Transformer short-circuit fault moment detection method, readable storage medium and program product

Abstract

The invention relates to a transformer short-circuit fault moment detection method, a readable storage medium and a program product. The method comprises the following steps: acquiring normal current data and fault current data of a target transformer; performing function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as that of the fault current data; performing difference processing on the fault current data and the standard current data to obtain a difference sequence; according to the difference value sequence, obtaining a potential fault point based on the current waveform characteristics of the normal current data and the fault current data; and based on the potential fault point, obtaining a target fault moment through a preset analysis method. The method can obtain the accurate moment when the short-circuit fault occurs in the transformer.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and particularly to a method for detecting the moment of transformer short-circuit fault, a readable storage medium, and a program product. Background Art

[0002] Currently, the detection methods for short-circuit faults mostly rely on hardware devices, such as current and voltage monitoring systems of sensors, relays, etc. The traditional monitoring system detects faults by collecting signals such as current and voltage during the operation of the transformer in real time and setting thresholds.

[0003] Traditional sensors and monitoring systems require a large number of hardware devices to support. However, due to the fact that short-circuit faults often occur rapidly, these sensors and monitoring systems usually cannot respond in time, resulting in difficulty for maintenance personnel to obtain the accurate moment when the short-circuit fault occurs in a timely manner, affecting the timeliness of locating and repairing the short-circuit fault. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method for detecting the moment of transformer short-circuit fault, a readable storage medium, and a program product that can detect the moment of transformer short-circuit fault.

[0005] In a first aspect, in one embodiment, the present application provides a method for detecting the moment of transformer short-circuit fault, the method comprising:

[0006] Obtaining normal current data and fault current data of a target transformer;

[0007] Performing function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as that of the fault current data;

[0008] Performing difference processing on the fault current data and the standard current data to obtain a difference sequence;

[0009] Based on the difference sequence, obtaining potential fault points based on the current waveform characteristics of the normal current data and the fault current data;

[0010] Based on the potential fault points, obtaining the target fault moment through a preset analysis method.

[0011] In one of the embodiments, the step of performing function fitting and data extension on the normal current data to obtain standard current data includes:

[0012] Performing sine function fitting on the normal current data to obtain a current fitting function;

[0013] Based on the current fitting function, extend the normal current data until the data length of the normal current data is the same as that of the fault current data, obtaining the standard current data.

[0014] In one embodiment, the step of obtaining potential fault points based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data includes:

[0015] Based on the current waveform characteristics, select a retrieval window; the retrieval window includes multiple data points of the difference sequence;

[0016] According to the retrieval window, obtain the forward windowed mean and the backward windowed mean of all data points of the difference sequence;

[0017] Based on the forward windowed mean and the backward windowed mean, and according to the potential fault judgment condition, detect all potential fault points from the difference sequence.

[0018] In one embodiment, the preset analysis method includes the local regression analysis method;

[0019] The step of obtaining the target fault time based on the potential fault points through the preset analysis method includes:

[0020] Use the local regression analysis method to strengthen the difference characteristics of all potential fault points, obtaining the feature-strengthened data;

[0021] Based on the local weighted regression model and the feature-strengthened data, obtain the regression calculation result for the feature-strengthened data;

[0022] Take the time corresponding to the first regression calculation result that exceeds the set threshold as the target fault time.

[0023] In one embodiment, before the step of using the local regression analysis method to strengthen the difference characteristics of all potential fault points and obtaining the feature-strengthened data, it further includes:

[0024] Use the moving average filter to filter out the potential fault points belonging to misjudgment points.

[0025] In one embodiment, the step of using the moving average filter to filter out the potential fault points belonging to misjudgment points includes:

[0026] Select a filter window according to the interference characteristics of the fault current data; the window width of the filter window is greater than or equal to the interference width of the fault current data;

[0027] Based on the filter window, use the moving average filter to obtain the first moving average value of each potential fault point;

[0028] Starting from each potential fault point, multiple data points of the difference sequence are taken backward to calculate the corresponding second moving average values of the multiple data points;

[0029] Based on the first moving average value and the corresponding second moving average value of each potential fault point, determine and remove the potential fault points that belong to misjudgment points.

[0030] In a second aspect, in an embodiment, the present application provides a transformer short - circuit fault time detection device, which includes:

[0031] A data acquisition module, configured to acquire the normal current data and the fault current data of the target transformer;

[0032] A data fitting and extension module, configured to perform function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as the data length of the fault current data;

[0033] A difference processing module, configured to perform difference processing on the fault current data and the standard current data to obtain a difference sequence;

[0034] A potential fault point acquisition module, configured to obtain potential fault points based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data;

[0035] A target fault time acquisition module, configured to obtain the target fault time based on the potential fault points through a preset analysis method.

[0036] In a third aspect, in an embodiment, the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps in the method embodiments of the first aspect are implemented.

[0037] In a fourth aspect, in an embodiment, the present application provides a computer - readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method embodiments of the first aspect are implemented.

[0038] In a fifth aspect, in an embodiment, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in the method embodiments of the first aspect are implemented.

[0039] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for detecting the short-circuit fault time of a transformer. The method obtains the normal current data and fault current data of the target transformer; performs function fitting and data extension on the normal current data to obtain standard current data; performs difference processing on the fault current data and the standard current data to obtain a difference sequence; based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data, obtains potential fault points, and uses a preset analysis method to analyze these potential fault points, thereby obtaining the target fault time. Through the above technical means, the present application can accurately detect the short-circuit fault time of the transformer, thereby improving the maintenance efficiency of the transformer short-circuit fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0041] Figure 1 It is an application environment diagram of the method for detecting the short-circuit fault time of a transformer in an embodiment;

[0042] Figure 2 It is a flowchart of the method for detecting the short-circuit fault time of a transformer in an embodiment;

[0043] Figure 3 It is a flowchart of obtaining standard current data in an embodiment;

[0044] Figure 4 It is a flowchart of detecting all potential fault points in an embodiment;

[0045] Figure 5 It is a flowchart of obtaining the target fault time in an embodiment;

[0046] Figure 6 It is a flowchart of filtering out misjudged points in an embodiment;

[0047] Figure 7 It is a structural block diagram of the device for detecting the short-circuit fault time of a transformer in an embodiment;

[0048] Figure 8 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] A transformer is a key equipment in the power system. It is widely used in the process of power transmission and distribution and undertakes the important function of voltage conversion. However, due to factors such as power load fluctuations, equipment aging, and external environmental changes, transformers are prone to short-circuit faults during long-term operation. Short-circuit faults will generate large short-circuit currents in the power system, which will in turn cause disasters such as equipment damage, power grid outages, and even more serious fires, bringing huge economic losses and safety risks to society. Therefore, timely and accurately detecting and diagnosing short-circuit faults in transformers has become an important issue in the power industry.

[0051] Currently, the detection methods for short-circuit faults mostly rely on hardware devices, such as current and voltage monitoring systems with sensors, relays, etc. Traditional monitoring systems detect faults by collecting signals such as current and voltage during the operation of transformers in real time and setting thresholds. However, traditional sensors and monitoring systems require a large number of hardware devices to support, increasing the complexity and maintenance cost of the system; moreover, due to the influence of current waveforms by noise and environmental fluctuations, it is difficult for existing technologies to cope with variable current waveforms and prone to false judgments or missed judgments; in addition, short-circuit faults occur rapidly, and the response speed of existing systems is relatively slow, which may cause the power system to be unable to take measures promptly. Therefore, there is still significant room for improvement in terms of accuracy, sensitivity, and system cost in existing technologies.

[0052] Therefore, in order to solve the above problems, it is necessary to improve the existing methods, accurately analyze the difference and change trend of current waveforms, and use data smoothing techniques such as local regression analysis and moving average filtering to eliminate the interference of noise and short-term fluctuations, avoid the occurrence of false judgments, improve the timeliness and accuracy of transformer fault diagnosis, and provide a more reliable guarantee for the stable operation of the power system.

[0053] The objective of the present invention is to provide a method for judging the moment of short-circuit faults in transformers based on the change of current difference, which improves the accuracy and timeliness of transformer fault diagnosis through data difference analysis and data smoothing techniques.

[0054] The method for detecting the moment of short-circuit faults in transformers provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or can also be a cloud server providing cloud computing services.

[0055] In one embodiment, as Figure 2 shown, a method for detecting the short-circuit fault moment of a transformer is provided. In this embodiment, this method is exemplified by being applied to the terminal 102. It can be understood that this method can also be applied to the server, and can also be applied to a system including the terminal and the server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S202 to step S210:

[0056] Step S202, obtain the normal current data and fault current data of the target transformer.

[0057] Among them, the normal current data can be the current data of the target transformer collected when the target transformer is operating normally without a short-circuit fault. The fault current data can refer to the current data of the target transformer within a specified time range obtained when a short-circuit fault characteristic appears in the power supply line where the target transformer is located; within the above specified time range, it can be determined that at a certain moment among them, the target transformer has a short-circuit fault.

[0058] Specifically, the terminal can obtain the current data of the target transformer collected when the target transformer is operating normally without a short-circuit fault, and obtain the fault current data of the target transformer within a specified time range.

[0059] In some examples, the terminal can obtain the normal current data and the fault current data from the current sensor connected to the target transformer. Optionally, the above current sensor has characteristics such as high sensitivity, wide frequency band, and fast response time to ensure that the current sensor can efficiently capture the instantaneous current change of the target transformer during operation, thereby ensuring the accuracy of the collected current data.

[0060] Furthermore, the normal current data and fault current data of the target transformer collected by the above current sensor are current discrete data points. In practical applications, the above current discrete data points can be used to convert the collected data into an easily utilizable data format, obtaining two data sets that can be represented by waveforms. For example, the normal current data can be represented as normal current waveform data a = {a1, a2, …, ai, …, am}, and the fault current data can be represented as fault current waveform data b = {b1, b2, …, bi, …, bn}; where ai represents the i-th data point of the normal current data, bi represents the i-th data point of the fault current data, m represents the data length of the normal current data, and n represents the data length of the fault current data.

[0061] Step S204: Perform function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as that of the fault current data.

[0062] Among them, the standard current data is the current data set after data extension processing of the normal current data. The data length refers to the number of current data points included in the normal current data, standard current data, or fault current data.

[0063] Exemplarily, a preset fitting function can be used to perform function fitting on the normal current data. Optionally, the preset fitting function includes fitting functions such as trigonometric functions.

[0064] Specifically, the terminal uses the preset fitting function to fit the normal current data, and then extends the fitted normal current data, thereby obtaining standard current data with the same data length as the fault current data.

[0065] Step S206: Perform difference processing on the fault current data and the standard current data to obtain a difference sequence.

[0066] Specifically, when the data lengths of the standard current data and the fault current data are the same, the moments of the standard current data and the fault current data can be in one-to-one correspondence. The terminal can calculate the current difference at each corresponding moment to obtain a difference sequence containing the current differences at each moment.

[0067] Exemplarily, taking the ti moment as an example, the terminal can calculate the difference between the data point of the standard current data at this moment and the data point of the fault current data at this moment: ci = bi - ai. Through this calculation method, a difference sequence c = {c1, c2, …, ci, …, cn} of the current differences at each moment can be further calculated; where ci is the i-th data point of the difference sequence, and n is the data length of the difference sequence.

[0068] Step S208: Based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data, obtain potential fault points.

[0069] Among them, the moment corresponding to the potential fault point may be the moment when a short - circuit fault occurs.

[0070] Exemplarily, according to the data distribution of the normal current data or the fault current data, the current waveform characteristics of the normal current data or the fault current data can be obtained.

[0071] Specifically, the terminal combines the difference sequence with the current waveform characteristics of the normal current data and the fault current data to obtain potential fault points in the difference sequence.

[0072] Step S210: Based on the potential fault points, obtain the target fault moment through a preset analysis method.

[0073] Among them, the target fault moment represents the moment when the target transformer has a short - circuit fault. In some examples, the preset analysis method may include the regression analysis method.

[0074] Specifically, the terminal can analyze and obtain the target fault moment according to all the obtained potential fault points by using the preset analysis method.

[0075] The above - mentioned method for detecting the short - circuit fault moment of a transformer obtains the normal current data and the fault current data of the target transformer; performs function fitting and data extension on the normal current data to obtain standard current data with the same data length as the fault current data; performs difference processing on the fault current data and the standard current data to obtain a difference sequence; based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data, obtains potential fault points; based on the potential fault points, obtains the target fault moment through a preset analysis method. Through the above - mentioned manner, the present application can accurately detect the short - circuit fault moment of the transformer.

[0076] In one of the embodiments, as Figure 3 shown, the step of performing function fitting and data extension on the normal current data to obtain standard current data includes the following steps S302 to S304. Among them:

[0077] Step SS02: Perform sine - function fitting on the normal current data to obtain a current fitting function.

[0078] Specifically, the terminal can use the sine function to perform function fitting on the normal current data, thereby obtaining the corresponding current fitting function.

[0079] Step S304: Based on the current fitting function, extend the normal current data until the data length of the normal current data is the same as that of the fault current data, obtaining the standard current data.

[0080] Specifically, based on the original data of the normal current data, the terminal combines the function characteristics of the current fitting function to extend and expand the normal current data, so as to obtain more data points of the simulated normal current data, and finally obtain a standard current data with the same data length as the fault current data.

[0081] In one embodiment, the steps of obtaining potential fault points based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data include the following steps S402 to S406. Among them:

[0082] Step S402: Select a search window based on the current waveform characteristics.

[0083] Among them, the search window includes multiple data points of the difference sequence. Optionally,

[0084] Specifically, the terminal can select a search window with an appropriate window width based on the current waveform characteristics of the normal current data and the fault current data. Optionally, the width of the search window can be 3 to 5 adjacent data points in the difference sequence.

[0085] Step S404: According to the search window, obtain the forward window mean and the backward window mean of all data points of the difference sequence.

[0086] Exemplarily, the forward window mean of the data points of the difference sequence can be calculated by the following formula 1:

[0087] (Formula 1)

[0088] Among them, is the forward window mean of the i-th data point of the difference sequence, d is the window width of the search window, is the j-th data point of the difference sequence.

[0089] Exemplarily, the backward window mean of the data points of the difference sequence can be calculated by the following formula 2:

[0090] (Formula 2)

[0091] Among them, is the backward window mean of the i-th data point of the difference sequence, d is the window width of the search window, is the j-th data point of the difference sequence.

[0092] Specifically, the terminal calculates the forward window mean and backward window mean of each data point for all moments of the difference sequence respectively.

[0093] Step S406: Based on the forward window mean and the backward window mean, and according to the potential fault judgment condition, all potential fault points are detected from the difference sequence.

[0094] Exemplarily, the potential fault judgment condition can be to satisfy the following formula 3:

[0095] (Formula 3)

[0096] Among them, the coefficient can be set according to the data length of the difference sequence.

[0097] Specifically, if the data points of the difference sequence satisfy the above potential fault judgment condition, the terminal can determine that the data point is a potential fault point. In the above manner, the terminal can retrieve the data points at all moments of the difference sequence, thereby detecting all potential fault points therein.

[0098] In one embodiment, as Figure 5 shown, the preset analysis method includes the local regression analysis method; the steps of obtaining the target fault moment through the preset analysis method based on the potential fault points include the following steps S502 to S504. Among them:

[0099] Step S502: Use the local regression analysis method to strengthen the difference features of all potential fault points to obtain feature-enhanced data.

[0100] Among them, the local regression analysis method can be used to highlight the difference features of all obtained potential fault points.

[0101] Specifically, the terminal can further strengthen the difference features of all potential fault points in the difference sequence through the local regression analysis method to obtain feature-enhanced data including all potential fault points with enhanced difference features.

[0102] Step S504: Based on the locally weighted regression model and the feature-enhanced data, obtain the regression calculation result for the feature-enhanced data.

[0103] Exemplarily, the locally weighted regression model can be expressed as the following formula 4:

[0104] (Formula 4)

[0105] Among them, is the weighting coefficient, is the j-th data point of the difference sequence, is the regression calculation result corresponding to the j-th data point of the difference sequence. It should be noted that the farther away from the center point is, the corresponding weight k j is smaller, the closer to the center point is, the corresponding weight k j is larger.

[0106] Specifically, the terminal can calculate the regression calculation result corresponding to each potential fault point according to the above local weighted regression model and the obtained feature-enhanced data in chronological order.

[0107] Step S506: Take the moment corresponding to the first regression calculation result that exceeds the set threshold as the target fault moment.

[0108] Specifically, when the regression calculation result corresponding to the potential fault point at a certain moment calculated in chronological order exceeds the set threshold, the terminal determines that this moment is the target fault moment when the target transformer has a short-circuit fault.

[0109] In one embodiment, before the step of using the local regression analysis method to strengthen the difference features of all potential fault points to obtain feature-enhanced data, the following steps are further included:

[0110] Use moving average filtering to filter out the potential fault points belonging to misjudgment points.

[0111] It can be understood that the fault current is more susceptible to various factors of interference, and there may be various interference-induced spikes in the waveform of the fault current data. This spike interference results in that the original potential fault points not only include potential short-circuit fault points but also misjudgment points caused by the above spike interference.

[0112] Specifically, before the step of using the local regression analysis method to strengthen the difference features of all potential fault points to obtain feature-enhanced data, the terminal can also first use the method of moving average filtering to filter out the potential fault points belonging to misjudgment points among the above potential fault points.

[0113] In one embodiment, the step of using moving average filtering to filter out the potential fault points belonging to misjudgment points includes the following steps S602 to S608. Among them:

[0114] Step S602: Select a filtering window according to the interference characteristics of the fault current data.

[0115] Among them, the window width of the filtering window is greater than or equal to the interference width of the fault current data. The interference width can be the maximum width of the above spike interference.

[0116] Specifically, the terminal selects a filtering window whose window width is greater than or equal to the interference width of the fault current data according to the interference characteristics of the fault current data.

[0117] Step S604: Based on the filtering window, use moving average filtering to obtain the first moving average value of each potential fault point.

[0118] Exemplarily, according to the following formula 5, the moving average value corresponding to the potential fault point can be calculated through moving average filtering:

[0119] (Formula 5)

[0120] Wherein, is the moving average value corresponding to the potential fault point at time , w is the window width of the filtering window, is the data point corresponding to time in the difference sequence.

[0121] Specifically, the terminal uses the set filtering window, and through the moving average filtering method shown in the above formula 5, calculates the first moving average value corresponding to each potential fault point based on the difference sequence.

[0122] Step S606: Starting from each potential fault point, take multiple data points of the difference sequence backward to calculate the second moving average value corresponding to the multiple data points.

[0123] Specifically, the terminal starts from each of the above potential fault points, and uses the moving average filtering method shown in the above formula 5 to calculate the second moving average value corresponding to the multiple data points of the difference sequence backward respectively.

[0124] For example, taking the first moving average value corresponding to the potential fault point at time as an example, the terminal further calculates the second moving average values , , corresponding to the data points of the difference sequence at times , , . It can be understood that the above method for obtaining the second moving average value is only one example. In fact, other numbers of data points of the difference sequence can also be selected backward to obtain the corresponding second moving average value, and the present application does not limit this.

[0125] Step S608: Determine and remove the potential fault points belonging to misjudgment points according to the first moving average value and the second moving average value of each potential fault point.

[0126] Specifically, when the first moving average value of the potential fault point is basically consistent with the second moving average value of multiple data points of the difference sequence obtained backward from the potential fault point (i.e., the difference between the two is less than a preset threshold), the terminal can determine that the potential fault point belongs to a misjudgment point caused by interference, and filter out the potential fault point belonging to the misjudgment point.

[0127] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0128] Based on the same inventive concept, an embodiment of the present application also provides a transformer short-circuit fault time detection device for implementing the transformer short-circuit fault time detection method involved above. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the transformer short-circuit fault time detection device provided below can refer to the limitations on the transformer short-circuit fault time detection method in the above text, and will not be repeated here.

[0129] In an exemplary embodiment, as Figure 7 shown, the present application provides a transformer short-circuit fault time detection device 700, and the device 700 includes:

[0130] A data acquisition module 702, configured to acquire normal current data and fault current data of a target transformer;

[0131] A data fitting and extension module 704, configured to perform function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as the data length of the fault current data;

[0132] A difference processing module 706, configured to perform difference processing on the fault current data and the standard current data to obtain a difference sequence;

[0133] A potential fault point acquisition module 708, configured to obtain potential fault points based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data;

[0134] A target fault time acquisition module 710, configured to obtain a target fault time based on potential fault points through a preset analysis method.

[0135] In one embodiment, the data fitting and extension module 704 is further configured to:

[0136] Perform sine function fitting on the normal current data to obtain a current fitting function;

[0137] Based on the current fitting function, extend the normal current data until the data length of the normal current data is the same as that of the fault current data, to obtain standard current data.

[0138] In one embodiment, the potential fault point acquisition module 708 is further configured to:

[0139] Select a retrieval window based on the current waveform characteristics; the retrieval window includes multiple data points of the difference sequence;

[0140] According to the retrieval window, obtain the forward window mean and the backward window mean of all data points of the difference sequence;

[0141] Based on the forward window mean and the backward window mean, and according to the potential fault judgment condition, detect all potential fault points from the difference sequence.

[0142] In one embodiment, the preset analysis method includes local regression analysis; the target fault time acquisition module 710 is further configured to:

[0143] Utilize local regression analysis to strengthen the difference characteristics of all potential fault points to obtain feature-enhanced data;

[0144] Based on the locally weighted regression model and the feature-enhanced data, obtain a regression calculation result for the feature-enhanced data;

[0145] Take the moment corresponding to the first regression calculation result that exceeds the set threshold as the target fault time.

[0146] In one embodiment, the target fault time acquisition module 710 is further configured to:

[0147] Utilize moving average filtering to filter out potential fault points belonging to misjudgment points.

[0148] In one embodiment, the target fault time acquisition module 710 is further configured to:

[0149] Select a filtering window according to the interference characteristics of the fault current data; the window width of the filtering window is greater than or equal to the interference width of the fault current data;

[0150] Based on the filtering window, the first moving average value of each potential fault point is obtained by using moving average filtering;

[0151] Starting from each potential fault point, multiple data points of the difference sequence are taken backward to calculate the second moving average value corresponding to the multiple data points;

[0152] According to the first moving average value and the corresponding second moving average value of each potential fault point, the potential fault points belonging to the misjudgment points are determined and removed.

[0153] Each module in the above transformer short - circuit fault time detection device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0154] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through the system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non - volatile storage medium and an internal memory. The non - volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non - volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, near - field communication (NFC), or other technologies. The computer program, when executed by the processor, implements a method for detecting the time of transformer short - circuit faults. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a key, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0155] Those skilled in the art can understand, Figure 8The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0156] In one embodiment, a computer device is also provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0158] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0159] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0160] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0161] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for detecting the moment of a transformer short - circuit fault, characterized in that, The method includes: Obtaining normal current data and fault current data of a target transformer; Performing function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as that of the fault current data; Performing difference processing on the fault current data and the standard current data to obtain a difference sequence; Based on the difference sequence, obtaining potential fault points based on the current waveform characteristics of the normal current data and the fault current data; Based on the potential fault points, obtaining a target fault time through a preset analysis method.

2. The method according to claim 1, characterized in that, The step of performing function fitting and data extension on the normal current data to obtain standard current data includes: Performing sine function fitting on the normal current data to obtain a current fitting function; Based on the current fitting function, performing data extension on the normal current data until the data length of the normal current data is the same as that of the fault current data, to obtain the standard current data.

3. The method according to claim 2, wherein The step of obtaining potential fault points based on the difference sequence, based on the current waveform characteristics of the normal current data and the fault current data, includes: Based on the current waveform characteristics, selecting a retrieval window; the retrieval window includes multiple data points of the difference sequence; According to the retrieval window, obtaining the forward window mean and the backward window mean of all data points of the difference sequence; Based on the forward window mean and the backward window mean, detecting all the potential fault points from the difference sequence according to potential fault judgment conditions.

4. The method according to claim 1, characterized in that, The preset analysis method includes local regression analysis; The step of obtaining a target fault time through a preset analysis method based on the potential fault points includes: Using local regression analysis to strengthen the difference characteristics of all the potential fault points to obtain feature-enhanced data; Based on a locally weighted regression model and the feature-enhanced data, obtaining a regression calculation result for the feature-enhanced data; Taking the time corresponding to the first regression calculation result that exceeds a set threshold as the target fault time.

5. The method according to claim 4, wherein Before the step of using local regression analysis to strengthen the difference characteristics of all the potential fault points to obtain feature-enhanced data, it further includes: Using a moving average filtering technique to filter out the potential fault points belonging to misjudgment points.

6. The method according to claim 5, characterized in that, The step of using a moving average filtering technique to filter out the potential fault points belonging to misjudgment points includes: Selecting a filtering window according to the interference characteristics of the fault current data; the window width of the filtering window is greater than or equal to the interference width of the fault current data; Based on the filtering window, using moving average filtering to obtain the first moving average value of each potential fault point; Starting from each potential fault point, taking multiple data points of the difference sequence backward to calculate the corresponding second moving average value of the multiple data points; According to the first moving average value of each potential fault point and the corresponding second moving average value, determining and removing the potential fault points belonging to the misjudgment points.

7. A detecting device for the short-circuit fault moment of a transformer, characterized in that, The device includes: A data acquisition module, configured to acquire normal current data and fault current data of a target transformer; A data fitting and extension module, configured to perform function fitting and data extension on the normal current data to obtain standard current data; the data length of the standard current data is the same as that of the fault current data; A difference processing module, configured to perform difference processing on the fault current data and the standard current data to obtain a difference sequence; A potential fault point acquisition module, configured to obtain potential fault points based on the difference sequence and the current waveform characteristics of the normal current data and the fault current data; A target fault time acquisition module, configured to obtain a target fault time based on the potential fault points through a preset analysis method.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images