A multi-dimensional transformer fault diagnosis and condition assessment system and method

Abstract

The application provides a multi-dimensional transformer fault diagnosis and state evaluation system and method, and belongs to the technical field of transformer fault diagnosis.The multi-dimensional transformer fault diagnosis and state evaluation system comprises a receiving module, a classification module, a diagnosis module, an analysis module and an evaluation module.The receiving module is used for receiving historical operation parameters of the transformer uploaded by a user and analyzing fault characteristic parameter frequencies.The classification module is used for receiving current operation parameters of the transformer and extracting suspected category characteristic parameters.The diagnosis module is used for comparing the suspected category characteristic parameters with the fault characteristic parameter frequencies to determine fault category characteristic parameters.The analysis module is used for determining fault levels of the fault category characteristic parameters.The application comprehensively judges the health state of the transformer, thereby comprehensively evaluating the fault of the transformer, so that maintenance personnel can formulate corresponding maintenance measures.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of transformer fault diagnosis, and in particular relates to a multi-dimensional transformer fault diagnosis and state evaluation system and method. BACKGROUND

[0002] As one of the key pivotal devices in the power system, the transformer is uninterruptedly operated in the power system, and its own operation state directly affects the safe and stable operation of the entire power system. When the transformer has a serious operation condition without taking effective measures in time, it may cause fire, explosion, and even lead to large-area power outage accidents. Therefore, when the transformer fails, through the fault diagnosis technology, the fault type of the transformer can be accurately judged, which can facilitate the staff to take corresponding maintenance measures in time, reduce the fault loss, and avoid the expansion of the accident, which is of great significance.

[0003] At present, in the process of transformer fault diagnosis, the conventional way is to collect operation parameters and judge whether the transformer has a fault by concentrating the operation parameters. For this way, the diagnosis process is not only relatively cumbersome, but also relatively slow, which is easy to occupy a large amount of diagnosis time, leading to the fault information with hysteresis, which is not conducive to the operation safety of the transformer. SUMMARY

[0004] The embodiment of the present application provides a multi-dimensional transformer fault diagnosis and state evaluation system and method, which aims to solve the problem of existing fault information hysteresis caused by collecting operation parameters and judging whether the transformer has a fault by concentrating the operation parameters.

[0005] In view of the above problems, the technical scheme provided by the present application is:

[0006] In a first aspect, a multi-dimensional transformer fault diagnosis and state evaluation system, the fault diagnosis and state evaluation system comprises:

[0007] A receiving module for receiving historical operation parameters of the transformer uploaded by a user and analyzing fault characteristic parameter frequencies;

[0008] A classification module for receiving current operation parameters of the transformer and extracting suspected category characteristic parameters;

[0009] A diagnosis module for comparing the suspected category characteristic parameters with the fault characteristic parameter frequencies to determine fault category characteristic parameters;

[0010] An analysis module for determining the fault level of the fault category characteristic parameters;

[0011] an evaluation module configured to determine a fault type and a credible health state value of the fault category feature parameter, and generate a visual chart of the fault type, the fault level and the credible health state value.

[0012] As a preferred technical solution of the present application, the receiving module comprises:

[0013] an identifying unit configured to identify a fault feature parameter in historical operation parameters of the transformer after receiving the historical operation parameters uploaded by a user;

[0014] a statistical unit configured to count a fault frequency of the fault feature parameter to obtain a fault feature parameter frequency;

[0015] a first labeling unit configured to create a first semantic keyword / word for the fault feature parameter frequency, label the fault feature parameter frequency with a level label, and associate the first semantic keyword / word with the level label.

[0016] As a preferred technical solution of the present application, the historical operation parameters comprise voltage parameters, current parameters, oil temperature parameters, chromatographic parameters, sound wave parameters, vibration parameters and temperature parameters.

[0017] As a preferred technical solution of the present application, the classification module comprises:

[0018] a receiving unit configured to receive current operation parameters of the transformer and classify to obtain initial category feature parameters;

[0019] a first judging unit configured to judge whether the initial category feature parameters are within a preset threshold interval corresponding to the initial category feature parameters.

[0020] As a preferred technical solution of the present application, the classification module further comprises a creating unit configured to extract suspected category feature parameters and create a second semantic keyword / word if the initial category feature parameters are outside the preset threshold interval corresponding to the initial category feature parameters.

[0021] As a preferred technical solution of the present application, the diagnosis module comprises:

[0022] a first comparing unit configured to compare the second semantic keyword / word with the first semantic keyword / word to obtain a first comparison similarity;

[0023] a second comparing unit configured to compare the suspected category feature parameters with the fault feature parameter frequency based on the first comparison similarity to obtain a second comparison similarity;

[0024] a processing unit configured to apply a first weight to the second comparison similarity to obtain a first confidence degree;

[0025] a second judging unit configured to judge whether the first confidence degree is in a first preset confidence interval, and if so, determine the suspected category characteristic parameter as a fault category characteristic parameter.

[0026] As a preferred technical solution of the present application, the analysis module comprises:

[0027] a third comparing unit configured to compare the fault category characteristic parameter with a corresponding characteristic parameter threshold to obtain a comparison result;

[0028] a first determining unit configured to determine a fault level of the fault category characteristic parameter according to the comparison result.

[0029] As a preferred technical solution of the present application, the evaluation module comprises:

[0030] a calculating unit configured to calculate an initial health state value of the fault category characteristic parameter based on the fault level;

[0031] a weighting unit configured to give a weight to the initial health state value based on the level label to obtain a comprehensive health state value;

[0032] a third judging unit configured to judge whether the comprehensive health state value is in a second preset confidence interval.

[0033] As a preferred technical solution of the present application, the evaluation module further comprises a second determining unit configured to determine a fault type according to the fault category characteristic parameter, if the comprehensive health state value is in the second preset confidence interval, determine the comprehensive health state value as a credible health state value, and generate a visual chart of the fault type, the fault level and the credible health state value.

[0034] In a second aspect, an embodiment of the present application provides a multi-dimensional transformer fault diagnosis and state evaluation method, which comprises the following steps:

[0035] S1, receiving historical operation parameters of the transformer uploaded by a user and analyzing fault characteristic parameter frequencies;

[0036] S2, receiving current operation parameters of the transformer and extracting suspected category characteristic parameters;

[0037] S3, comparing the suspected category characteristic parameters with the fault characteristic parameter frequencies to determine fault category characteristic parameters;

[0038] S4, determining a fault level of the fault category characteristic parameter;

[0039] S5, determine the fault type and the credible health state value of the fault category characteristic parameter, and generate a visual chart of the fault type, the fault level and the credible health state value.

[0040] The above technical solution provided by the embodiment of the present application has at least the following beneficial effects:

[0041] (1) The current operation parameter is pre-sorted to obtain the suspected category characteristic parameter, then the suspected category characteristic parameter is diagnosed, and after weighted processing, the fault category characteristic parameter can be further determined, which can be used as a basis for judging whether there is a fault, not only can accelerate the diagnosis speed, but also can guarantee the accuracy of diagnosis.

[0042] (2) The health state of the transformer is comprehensively judged, so that the fault of the transformer can be comprehensively evaluated, so that the maintenance personnel can formulate corresponding maintenance measures.

[0043] The above description is only a summary of the technical solution of the present application, in order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 is a structural schematic diagram of a multi-dimensional transformer fault diagnosis and state evaluation system disclosed by the present application;

[0045] Figure 2 is a flow chart of a multi-dimensional transformer fault diagnosis and state evaluation method disclosed by the present application.

[0046] Explanation of reference numerals: 100, receiving module; 110, identification unit; 120, statistical unit; 130, first label unit; 200, classification module; 210, receiving unit; 220, first judgment unit; 230, creation unit; 300, diagnosis module; 310, first comparison unit; 320, second comparison unit; 330, processing unit; 340, second judgment unit; 400, analysis module; 410, third comparison unit; 420, first determination unit; 500, evaluation module; 510, calculation unit; 520, weighting unit; 530, third judgment unit; 540, second determination unit. DETAILED DESCRIPTION

[0047] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0048] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0049] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0050] Embodiment one

[0051] Referring to the drawings shown in the accompanying drawings, Figure 1 The present application provides a technical solution: a multi-dimensional transformer fault diagnosis and state evaluation system, the fault diagnosis and state evaluation system comprises:

[0052] A receiving module 100 for receiving historical operating parameters of the transformer uploaded by a user and analyzing fault characteristic parameter frequencies;

[0053] A classification module 200 for receiving current operating parameters of the transformer and extracting suspected category characteristic parameters;

[0054] A diagnosis module 300 for comparing and determining fault category characteristic parameters by comparing the suspected category characteristic parameters with the fault characteristic parameter frequencies;

[0055] An analysis module 400 for determining fault levels of the fault category characteristic parameters;

[0056] An evaluation module 500 for determining fault types and credible health state values of the fault category characteristic parameters, and generating a visual chart of the fault types, the fault levels and the credible health state values.

[0057] Specifically, the application firstly obtains a plurality of fault characteristic parameter frequencies according to historical operation parameters and archives them; wherein one fault type corresponds to one fault characteristic parameter frequency. Upon receiving the current operation parameters transmitted by the transformer each time, the suspected category characteristic parameters are screened out; that is, the current operation parameters are pre-sorted, which can not only avoid repeated comparison, but also improve the comparison speed.

[0058] Then, the suspected category characteristic parameters are diagnosed, that is, the suspected category characteristic parameters are compared with the fault characteristic parameter frequencies of the same type of fault, and after weighted processing, the fault category characteristic parameters can be further determined, which can be used as a basis for judging whether there is a fault, so as to guarantee the accuracy of the diagnosis.

[0059] Finally, based on historical factors, the health status of the transformer can be comprehensively judged, that is, the fault category characteristic parameters and the fault characteristic parameter frequencies of the same type of fault are used to finally obtain a reliable health status value.

[0060] Further, the receiving module 100 comprises:

[0061] The identification unit 110 is configured to identify the fault characteristic parameters in the historical operation parameters after receiving the historical operation parameters of the transformer uploaded by the user; wherein the historical operation parameters include voltage parameters, current parameters, oil temperature parameters, chromatographic parameters, sound wave parameters, vibration parameters and temperature parameters.

[0062] The statistical unit 120 is configured to count the fault frequency of the fault characteristic parameters to obtain the fault characteristic parameter frequency.

[0063] The first labeling unit 130 is configured to create a first semantic keyword / word for the fault characteristic parameter frequency, mark a level label for the fault characteristic parameter frequency, and associate the first semantic keyword / word with the level label.

[0064] Specifically, the historical operation parameters include seven different types of characteristic parameters, each type has a corresponding fault characteristic parameter; for example, the voltage parameter has a fault characteristic parameter indicating its own fault. The fault characteristic parameter frequency refers to the total number of faults of each type of fault characteristic parameter. In the process of marking the level label, according to the preset rule, according to which frequency interval the fault characteristic parameter frequency is in, the labels with green, yellow and red colors are given respectively; for example, the green label corresponds to level one, the yellow label corresponds to level two and the red label corresponds to level three.

[0065] Further, the classification module 200 comprises:

[0066] a receiving unit 210 configured to receive current operation parameters of the transformer and classify to obtain initial category characteristic parameters;

[0067] a first judging unit 220 configured to judge whether the initial category characteristic parameters are within corresponding preset threshold intervals;

[0068] a creating unit 230 configured to extract suspected category characteristic parameters and create second semantic keywords / words if the initial category characteristic parameters are outside the corresponding preset threshold intervals.

[0069] Specifically, the initial category characteristic parameters also have seven types and one-to-one correspond to the seven types of historical operation parameters. The initial category characteristic parameters are analyzed one by one according to the current operation parameters transmitted by the transformer, and the suspected category characteristic parameters are finally determined, so that real-time monitoring can be realized and the maintenance efficiency of the transformer can be improved.

[0070] Further, the diagnosis module 300 comprises:

[0071] a first comparing unit 310 configured to compare the second semantic keywords / words with the first semantic keywords / words to obtain a first comparison similarity;

[0072] a second comparing unit 320 configured to compare the suspected category characteristic parameters with the fault characteristic parameter frequency based on the first comparison similarity to obtain a second comparison similarity;

[0073] a processing unit 330 configured to apply a first weight to the second comparison similarity to obtain a first confidence degree;

[0074] a second judging unit 340 configured to judge whether the first confidence degree is within a first preset confidence interval, and if so, determine the suspected category characteristic parameters as fault category characteristic parameters.

[0075] Specifically, the first comparison similarity meets the requirements before the second comparison similarity is compared, which not only avoids errors in fault comparison, but also saves comparison time and improves the monitoring ability of the transformer. At the same time, the second comparison similarity is weighted processed to ensure that the second comparison similarity is more reliable, so that the fault judgment of the transformer is more accurate.

[0076] Further, the analysis module 400 comprises:

[0077] a third comparing unit 410 configured to compare the fault category characteristic parameters with corresponding characteristic parameter thresholds to obtain a comparison result;

[0078] a first determining unit 420 configured to determine a fault level of the fault category characteristic parameters according to the comparison result.

[0079] Specifically, each type of feature parameter threshold has different threshold intervals, the threshold intervals are in order and correspond to the fault levels one by one; by comparing the results to determine which threshold interval is specifically fallen into, the specific fault level can be finally determined, thereby providing convenience for health state assessment.

[0080] Further, the evaluation module 500 comprises:

[0081] A calculation unit 510, configured to calculate an initial health state value of the fault category feature parameter based on the fault level;

[0082] A weighting unit 520, configured to give a weight to the initial health state value based on the level label, to obtain a comprehensive health state value;

[0083] A third judging unit 530, configured to judge whether the comprehensive health state value is in a second preset confidence interval;

[0084] A second determining unit 540, configured to determine a fault type according to the fault category feature parameter, if the comprehensive health state value is in the second preset confidence interval, determine the comprehensive health state value as a credible health state value, and generate a visual chart of the fault type, the fault level and the credible health state value.

[0085] Specifically, according to the fault level, an initial health state value is first determined, and then a comprehensive health state value is determined in combination with the historical level label, so that the fault of the transformer can be comprehensively evaluated to enable the maintenance personnel to formulate corresponding maintenance measures; and the comprehensive health state value is further processed, so that the comprehensive health state value is more credible.

[0086] It should be noted that the first semantic keyword / word and the second semantic keyword / word both refer to a semantic keyword or a semantic keyword.

[0087] Embodiment Two

[0088] The embodiment of the present application also discloses a multi-dimensional transformer fault diagnosis and state assessment method, referring to the accompanying drawings Figure 2 The fault diagnosis and state assessment method comprises the following steps:

[0089] S1, receiving the historical operation parameters of the transformer uploaded by a user and analyzing fault feature parameter frequency;

[0090] S2, receiving the current operation parameters of the transformer and extracting suspected category feature parameters;

[0091] S3, determining a fault category characteristic parameter by matching the suspected category characteristic parameter with the fault characteristic parameter frequency;

[0092] S4, determining a fault level of the fault category characteristic parameter;

[0093] S5, determining a fault type and a credible health state value of the fault category characteristic parameter, and generating a visual chart of the fault type, the fault level and the credible health state value.

[0094] It should be understood that the particular order or hierarchy of steps in the processes disclosed is an example that can be re-arranged as desired. The particular order or hierarchy of steps in the processes disclosed should not be interpreted as reflecting a preference or requiring a particular order among steps for the purposes of the disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy presented.

[0095] In the above detailed description, various features are grouped together in single embodiments for the purpose of streamlining the disclosure. This disclosed approach is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are explicitly recited in each claim. Rather, as the claims below reflect, inventive subject matter can lie in fewer than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate preferred embodiment of the present application.

[0096] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0097] The steps of a method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium can reside as discrete components in a user terminal.

[0098] For a software implementation, the techniques described herein can be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes can be stored in memory units and executed by processors. The memory unit can be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.

[0099] The above description includes one or more examples of the embodiments. Of course, not all possible combinations of components or methods described above can be claimed as embodiments. One of ordinary skill in the art can recognize that modifications and variations of the described embodiments can be made without departing from the scope of the present disclosure. It is therefore intended that the embodiments described herein be considered in all respects as illustrative and not restrictive, particularly as numerous modifications and further embodiments can become apparent to those skilled in the art. Accordingly, the scope of the present disclosure is intended to be defined by the following claims rather than the description. Moreover, the use of the term "or" in the claims is meant to encompass both "and" and "or" unless specifically stated otherwise.

Claims

1. A multi-dimensional transformer fault diagnosis and condition assessment system, characterized in that, The fault diagnosis and condition assessment system includes: A receiving module is used to receive historical operating parameters of the transformer uploaded by the user and analyze the frequency of fault characteristic parameters. The receiving module includes: an identification unit, used to identify fault characteristic parameters in the historical operating parameters after receiving them; a statistics unit, used to count the fault frequencies of the fault characteristic parameters to obtain the frequency of the fault characteristic parameters; and a first tagging unit, used to create a first semantic keyword / word for the frequency of the fault characteristic parameters, simultaneously tag the frequency of the fault characteristic parameters with a level tag, and associate the first semantic keyword / word with the level tag. A classification module is used to receive the current operating parameters of the transformer and extract suspected category feature parameters. The classification module includes: a receiving unit for receiving the current operating parameters of the transformer and classifying them to obtain initial category feature parameters; a first judging unit for judging whether the initial category feature parameters are within their corresponding preset threshold range; the classification module further includes a creation unit for extracting suspected category feature parameters and creating a second semantic keyword / word if the initial category feature parameters are outside their corresponding preset threshold range. A diagnostic module is used to determine fault category feature parameters by comparing the frequency of the suspected category feature parameters with that of the fault feature parameters. The diagnostic module includes: a first comparison unit, used to compare the second semantic keyword / word with the first semantic keyword / word to obtain a first comparison similarity; a second comparison unit, used to compare the frequency of the suspected category feature parameters with that of the fault feature parameters based on the first comparison similarity to obtain a second comparison similarity; a processing unit, used to apply a first weight to the second comparison similarity to obtain a first confidence level; and a second judgment unit, used to determine whether the first confidence level is within a first preset confidence interval. If it is, the suspected category feature parameter is determined as a fault category feature parameter. An analysis module is used to determine the fault level of the fault category characteristic parameters; An evaluation module is used to determine the fault type and credible health status value of the fault category feature parameters, and to generate a visualization chart of the fault type, the fault level, and the credible health status value. The evaluation module includes: a calculation unit for calculating an initial health status value of the fault category feature parameters based on the fault level; a weighting unit for assigning weights to the initial health status value based on the level label to obtain a comprehensive health status value; and a third judgment unit for determining whether the comprehensive health status value is within a second preset confidence interval. The evaluation module also includes a second determination unit for determining the fault type based on the fault category feature parameters. If the comprehensive health status value is within the second preset confidence interval, the comprehensive health status value is determined as a credible health status value, and a visualization chart of the fault type, the fault level, and the credible health status value is generated.

2. The multi-dimensional transformer fault diagnosis and condition assessment system according to claim 1, characterized in that, The historical operating parameters include voltage parameters, current parameters, oil temperature parameters, chromatographic parameters, acoustic parameters, vibration parameters, and temperature parameters.

3. The multi-dimensional transformer fault diagnosis and condition assessment system according to claim 1, characterized in that, The analysis module includes: The third comparison unit is used to compare the fault category feature parameters with their corresponding feature parameter thresholds to obtain the comparison results. The first determining unit is used to determine the fault level of the fault category feature parameters based on the comparison results.

4. A multi-dimensional transformer fault diagnosis and condition assessment method, applied to the multi-dimensional transformer fault diagnosis and condition assessment system according to any one of claims 1 to 3, characterized in that, The fault diagnosis and condition assessment method includes the following steps: S1, Receive the historical operating parameters of the transformer uploaded by the user and analyze the frequency of fault characteristic parameters; S2, Receive the current operating parameters of the transformer and extract the suspected category feature parameters; S3, compare the frequency of the suspected category feature parameters with that of the fault feature parameters to determine the fault category feature parameters; S4, determine the fault level of the fault category characteristic parameters; S5, determine the fault type and trusted health status value of the fault category feature parameters, and generate a visualization chart of the fault type, the fault level and the trusted health status value.

Images