Transformer state comprehensive judgment method and system based on digital gas relay and medium

Abstract

The invention relates to the field of transformers, in particular to a transformer state comprehensive judgment method and system based on a digital gas relay and a medium. The invention provides a weight adaptive fuzzy recognition comprehensive state evaluation method combining an industry score deduction criterion and a wooden barrel effect on the basis of data such as temperature, pressure, gas volume and gas production rate of a digital gas relay and online monitoring data such as oil chromatography, iron core grounding current, partial discharge and vibration. And early warning of major faults is realized. The action reliability of the digital gas relay is improved, and the alarming and tripping accuracy of the gas relay is improved.

Description

Technical Field

[0001] The present invention relates to the field of transformer condition monitoring, and specifically to a method, system and medium for comprehensive judgment of transformer conditions based on a digital gas relay. Background Art

[0002] At present, the alarm strategy of the digital gas relay of the transformer is not yet perfect. Most of them use gas temperature and pressure data as the basis for action alarm, and there are many cases of misjudgment and missed judgment. In order to improve the accuracy and reliability of the gas relay gas action alarm and tripping of the transformer, a comprehensive judgment strategy for the transformer condition based on the digital gas relay is proposed. Summary of the Invention

[0003] Aiming at the defects of the prior art, the present invention provides a method, system and medium for comprehensive judgment of transformer conditions based on a digital gas relay. Based on the self-data such as temperature, pressure, gas volume, and gas production rate of the digital gas relay, combined with on-line monitoring data such as oil chromatography, core grounding current, partial discharge, and vibration, a weight adaptive fuzzy recognition comprehensive state evaluation strategy combining industry deduction criteria and the cask effect is proposed to achieve early warning of major faults. Improve the reliability of the digital gas relay action and improve the accuracy of the gas relay alarm and tripping.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for comprehensive judgment of transformer conditions based on a digital gas relay, including the following steps: S01. Data collection, collect multi-dimensional data related to the gas relay and transformer conditions, preprocess the collected multi-dimensional data, and divide the data into an index layer, an element layer, and a target layer. The index layer is the collected multi-dimensional data, the element layer is to divide the multi-dimensional data of the index layer into gas relay data, hydrocarbon gas concentration data, and transformer on-line monitoring data, and the target layer is the evaluation of the operation state of the transformer body; S02. Calculate the subjective weight, select multiple experts to score the collected data, sort the data of each layer according to the expert scores, and calculate the average value of the scoring weights of each expert to obtain the subjective weight; S03. Obtain the objective weight by calculating the conflict and comparison degree of the evaluation index; S04. Use the multiplication synthesis normalization method to calculate the combined weight; S05. Adopt the weight adaptive method of industry deduction criteria and the cask effect to conduct fuzzy recognition comprehensive state evaluation; First, comprehensively consider the equipment characteristics and data conditions, and start from the operation and maintenance guide to conduct quantitative evaluation of the equipment state to obtain an effective basic score , the effective basic score It is the product of the combined weight and the multi-dimensional data; secondly, according to the on-site measured data, considering the barrel effect for weight self-adaptation, the effective on-site score Y2 is obtained. , where A, B, and C are respectively the basic data set, the necessary data set, and the optional data set divided from the collected data. , , are respectively the barrel effect coefficients corresponding to A, B, and C; finally, the fuzzy comprehensive evaluation method is used to obtain the status score Y. , where is the weighted value highlighting the main factors. S06. Output the operating status of the transformer according to the status score.

[0005] Furthermore, in step S01, the preprocessing of the collected data includes: data cleaning to remove null value data; through user research and data obtained from actual transformer substations, the data types are divided into basic data, necessary data, and optional data; set the initial values of each index and the alarm values of each level, and the initial value is the factory test value, the handover test value, the early test value, and the first test value after the disassembly and repair of the core components or the main body of the equipment.

[0006] Furthermore, the process of obtaining the subjective weight in step S02 is as follows: Construct an index set , is one dimension of the multi-dimensional data. Based on expert experience, is scored, and the index set of each level is reordered according to the expert scores. The ratio of the importance scores of adjacent indicators is used as the weight ratio of the two indicators , , to obtain the expert subjective weight , m is the number of indicators at the corresponding level, is the index The subjective weight obtained based on a certain expert's scoring. According to the recurrence relationship, the subjective weights of other indicators are obtained , to obtain the subjective weights of each indicator based on this expert's scoring , and the average value of the scoring weights of each expert is obtained to get the final subjective weight.

[0007] Furthermore, in step S03, the process of determining the objective weight is: first, dimensionless processing of the indicators. For the positive degradation index, the processing formula is: , for the negative degradation index, the processing formula is: , where is the i-th original measured data of the indicator , is the data after dimensionless processing; secondly, calculate the standard deviation of the indicator , where is the measured average value of the index ; n is the number of measured data of the index . A correlation coefficient matrix is constructed , , are two data in the index . Calculate the information content of each index, , is the information content contained in the index . The greater the information content, the greater the role of the index in the evaluation system and the greater the weight; calculate the objective weight , .

[0008] Furthermore, the combined weight , , where represents the subjective weight, represents the objective weight, and m represents the number of indices in the index set.

[0009] Furthermore, it also includes step S07: post-evaluate the comprehensive judgment result and correct the weight deviation, obtain the historical data of the equipment operation state, and correct the combined weight matrix according to the historical fault state value and maintenance data. Set , , as the deviation system weight coefficient matrices of the basic data, necessary data, and optional data layers respectively, is the deviation performance evaluation coefficient. Apply the deviation integral method to calculate the deviation of each parameter state value corresponding to the historical score value; , t represents the sampling time period, n represents the number of samplings, is the deviation term of the i-th variable, The larger it is, the smaller the cumulative error generated by the deviation correction and the better the deviation correction effect. Conversely, the deviation correction effect is worse. Establish a joint deviation correction model, and use , , as the subsystem input to obtain the joint deviation correction model and achieve joint deviation correction, , is the combined weight matrix after deviation correction.

[0010] Further, the data collected in step S01 includes temperature, pressure, gas volume, gas collection rate, gas collection rate growth rate, hydrocarbon gas concentration, iron core grounding current, partial discharge quantity, body vibration, and infrared temperature measurement. Among them, temperature, pressure, gas volume, gas collection rate, and gas collection rate growth rate are gas relay data. The hydrocarbon gas concentration includes H2 content, CH4 content, C2H4 content, C2H6 content, C2H2 content, CO content, and total hydrocarbon content. The iron core grounding current, partial discharge quantity, body vibration, and infrared temperature measurement are transformer on-line monitoring data.

[0011] Further, the transformer states output in step S06 include normal, attention, abnormal, and severe.

[0012] The present invention also discloses a comprehensive transformer state judgment system based on a digital gas relay, including a processor and a memory storing program instructions. The processor is configured to execute the comprehensive transformer state judgment method based on the digital gas relay as described above when running the program instructions.

[0013] The present invention also discloses a storage medium storing program instructions, and the program instructions execute the comprehensive transformer state judgment method based on the digital gas relay as described above when running.

[0014] Advantages of the present invention: The present invention provides a comprehensive research and judgment strategy for transformer states based on a digital gas relay. By adopting a data-driven combined weighting fuzzy evaluation technology and combining the industry deduction system and the weight self-adaptation method of the barrel effect, a research and judgment strategy for the digital gas relay is established to provide a discrimination basis for its alarm and action. The present invention takes into account the differences in oil chromatography, grounding current, partial discharge, and vibration monitoring data, preprocesses the data by normalization, and then uses a combined weighting fuzzy evaluation algorithm for comprehensive evaluation. It has the advantages of comprehensive evaluation dimensions and high accuracy. Description of the Drawings

[0015] Figure 1 It is a flowchart of the method described in Embodiment 1; Figure 2 It is a schematic diagram of the system described in Embodiment 2. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0017] This embodiment discloses a comprehensive method for judging the state of a transformer based on a digital gas relay, as Figure 1 shown, which includes the following steps: S01. Data collection: Collect multi-dimensional data related to the gas relay and the state of the transformer, preprocess the collected data, and divide the data into an index layer, a factor layer, and a target layer. The index layer is the collected multi-dimensional data, the factor layer is to divide the multi-dimensional data of the index layer into gas relay data, hydrocarbon gas concentration data, and transformer on-line monitoring data, and the target layer is the evaluation of the operating state of the transformer body.

[0018] In this embodiment, the evaluation data of the operating state of the transformer body altogether includes thermal faults, insulation faults, and mechanical faults, specifically including: inter-turn short circuit of the coil, multi-point grounding of the iron core and clamping parts, partial discharge, decomposition of gases in oil, winding deformation, overheating of the oil temperature, and abnormal mechanical vibration. Based on this, the data collected in this step includes temperature, pressure, gas volume, gas collection rate, growth rate of gas collection rate, hydrocarbon gas concentration, iron core grounding current, partial discharge amount, body vibration, and infrared temperature measurement. Among them, temperature, pressure, gas volume, gas collection rate, and growth rate of gas collection rate are gas relay data, and hydrocarbon gas concentration includes H2 content, CH4 content, C2H4 content, C2H6 content, C2H2 content, CO content, and total hydrocarbon content. The iron core grounding current, partial discharge amount, body vibration, and infrared temperature measurement are transformer on-line monitoring data.

[0019] The preprocessing of the data includes: 1. Cleaning the data to remove null values; 2. Investigating user requirements through the Kano model, and combining the actual monitoring data types on the station to divide the data types into basic data, necessary data, and optional data, and determining the requirements of users for data types and data volumes in different scenarios. 3. Setting the initial values of each index and the alarm values of each level. The initial values are the factory test values, handover test values, early test values, and the first test values after the disassembly and overhaul of the core components or the main body of the equipment, etc.

[0020] This embodiment divides the data into a target layer, a factor layer, and an index layer, specifically as follows: Target layer: Y is the evaluation of the operating state of the transformer body, and the output is normal, attention, abnormal, and serious.

[0021] Factor layer: Gas relay data A1, hydrocarbon gas concentration A2, on-line monitoring data A3.

[0022] Index layer: Temperature, pressure, gas volume, gas collection rate, growth rate of gas collection rate, hydrocarbon gas concentration, iron core grounding current, partial discharge amount, body vibration, infrared temperature measurement.

[0023] A1: B11 (temperature), B12 (pressure), B13 (gas volume), B14 (gas collection rate), B15 (growth rate of gas collection rate) A2: B21 (H2 content), B22 (CH4 content), B23 (C2H4 content), B24 (C2H6 content), B25 (C2H2 content), B26 (CO content), B27 (total hydrocarbon content) A3: B31 (iron core grounding current), B32 (tank infrared temperature measurement), B33 (partial discharge), B34 (body vibration) Determine the evaluation set V = {"normal" v1, "attention" v2, "abnormal" v3, "serious" v4}

[0024] S02. Calculate the subjective weight. Select multiple experts to score the collected data, sort the data at each level in descending order of importance, and calculate the average value of the scoring weights of each expert to obtain the subjective weight. The specific process is as follows: Construct the index set , is one dimension of the multi-dimensional data. Based on expert experience, score , and re-sort the index set at each level according to the expert scores. The ratio of the importance scores of adjacent indexes is used as the weight ratio of the two indexes , , to obtain the expert subjective weight , m is the number of indexes at the corresponding level, is the index The subjective weight obtained based on a certain expert's score. According to the recurrence relationship, the subjective weights of other indexes are obtained , to obtain the subjective weights of each index based on the score of this expert , calculate the average value of the scoring weights of each expert to obtain the final subjective weight

[0025] S03. Obtain the objective weight by calculating the conflict and comparison degree of the evaluation indexes. The specific process is as follows: First, perform dimensionless processing on the indexes. For the positive deterioration index, the processing formula is: , for the negative deterioration index, the processing formula is: , where is the index The i-th original measured data, is The data after dimensionless processing; secondly, calculate the index standard deviation , in the formula, is the index The measured average value; n is the number of measured data of the index . Construct the correlation coefficient matrix, , calculate the information content of each indicator , , is the information content contained in the indicator . The greater the information content, the greater the role and weight of the indicator in the evaluation system; calculate the objective weight , .

[0026] S04. Use the multiplication synthesis normalization method to calculate the combined weight , .

[0027] S05. Adopt the weight self - adaptation method of industry deduction criteria and the barrel effect to conduct fuzzy recognition comprehensive state evaluation

[0028] First, comprehensively consider the equipment characteristics and data conditions, and start from the operation and maintenance guidelines to conduct a quantitative evaluation of the equipment state, obtaining an effective basic score , , where represents the combined weight is the indicator set, and the elements in the indicator set are the multi - dimensional data collected in step S01

[0029] Secondly, according to the on - site measured data, that is, basic data, necessary data, and optional data, consider the barrel effect for weight self - adaptation to obtain an effective on - site score Y2. The basic data set , includes operation data A1, body high - voltage test data A2, bushing high - voltage test data A3, oil test data A4, etc.; the necessary data set is the gas relay data, including temperature B1, pressure B2, gas volume B3, gas collection rate B4, hydrocarbon gas concentration B5, etc.; the optional data set , includes core grounding current C1, partial discharge C2, dissolved gas concentration in oil C3, vibration data C4, etc. The barrel effect coefficient of each indicator is , is the deviation degree of the measured data from the rated value or normal value. The larger the value, the greater the negative or positive deviation scale .

[0030] Finally, use the fuzzy comprehensive evaluation method to establish a corresponding fuzzy evaluation model, and set corresponding weights for the indicator system of the structural model. The weight coefficient also considers the influence of the barrel effect, conduct weighted highlighting of the main factors, and obtain the state score Y , where is the weighted highlighting value of the main factor

[0031] S06. Output the operating status of the transformer according to the status score, which is divided into four types: normal, attention, abnormal, and severe. The normal status indicates that the transformer is in good condition and this evaluation ends; the attention status indicates that the transformer status is not very clear, potential hazards and faults may exist, and further detailed evaluation is required; the abnormal status indicates that potential hazards or faults may exist in the transformer and further detailed evaluation is required; the severe status indicates that some abnormal changes are occurring or have occurred inside the transformer, and it should immediately enter the fault diagnosis stage and output signals such as alarm tripping.

[0032] S07. Conduct post-evaluation and weight correction on the comprehensive judgment result. Obtain the historical data of the equipment operating status, and correct the weight system matrix according to the historical fault status values and maintenance data. Set 、 、 to be the weight coefficient matrices of the correction systems for the basic data, necessary data, and optional data layers respectively, is the correction performance evaluation coefficient. Apply the deviation integral method to calculate the deviation of the state values of each parameter corresponding to the historical score values.

[0033] , is the deviation term of the i-th variable, The larger it is, the smaller the cumulative error generated by the correction, and the better the correction effect. On the contrary, the correction effect is worse. Establish a combined correction model, and use 、 、 as the subsystem inputs to obtain the combined correction model and achieve combined correction, , is the combined weight matrix after correction.

[0034] Embodiment 2 This embodiment discloses a comprehensive transformer status judgment system based on a digital gas relay. As Figure 2 shown, it includes a processor and a memory. Optionally, the device may further include a communication interface and a bus. Among them, the processor, communication interface, and memory can complete mutual communication through the bus. The communication interface can be used for information transmission. The processor can call the logical instructions in the memory to execute the comprehensive transformer status judgment method based on the digital gas relay in the above embodiment.

[0035] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0036] The memory, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor executes functional applications and data processing by running the program instructions / modules stored in the memory, that is, implements the method for comprehensive judgment of transformer status based on a digital gas relay in the above embodiments. The memory may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory.

[0037] Embodiment 3 The embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are configured to execute the method for comprehensive judgment of transformer status based on a digital gas relay as described above.

[0038] The above computer-readable storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0039] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transient storage medium, including: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or may also be a transient storage medium.

[0040] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments only represent possible variations. Unless explicitly required, the individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and do not limit the scope of protection. As used in the description herein, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or apparatus comprising the element. Herein, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0041] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The technician can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0042] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms. The units described as separate components can be or may not be physically separated. The components displayed as units can be or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

Claims

1. A method for comprehensive determination of transformer status based on a digital gas relay, characterized in that: The following steps are involved: S01. Data collection: collect multidimensional data related to the status of gas relays and transformers, pre-process the collected multidimensional data, and divide the data into an indicator layer, an element layer, and a target layer. The indicator layer is the collected multidimensional data. The element layer divides the multidimensional data of the indicator layer into gas relay data, hydrocarbon gas concentration data, and transformer online monitoring data. The target layer is the transformer body operation status evaluation. S02. Calculate the subjective weight, select multiple experts to score the collected data, sort the data at each layer according to the expert scores, and calculate the average of the score weights of each expert to obtain the subjective weight; S03. Obtain objective weights by calculating the conflict and contrast of evaluation indicators; S04. Calculate the combination weight using the multiplication synthesis normalization method; S05. Use the weighted adaptive method of industry deduction criteria and the barrel effect to conduct fuzzy identification comprehensive status assessment; first, comprehensively consider the equipment characteristics and data conditions, and proceed from the operation and maintenance guidelines to conduct a quantitative assessment of the equipment status and obtain an effective basic score , effective basic score is the product of the combined weight and the multidimensional data; Secondly, based on the actual measured data on site, the weights are adapted considering the barrel effect to obtain the effective site score Y2. , where A, B, and C are the basic data set, necessary data set, and optional data set divided from the collected data, respectively. , , are the barrel effect coefficients corresponding to A, B, and C respectively; finally, the fuzzy comprehensive evaluation method is used to obtain the state score Y. ,in Highlight weighted values ​​for main factors; S06. Output the transformer operation status according to the status score.

2. The method for comprehensive determination of transformer status based on a digital gas relay according to claim 1 is characterized in that: In step S01, the preprocessing of the collected data includes: data cleaning, removing null value data; classifying the data types into basic data, necessary data and optional data through user surveys and data obtained at actual transformer stations; setting the initial value of each indicator and each level of alarm value. The initial value is the factory test value, the handover test value, the early test value, and the first test value after the dismantling maintenance of the core components or the main body of the equipment.

3. The method for comprehensive determination of transformer status based on a digital gas relay according to claim 1 is characterized in that: The process of obtaining the subjective weight in step S02 is: Building a Metric Set , is one dimension in multidimensional data, based on expert experience Scoring is performed and the indicator set of each level is reordered according to the expert scores. The ratio of the importance scores of adjacent indicators is used as the weight ratio of the two indicators. , , get the expert's subjective weight , m is the number of indicators at the corresponding level, For indicators Based on the subjective weight obtained by an expert's scoring, the subjective weights of other indicators are obtained according to the recursive relationship. , get the subjective weight of each indicator based on the expert's score , find the mean of the scoring weights of each expert and get the final subjective weight.

4. The method for comprehensive determination of transformer status based on a digital gas relay according to claim 1 is characterized in that: In step S03, the process of determining the objective weight is as follows: First, the indicator is dimensionless processed, and the processing formula for the positive degradation indicator is: , for the negative degradation index processing formula: ,in For indicators The i-th original measured data, for Dimensionless processed data; secondly, calculate the standard deviation of the indicator , where For indicators The measured average value; n is the index The number of measured data, construct the correlation coefficient matrix, , , For indicators Calculate the information content of each indicator using the two data in , , For indicators The amount of information contained. The greater the amount of information, the greater the role of the indicator in the evaluation system and the greater its weight; calculate the objective weight , .

5. The method for comprehensive determination of transformer status based on a digital gas relay according to claim 3 or 4, characterized in that: Combination weight , ,in represents the subjective weight, represents the objective weight, and m represents the number of indicators in the indicator set.

6. The method for comprehensive determination of transformer status based on a digital gas relay according to claim 1 is characterized in that: The step S07 is also included, post-evaluating the comprehensive judgment results and correcting the weights, obtaining the historical data of the equipment operation status, and adjusting the combined weight matrix according to the historical fault status values ​​and maintenance data. Correction, setting , , They are the weight coefficient matrices of the correction system for basic data, necessary data, and optional data layers, To evaluate the performance of deviation correction, the deviation integral method is applied to calculate the deviation of each parameter state value corresponding to the historical score value; , t represents the sampling time period, n represents the number of samples, is the deviation term of the ith variable, The larger the value, the smaller the cumulative error caused by the correction, and the better the correction effect. On the contrary, the correction effect is worse. A joint correction model is established. , , As the input of the subsystem, the joint correction model is obtained to achieve joint correction. , is the combined weight matrix after correction.

7. The method for comprehensive determination of transformer status based on digital gas relay according to claim 1 is characterized in that The data collected in step S01 include temperature, pressure, gas volume, gas collection rate, gas collection rate growth rate, hydrocarbon gas concentration, core grounding current, local discharge, body vibration, and infrared temperature measurement, among which temperature, pressure, gas volume, gas collection rate, and gas collection rate growth rate are gas relay data, hydrocarbon gas concentration includes H2 content, CH4 content, C2H4 content, C2H6 content, C2H2 content, CO content, and total hydrocarbon content, and core grounding current, local discharge, body vibration, and infrared temperature measurement are transformer online monitoring data.

8. The method for comprehensive determination of transformer status based on digital gas relay according to claim 1 is characterized in that: The transformer status output in step S06 includes normal, caution, abnormal and severe.

9. A transformer state comprehensive judgment system based on a digital gas relay, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for comprehensive transformer status judgment based on a digital gas relay as described in any one of claims 1 to 8 when running the program instructions.

10. A storage medium storing program instructions, characterized in that: When the program instructions are run, the method for comprehensive transformer status judgment based on a digital gas relay as described in any one of claims 1 to 8 is executed.

Images