Power equipment fault diagnosis method and device, medium and equipment

Abstract

The invention discloses a power equipment fault diagnosis method and device, a medium and equipment. According to the method, the sound signal, the vibration signal and the characteristic spectrum of the power equipment are obtained, the preset position of the equipment is combined, the characteristic values of the sound signal and the vibration signal and the distance from the center of the equipment are calculated, and then the influence value is obtained. According to the process, the technical means of signal processing and data analysis are utilized, and whether the power equipment breaks down or not is accurately judged by comparing the fault influence value with the threshold value in the preset database. The method not only improves the accuracy and reliability of fault detection, but also optimizes the maintenance and operation flow of the power equipment through data-driven decision support, and solves the problem that whether the power equipment has a fault cannot be accurately judged in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of diagnosis of power equipment failures, and particularly to a method, device, medium and equipment for diagnosing power equipment failures. Background Art

[0002] In today's society, whether it is people's daily life or enterprises' production activities, they all rely on the efficient, safe and reliable operation of the electrical system. Maintaining power equipment and keeping it in good working condition is the top priority of the operation and maintenance work of front-line personnel.

[0003] However, the current power equipment fault diagnosis technology mainly has the following problems: 1) It mainly conducts acoustic imaging tests after detecting abnormal sounds, but this instrument is expensive and the detection is carried out after the abnormal sound occurs. 2) Abnormal sounds are often detected by operation and maintenance personnel during inspections, and the acoustic signals of abnormal sounds cannot be detected and analyzed in a timely manner. Especially for the internal discharge abnormal sounds of GIS, defects can be detected in a timely manner through the judgment of timely acoustic characteristic signals, and power outages can be processed to avoid the occurrence of unplanned power outage accidents. 3) For some equipment, such as abnormal sounds inside switch cabinets, acoustic imaging is limited by the observation window and may not be convenient for testing. And the sound level can only collect the sound pressure magnitude and cannot perform acoustic signal feature analysis. These problems lead to the inability of the existing technology to accurately judge whether a power equipment has failed. Summary of the Invention

[0004] The present invention provides a method, device, medium and equipment for diagnosing power equipment failures to solve the problem in the existing technology that it is impossible to accurately judge whether a power equipment has failed.

[0005] In a first aspect, the present application provides a method for diagnosing power equipment failures, including:

[0006] Obtaining each acoustic signal, each vibration signal, the characteristic spectrum of each acoustic signal and the characteristic spectrum of each vibration signal of the power equipment;

[0007] Calculating each first eigenvalue of each acoustic signal, each second eigenvalue of each vibration signal, each first distance of each acoustic signal and each second distance of each vibration signal according to the each acoustic signal, each vibration signal, the characteristic spectrum of each acoustic signal and the characteristic spectrum of each vibration signal and the preset positions of the power equipment;

[0008] Calculating the influence value of each power equipment according to the each first eigenvalue, each second eigenvalue, each first distance and each second distance;

[0009] Based on the influence values of each power device, the fault influence values of each power device in the preset database, and each preset threshold, it is determined whether the power device has a fault.

[0010] In this application, by comprehensively collecting the acoustic signals and vibration signals of power devices and their characteristic spectra, the subtle changes in the device state can be comprehensively captured. Using these data, combined with the preset positions of the power devices, the characteristic values of the acoustic signals and vibration signals and their distances from the device center are calculated, so as to obtain more accurate influence values. This process not only improves the accuracy of fault diagnosis, but also enhances the sensitivity to changes in the device state. Finally, by comparing with the fault influence values and thresholds in the preset database, this application can quickly and accurately determine whether the power device has a fault, thus significantly improving the operation and maintenance efficiency and reliability of the power device. This application solves the problem in the prior art that it is impossible to accurately determine whether the power device has a fault.

[0011] As a preferred embodiment of the first aspect, the step of determining whether the power device has a fault based on the influence values of each power device, the fault influence values of each power device in the preset database, and each preset threshold is specifically as follows:

[0012] According to the fault influence values of each power device, the average value of the fault influence of the power device is calculated;

[0013] Based on the average value of the fault influence, the fault influence values of each power device in the preset database, and each preset threshold, it is determined whether the power device has a fault.

[0014] In this preferred embodiment, this application provides a more accurate fault diagnosis method by calculating the fault influence values of each power device and obtaining the average value of the fault influence. This method uses the comparison of the average value of the fault influence with the fault influence values in the preset database and the preset thresholds to more reliably determine whether the power device has a fault. Since the average value of the fault influence synthesizes multiple measurement results, it reduces the influence of single measurement errors and improves the stability and accuracy of diagnosis. Therefore, compared with the methods that only rely on single measurement or do not rely on statistical data, this application can more effectively identify the abnormal state of the power device, give early warnings of potential faults, thus improving the reliability and safety of the power system, reducing the risk of unexpected power outages, and ensuring the continuity and stability of power supply.

[0015] As a preferred embodiment of the first aspect, the step of determining whether the power device has a fault based on the average value of the fault influence, the fault influence values of each power device in the preset database, and each preset threshold is specifically as follows:

[0016] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is less than or equal to a preset first threshold, it is determined that the power device has a fault;

[0017] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is less than a preset second threshold, it is determined that the power device is operating normally.

[0018] In this preferred embodiment, the present application determines the state of the power device by comparing the average value of the fault impacts with the fault impact values in the database and combining two preset thresholds, providing a highly accurate fault diagnosis method. First, the average value of the fault impacts is calculated based on multiple measurements, which can reduce accidental errors and provide a more stable indication of the device state. Then, by setting two thresholds, the present application can distinguish whether the device has a fault or is operating normally. If the difference between the average value of the fault impacts and the fault impact values in the database is within the first threshold, it indicates that the device state deviates significantly from the normal range, thus determining that the device has a fault; if the difference is less than the second threshold, it is considered that the device state is within the normal fluctuation range, and it is determined that the device is operating normally. This method improves the accuracy and reliability of fault diagnosis, reduces the possibility of misjudgment, effectively prevents and reduces faults of power devices, and ensures the stable operation of the power system through precise numerical comparison and threshold setting.

[0019] As a preferred embodiment of the first aspect, the step of determining that the power device is operating normally when the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is less than a preset second threshold further includes:

[0020] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is greater than a preset first threshold and greater than a preset third threshold, it is determined that each acoustic signal, each vibration signal, the characteristic spectrum of each acoustic signal, or the characteristic spectrum of each vibration signal has not been acquired;

[0021] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is greater than a preset first threshold, and the absolute value is greater than the second threshold and less than the third threshold, it is determined that each acoustic signal, each vibration signal, the characteristic spectrum of each acoustic signal, and the characteristic spectrum of each vibration signal need to be re-acquired.

[0022] In this preferred embodiment, the present application finely determines the operating state of the power equipment by setting three thresholds, improving the accuracy of diagnosis and the guidance of operation. First, if the absolute value of the difference between the average value of the fault impact and the fault impact value in the database is less than the second threshold, it is considered that the power equipment is operating normally, because a smaller difference indicates that the equipment state is close to the normal state. Second, if the absolute value of the difference is greater than the first threshold and greater than the third threshold, this indicates that the equipment state is extremely different from the normal state and exceeds the normal fluctuation range. Therefore, it is determined that the key sound signal and vibration signal data have not been successfully obtained, which may be due to measurement equipment failure or operation error. Finally, if the absolute value of the difference is greater than the first threshold but less than the third threshold, this indicates that although the equipment state is abnormal but has not reached an extreme situation, which may be due to incomplete signal acquisition or environmental interference. Therefore, it is necessary to re-obtain the signal and the characteristic spectrogram for more accurate diagnosis. This method not only can accurately determine whether the equipment is operating normally through refined threshold judgment, but also can provide clear operation guidance when the data acquisition is incomplete or there are doubts, thus improving the reliability and practicality of the power equipment fault diagnosis.

[0023] As a preferred embodiment of the first aspect, the obtaining of each sound signal, each vibration signal, the characteristic spectrogram of each sound signal, and the characteristic spectrogram of each vibration signal of the power equipment is specifically as follows:

[0024] According to each preset sound signal input module and each preset vibration signal input module, each sound signal, each vibration signal, the characteristic spectrogram of each sound signal, and the characteristic spectrogram of each vibration signal of the power equipment are obtained.

[0025] In this preferred embodiment, the present application obtains the sound signal, vibration signal, and their characteristic spectrograms of the power equipment by using the preset sound signal input module and vibration signal input module, improving the standardization and accuracy of data acquisition. Since the fault diagnosis of power equipment depends on accurate and reliable data input, the present application ensures the consistency and comparability of data through the standardized sound signal and vibration signal acquisition modules. This standardized acquisition method reduces the errors caused by human operation differences or equipment inaccuracies, making the obtained sound signals and vibration signals more accurately reflect the actual state of the power equipment. Further, by analyzing the characteristic spectrograms of these signals, the operating condition of the equipment can be understood more deeply, thus realizing the early warning and accurate diagnosis of power equipment faults.

[0026] In the second aspect, the present application provides a diagnostic device for power equipment faults. The diagnostic device for power equipment faults includes an acquisition module, a calculation module, and a judgment module;

[0027] The acquisition module is used to acquire various acoustic signals, various vibration signals, characteristic spectrograms of various acoustic signals, and characteristic spectrograms of various vibration signals of the power equipment;

[0028] The calculation module is used to calculate various first characteristic values of various acoustic signals, various second characteristic values of various vibration signals, various first distances of various acoustic signals, and various second distances of various vibration signals according to the various acoustic signals, various vibration signals, characteristic spectrograms of various acoustic signals, characteristic spectrograms of various vibration signals, and preset positions of the power equipment;

[0029] Calculate the influence values of various power equipment according to the various first characteristic values, various second characteristic values, various first distances, and various second distances;

[0030] The judgment module is used to judge whether the power equipment fails according to the influence values of various power equipment, the fault influence values of various power equipment in the preset database, and various preset thresholds.

[0031] This device uses three modules to work in division of labor and coordination, which can diagnose the faults of the power system more accurately. This application can comprehensively capture the subtle changes in the equipment state by comprehensively collecting the acoustic signals and vibration signals of the power equipment and their characteristic spectrograms. Using these data, combined with the preset positions of the power equipment, the characteristic values of the acoustic signals and vibration signals and their distances from the equipment center are calculated, so as to obtain more accurate influence values. This process not only improves the accuracy of fault diagnosis, but also enhances the sensitivity to the changes in the equipment state. Finally, by comparing with the fault influence values and thresholds in the preset database, this application can quickly and accurately judge whether the power equipment fails, thus significantly improving the operation and maintenance efficiency and reliability of the power equipment. This application solves the problem that it is impossible to accurately judge whether the power equipment fails in the prior art.

[0032] As a preferred embodiment of the second aspect, the judgment module includes a calculation unit and a judgment unit, specifically:

[0033] The calculation unit is used to calculate the average value of the fault influence of the power equipment according to the fault influence values of various power equipment;

[0034] The judgment unit is used to judge whether the power equipment fails according to the average value of the fault influence, the fault influence values of various power equipment in the preset database, and various preset thresholds.

[0035] In this preferred embodiment, the present application provides a more accurate fault diagnosis method by calculating the fault impact values of each power device and obtaining the average value of the fault impacts. This method can more reliably determine whether a power device has failed by comparing the average value of the fault impacts with the fault impact values in the preset database and the preset thresholds. Since the average value of the fault impacts synthesizes multiple measurement results, it reduces the influence of single measurement errors and improves the stability and accuracy of diagnosis. Therefore, compared with the methods that only rely on single measurement or do not rely on statistical data, the present application can more effectively identify the abnormal states of power devices, timely warn of potential faults, thereby improving the reliability and safety of the power system, reducing the risk of unexpected power outages, and ensuring the continuity and stability of power supply.

[0036] As a preferred embodiment of the second aspect, the judging unit is configured to judge whether a power device has failed according to the average value of the fault impacts, the fault impact values of each power device in the preset database, and the preset thresholds. Specifically:

[0037] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is less than or equal to the preset first threshold, it is determined that the power device has failed;

[0038] If the absolute value of the difference between the average value of the fault impacts and the fault impact values of each power device in the preset database is less than the preset second threshold, it is determined that the power device is operating normally.

[0039] In this preferred embodiment, the present application provides a highly accurate fault diagnosis method by comparing the difference between the average value of the fault impacts and the fault impact values in the database and combining two preset thresholds to judge the state of the power device. First, the average value of the fault impacts is calculated based on multiple measurements, which can reduce accidental errors and provide a more stable indication of the device state. Then, by setting two thresholds, the present application can distinguish whether the device has failed or is operating normally. If the difference between the average value of the fault impacts and the fault impact values in the database is within the first threshold, it indicates that the device state significantly deviates from the normal range, and thus it is determined that the device has failed; if the difference is less than the second threshold, it is considered that the device state is within the normal fluctuation range, and it is determined that the device is operating normally. This method improves the accuracy and reliability of fault diagnosis through precise numerical comparison and threshold setting, reduces the possibility of misjudgment, thereby effectively preventing and reducing faults of power devices and ensuring the stable operation of the power system.

[0040] In a third aspect, the present application provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the diagnostic method for power equipment faults as described above. The beneficial effects are the same as those of the diagnostic method for power equipment faults provided in the first aspect of the present application.

[0041] In a fourth aspect, the present application provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements any one of the diagnostic methods for power equipment faults described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 : It is a schematic flowchart of an embodiment of the diagnostic method for power equipment faults provided by the present application;

[0043] Figure 2 : It is a schematic structural diagram of an embodiment of each module of the diagnosis of power equipment faults provided by the present application;

[0044] Figure 3 : It is a schematic structural diagram of an embodiment of the diagnostic device for power equipment faults provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment 1

[0047] Please refer to Figure 1 , which is a diagnostic method for power equipment faults provided by an embodiment of the present invention.

[0048] In this embodiment, the process of the diagnostic method for power equipment faults in the present application is described in detail through steps S01 - S04.

[0049] As Figure 2 shown, Figure 2 are the respective modules for diagnosing power equipment faults in the present application, including an acoustic signal input module, a vibration signal input module, and a discrimination module, and also include an external database and an output module;

[0050] The external database stores the characteristic sound signals, characteristic vibration signals, characteristic spectrograms of sound signals, and characteristic spectrograms of vibration signals when power equipment fails. The database allows users to upload the characteristic sound signals, characteristic vibration signals, characteristic spectrograms of sound signals, and characteristic spectrograms of vibration signals when power equipment fails by themselves.

[0051] The sound signal input module is: MediaRecorder.AudioSource.MIC, that is, a microphone acquisition device, with a sampling rate of 22050Hz, a sampling precision of 16bit for audio, and the input voice stream is in mono.

[0052] When recording, call the AudioRecord interface of the API to obtain a recording object, then call mediaPlayer.start() to start playing the dedicated test voice for the left and right channels. At the same time, create a recording thread, call the startRecording() method of the AudioRecord object to enable the recording function, and mark the isRecording status as true to indicate the recording state. After the test voice is played, call the stop method of the recording object to stop recording and mark the isRecording status as false. And save the normalized data in the form of a generic linked list data of LinkedList<short[]> to the memory for subsequent feature extraction processing.

[0053] S01: Obtain each sound signal, each vibration signal, the characteristic spectrogram of each sound signal, and the characteristic spectrogram of each vibration signal of the power equipment.

[0054] As a preferred embodiment of Embodiment 1, the obtaining of each sound signal, each vibration signal, the characteristic spectrogram of each sound signal, and the characteristic spectrogram of each vibration signal of the power equipment is specifically as follows:

[0055] Obtain each sound signal and the characteristic spectrogram of each sound signal through the sound signal input module at at least three positions with a linear interval greater than 1 meter, and input them into the discrimination module.

[0056] Obtain each vibration signal and the characteristic spectrogram of each vibration signal through the vibration signal module, repeat at least three times and ensure that the number of times of obtaining vibration signals is equal to the number of times of obtaining sound signals, and input all the obtained vibration signals into the discrimination module.

[0057] The discrimination module compares the sound signals with the vibration signals and the characteristic data of the power equipment failure in the database.

[0058] In this preferred embodiment, the present application obtains the acoustic signals, vibration signals and their characteristic spectra of power equipment by using a preset acoustic signal input module and vibration signal input module, improving the standardization and accuracy of data collection. Since the fault diagnosis of power equipment depends on accurate and reliable data input, the present application ensures the consistency and comparability of data through a standardized acoustic signal and vibration signal acquisition module. This standardized acquisition method reduces errors caused by differences in manual operations or equipment inaccuracies, making the obtained acoustic signals and vibration signals more accurately reflect the actual state of power equipment. Further, by analyzing the characteristic spectra of these signals, the operating conditions of the equipment can be more deeply understood, thus realizing early warning and accurate diagnosis of power equipment faults.

[0059] S02: Calculate the respective first eigenvalues of each acoustic signal, the respective second eigenvalues of each vibration signal, the respective first distances of each acoustic signal, and the respective second distances of each vibration signal according to the respective acoustic signals, the respective vibration signals, the characteristic spectra of each acoustic signal, the characteristic spectra of each vibration signal, and the preset positions of the power equipment.

[0060] S03: Calculate the influence values of each power equipment according to the respective first eigenvalues, the respective second eigenvalues, the respective first distances, and the respective second distances.

[0061] As a preferred embodiment of Embodiment 1, calculating the influence values of each power equipment according to the respective first eigenvalues, the respective second eigenvalues, the respective first distances, and the respective second distances specifically includes:

[0062] The formula for the influence value of the power equipment is as follows:

[0063]

[0064] where k is the influence value, x a , y a represent the eigenvalue x (respective first eigenvalues) of the acoustic signal a and the corresponding eigenvalue y (respective first eigenvalues), x b , y b represent the eigenvalue x (respective second eigenvalues) of the vibration signal b and the corresponding eigenvalue y (respective second eigenvalues), s is the distance between the acoustic signal receiving position and the center position of the power equipment (respective first distances), and d is the distance between the vibration signal receiving position and the center position of the power equipment (respective second distances).

[0065] S04: Determine whether the power equipment has a fault according to the influence values of each power equipment, the fault influence values of each power equipment in the preset database, and the preset thresholds.

[0066] As a preferred embodiment of the first embodiment, judging whether a power device fails according to the influence value of each power device, the fault influence value of each power device in the preset database, and each preset threshold is specifically as follows:

[0067] According to the number of times of acquiring the sound signal and the number of times of acquiring the vibration signal, the influence value k takes the average value.

[0068] If the absolute value of the difference between the influence value k and the influence value k λ of a certain power device failure in the database is less than or equal to 0.64, it is determined that the power device under inspection has this failure;

[0069] If the absolute value of the difference between the influence value k and the influence value k0 when the power device is operating normally is less than 1.00, the current power device is operating normally;

[0070] If the absolute value of the difference between the influence value k and the influence value of any power device failure in the current database is greater than 0.64, and the absolute value of the difference from the influence value k0 when the power device is operating normally is greater than 1.25, the user is warned that the power device under inspection has an unknown failure and the user is asked whether to upload the current characteristic sound signal, characteristic vibration signal, sound signal characteristic spectrogram, and vibration signal characteristic spectrogram;

[0071] If the absolute value of the difference between the influence value k and the influence value of any power device failure in the current database is greater than 0.64, and the difference from the influence value k0 when the power device is operating normally is between 1.00 and 1.25, it is prompted that the measurement fluctuation of the user is large and retesting is required.

[0072] Among them, the influence value k0 when the power device in the database operates normally and the influence value k λ of a certain power device failure will be automatically corrected after the user adds new data to the database. The correction method is to take the average value of the influence values after adding new data.

[0073] In this preferred embodiment, the present application refines the judgment of the operating state of power equipment by setting three thresholds, improving the accuracy of diagnosis and the guidance of operation. First, if the absolute value of the difference between the average fault impact and the fault impact value in the database is less than the second threshold, it is considered that the power equipment is operating normally, because a smaller difference indicates that the equipment state is close to the normal state. Second, if the absolute value of the difference is greater than the first threshold and greater than the third threshold, this indicates that the equipment state is extremely different from the normal state and exceeds the normal fluctuation range. Therefore, it is judged that the key acoustic signal and vibration signal data have not been successfully obtained, which may be due to measurement equipment failure or operation error. Finally, if the absolute value of the difference is greater than the first threshold but less than the third threshold, this indicates that although the equipment state is abnormal but has not reached an extreme situation, which may be due to incomplete signal acquisition or environmental interference. Therefore, it is necessary to re-acquire the signal and the characteristic spectrum for more accurate diagnosis. This method not only can accurately judge whether the equipment is operating normally through refined threshold judgment, but also can provide clear operation guidance when the data acquisition is incomplete or there are doubts, thus improving the reliability and practicality of the power equipment fault diagnosis.

[0074] By comprehensively collecting the acoustic signals, vibration signals and their characteristic spectra of power equipment, the present application can comprehensively capture the subtle changes in the equipment state. Using these data, combined with the preset position of the power equipment, the characteristic values of the acoustic signals and vibration signals and their distances from the equipment center are calculated, so as to obtain a more accurate impact value. This process not only improves the accuracy of fault diagnosis, but also enhances the sensitivity to the changes in the equipment state. Finally, by comparing with the fault impact values and thresholds in the preset database, the present application can quickly and accurately judge whether the power equipment has failed, thus significantly improving the operation and maintenance efficiency and reliability of the power equipment. The present application solves the problem in the prior art that it is impossible to accurately judge whether the power equipment has failed.

[0075] Embodiment 2

[0076] Please refer to Figure 3 , a diagnostic device for power equipment faults provided by an embodiment of the present application.

[0077] In this embodiment, the diagnostic device for power equipment faults includes an acquisition module 10, a calculation module 20 and a judgment module 30.

[0078] As Figure 2 shown, Figure 2 are the various modules for power equipment fault diagnosis of the present application, including an acoustic signal input module, a vibration signal input module and a discrimination module, and also include an external database and an output module;

[0079] The external database stores the characteristic sound signals, characteristic vibration signals, characteristic spectrograms of sound signals, and characteristic spectrograms of vibration signals when power equipment fails; the database allows users to upload the characteristic sound signals, characteristic vibration signals, characteristic spectrograms of sound signals, and characteristic spectrograms of vibration signals when power equipment fails by themselves.

[0080] The sound signal input module is: MediaRecorder.AudioSource.MIC, i.e., a microphone acquisition device, with a sampling rate of 22050Hz, a sampling precision of 16 bits for audio, and the input voice stream is in mono.

[0081] When recording, call the AudioRecord interface of the API to obtain a recording object, then call mediaPlayer.start() to start playing the dedicated test voice for the left and right channels. At the same time, create a recording thread, call the startRecording() method of the AudioRecord object to enable the recording function, and mark the isRecording status as true to indicate the recording state; after the test voice is played, call the stop method of the recording object to stop recording and mark the isRecording status as false; and save the normalized data in the form of a generic linked list data of LinkedList<short[]> to the memory for subsequent feature extraction processing.

[0082] The acquisition module 10 is used to acquire various sound signals, various vibration signals, characteristic spectrograms of various sound signals, and characteristic spectrograms of various vibration signals of the power equipment.

[0083] As a preferred embodiment of the second embodiment, the acquisition of various sound signals, various vibration signals, characteristic spectrograms of various sound signals, and characteristic spectrograms of various vibration signals of the power equipment is specifically as follows:

[0084] Acquire various sound signals and characteristic spectrograms of various sound signals through the sound signal input module at at least three positions with a linear interval greater than 1 meter, and transmit them to the discrimination module;

[0085] Acquire various vibration signals and characteristic spectrograms of various vibration signals through the vibration signal module, repeat at least three times and ensure that the number of times of acquiring vibration signals is equal to the number of times of acquiring sound signals, and transmit all the obtained vibration signals to the discrimination module;

[0086] The discrimination module compares the sound signals with the vibration signals and the characteristic data of the power equipment failure in the database.

[0087] In this preferred embodiment, the present application obtains the acoustic signals, vibration signals and their characteristic spectra of power equipment by using a preset acoustic signal recording module and vibration signal recording module, improving the standardization and accuracy of data acquisition. Since the fault diagnosis of power equipment depends on accurate and reliable data input, the present application ensures the consistency and comparability of data through standardized acoustic signal and vibration signal acquisition modules. This standardized acquisition method reduces errors caused by differences in manual operations or equipment inaccuracies, making the obtained acoustic signals and vibration signals more accurately reflect the actual state of the power equipment. Further, by analyzing the characteristic spectra of these signals, the operating conditions of the equipment can be understood more deeply, thereby realizing early warning and accurate diagnosis of power equipment faults.

[0088] The calculation module 20 is used to calculate, according to the respective acoustic signals, respective vibration signals, characteristic spectra of the respective acoustic signals, characteristic spectra of the respective vibration signals, and preset positions of the power equipment, respective first characteristic values of the respective acoustic signals, respective second characteristic values of the respective vibration signals, respective first distances of the respective acoustic signals, and respective second distances of the respective vibration signals;

[0089] The calculation module 20 is further used to calculate, according to the respective first characteristic values, respective second characteristic values, respective first distances, and respective second distances, influence values of the respective power equipment;

[0090] As a preferred embodiment of the second embodiment, calculating the influence values of the respective power equipment according to the respective first characteristic values, respective second characteristic values, respective first distances, and respective second distances specifically includes:

[0091] The formula for the influence value of the power equipment is as follows:

[0092]

[0093] where k is the influence value, x a , y a represent the characteristic value x (respective first characteristic values) of the acoustic signal a and the corresponding characteristic value y (respective first characteristic values), x b , y b represent the characteristic value x (respective second characteristic values) of the vibration signal b and the corresponding characteristic value y (respective second characteristic values), s is the distance between the acoustic signal receiving position and the center position of the power equipment (respective first distances), and d is the distance between the vibration signal receiving position and the center position of the power equipment (respective second distances).

[0094] The judgment module 30 is used to judge whether the power equipment has a fault according to the influence values of the respective power equipment, fault influence values of the respective power equipment in the preset database, and preset respective thresholds.

[0095] As a preferred embodiment of the second embodiment, determining whether a power device has a fault according to the influence values of the respective power devices, the fault influence values of the respective power devices in the preset database, and the respective preset thresholds is specifically as follows:

[0096] According to the number of times of acquiring the acoustic signal and the number of times of acquiring the vibration signal, the influence value k takes an average value.

[0097] If the absolute value of the difference between the influence value k and the influence value k λ of a certain power device fault in the database is less than or equal to 0.64, it is determined that the power device under inspection has this fault;

[0098] If the absolute value of the difference between the influence value k and the influence value k0 when the power device is operating normally is less than 1.00, the current power device is operating normally;

[0099] If the absolute value of the difference between the influence value k and the influence value of any power device fault in the current database is greater than 0.64, and the absolute value of the difference between the influence value k and the influence value k0 when the power device is operating normally is greater than 1.25, the user is warned that the power device under inspection has an unknown fault and the user is asked whether to upload the current characteristic acoustic signal, characteristic vibration signal, acoustic signal characteristic spectrogram, and vibration signal characteristic spectrogram;

[0100] If the absolute value of the difference between the influence value k and the influence value of any power device fault in the current database is greater than 0.64, and the difference between the influence value k and the influence value k0 when the power device is operating normally is between 1.00 and 1.25, it is prompted that the measurement fluctuation of the user is relatively large and a retest is required.

[0101] Among them, the influence value k0 when the power device in the database is operating normally and the influence value k of a certain power device fault λ will be automatically corrected after the user adds new data to the database. The correction method is to take the average value of the influence values after adding the new data.

[0102] In this preferred embodiment, the present application finely determines the operating state of power equipment by setting three thresholds, improving the accuracy of diagnosis and the guidance of operation. First, if the absolute value of the difference between the average value of the fault impact and the fault impact value in the database is less than the second threshold, it is considered that the power equipment is operating normally, because a smaller difference indicates that the equipment state is close to the normal state. Second, if the absolute value of the difference is greater than the first threshold and greater than the third threshold, this indicates that the equipment state is extremely different from the normal state and exceeds the normal fluctuation range. Therefore, it is determined that the key acoustic signal and vibration signal data have not been successfully obtained, which may be caused by measurement equipment failure or operation error. Finally, if the absolute value of the difference is greater than the first threshold but less than the third threshold, this indicates that although the equipment state is abnormal, it has not reached an extreme situation, which may be caused by incomplete signal acquisition or environmental interference. Therefore, it is necessary to re-acquire the signal and the characteristic spectrum for more accurate diagnosis. This method not only accurately determines whether the equipment is operating normally through refined threshold judgment, but also provides clear operation guidance when the data acquisition is incomplete or there are doubts, thus improving the reliability and practicality of the fault diagnosis of power equipment.

[0103] This device uses three modules to work in division and coordination to more accurately diagnose faults in the power system. The present application comprehensively collects the acoustic signals and vibration signals of power equipment and their characteristic spectra, and can comprehensively capture the subtle changes in the equipment state. Using these data, combined with the preset position of the power equipment, the characteristic values of the acoustic signals and vibration signals and their distances from the equipment center are calculated, so as to obtain a more accurate impact value. This process not only improves the accuracy of fault diagnosis, but also enhances the sensitivity to changes in the equipment state. Finally, by comparing with the fault impact values and thresholds in the preset database, the present application can quickly and accurately determine whether the power equipment has failed, thus significantly improving the operation and maintenance efficiency and reliability of the power equipment. The present application solves the problem in the prior art that it is impossible to accurately determine whether the power equipment has failed.

[0104] Embodiment 3:

[0105] The embodiment of the present application provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the diagnostic method for a power equipment fault described above;

[0106] Among them, for the diagnostic method of a power equipment fault, when it is implemented in the form of a software functional unit and used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0107] Embodiment 4

[0108] This application provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it realizes any one of the diagnostic methods of power equipment faults described in Embodiment 1.

[0109] For the above specific embodiments, the purpose, technical solution, and beneficial effects of the present invention have been further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for diagnosing a fault in an electric power device, characterized in that: include: Acquire each sound signal, each vibration signal, a characteristic spectrum of each sound signal, and a characteristic spectrum of each vibration signal of the electric power equipment; Calculate each first characteristic value of each sound signal, each second characteristic value of each vibration signal, each first distance of each sound signal, and each second distance of each vibration signal according to each sound signal, each vibration signal, the characteristic spectrum of each sound signal, and the preset position of the electric power equipment; Calculate the influence value of each power device according to each first characteristic value, each second characteristic value, each first distance and each second distance; Whether a fault occurs in the power equipment is determined based on the impact value of each power equipment, the fault impact value of each power equipment in the preset database, and each preset threshold value.

2. The method for diagnosing a fault in an electric power device according to claim 1, characterized in that: The determining whether a fault occurs in the power equipment according to the impact value of each power equipment, the fault impact value of each power equipment in the preset database, and each preset threshold value is specifically as follows: Calculating the average value of the fault impact of the power equipment according to the fault impact value of each power equipment; Whether a fault occurs in the power equipment is determined based on the fault impact average value, the fault impact value of each power equipment in the preset database, and each preset threshold value.

3. The method for diagnosing a fault in an electric power device according to claim 2, characterized in that: The determining whether a fault occurs in the power equipment according to the fault impact average value, the fault impact value of each power equipment in the preset database and each preset threshold value is specifically as follows: If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is less than or equal to a preset first threshold, it is determined that the power device has a fault; If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is smaller than a preset second threshold, it is determined that the power device is operating normally.

4. The method for diagnosing a fault in an electric power device according to claim 3, characterized in that: If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is less than a preset second threshold, determining that the power device is operating normally also includes: If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is greater than a preset first threshold and greater than a preset third threshold, it is determined that each sound signal, each vibration signal, a characteristic spectrum of each sound signal or a characteristic spectrum of each vibration signal is not obtained; If the absolute value of the difference between the fault impact average value and the fault impact value of each power equipment in the preset database is greater than the preset first threshold, and the absolute value is greater than the second threshold and less than the third threshold, it is determined that it is necessary to re-acquire each sound signal, each vibration signal, the characteristic spectrum of each sound signal, and the characteristic spectrum of each vibration signal.

5. The method for diagnosing a fault in an electric power device according to claim 1, characterized in that: The step of obtaining each acoustic signal, each vibration signal, each characteristic spectrum of each acoustic signal and each characteristic spectrum of each vibration signal of the electric power equipment is specifically as follows: According to each preset sound signal recording module and each preset vibration signal recording module, each sound signal, each vibration signal, each characteristic spectrum of each sound signal and each characteristic spectrum of each vibration signal of the power equipment are obtained.

6. A diagnostic device for power equipment failure, characterized in that: It includes an acquisition module, a calculation module and a judgment module; The acquisition module is used to acquire each sound signal, each vibration signal, a characteristic spectrum of each sound signal and a characteristic spectrum of each vibration signal of the electric equipment; The calculation module is used to calculate each first characteristic value of each sound signal, each second characteristic value of each vibration signal, each first distance of each sound signal, and each second distance of each vibration signal according to each sound signal, each vibration signal, the characteristic spectrum of each sound signal, the characteristic spectrum of each vibration signal, and the preset position of the electric power equipment; Calculate the influence value of each power device according to each first characteristic value, each second characteristic value, each first distance and each second distance; The judgment module is used to judge whether a fault occurs in the power equipment according to the impact value of each power equipment, the fault impact value of each power equipment in the preset database, and each preset threshold value.

7. The device for diagnosing a fault in an electric power device according to claim 6, characterized in that: The judgment module includes a calculation unit and a judgment unit, specifically: The calculation unit is used to calculate the average value of the fault impact of the power equipment according to the fault impact value of each power equipment; The judgment unit is used to judge whether a fault occurs in the power equipment according to the fault impact average value, the fault impact value of each power equipment in the preset database and each preset threshold value.

8. The device for diagnosing a fault in an electric power device according to claim 7, characterized in that: The judgment unit is used to judge whether a fault occurs in the power equipment according to the fault impact average value, the fault impact value of each power equipment in the preset database and each preset threshold value, specifically: If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is less than or equal to a preset first threshold, it is determined that the power device has a fault; If the absolute value of the difference between the fault impact average value and the fault impact value of each power device in the preset database is smaller than a preset second threshold, it is determined that the power device is operating normally.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for diagnosing a fault of an electric power device as claimed in any one of claims 1 to 5.

10. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for diagnosing a fault of an electric power device as claimed in any one of claims 1 to 5 when executing the computer program.

Images