Transformer fault early warning method and device based on vibration frequency domain characteristic value
Through the transformer fault warning method based on the vibration frequency domain characteristic value, vibration signals are collected and analyzed in real time, state evaluation coefficients are calculated and compared with thresholds, the problems of high calculation complexity and hysteresis in the prior art are solved, and timely early warning and efficient monitoring of transformer faults are realized.
Patent Information
- Application Number
- CN202411973589.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-05-09
AI Technical Summary
The existing transformer fault monitoring methods have high computational complexity and are difficult to widely promote. The traditional methods have lags and are difficult to detect early or potential faults in a timely manner.
The transformer fault warning method based on the characteristic value of the vibration frequency domain is adopted, and fault warning is achieved by collecting vibration signals in real time, frequency domain analysis, calculating the status evaluation coefficients and comparing them with the preset threshold.
Simplifies the fault monitoring process, reduces calculation costs, maintains high warning accuracy, is suitable for a variety of transformers and specifications, reducing the impact of faults on the power system.
Smart Images
Figure CN119961719A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of transformer fault diagnosis, and in particular relates to a transformer fault early warning method and device based on vibration frequency domain characteristic values. Background Art
[0002] As a key equipment in the power system, the stability of the transformer's operating status is directly related to the safety of the entire power system; however, due to the complexity of the transformer's internal structure and the diversity of its operating environment, its fault types are diverse and difficult to predict; traditional transformer fault monitoring methods mainly rely on the analysis of parameters such as dissolved gas, temperature and current in transformer oil, but the above traditional methods often have lags and it is difficult to detect early or potential faults in a timely manner.
[0003] In recent years, with the rapid development of sensor technology and signal processing technology, transformer fault monitoring methods based on vibration signals have gradually emerged. Since the transformer will vibrate during operation, and the vibration signal contains rich status information, such as winding looseness, core deformation, insulation aging and other fault information can be reflected by the vibration signal. Therefore, by analyzing the vibration signal, real-time monitoring of the transformer operating status and fault warning can be achieved. At present, although some transformer fault monitoring methods based on vibration signals have been proposed, the existing fault monitoring methods often use complex feature extraction algorithms and classification models, resulting in high computational complexity and difficult to be widely promoted in practical applications. Summary of the invention
[0004] In response to the technical problems existing in the prior art, the present invention provides a transformer fault warning method and device based on vibration frequency domain eigenvalues to solve the technical problem that the existing fault monitoring methods often adopt complex feature extraction algorithms and classification models, resulting in high computational complexity and difficult to be widely promoted in practical applications.
[0005] In order to achieve the above object, the technical solution adopted by the present invention is: The present invention provides a transformer fault early warning method based on vibration frequency domain characteristic values, comprising: Collect the vibration signal of the transformer to be warned in real time to obtain the real-time vibration signal; Performing frequency domain analysis on the real-time vibration signal to obtain vibration frequency domain characteristic values; According to the vibration frequency domain characteristic value, the state assessment coefficient of the current operating state of the transformer to be warned is calculated; The state evaluation coefficient of the current operating state of the transformer to be warned is compared with the preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned.
[0006] Furthermore, the process of collecting the vibration signal of the transformer to be warned in real time and obtaining the real-time vibration signal is as follows: According to preset signal sampling parameters, data is collected from the vibration sensor pre-installed on the transformer to be warned to obtain a real-time vibration signal; wherein the vibration sensor pre-installed on the transformer to be warned is an acceleration sensor installed on the surface of the oil tank of the transformer to be warned.
[0007] Furthermore, the vibration frequency domain characteristic values include the frequency domain amplitude average value of the real-time vibration signal, the center of gravity frequency of the real-time vibration signal, the sum of the 50 Hz odd-order harmonic amplitudes of the real-time vibration signal, and the sum of the 50 Hz even-order harmonic amplitudes of the real-time vibration signal.
[0008] Furthermore, the calculation formula for the frequency domain amplitude average value of the real-time vibration signal is specifically:
[0009] in, is the frequency domain amplitude average value of the real-time vibration signal; is the frequency number of the real-time vibration signal; The real-time vibration signal The amplitude of each frequency point; The calculation formula of the center of gravity frequency of the real-time vibration signal is as follows:
[0010] in, is the center of gravity frequency of the real-time vibration signal; The real-time vibration signal The frequency value of each frequency point; The calculation formula for the sum of the amplitudes of the 50Hz odd-order harmonics of the real-time vibration signal is as follows:
[0011] in, is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the number of even and odd harmonic frequency points in the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal; The calculation formula for the sum of the amplitudes of the 50Hz even-order harmonics of the real-time vibration signal is as follows:
[0012] in, is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal.
[0013] Furthermore, according to the vibration frequency domain eigenvalue, the process of calculating the state assessment coefficient of the current operating state of the transformer to be warned is as follows: The vibration frequency domain eigenvalue is input into the pre-built transformer operation status assessment model to calculate the status assessment coefficient of the current operation status of the transformer to be warned; wherein the pre-built transformer operation status assessment model is specifically as follows:
[0014] in, is the status assessment coefficient of the current operating status of the transformer to be warned; is the frequency domain amplitude average value of the real-time vibration signal; is the average frequency domain amplitude value of the transformer to be warned in normal operation; is the center of gravity frequency of the real-time vibration signal; The center of gravity frequency of the transformer to be warned in normal operation; is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; The sum of the amplitudes of 50Hz odd-order harmonics under normal operation of the transformer to be warned; is the sum of the amplitudes of 50Hz even-order harmonics under normal operation of the transformer to be warned.
[0015] Furthermore, the preset evaluation coefficient threshold is determined based on historical operating data and known fault modes of the transformer to be warned.
[0016] Furthermore, the state evaluation coefficient of the current operating state of the transformer to be warned is compared with the preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned, which is specifically as follows: Compare the state evaluation coefficient of the current operating state of the transformer to be warned with the preset evaluation coefficient threshold; If the state assessment coefficient of the current operating state of the transformer to be warned exceeds the preset assessment coefficient threshold, the fault warning result of the transformer to be warned is output as fault, and a preset fault warning signal is issued; otherwise, the fault warning result of the transformer to be warned is normal.
[0017] The present invention also provides a transformer fault early warning system based on vibration frequency domain characteristic values, comprising: A vibration signal acquisition module is used to collect the vibration signal of the transformer to be warned in real time and obtain the real-time vibration signal; A frequency domain analysis module, used to perform frequency domain analysis on the real-time vibration signal to obtain a vibration frequency domain characteristic value; A state assessment module is used to calculate the state assessment coefficient of the current operating state of the transformer to be warned according to the vibration frequency domain characteristic value; The early warning module is used to compare the state evaluation coefficient of the current operating state of the transformer to be warned with a preset evaluation coefficient threshold to obtain a fault early warning result of the transformer to be warned.
[0018] The present invention also provides a transformer fault early warning device based on vibration frequency domain characteristic values, comprising: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the transformer fault early warning method based on vibration frequency domain eigenvalues is executed.
[0019] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the transformer fault early warning method based on vibration frequency domain characteristic values is implemented.
[0020] Compared with the prior art, the present invention has the following beneficial effects: The transformer fault early warning method based on vibration frequency domain eigenvalues provided by the present invention calculates the state evaluation coefficient of the current operating state of the transformer to be warned based on the vibration frequency domain eigenvalues of the vibration signal of the transformer to be warned, and realizes accurate early warning of transformer faults by comparing the threshold values of the state evaluation coefficient of the current operating state of the transformer to be warned; the present invention simplifies the complex process of traditional fault monitoring, reduces the calculation cost, and maintains a high early warning accuracy; the method is applicable to transformers of various models and specifications, and enhances the versatility and practicality of the early warning method; by implementing the method of the present invention, operation and maintenance personnel can timely identify transformer faults based on real-time vibration signals, reduce the impact of faults on the power system, ensure stable operation of the power grid, and improve operation and maintenance efficiency and equipment service life.
[0021] Furthermore, frequency domain eigenvalues are extracted from the real-time vibration signal through simple frequency domain analysis, and then the pre-built transformer operation status assessment model is used to calculate the state assessment coefficient reflecting the current operation status of the transformer. By comparing the relationship between the state assessment coefficient and the preset threshold, timely early warning of transformer faults can be achieved. This not only improves the efficiency of feature extraction, but also reduces the computational complexity, making it easier to promote in practical applications.
[0022] The transformer fault warning system based on vibration frequency domain eigenvalues, the transformer fault warning device based on vibration frequency domain eigenvalues and the computer-readable storage medium provided by the present invention have all the advantages of the above-mentioned transformer fault warning method based on vibration frequency domain eigenvalues. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 A flowchart of a transformer fault early warning method based on vibration frequency domain eigenvalues provided in Example 1; Figure 2 A structural block diagram of a transformer fault early warning system based on vibration frequency domain eigenvalues provided in Example 2; Figure 3 This is a structural block diagram of a transformer fault warning device based on vibration frequency domain eigenvalues provided in Example 3. DETAILED DESCRIPTION
[0025] In order to make the technical problems, technical solutions and beneficial effects solved by this application clearer, the technical solutions in the embodiments of this application will be described clearly and completely in combination with the drawings in the embodiments of this application; obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0026] Example 1 As attached Figure 1 As shown, a transformer fault early warning method based on vibration frequency domain characteristic values provided in this embodiment 1 includes the following steps: Step 1: collect the vibration signal of the transformer to be warned in real time to obtain the real-time vibration signal. Specifically, according to the preset signal sampling parameters, collect data from the vibration sensor pre-installed on the transformer to be warned to obtain the real-time vibration signal; wherein the vibration sensor pre-installed on the transformer to be warned is an acceleration sensor installed on the surface of the oil tank of the transformer to be warned.
[0027] It should be noted that the steps for collecting the vibration signal of the transformer to be warned in real time and obtaining the real-time vibration signal are as follows: Arrange the pre-selected acceleration sensor on the oil tank surface of the transformer to be warned; set the signal sampling parameters before collecting the vibration signal; wherein the preset signal sampling parameters include sampling frequency, sampling time and number of sampling points to ensure that the vibration characteristics of the transformer can be accurately captured; align the acceleration sensor installed on the oil tank surface of the transformer to be warned with the data acquisition device vector, start the preset data acquisition program, and collect data according to the preset signal sampling parameters to obtain the real-time vibration signal.
[0028] Step 2: Perform frequency domain analysis on the real-time vibration signal to obtain vibration frequency domain characteristic values, wherein the vibration frequency domain characteristic values include the frequency domain amplitude average value of the real-time vibration signal, the center of gravity frequency of the real-time vibration signal, the amplitude sum of the 50 Hz odd-order harmonics of the real-time vibration signal, and the amplitude sum of the 50 Hz even-order harmonics of the real-time vibration signal.
[0029] Specifically, the process of performing frequency domain analysis on the real-time vibration signal to obtain the vibration frequency domain characteristic value is as follows: Step 21: According to the real-time vibration signal, the frequency domain amplitude average value of the real-time vibration signal is calculated using the calculation formula of the frequency domain amplitude average value of the real-time vibration signal; wherein the calculation formula of the frequency domain amplitude average value of the real-time vibration signal is specifically:
[0030] in, is the frequency domain amplitude average value of the real-time vibration signal; is the frequency number of the real-time vibration signal; The real-time vibration signal The amplitude of a frequency point.
[0031] Step 22: Calculate the center of gravity frequency of the real-time vibration signal according to the real-time vibration signal and using the calculation formula of the center of gravity frequency of the real-time vibration signal; wherein the calculation formula of the center of gravity frequency of the real-time vibration signal is specifically:
[0032] in, is the center of gravity frequency of the real-time vibration signal; The real-time vibration signal The frequency value of a frequency point.
[0033] Step 23, according to the real-time vibration signal, and using the calculation formula of the 50 Hz odd-order frequency harmonic amplitude sum of the real-time vibration signal, calculate the 50 Hz odd-order frequency harmonic amplitude sum of the real-time vibration signal; wherein, the calculation formula of the 50 Hz odd-order frequency harmonic amplitude sum of the real-time vibration signal is as follows:
[0034] in, is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the number of even and odd harmonic frequency points in the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal.
[0035] Step 24: According to the real-time vibration signal, the 50 Hz even-order frequency multiple harmonic amplitude sum of the real-time vibration signal is calculated using the calculation formula of the 50 Hz even-order frequency multiple harmonic amplitude sum of the real-time vibration signal; wherein the calculation formula of the 50 Hz even-order frequency multiple harmonic amplitude sum of the real-time vibration signal is as follows:
[0036] in, is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal.
[0037] Step 3: Calculate the state evaluation coefficient of the current operating state of the transformer to be warned according to the vibration frequency domain eigenvalue. Specifically, input the vibration frequency domain eigenvalue into the pre-built transformer operating state evaluation model, evaluate the current operating state of the transformer to be warned, and calculate the state evaluation coefficient of the current operating state of the transformer to be warned.
[0038] The pre-built transformer operation status assessment model is as follows:
[0039] in, is the status assessment coefficient of the current operating status of the transformer to be warned; is the frequency domain amplitude average value of the real-time vibration signal; is the average frequency domain amplitude value of the transformer to be warned in normal operation; is the center of gravity frequency of the real-time vibration signal; The center of gravity frequency of the transformer to be warned in normal operation; is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; The sum of the amplitudes of 50Hz odd-order harmonics under normal operation of the transformer to be warned; is the sum of the amplitudes of 50Hz even-order harmonics under normal operation of the transformer to be warned.
[0040] Step 4: Determine the evaluation coefficient threshold value based on the historical operation data and known fault modes of the transformer to be warned, and obtain a preset evaluation coefficient threshold value. Specifically, the process of determining the evaluation coefficient threshold value based on the historical operation data and known fault modes of the transformer to be warned is as follows: According to the known fault mode of the transformer to be warned, the vibration signal of the transformer to be warned under normal operating status within a preset historical time period is collected to obtain a historical normal vibration signal; the historical normal vibration signal is input into a pre-built transformer operation status evaluation model to obtain the state coefficient of the transformer to be warned under normal operating status within the preset historical time period; according to the state coefficient of the transformer to be warned under normal operating status within the preset historical time period, a preset evaluation coefficient threshold is calculated.
[0041] Specifically, the calculation formula of the preset evaluation coefficient threshold is as follows:
[0042] in, is the preset evaluation coefficient threshold; Preset the status coefficient of the transformer to be warned under normal operating conditions within a historical time period; is the safety factor.
[0043] Taking the determination process of the evaluation coefficient threshold of a transformer as an example, the details are as follows: The vibration signals of the example transformer under normal operating conditions in the past year were collected, and the state coefficient of the example transformer under normal operating conditions within a preset historical time period was calculated; it was found through statistics that the state coefficient of the transformer under normal operating conditions within the preset historical time period was distributed between 0.8 and 1.2; in order to avoid false alarms, 105% of the state coefficient was selected as the preset evaluation coefficient threshold; after calculation, the preset evaluation coefficient threshold was 1.25.
[0044] Step 5: Compare the status evaluation coefficient of the current operating status of the transformer to be warned with the preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned. Specifically, the implementation process is as follows: The state assessment coefficient of the current operating state of the transformer to be warned is compared with the preset assessment coefficient threshold.
[0045] If the state evaluation coefficient of the current operating state of the transformer to be warned exceeds the preset evaluation coefficient threshold, the fault warning result of the transformer to be warned is output as fault, and a preset fault warning signal is issued; for example, when the state evaluation coefficient of the current operating state of the transformer to be warned is greater than 1.25, a preset fault warning signal is issued; otherwise, the fault warning result of the transformer to be warned is normal.
[0046] The transformer fault warning method based on vibration frequency domain eigenvalues described in this embodiment 1 analyzes the vibration frequency domain eigenvalues and calculates the state evaluation coefficient of the current operating state of the transformer to be warned according to the vibration frequency domain eigenvalues; combined with reasonable threshold setting, and by comparing the threshold of the state evaluation coefficient of the current operating state of the transformer to be warned, accurate warning of transformer faults is achieved; the method described in this embodiment 1 simplifies the complex process of traditional fault monitoring, reduces the calculation cost, and maintains a high warning accuracy; the method is applicable to transformers of various models and specifications, enhances the versatility and practicality of the warning method, and operation and maintenance personnel can timely identify transformer faults based on real-time data, reduce the impact of faults on the power system, ensure stable operation of the power grid, and improve operation and maintenance efficiency and equipment service life.
[0047] Example 2 As attached Figure 2 As shown, this embodiment 2 provides a transformer fault warning system based on vibration frequency domain characteristic values, including a vibration signal acquisition module, a frequency domain analysis module, a state evaluation module and a warning module.
[0048] The vibration signal acquisition module is used to collect the vibration signal of the transformer to be warned in real time to obtain the real-time vibration signal; the frequency domain analysis module is used to perform frequency domain analysis on the real-time vibration signal to obtain the vibration frequency domain eigenvalue; the state evaluation module is used to calculate the state evaluation coefficient of the current operating state of the transformer to be warned according to the vibration frequency domain eigenvalue; the warning module is used to compare the state evaluation coefficient of the current operating state of the transformer to be warned with a preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned.
[0049] Preferably, the transformer fault warning system based on vibration frequency domain eigenvalues also includes a threshold setting module; the threshold setting module is used to determine the evaluation coefficient threshold according to the historical operating data and known fault modes of the transformer to be warned, so as to obtain a preset evaluation coefficient threshold.
[0050] Example 3 As attached Figure 3 As shown, this embodiment 3 provides a transformer fault warning device based on vibration frequency domain eigenvalues, including: a memory for storing a computer program; a processor for implementing the steps of a transformer fault warning method based on vibration frequency domain eigenvalues when executing the computer program.
[0051] When the processor executes the computer program, the steps of the transformer fault early warning method based on vibration frequency domain characteristic values are implemented, for example: The vibration signal of the transformer to be warned is collected in real time to obtain a real-time vibration signal; the real-time vibration signal is analyzed in the frequency domain to obtain the vibration frequency domain eigenvalue; according to the vibration frequency domain eigenvalue, a state evaluation coefficient of the current operating state of the transformer to be warned is calculated; according to the historical operating data and known fault modes of the transformer to be warned, an evaluation coefficient threshold is determined to obtain a preset evaluation coefficient threshold; the state evaluation coefficient of the current operating state of the transformer to be warned is compared with the preset evaluation coefficient threshold to obtain a fault warning result of the transformer to be warned.
[0052] Alternatively, when the processor executes the computer program, the functions of each module in the transformer fault early warning system based on vibration frequency domain eigenvalues are realized, for example: A vibration signal acquisition module is used to acquire the vibration signal of the transformer to be warned in real time to obtain a real-time vibration signal; a frequency domain analysis module is used to perform frequency domain analysis on the real-time vibration signal to obtain vibration frequency domain eigenvalues; a state evaluation module is used to calculate the state evaluation coefficient of the current operating state of the transformer to be warned based on the vibration frequency domain eigenvalues; a threshold setting module is used to determine the evaluation coefficient threshold based on the historical operating data and known fault modes of the transformer to be warned to obtain a preset evaluation coefficient threshold; an early warning module is used to compare the state evaluation coefficient of the current operating state of the transformer to be warned with the preset evaluation coefficient threshold to obtain a fault early warning result of the transformer to be warned.
[0053] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing preset functions, and the instruction segments are used to describe the execution process of the computer program in the transformer fault early warning device based on vibration frequency domain characteristic values.
[0054] For example, the computer program can be divided into a vibration signal acquisition module, a frequency domain analysis module, a state evaluation module, a threshold setting module and an early warning module, and the specific functions of each module are as follows: A vibration signal acquisition module is used to acquire the vibration signal of the transformer to be warned in real time to obtain a real-time vibration signal; a frequency domain analysis module is used to perform frequency domain analysis on the real-time vibration signal to obtain vibration frequency domain eigenvalues; a state evaluation module is used to calculate the state evaluation coefficient of the current operating state of the transformer to be warned based on the vibration frequency domain eigenvalues; a threshold setting module is used to determine the evaluation coefficient threshold based on the historical operating data and known fault modes of the transformer to be warned to obtain a preset evaluation coefficient threshold; an early warning module is used to compare the state evaluation coefficient of the current operating state of the transformer to be warned with the preset evaluation coefficient threshold to obtain a fault early warning result of the transformer to be warned.
[0055] The transformer fault warning device based on vibration frequency domain eigenvalues can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The transformer fault warning device based on vibration frequency domain eigenvalues may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above is an example of a transformer fault warning device based on vibration frequency domain eigenvalues, and does not constitute a limitation on the transformer fault warning device based on vibration frequency domain eigenvalues, and may include more components than the above, or a combination of certain components, or different components. For example, the transformer fault warning device based on vibration frequency domain eigenvalues may also include input and output devices, network access devices, buses, etc.
[0056] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The processor is the control center of the transformer fault warning device based on vibration frequency domain characteristic values, and uses various interfaces and lines to connect the various parts of the transformer fault warning device based on vibration frequency domain characteristic values.
[0057] The memory can be used to store the computer program and / or module, and the processor implements various functions of the transformer fault early warning device based on vibration frequency domain eigenvalues by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.
[0058] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0059] Example 4 This embodiment 4 also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the transformer fault early warning method based on vibration frequency domain characteristic values are implemented, for example: The vibration signal of the transformer to be warned is collected in real time to obtain a real-time vibration signal; the real-time vibration signal is analyzed in the frequency domain to obtain the vibration frequency domain eigenvalue; according to the vibration frequency domain eigenvalue, a state evaluation coefficient of the current operating state of the transformer to be warned is calculated; according to the historical operating data and known fault modes of the transformer to be warned, an evaluation coefficient threshold is determined to obtain a preset evaluation coefficient threshold; the state evaluation coefficient of the current operating state of the transformer to be warned is compared with the preset evaluation coefficient threshold to obtain a fault warning result of the transformer to be warned.
[0060] If the integrated module / unit of the transformer fault early warning system based on vibration frequency domain eigenvalues is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
[0061] Based on such understanding, the present invention implements all or part of the processes in the above-mentioned transformer fault early warning method based on vibration frequency domain characteristic values, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned transformer fault early warning method based on vibration frequency domain characteristic values can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or preset intermediate form, etc.
[0062] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.
[0063] It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electrical carrier signals and telecommunication signals.
[0064] The transformer early warning method based on vibration frequency domain eigenvalues described in the present invention realizes real-time monitoring and early warning of the transformer state through vibration frequency domain eigenvalue analysis and reasonable threshold setting, and effectively solves the problems of low efficiency and inaccurate early warning in traditional fault monitoring methods; specifically, a vibration sensor installed on the transformer is used to collect vibration signals in real time; the collected vibration signals are subjected to frequency domain analysis to extract frequency domain eigenvalues; the extracted frequency domain eigenvalues are input into the evaluation model, and a state evaluation coefficient reflecting the current operating state of the transformer is obtained by calculation; a reasonable state evaluation coefficient threshold is set according to the normal operating state of the transformer and known fault modes; the calculated state coefficient is compared with the threshold, and if the state coefficient exceeds the threshold, a fault early warning signal is issued; the present invention can timely discover and handle potential transformer faults, reduce the impact of faults on the power system, ensure stable operation of the power grid, improve operation and maintenance efficiency and equipment service life, promote the intelligent transformation of the power system, is applicable to transformers of various models and specifications, and enhances the versatility and practicality of the early warning method.
[0065] The above embodiment is only one of the implementation methods that can realize the technical solution of the present invention. The scope of protection claimed by the present invention is not limited only to this embodiment, but also includes changes, replacements and other implementation methods that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention.
Claims
1. A transformer fault early warning method based on vibration frequency domain eigenvalues, characterized in that: include: Collect the vibration signal of the transformer to be warned in real time to obtain the real-time vibration signal; Performing frequency domain analysis on the real-time vibration signal to obtain vibration frequency domain characteristic values; According to the vibration frequency domain characteristic value, the state assessment coefficient of the current operating state of the transformer to be warned is calculated; The state evaluation coefficient of the current operating state of the transformer to be warned is compared with the preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned.
2. A transformer fault early warning method based on vibration frequency domain eigenvalues according to claim 1, characterized in that: The process of collecting the vibration signal of the transformer to be warned in real time and obtaining the real-time vibration signal is as follows: According to preset signal sampling parameters, data is collected from the vibration sensor pre-installed on the transformer to be warned to obtain a real-time vibration signal; wherein the vibration sensor pre-installed on the transformer to be warned is an acceleration sensor installed on the surface of the oil tank of the transformer to be warned.
3. A transformer fault early warning method based on vibration frequency domain eigenvalues according to claim 1, characterized in that: The vibration frequency domain characteristic values include the frequency domain amplitude average value of the real-time vibration signal, the center of gravity frequency of the real-time vibration signal, the sum of the 50 Hz odd-order harmonic amplitudes of the real-time vibration signal, and the sum of the 50 Hz even-order harmonic amplitudes of the real-time vibration signal.
4. A transformer fault early warning method based on vibration frequency domain characteristic values according to claim 3, characterized in that: The calculation formula for the frequency domain amplitude average value of the real-time vibration signal is as follows: in, is the frequency domain amplitude average value of the real-time vibration signal; is the frequency number of the real-time vibration signal; The real-time vibration signal The amplitude of each frequency point; The calculation formula of the center of gravity frequency of the real-time vibration signal is as follows: in, is the center of gravity frequency of the real-time vibration signal; The real-time vibration signal The frequency value of each frequency point; The calculation formula for the sum of the amplitudes of the 50Hz odd-order harmonics of the real-time vibration signal is as follows: in, is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the number of even and odd harmonic frequency points in the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal; The calculation formula for the sum of the amplitudes of the 50Hz even-order harmonics of the real-time vibration signal is as follows: in, is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; It is the amplitude of odd-order harmonics of the fundamental frequency 50Hz in the real-time vibration signal.
5. The transformer fault early warning method based on vibration frequency domain eigenvalues according to claim 1 is characterized in that: According to the vibration frequency domain eigenvalue, the process of calculating the status assessment coefficient of the current operating status of the transformer to be warned is as follows: The vibration frequency domain eigenvalue is input into the pre-built transformer operation status assessment model to calculate the status assessment coefficient of the current operation status of the transformer to be warned; wherein the pre-built transformer operation status assessment model is specifically as follows: in, is the status assessment coefficient of the current operating status of the transformer to be warned; is the frequency domain amplitude average value of the real-time vibration signal; is the average frequency domain amplitude value of the transformer to be warned in normal operation; is the center of gravity frequency of the real-time vibration signal; The center of gravity frequency of the transformer to be warned in normal operation; is the sum of the 50Hz odd-order harmonic amplitudes of the real-time vibration signal; is the amplitude sum of 50Hz even-order harmonics of the real-time vibration signal; The sum of the 50Hz odd-order harmonic amplitudes in the normal operation of the transformer to be warned; is the sum of the amplitudes of 50Hz even-order harmonics under normal operation of the transformer to be warned.
6. The transformer fault early warning method based on vibration frequency domain eigenvalues according to claim 1 is characterized in that: The preset evaluation coefficient threshold is determined based on the historical operating data and known fault modes of the transformer to be warned.
7. The transformer fault early warning method based on vibration frequency domain characteristic value according to claim 1 is characterized in that: The process of comparing the state evaluation coefficient of the current operating state of the transformer to be warned with the preset evaluation coefficient threshold to obtain the fault warning result of the transformer to be warned is as follows: Compare the state evaluation coefficient of the current operating state of the transformer to be warned with the preset evaluation coefficient threshold; If the state evaluation coefficient of the current operating state of the transformer to be warned exceeds the preset evaluation coefficient threshold, the fault warning result of the transformer to be warned is output as fault, and a preset fault warning signal is issued; Otherwise, the fault warning result of the transformer to be warned is normal.
8. A transformer fault early warning system based on vibration frequency domain eigenvalues, characterized in that: include: A vibration signal acquisition module is used to collect the vibration signal of the transformer to be warned in real time and obtain the real-time vibration signal; A frequency domain analysis module, used to perform frequency domain analysis on the real-time vibration signal to obtain a vibration frequency domain characteristic value; A state assessment module is used to calculate the state assessment coefficient of the current operating state of the transformer to be warned according to the vibration frequency domain characteristic value; The early warning module is used to compare the state evaluation coefficient of the current operating state of the transformer to be warned with a preset evaluation coefficient threshold to obtain a fault early warning result of the transformer to be warned.
9. A transformer fault early warning device based on vibration frequency domain characteristic values, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the transformer fault early warning method based on vibration frequency domain eigenvalues according to any one of claims 1 to 7 is executed.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the transformer fault early warning method based on vibration frequency domain eigenvalues as described in any one of claims 1 to 7 is implemented.