponding to the sub-data group is recorded as a faulty transformer.

[0027] Preferably, calculate the qualification rate of each transformer based on the preprocessed data, and screen out abnormal transformers according to the qualification rate of the transformers, including:

[0028] Select a transformer and all the preprocessed data of the transformer;

[0029] Select a sub-data group;

[0030] Set the qualification threshold;

[0031] Judge whether each working data of the sub-data group is greater than or equal to the qualification threshold;

[0032] If each working data of the sub-data group is greater than or equal to the qualification threshold, the sub-data group is qualified;

[0033] Return to select a sub-data group until all the sub-data groups of the transformer are selected, and calculate the qualification rate of the sub-data groups of the transformer;

[0034] Return to select a transformer and all the preprocessed data of the transformer until all the transformers are selected, and obtain the qualification rate of each transformer.

[0035] Preferably, calculate the qualification rate of each transformer based on the preprocessed data, and screen out abnormal transformers according to the qualification rate of the transformers, and also include:

[0036] Select all the transformers;

[0037] Sort all the transformers from small to large according to the qualification rate of the transformers, and screen out the top M transformers; record the top M transformers as abnormal transformers.

[0038] Preferably, before calculating the working score of each abnormal transformer and screening out the faulty transformers according to the working score of the abnormal transformers, it includes:

[0039] Obtain the historical data of multiple transformers; the historical data of each transformer includes multiple historical sub-data groups;

[0040] Select a historical sub-data group from the historical data of multiple transformers, and calculate the average value of the historical sub-data group;

[0041] Return to select a historical sub-data group from the historical data of multiple transformers until the average value of each historical sub-data group is obtained;

[0042] Normalize the average value of all historical sub - data groups to obtain the normalized average value, and record the normalized average value as the score of the sub - data group.

[0043] Preferably, calculate the working score of each abnormal transformer, and screen out the faulty transformers according to the working scores of the abnormal transformers, including:

[0044] Select an abnormal transformer and all its pre - processed data;

[0045] Set corresponding weight coefficients for each sub - data group included in the pre - processed data;

[0046] Calculate the working score of the abnormal transformer through formula (1) in combination with the weight coefficients of the sub - data groups;

[0047] Formula (1);

[0048] Wherein, is the working score of the abnormal transformer, is the score of the i - th sub - data group of the abnormal transformer, is the historical score of the i - th sub - data group of the abnormal transformer, is the weight coefficient of the i - th sub - data group of the abnormality, is the total number of sub - data groups;

[0049] Return to select an abnormal transformer and all its pre - processed data until the working scores of all abnormal transformers are obtained.

[0050] Preferably, calculating the working score of each abnormal transformer and screening out the faulty transformers according to the working scores of the abnormal transformers further includes:

[0051] Sort all abnormal transformers in descending order according to the working scores, and screen out the top N abnormal transformers; record the top N abnormal transformers as faulty transformers;

[0052] Suspend the operation of the faulty transformer and issue a warning.

[0053] On the other hand, the present application also provides a transformer intelligent monitoring and fault warning system, including:

[0054] An acquisition component, which acquires the working data of the transformer through the acquisition component;

[0055] A processing component, the processing component includes a processing unit and a data unit, processes the working data of the transformer through the data unit, and executes the transformer intelligent monitoring and fault warning method as described in any one of the foregoing through all processing units in combination with the processing results.

[0056] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0057] By setting acquisition parameters, respectively acquiring the working data of different acquisition targets of multiple transformers according to the acquisition parameters, and preprocessing all the working data to obtain preprocessed data, then calculating the qualification rate of each transformer based on the preprocessed data, screening out abnormal transformers according to the qualification rate of the transformers, and finally calculating the working score of each abnormal transformer and screening out faulty transformers according to the working score of the abnormal transformers. This application can detect multiple transformers simultaneously and screen out faulty transformers from multiple transformers based on the working scores of the transformers. Since the working scores are calculated based on different detection items of the transformers and each detection item has a corresponding weight coefficient, this application can focus on different detection items to screen out faulty transformers in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a schematic flowchart of a method for intelligent monitoring and fault warning of transformers proposed by the present invention;

[0059] Figure 2 is a schematic structural diagram of a system for intelligent monitoring and fault warning of transformers proposed by the present invention.

[0060] Reference numerals: 100, acquisition component; 200, processing component; 201, processing unit; 202, data unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] Example 1, as Figure 1 shown, a method for intelligent monitoring and fault warning of transformers proposed by the present invention includes:

[0062] S100, setting acquisition parameters, and respectively acquiring the working data of different acquisition targets of multiple transformers according to the acquisition parameters;

[0063] S200, preprocessing all the working data to obtain preprocessed data;

[0064] S300, calculating the qualification rate of each transformer based on the preprocessed data, and screening out abnormal transformers according to the qualification rate of the transformers;

[0065] S400, calculating the working score of each abnormal transformer and screening out faulty transformers according to the working score of the abnormal transformers.

[0066] In the present invention, by setting acquisition parameters, the working data of different acquisition targets of multiple transformers are respectively acquired according to the acquisition parameters, and all the working data are preprocessed to obtain preprocessed data. Then, the qualification rate of each transformer is calculated based on the preprocessed data, the abnormal transformers are screened out according to the qualification rate of the transformers, and finally, the working score of each abnormal transformer is calculated, and the faulty transformers are screened out according to the working scores of the abnormal transformers. This application can detect multiple transformers simultaneously and screen out the faulty transformers from multiple transformers based on the working scores of the transformers. Since the working scores are calculated based on different detection items of the transformers, and each detection item has a corresponding weight coefficient, this application can focus on different detection items to screen out the faulty transformers in a timely manner.

[0067] In an optional embodiment, the S100 includes:

[0068] S110, creating a working data table;

[0069] S120, selecting a transformer and respectively setting acquisition parameters for each acquisition target of the transformer; the acquisition targets include transformer temperature data, transformer voltage data, and transformer oil quality data groups, and the acquisition parameters include acquisition period and acquisition frequency;

[0070] Specifically, the types of acquisition targets of the transformer can be adjusted according to the detection items of the transformer. Each acquisition target corresponds to a detection item of the transformer. The more detection items the transformer has, the more acquisition targets the transformer has;

[0071] S130, respectively acquiring the working data of multiple acquisition targets according to the acquisition parameters of each acquisition target of the transformer, thereby obtaining multiple sub-data groups, and putting the multiple sub-data groups into the working data table;

[0072] Specifically, since each acquisition target corresponds to a detection item of the transformer, each sub-data group contains the same type of detection data. That is, for transformer A, if transformer A includes sub-data group A-1, sub-data group A-2, and sub-data group A-3, then the working data contained in sub-data group A-1 are the transformer temperature data at different acquisition nodes, the working data contained in sub-data group A-2 are the transformer voltage data at different acquisition nodes, and the working data contained in sub-data group A-3 are the transformer oil quality data at different acquisition nodes;

[0073] S140, returning to step S120 until all the transformers are selected, and obtaining the working data of each transformer.

[0074] It should be noted that this application monitors multiple transformers on a transmission line simultaneously. Therefore, when collecting the data of the transformers, it is necessary to collect the working data of multiple transformers at the same time, so as to facilitate the calculation of the working scores of multiple transformers, and finally screen out the faulty transformers according to the working scores of the transformers.

[0075] In order to ensure that the working data of multiple transformers has sufficient credibility, when setting the acquisition parameters, it should be ensured that the acquisition parameters for the same acquisition target between different transformers are as consistent as possible, so as to ensure that the working data of the same acquisition target of different transformers is comparable to each other, thus facilitating the subsequent calculation of the working scores of different transformers.

[0076] In an optional embodiment, the S200 includes:

[0077] S210, randomly select a transformer and all its working data from the working data table;

[0078] S220, select a sub-data group from all the working data of this transformer, and judge whether there is corresponding acquisition data for each acquisition node of this sub-data group;

[0079] S230, if there is no corresponding acquisition data for an acquisition node in this sub-data group, then mark the acquisition node before the acquisition node with corresponding acquisition data as a missing node;

[0080] S240, copy the acquisition data corresponding to any acquisition node adjacent to the missing node to the missing node to fill the missing node;

[0081] S250, if there is corresponding acquisition data for each acquisition node of this sub-data group, then return to step S220 until all the sub-data groups of this transformer have been selected, and obtain the preprocessed data of this transformer;

[0082] S260, return to step S210 until all the transformers have been selected, and obtain the preprocessed data of all the transformers.

[0083] It should be noted that during the process of collecting the working data of the transformers, there may be a situation of missed collection, resulting in missing working data. If the missing data cannot be supplemented in time, it may affect the subsequent calculation of the working scores of the transformers.

[0084] In an optional embodiment, after the S230, it further includes:

[0085] S231, set a missing threshold;

[0086] S232, judge whether the number of missing nodes of this sub-data group is greater than or equal to the missing threshold;

[0087] S233. If the number of missing nodes in the sub - data group is greater than or equal to the missing threshold, the transformer corresponding to the sub - data group is recorded as a faulty transformer.

[0088] It should be noted that if there are multiple missing nodes in a sub - data group, it may be that the acquisition component corresponding to the sub - data group is damaged or the transformer corresponding to the sub - data group has a fault. In either case, a warning needs to be issued for the transformer.

[0089] In an alternative embodiment, the S300 includes:

[0090] S310. Select a transformer and all its pre - processed data.

[0091] S320. Select a sub - data group and calculate its average value.

[0092] S330. Set a qualified range based on the average value of each sub - data group.

[0093] S340. Determine whether each working data of the sub - data group is within the qualified range.

[0094] S350. If each working data of the sub - data group is within the qualified range, the sub - data group is qualified.

[0095] S360. Return to select a sub - data group until all sub - data groups of the transformer have been selected, and calculate the qualification rate of the sub - data groups of the transformer.

[0096] S370. Return to select a transformer and all its pre - processed data until all transformers have been selected, and obtain the qualification rate of each transformer.

[0097] It should be noted that when performing step S330, the average value of the sub - data group can be used as a reference, and a deviation of 20% can be used as the deviation threshold to obtain the qualified range of the sub - data group. Since the working data of the transformer is in a relatively stable state during operation, if the working data of a sub - data group is not within the qualified range of the sub - data group, it means that there may be an abnormality in the detection item corresponding to the sub - data group. If there are abnormalities in the detection items corresponding to multiple sub - data groups of a transformer, it will result in a low qualification rate of the transformer, and it can be initially determined that the transformer is an abnormal transformer.

[0098] In an alternative embodiment, the S300 further includes:

[0099] S380. Select all transformers.

[0100] S390, sort all the transformers in ascending order according to their qualification rates, and select the top M transformers; mark the top M transformers as abnormal transformers.

[0101] It should be noted that the larger the value of M is set, the more the number of abnormal transformers will be;

[0102] After calculating the qualification rate of each transformer, by selecting the top M transformers with lower qualification rates, since the qualification rates of these M transformers are the lowest, the probability of problems occurring in these M transformers is the greatest. Therefore, these transformers are marked as abnormal transformers to facilitate determining whether the abnormal transformers have actually failed through subsequent steps.

[0103] In an optional embodiment, before the S400, it includes:

[0104] K100, obtain the historical data of multiple transformers; the historical data of each transformer includes multiple historical sub-data groups;

[0105] K200, select a historical sub-data group from the historical data of multiple transformers and calculate the average value of this historical sub-data group;

[0106] K300, return to select a historical sub-data group from the historical data of multiple transformers until the average value of each historical sub-data group is obtained;

[0107] K400, perform normalization processing on the average values of all historical sub-data groups to obtain the normalized average value, and record the normalized average value as the score of the sub-data group;

[0108] Specifically, normalization is to scale the data to a specific range, usually to eliminate the influence of data of different magnitudes on model training and prediction. Normalization can improve the performance of the model, accelerate the training speed of the model, and improve the accuracy of the model.

[0109] It should be noted that before calculating the working score of the transformer through Formula 1, it is necessary to first determine the score of each acquisition target of the transformer, and then the working score of the transformer can be calculated in combination with the score of the acquisition target and the weight coefficient of the acquisition target. The reason for selecting the historical average value of the acquisition target as the scoring standard of the acquisition target is to ensure that the real-time collected working data is referenceable relative to the historical working data.

[0110] In an optional embodiment, the S400 includes:

[0111] S410, select an abnormal transformer and all the preprocessed data of this abnormal transformer;

[0112] S420, set corresponding weight coefficients for each sub - data group included in the pre - processed data;

[0113] S430, calculate the working score of the abnormal transformer through formula 1 in combination with the weight coefficients of the sub - data groups;

[0114] Formula 1;

[0115] Among them, is the working score of the abnormal transformer, is the score of the i - th sub - data group of the abnormal transformer, is the historical score of the i - th sub - data group of the abnormal transformer, is the weight coefficient of the i - th abnormal sub - data group, is the total number of sub - data groups;

[0116] Specifically, when calculating the score of the i - th sub - data group of the abnormal transformer, first calculate the average value of this sub - data group and then perform normalization to obtain the score of the sub - data group;

[0117] Since the weight coefficients can be freely adjusted, the key detection items for transformer fault detection can be adjusted by adjusting the magnitudes of the weight coefficients. The larger the weight coefficient corresponding to the acquisition target, the more emphasis is placed on the detection item corresponding to this acquisition target;

[0118] S440, return to step S410 until the working scores of all abnormal transformers are obtained.

[0119] It should be noted that through the foregoing embodiments, M abnormal transformers with relatively low qualification rates are determined from multiple transformers. In order to further find the faulty transformers with faults from the abnormal transformers, calculate the working score of each abnormal transformer through formula 1, and use the working score as the basis for evaluating whether the abnormal transformer is normal.

[0120] The working score is composed of the scores of each sub - data group of the transformer. Therefore, the working score can reflect whether the transformer is working normally. The higher the working score, the further the abnormal transformer is from the normal working state of the transformer, that is, the greater the possibility of a fault.

[0121] Since weight coefficients can be set for each sub - data group, different weights are assigned to different acquisition targets, enabling different detection items to be emphasized when checking transformer faults. For example, the acquisition targets of a transformer are transformer temperature data, transformer voltage data, and transformer oil quality data respectively, and the corresponding weights for each acquisition target are 1.0, 1.0, and 2.0 in sequence. Then it can be seen that in this transformer fault check, the acquisition target mainly targeted is the transformer oil quality data. Since the weight coefficient corresponding to the transformer oil quality data is relatively high, as long as there is a slight abnormal value in the transformer oil quality data, it will cause the working score of the transformer to increase rapidly, thus making it easier to find the transformer with faults in the transformer oil quality data.

[0122] In an optional embodiment, the S400 further includes:

[0123] S450, sort all abnormal transformers in descending order of the working score, and screen out the top N abnormal transformers; mark the top N abnormal transformers as faulty transformers;

[0124] S460, suspend the operation of the faulty transformers and issue a warning.

[0125] It should be noted that the working score of each abnormal transformer is calculated through Formula 1. Since the larger the working score, the greater the probability that the abnormal transformer has problems in this detection. Therefore, N abnormal transformers with higher working scores are screened out, these N abnormal transformers are marked as faulty transformers, and the operation of the faulty transformers is suspended.

[0126] In this application, by first detecting the qualification rate of each transformer, M abnormal transformers with lower qualification rates are initially screened out from multiple transformers. Then, the working scores of the M abnormal transformers are calculated, and the working score is used as the criterion for judging whether the transformer is working properly, so as to screen out N faulty transformers with higher working scores. After detecting the faulty transformers, the operation of the faulty transformers is suspended and a warning is issued. By double - detecting the transformers, the possibility of missed judgment and misjudgment during transformer detection is reduced.

[0127] This application also provides a transformer intelligent monitoring and fault warning system, including an acquisition component 100 and a processing component 200.

[0128] The working data of the transformer is collected through the acquisition component 100. The processing component 200 includes a processing unit 201 and a data unit 202. The working data of the transformer is processed through the data unit 202, and the processing unit 201 executes the transformer intelligent monitoring and fault warning method described in Embodiment 1 for the transformer in combination with the processing result;

[0129] Specifically, in this application, multiple transformers are detected simultaneously. Therefore, at least one corresponding acquisition component 100 is provided for each transformer.

[0130] It should be noted that the working data of multiple transformers are collected by the acquisition component 100. Since the acquisition component 100 is communicatively connected to the processing component, the collected working data can be transmitted to the processing component 200. Then, the processing component 200 combines the working data of multiple transformers to screen out the faulty transformers and issue a warning.

[0131] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made without departing from the spirit of the present invention within the scope of knowledge possessed by those skilled in the art to which the present invention pertains.

Claims

1. A transformer intelligent monitoring and fault early warning method, characterized in that: include: Set acquisition parameters, and respectively acquire working data of different acquisition targets of multiple transformers according to the acquisition parameters; Preprocess all working data to obtain preprocessed data; Calculate the qualified rate of each transformer based on the preprocessed data, and screen out abnormal transformers according to the qualified rate of the transformers; Calculate the working score of each abnormal transformer, and screen out the faulty transformers according to the working scores of the abnormal transformers; Select an abnormal transformer and all preprocessed data of the abnormal transformer; Setting a corresponding weight coefficient for each sub-data group included in the preprocessed data; The working score of the abnormal transformer is calculated by combining the weight coefficient of the sub-data group through formula 1; Formula 1; in, is the working score of the abnormal transformer, is the score of the ith sub-dataset of the anomaly transformer, is the historical score of the i-th sub-data group of the anomaly transformer, is the weight coefficient of the abnormal i-th sub-data group, is the total number of sub-data groups; Return and select an abnormal transformer and all preprocessed data of the abnormal transformer until the working scores of all abnormal transformers are obtained.

2. A transformer intelligent monitoring and fault early warning method according to claim 1, characterized in that: Set the acquisition parameters and collect the working data of different acquisition targets of multiple transformers according to the acquisition parameters, including: Create a work data table; A transformer is selected, and collection parameters are set for each collection target of the transformer; the collection targets include transformer temperature data, transformer voltage data, and transformer oil quality data, and the collection parameters include collection period and collection frequency; According to the acquisition parameters of each acquisition target of the transformer, the working data of multiple acquisition targets are respectively acquired, thereby obtaining multiple sub-data groups, and the multiple sub-data groups are put into the working data table; Return to select a transformer until all transformers are selected and the working data of each transformer is obtained.

3. A transformer intelligent monitoring and fault early warning method according to claim 2, characterized in that: All working data are preprocessed to obtain preprocessed data, including: Randomly select a transformer and all the working data of the transformer from the working data table; Select a sub-data group from all the working data of the transformer, and determine whether each acquisition node of the sub-data group has corresponding acquisition data; If there is no corresponding collected data under the collection node of the sub-data group, the collection node with corresponding collected data will be recorded as a missing node; Copy the collected data corresponding to any collection node adjacent to the missing node to the missing node to fill the missing node; If each acquisition node of the sub-data group has corresponding acquisition data, then return to select a sub-data group from all the working data of the transformer until all the sub-data groups of the transformer are selected to obtain the pre-processed data of the transformer; Return to randomly select a transformer and all the working data of the transformer from the working data table until all transformers are selected to obtain the preprocessing data of all transformers.

4. A transformer intelligent monitoring and fault early warning method according to claim 3, characterized in that: After the step of marking the acquisition node with corresponding acquisition data as a missing node if there is an acquisition node in the sub-data group but no corresponding acquisition data, the method further includes: Set missing threshold; Determine whether the number of missing nodes in the sub-data group is greater than or equal to a missing threshold; If the number of missing nodes in the sub-data group is greater than or equal to the missing threshold, the transformer corresponding to the sub-data group is recorded as a faulty transformer.

5. A transformer intelligent monitoring and fault early warning method according to claim 4, characterized in that: The qualified rate of each transformer is calculated based on the preprocessed data, and abnormal transformers are screened out according to the qualified rate of the transformers, including: Select a transformer and all preprocessed data of the transformer; Select a sub-data group; Set eligibility thresholds; Determine whether each working data of the sub-data group is greater than or equal to a qualified threshold; If each working data of the sub-data group is greater than or equal to the qualified threshold, the sub-data group is qualified; Return to select a sub-data group until all sub-data groups of the transformer are selected, and calculate the qualified rate of the sub-data groups of the transformer; Return to select a transformer and all pre-processed data of the transformer until all transformers are selected and the qualified rate of each transformer is obtained.

6. A transformer intelligent monitoring and fault early warning method according to claim 5, characterized in that: The qualified rate of each transformer is calculated based on the preprocessed data, and abnormal transformers are screened out according to the qualified rate of the transformers. It also includes: Select all transformers; All transformers are sorted from small to large according to the qualified rate of the transformers, and the transformers in the first M are screened out; the first M transformers are recorded as abnormal transformers.

7. A transformer intelligent monitoring and fault early warning method according to claim 6, characterized in that: Before calculating the working score of each abnormal transformer and screening out the faulty transformer according to the working score of the abnormal transformer, the following steps are included: Acquire historical data of multiple transformers; each historical data of a transformer includes multiple historical sub-data groups; Select a historical sub-data group from the historical data of multiple transformers, and calculate the average value of the historical sub-data group; Return and select a historical sub-data group from the historical data of multiple transformers until the average value of each historical sub-data group is obtained; The average values ​​of all historical sub-data groups are normalized to obtain a normalized average value, which is recorded as the score of the sub-data group.

8. A transformer intelligent monitoring and fault early warning method according to claim 7, characterized in that: Calculate the working score of each abnormal transformer, and screen out the faulty transformers according to the working scores of the abnormal transformers, and also include: All abnormal transformers are sorted in descending order according to the work scores, and the top N abnormal transformers are selected; the top N abnormal transformers are recorded as faulty transformers; Suspend the operation of the faulty transformer and issue an early warning.

9. A transformer intelligent monitoring and fault warning system, characterized in that: include: A collection component, through which the working data of the transformer is collected; A processing component, wherein the processing component includes a processing unit and a data unit, and the working data of the transformer is processed by the data unit, and the transformer intelligent monitoring and fault warning method as described in any one of claims 1 to 8 is executed on the transformer by the processing unit in combination with the processing result.

Images