A sound fault detection method applied to power Internet of Things

By performing characteristic analysis and comprehensive evaluation of the sound signals of power equipment, the problem of fault detection accuracy in environmental impact and multiple fault conditions in the prior art is solved, and more accurate and reliable fault diagnosis is achieved.

CN118692497BActive Publication Date: 2024-11-19ZHONGYING QINGCHUANG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411172682.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-19
Estimated Expiration
2044-08-26

AI Technical Summary

Technical Problem

The prior art cannot accurately determine the source and type of fault sound in complex or unstable power operation environments, and cannot accurately determine the operating status of power equipment when multiple fault sounds exist at the same time, resulting in the accuracy of fault detection and Insufficient reliability.

Method used

By collecting the sound signals of power equipment, perform sound characteristics analysis, time series comparison analysis, reference library comparison analysis and environmental influencing factor evaluation, calculate fault evaluation index, and conduct comprehensive sound fault evaluation to improve the accuracy and reliability of fault detection.

Benefits of technology

Effectively capture the sound characteristics of the equipment under different working conditions, improve the pertinence and accuracy of fault detection, improve the reliability and accuracy of detection, and provide more accurate fault diagnosis results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118692497B_ABST
    Figure CN118692497B_ABST
Patent Text Reader

Abstract

The present invention discloses a sound fault detection method applied to an electric power Internet of Things, and relates to the technical field of the electric power Internet of Things. In the process of sound feature analysis, by collecting and analyzing the sound signals generated by designated electric equipment during operation, it is beneficial to accurately evaluate whether the sound signals meet the requirements as a basis for fault detection. Through this process, the sound features of the equipment under different working conditions are effectively captured, thereby providing basic data for subsequent fault detection, ensuring that the sound signals have undergone preliminary screening and verification before fault detection, and improving the pertinence and accuracy of fault detection. Through time series comparative analysis, the first sound fault information of the designated sound signal at each collection time point is obtained, and the first fault evaluation index is calculated, which is helpful to identify time-varying fault features that may exist in the equipment during operation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric power Internet of Things, and in particular to a sound fault detection method applied to electric power Internet of Things. Background Art

[0002] Power equipment will generate different sound signals in normal operation and fault conditions. By analyzing the characteristics of these sound signals, the operating status of the equipment can be identified. For example, the abnormal sound of a transformer may indicate the aging of the internal insulation material or other faults. Therefore, the characteristic analysis of sound signals has become an effective means of fault detection.

[0003] Prior art, such as the invention patent application with announcement number CN113362856A, discloses a sound fault detection method and device applied to the power Internet of Things. The device can collect sound signals and convert them into analog signals through a sound array sensor, and convert them into digital signals through an information processing module; then the digital signal is normalized, pre-emphasized, framed, and windowed in sequence; a short-time Fourier transform is used to obtain a sound feature matrix and feature parameters; a two-dimensional principal component analysis method is used to reduce the dimension of the sound feature matrix, and sound feature information is extracted from the sound feature matrix after the dimension reduction process, and the sound feature information is classified and identified to determine whether it is a fault sound, and if it is a fault sound, an orientation judgment is made.

[0004] With respect to the above scheme, the applicant of the present invention has found that the above technology has at least the following technical problems: 1. The above scheme lacks the content of evaluating the environmental influencing factors of the sound signal, which will lead to the inability to accurately judge the source and type of the fault sound in a complex or unstable power operation environment. In actual applications, the ambient temperature, wind speed and electric field strength factors will affect the sound signal, thereby affecting the accuracy of fault detection. If the influence of these factors cannot be ruled out, then even if advanced short-time Fourier transform and two-dimensional principal component analysis methods are used, it will lead to erroneous fault judgment.

[0005] 2. The above scheme lacks the content of comprehensive sound fault evaluation of sound signals, which results in the inability to accurately judge the actual operating status of the power equipment when multiple fault sounds exist at the same time. In actual applications, power equipment may have multiple faults at the same time, such as mechanical faults and electrical faults, and these faults will produce different sound characteristics. If these characteristics cannot be comprehensively evaluated, then even if the fault sound can be correctly identified, the overall operating status of the power equipment cannot be accurately judged. Summary of the invention

[0006] The purpose of the present invention is to provide a sound fault detection method applied to the power Internet of Things, which solves the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a sound fault detection method applied to the power Internet of Things, including: Step 1, sound feature analysis: Collecting the specified sound signal generated by the specified power equipment during operation, thereby evaluating whether the specified sound signal meets the requirements as the basis for fault detection of the specified power equipment.

[0008] Step 2: time series comparison and analysis: when the designated sound signal satisfies the basis for designated power equipment fault detection, the first sound fault information corresponding to the designated sound signal at each acquisition time point is obtained, and then the first fault assessment index corresponding to the designated power equipment is calculated.

[0009] Step 3: Reference library comparison and analysis: obtaining the second sound fault information corresponding to the specified sound signal, and then calculating the second fault assessment index corresponding to the specified power equipment.

[0010] Step 4: Environmental impact factor assessment: Collect the corresponding environmental impact factors within the specified power equipment setting range, and then calculate the corresponding environmental impact factors within the specified power equipment setting range.

[0011] Step 5: Comprehensive sound fault assessment: Based on the first fault assessment index and the second fault assessment index corresponding to the designated power equipment and the corresponding environmental impact factor within the setting range of the designated power equipment, assess whether the designated power equipment has an operating fault.

[0012] Step 6: Display prompt: When the designated sound signal does not meet the criteria for designated power equipment fault detection and the designated power equipment has an operating fault, a display prompt is performed.

[0013] Preferably, the first sound fault information corresponding to the designated sound signal at each acquisition time point is obtained, and the specific acquisition process is as follows: the designated sound signal corresponding to the designated power equipment is collected at each acquisition time point by a sound sensor, the continuous designated sound signal is divided into short time frames, the short-time energy in each short time frame is calculated to obtain each short-time energy, and then each short-time energy is calculated by the mean value, and the result obtained is the short-time energy, thereby obtaining the short-time energy corresponding to each acquisition time point;

[0014] The instantaneous sound pressure value and instantaneous amplitude corresponding to each acquisition time point are read from the sound sensor, and then the instantaneous sound pressure value corresponding to each acquisition time point is converted into the sound pressure level corresponding to each acquisition time point through a calculation formula.

[0015] Preferably, the first fault assessment index corresponding to the specified power equipment is calculated, and the specific calculation process is as follows: according to the set collection time points, n is the number corresponding to each collection time point, t=1, 2, ..., n, n is any integer greater than 2, and t represents the total number corresponding to the collection time points;

[0016] By calculating the formula

[0017] The first fault assessment index α corresponding to the specified power equipment is obtained, where et, Qt, and ut represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the tth acquisition time point, respectively, and et +1 , Qt +1 ,ut +1 They represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the t+1th acquisition time point, respectively. κ1, κ2, and κ3 are the weight factors corresponding to the set short-time energy, sound pressure level, and instantaneous amplitude, respectively.

[0018] The beneficial effects of the present invention are: 1. A sound fault detection method applied to the electric power Internet of Things provided by the present invention, in the process of sound feature analysis, by collecting and analyzing the sound signals generated by the specified power equipment during operation, it is beneficial to accurately evaluate whether the sound signals meet the requirements as the basis for fault detection. Through this process, the sound characteristics of the equipment under different working conditions are effectively captured, thereby providing basic data for subsequent fault detection, ensuring that the sound signal has undergone preliminary screening and verification before fault detection, thereby improving the pertinence and accuracy of fault detection, and obtaining the first sound fault information of the specified sound signal at each collection time point through time series comparative analysis, and calculating the first fault evaluation index, which is helpful to identify the time-varying fault characteristics that may exist in the equipment during operation.

[0019] 2. The embodiment of the present invention obtains the second sound fault information of the specified sound signal and calculates the second fault evaluation index, which is beneficial to compare the collected sound signal with the existing standard or reference data, so that the fault detection system can perform verification and comparison based on the existing knowledge base, thereby improving the reliability and accuracy of detection. Environmental factors will affect the normal operation of power equipment. Therefore, incorporating environmental factors into the evaluation system in fault detection will help improve the accuracy and reliability of detection.

[0020] 3. In the comprehensive sound fault assessment stage, the embodiment of the present invention performs a comprehensive analysis by combining the first fault assessment index, the second fault assessment index and the environmental impact factor, which is conducive to forming a comprehensive assessment of the equipment fault, integrating various data and analysis results, and providing more accurate fault diagnosis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a schematic flow chart of the implementation steps of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] See also Figure 1 As shown, the present invention provides a sound fault detection method applied to the power Internet of Things, the method comprising: step one, sound feature analysis: collecting a specified sound signal generated by a specified power device during operation, thereby evaluating whether the specified sound signal meets the requirements as a basis for fault detection of the specified power device.

[0025] It should be noted that sound signal is the digital form of sound represented in computers or electronic devices. The physical fluctuations of sound are converted into discrete digital data through sampling and quantization.

[0026] In a specific embodiment, the first sound fault information includes short-time energy, sound pressure level and instantaneous amplitude, the second sound fault information includes total harmonic distortion and zero-crossing rate, and the environmental influencing factors include ambient temperature, wind speed and electric field strength.

[0027] It should be noted that short-time energy refers to the total energy of a sound signal in a short time window. It is obtained by calculating the square sum of the sound sample values ​​in each time window, reflecting the intensity of the sound. When the power equipment is operating normally, the short-time energy remains in a stable range. If the short-time energy suddenly increases or becomes unstable, it indicates that there is an abnormal vibration or noise source inside the power equipment.

[0028] Sound pressure level is a parameter used to quantify the intensity of sound. It measures the size of the pressure change of sound relative to the reference pressure. In power equipment, the change of sound pressure level can reflect the operating status of the equipment. Under normal circumstances, the sound pressure level of power equipment remains within the design range. If the sound pressure level suddenly increases, it is due to mechanical or electrical failures inside the equipment, such as fan failure, transformer insulation aging and other problems, which cause the equipment to produce abnormal noise. On the contrary, a significant decrease in sound pressure level indicates that the equipment power has decreased or the operation is unstable.

[0029] The instantaneous amplitude is the intensity value of the sound signal at a specific point in time, reflecting the instantaneous changes in the sound waveform. If the instantaneous amplitude fluctuates greatly or has abnormal peaks, it indicates that the power equipment has mechanical vibration, looseness, or electrical problems. For power equipment, abnormal instantaneous amplitude can help identify potential faults, such as internal defects in transformers or motors.

[0030] In a specific embodiment, the evaluation of whether the designated sound signal satisfies the requirement as a basis for detecting faults in designated power equipment is carried out as follows: a designated sound signal generated by designated power equipment during operation is collected by a sound sensor, the designated sound signal is transmitted to a central database via a network, and the frequency of the designated sound signal is compared with each stored standard sound frequency interval. If the frequency of the designated sound signal belongs to a certain stored standard sound frequency interval, it indicates that the designated sound signal satisfies the requirement as a basis for detecting faults in designated power equipment. If the frequency of the designated sound signal does not belong to a certain stored standard sound frequency interval, it indicates that the designated sound signal does not meet the requirement as a basis for detecting faults in designated power equipment.

[0031] Step 2: time series comparison and analysis: when the designated sound signal satisfies the basis for designated power equipment fault detection, the first sound fault information corresponding to the designated sound signal at each acquisition time point is obtained, and then the first fault assessment index corresponding to the designated power equipment is calculated.

[0032] In a specific embodiment, the first sound fault information corresponding to the specified sound signal at each collection time point is obtained, and the specific acquisition process is as follows: the specified sound signal corresponding to the specified power equipment is collected by a sound sensor at each collection time point, and the continuous specified sound signal is divided into short time frames, and the short-time energy in each short time frame is calculated to obtain each short-time energy, and then each short-time energy is calculated by the average, and the result obtained is the short-time energy, thereby obtaining the short-time energy corresponding to each collection time point.

[0033] The instantaneous sound pressure value and instantaneous amplitude corresponding to each acquisition time point are read from the sound sensor, and then the instantaneous sound pressure value corresponding to each acquisition time point is converted into the sound pressure level corresponding to each acquisition time point through a calculation formula.

[0034] It should be noted that according to the calculation formula Calculate and obtain the short-time energy corresponding to a short time frame, y j is the sound signal value corresponding to the sampling point, j is the number corresponding to each sampling point, j = 1, 2, ..., m, m is any integer greater than 2, m represents the total number of sampling points, and each sampling point is included in the short time frame. The calculation formula is The sound pressure level TH corresponding to a certain acquisition time point is obtained, thereby obtaining the sound pressure level corresponding to each acquisition time point, where l and h represent the corresponding instantaneous sound pressure value and the standard sound pressure obtained from the database.

[0035] In a specific embodiment, the calculation specifies the first fault assessment index corresponding to the power equipment, and the specific calculation process is as follows: according to the set collection time points, t is the number corresponding to each collection time point, t=1, 2,..., n, n is any integer greater than 2, and n represents the total number corresponding to the collection time points.

[0036] By calculating the formula

[0037] The first fault assessment index α corresponding to the specified power equipment is obtained, where et, Qt, and ut represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the tth acquisition time point, respectively, and et +1 , Qt +1 ,ut +1 They represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the t+1th acquisition time point, respectively. κ1, κ2, and κ3 are the weight factors corresponding to the set short-time energy, sound pressure level, and instantaneous amplitude, respectively.

[0038] It should be noted that the values ​​of κ1, κ2 and κ3 are all greater than 0 and less than 1.

[0039] It should also be noted that the historical short-time energy weight factors, historical sound pressure level weight factors and historical instantaneous amplitude weight factors corresponding to each historical first fault assessment index are obtained from the database, and the median is selected from each historical short-time energy weight factor, each historical sound pressure level weight factor and each historical instantaneous amplitude weight factor, and the results are recorded as the weight factor corresponding to the set short-time energy, the weight factor corresponding to the sound pressure level, and the weight factor corresponding to the instantaneous amplitude.

[0040] Step 3: Reference library comparison and analysis: obtaining the second sound fault information corresponding to the specified sound signal, and then calculating the second fault assessment index corresponding to the specified power equipment.

[0041] In a specific embodiment, the second sound fault information corresponding to the specified sound signal is obtained, and the specific acquisition process is as follows: the collected specified sound signal is Fourier transformed, and the specified sound signal is converted from the time domain to the frequency domain, so as to obtain the spectrum of the specified sound signal, and the basic frequency of the specified sound signal is obtained in the spectrum, which is recorded as P, and the amplitude of each harmonic component is squared to obtain the harmonic power, which is recorded as D, thereby calculating the formula

[0042] Get the total harmonic distortion corresponding to the specified sound signal.

[0043] The designated sound signal is compared point by point at each set time point to detect whether the designated sound signal crosses the zero point between each adjacent time point. When the sign of the designated sound signal changes between certain adjacent time points, a zero crossing is recorded to obtain the number of zero crossings and the total number of times. The number of zero crossings is divided by the total number of times, and the result is recorded as the zero crossing rate corresponding to the designated sound signal.

[0044] It should be noted that total harmonic distortion is a parameter used to measure the degree of distortion of the harmonic components in the signal relative to the fundamental frequency. It is expressed as the ratio of the total power of the harmonic components to the power of the fundamental frequency components. The higher the total harmonic distortion, the more harmonic components there are in the signal and the more serious the distortion. The zero-crossing rate refers to the frequency of crossing the zero value in the signal, that is, the frequency at which the instantaneous amplitude of the signal changes from a positive value to a negative value or vice versa. It is used to describe the periodic characteristics and frequency content of the signal.

[0045] The amplitude of each harmonic component refers to the strength or amplitude of each harmonic frequency component of a specified sound signal in frequency domain analysis. In specified sound signal processing, the harmonic component refers to the frequency component that is an integer multiple of the fundamental frequency. For example, if the fundamental frequency is P0, then the harmonic frequencies include 2P0 and 3P0, etc. 2P0 and 3P0 are called second harmonic and third harmonic, respectively.

[0046] It should also be noted that the Fourier transform is a mathematical transformation used to convert time domain signals into frequency domain signals. The Fourier transform is used to decompose complex sound signals into the superposition of sine waves of different frequencies, thereby analyzing the frequency components in the sound signal. The time domain is a representation of sound signals in chronological order. The time domain signal shows how the sound signal changes over time. For example, the waveform diagram of the sound signal is a time domain representation. The frequency domain is a representation of the signal arranged according to frequency components. Through the Fourier transform, the sound signal is converted from the time domain to the frequency domain. The frequency domain diagram shows the intensity distribution of each frequency component of the sound signal.

[0047] The spectrum is the representation of the sound signal in the frequency domain, showing the amplitude and phase of each frequency component in the sound signal. In the sound signal, the fundamental frequency determines the pitch of the sound signal. For example, the notes in music are determined by their fundamental frequency, and the pitch in speech is also determined by the fundamental frequency. The harmonic components determine the sound quality and timbre of the signal. For example, in the sound of musical instruments, the combination of fundamental frequency and harmonics forms a unique timbre. In power systems, harmonic analysis is used to detect distortion or interference in signals.

[0048] In a specific embodiment, the second fault assessment index corresponding to the specified power equipment is calculated by the following specific calculation process: obtaining the standard total harmonic distortion and standard zero-crossing rate corresponding to the specified power equipment from a database.

[0049] By calculating the formula The second fault assessment index β corresponding to the specified power equipment is obtained, wherein f and Z represent the total harmonic distortion and zero-crossing rate corresponding to the specified power equipment, respectively; f′ and Z′ represent the standard total harmonic distortion and standard zero-crossing rate, respectively; μ1 and μ2 represent the weight factor corresponding to the set total harmonic distortion and the weight factor corresponding to the zero-crossing rate, respectively.

[0050] It should be noted that the values ​​of μ1 and μ2 are both greater than 0 and less than 1.

[0051] It should also be noted that the total harmonic distortion reflects the degree of nonlinear distortion in the signal and is particularly sensitive to harmonic changes caused by faults. Therefore, the total harmonic distortion weight factor is assigned a high weight. The zero-crossing rate indicates the frequency of the signal passing through the zero point, which is related to the volatility of the signal. It has an indicative effect on faults, but its relative influence is small. Therefore, the zero-crossing rate weight factor is assigned a low weight. Through statistical analysis and experimental verification of historical data, combined with actual fault cases, the weight factor corresponding to the set total harmonic distortion and the weight factor corresponding to the zero-crossing rate are obtained. For example, the weight factor corresponding to the total harmonic distortion is 0.8, and the weight factor corresponding to the zero-crossing rate is 0.2.

[0052] Step 4: Environmental impact factor assessment: Collect the corresponding environmental impact factors within the specified power equipment setting range, and then calculate the corresponding environmental impact factors within the specified power equipment setting range.

[0053] In a specific embodiment, the environmental impact factor corresponding to the setting range of the specified power equipment is calculated, and the specific calculation process is as follows: the standard ambient temperature, standard wind speed and standard electric field strength corresponding to the specified power equipment are obtained from the database.

[0054] By calculating the formula The environmental impact factor ψ corresponding to the setting range of the specified power equipment is obtained, where T, N, and E respectively represent the ambient temperature, wind speed, and electric field strength corresponding to the setting range of the specified power equipment, T′, N′, and E′ respectively represent the standard ambient temperature, standard wind speed, and standard electric field strength, and λ1, λ2, and λ3 respectively represent the weight factors corresponding to the set ambient temperature, the weight factors corresponding to the wind speed, and the weight factors corresponding to the electric field strength.

[0055] It should be noted that the values ​​of λ1, λ2, and λ3 are all greater than 0 and less than 1.

[0056] It should also be noted that ambient temperature directly affects the thermal performance and electrical characteristics of the equipment, leading to failures or performance degradation, so a high weight factor is assigned. Wind speed affects the cooling effect and operational stability, especially in outdoor environments. The risk of failure fluctuates with changes in wind speed, so the weight factor is set to medium. The electric field strength has little impact on the operation of power equipment. In some cases, it can cause short-term failures, but overall it has relatively little impact on equipment performance, so the electric field strength weight factor is assigned a low weight. The entire setting process combines actual equipment operation data with historical cases of environmental impacts to ensure the rationality of the weight factors, and ultimately obtains the weight factors corresponding to the set ambient temperature, wind speed, and electric field strength. For example, the ambient temperature weight factor is 0.5, the wind speed weight factor is 0.4, and the electric field strength weight factor is 0.1.

[0057] Certain situations include but are not limited to high electric field strength causing electrostatic discharge and strong electric field generating electromagnetic interference. In a dry environment, electrostatic discharge can cause instantaneous failure or interference of power equipment, affecting the normal operation of power equipment. Near high-voltage electrical equipment, electromagnetic interference can cause signal distortion or temporary equipment failure.

[0058] The embodiment of the present invention obtains the second sound fault information of the specified sound signal and calculates the second fault evaluation index, which is beneficial to compare the collected sound signal with the existing standard or reference data, so that the fault detection system can be verified and compared based on the existing knowledge base, thereby improving the reliability and accuracy of detection. Environmental factors will affect the normal operation of power equipment. Therefore, incorporating environmental factors into the evaluation system during fault detection will help improve the accuracy and reliability of detection.

[0059] Step 5: Comprehensive sound fault assessment: Based on the first fault assessment index and the second fault assessment index corresponding to the designated power equipment and the corresponding environmental impact factor within the setting range of the designated power equipment, assess whether the designated power equipment has an operating fault.

[0060] In a specific embodiment, the evaluation of whether a specified power equipment has an operational fault is performed as follows: based on a first fault assessment index and a second fault assessment index corresponding to the specified power equipment, and an environmental impact factor corresponding to the specified power equipment within a set range, the comprehensive fault assessment coefficient corresponding to the specified power equipment is analyzed and obtained. The comprehensive fault assessment coefficient includes values ​​0 and 1. When the comprehensive fault assessment coefficient is 0, it indicates that the specified power equipment has an operational fault. When the comprehensive fault assessment coefficient is 1, it indicates that the specified power equipment does not have an operational fault.

[0061] In a specific embodiment, the analysis obtains the comprehensive fault assessment coefficient corresponding to the specified power equipment, and the specific analysis process is as follows: According to the sound fault monitoring expression of the power equipment: The comprehensive fault assessment coefficient ξ corresponding to the specified power equipment is obtained, wherein ν1 and ν2 are weight factors corresponding to the set first fault assessment index and the second fault assessment index, respectively, X represents the set standard comprehensive fault assessment coefficient threshold, and r is a positive number.

[0062] It should be noted that the values ​​of ν1 and ν2 are both greater than 0 and less than 1, and r is a natural number.

[0063] It should also be noted that the first fault assessment index covers instantaneous signal characteristics such as short-time energy and sound pressure level, and is very sensitive to detecting real-time fault changes. Therefore, the first fault assessment index weight factor is assigned a high weight factor value. The second fault assessment index includes frequency domain characteristics such as total harmonic distortion and zero-crossing rate, which mainly reflect long-term and stable fault characteristics and have low relative importance. Therefore, the first fault assessment index weight factor is assigned a low weight factor value. Combined with historical data and expert opinions, the weight factor corresponding to the set first fault assessment index and the weight factor corresponding to the second fault assessment index are finally obtained.

[0064] In the comprehensive sound fault assessment stage, the embodiment of the present invention performs a comprehensive analysis by combining the first fault assessment index, the second fault assessment index and the environmental impact factor, which is conducive to forming a comprehensive assessment of the equipment fault, integrating various data and analysis results, and providing more accurate fault diagnosis results.

[0065] Step 6: Display prompt: When the designated sound signal does not meet the criteria for designated power equipment fault detection and the designated power equipment has an operating fault, a display prompt is performed.

[0066] The present invention provides a sound fault detection method applied to the electric power Internet of Things. In the process of sound feature analysis, by collecting and analyzing the sound signals generated by the specified electric equipment during operation, it is beneficial to accurately evaluate whether the sound signals meet the requirements as the basis for fault detection. Through this process, the sound features of the equipment under different working conditions are effectively captured, thereby providing basic data for subsequent fault detection, ensuring that the sound signals have undergone preliminary screening and verification before fault detection, thereby improving the pertinence and accuracy of fault detection. Through time series comparative analysis, the first sound fault information of the specified sound signal at each collection time point is obtained, and the first fault evaluation index is calculated, which is helpful to identify the time-varying fault features that may exist in the equipment during operation.

[0067] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they shall all fall within the protection scope of the present invention.

Claims

1. A sound fault detection method applied to the power Internet of Things, characterized in that: include: Step 1: Sound feature analysis: collect the specified sound signal generated by the specified power equipment during operation, and evaluate whether the specified sound signal meets the requirements for fault detection of the specified power equipment; Step 2: time series comparison and analysis: when the designated sound signal satisfies the basis for designated power equipment fault detection, the first sound fault information corresponding to the designated sound signal at each acquisition time point is obtained, and then the first fault assessment index corresponding to the designated power equipment is calculated; The specific calculation process of calculating the first fault assessment index corresponding to the specified power equipment is as follows: According to the set collection time points, t is the number corresponding to each collection time point, t=1, 2, ..., n, n is any integer greater than 2, and n represents the total number of collection time points; By calculating the formula The first fault assessment index α corresponding to the specified power equipment is obtained, where et, Qt, and ut represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the tth acquisition time point, respectively, and et +1 , Qt +1 ,ut +1 They represent the short-time energy, sound pressure level, and instantaneous amplitude corresponding to the t+1th acquisition time point, respectively; κ1, κ2, and κ3 are the weight factors corresponding to the set short-time energy, sound pressure level, and instantaneous amplitude, respectively; Step 3: Reference library comparison and analysis: obtaining the second sound fault information corresponding to the specified sound signal, and then calculating the second fault assessment index corresponding to the specified power equipment; The specific calculation process of calculating the second fault assessment index corresponding to the specified power equipment is as follows: Obtain the standard total harmonic distortion and standard zero-crossing rate corresponding to the specified power equipment from the database; By calculating the formula Obtain a second fault assessment index β corresponding to the specified power equipment, wherein f and Z represent the total harmonic distortion and zero-crossing rate corresponding to the specified power equipment, respectively; f′ and Z′ represent the standard total harmonic distortion and standard zero-crossing rate, respectively; μ1 and μ2 represent the weight factor corresponding to the set total harmonic distortion and the weight factor corresponding to the zero-crossing rate, respectively; Step 4: Environmental impact factor assessment: Collect the corresponding environmental impact factors within the setting range of the specified power equipment, and then calculate the corresponding environmental impact factors within the setting range of the specified power equipment; The calculation specifies the environmental impact factor corresponding to the setting range of the power equipment, and the specific calculation process is as follows: Obtaining the standard ambient temperature, standard wind speed and standard electric field strength corresponding to the specified power equipment from the database; By calculating the formula Obtain the environmental impact factor ψ corresponding to the setting range of the specified power equipment, where T, N, and E represent the ambient temperature, wind speed, and electric field strength corresponding to the setting range of the specified power equipment, respectively; T′, N′, and E′ represent the standard ambient temperature, standard wind speed, and standard electric field strength, respectively; and λ1, λ2, and λ3 represent the weight factor corresponding to the set ambient temperature, the weight factor corresponding to the wind speed, and the weight factor corresponding to the electric field strength, respectively; Step 5: Comprehensive sound fault assessment: Based on the first fault assessment index and the second fault assessment index corresponding to the designated power equipment and the corresponding environmental impact factor within the set range of the designated power equipment, assess whether the designated power equipment has an operation fault; The evaluation specifies whether there is an operating fault in the power equipment, and the specific evaluation process is as follows: According to the first fault assessment index and the second fault assessment index corresponding to the designated power equipment, and the corresponding environmental impact factor within the setting range of the designated power equipment, a comprehensive fault assessment coefficient corresponding to the designated power equipment is analyzed and obtained. The comprehensive fault assessment coefficient includes values ​​0 and 1. When the comprehensive fault assessment coefficient is 0, it indicates that the designated power equipment has an operating fault. When the comprehensive fault assessment coefficient is 1, it indicates that the designated power equipment does not have an operating fault. The analysis obtains the comprehensive fault assessment coefficient corresponding to the specified power equipment. The specific analysis process is as follows: According to the sound fault monitoring expression of power equipment: Obtain the comprehensive fault assessment coefficient ξ corresponding to the specified power equipment, wherein ν1 and ν2 are respectively the weight factors corresponding to the set first fault assessment index and the second fault assessment index, X represents the set standard comprehensive fault assessment coefficient threshold, and r is a positive number; Step 6: Display prompt: When the designated sound signal does not meet the criteria for designated power equipment fault detection and the designated power equipment has an operating fault, a display prompt is performed.

2. The sound fault detection method applied to the power Internet of Things according to claim 1 is characterized in that: The first sound fault information includes short-time energy, sound pressure level and instantaneous amplitude, the second sound fault information includes total harmonic distortion and zero-crossing rate, and the environmental influencing factors include ambient temperature, wind speed and electric field strength.

3. The sound fault detection method applied to the power Internet of Things according to claim 2 is characterized in that: The specific evaluation process of evaluating whether the specified sound signal meets the requirements for detecting the fault of the specified power equipment is as follows: The designated sound signal generated by the designated power equipment during operation is collected by the sound sensor, and the designated sound signal is transmitted to the central database through the network. The frequency of the designated sound signal is compared with the stored standard sound frequency intervals. If the frequency of the designated sound signal belongs to a stored standard sound frequency interval, it indicates that the designated sound signal meets the requirements as a basis for fault detection of the designated power equipment. If the frequency of the designated sound signal does not belong to a stored standard sound frequency interval, it indicates that the designated sound signal does not meet the requirements as a basis for fault detection of the designated power equipment.

4. The sound fault detection method applied to the power Internet of Things according to claim 3 is characterized in that: The specific acquisition process of obtaining the first sound fault information corresponding to the specified sound signal at each acquisition time point is as follows: The designated sound signal corresponding to the designated power equipment is collected at each collection time point by a sound sensor, and the continuous designated sound signal is divided into short time frames, and the short-time energy in each short time frame is calculated to obtain each short-time energy, and then each short-time energy is calculated by the average value, and the result obtained is the short-time energy, thereby obtaining the short-time energy corresponding to each collection time point; The instantaneous sound pressure value and instantaneous amplitude corresponding to each acquisition time point are read from the sound sensor, and then the instantaneous sound pressure value corresponding to each acquisition time point is converted into the sound pressure level corresponding to each acquisition time point through a calculation formula.

5. The sound fault detection method applied to the power Internet of Things according to claim 4 is characterized in that: The specific acquisition process of obtaining the second sound fault information corresponding to the specified sound signal is as follows: The collected specified sound signal is subjected to Fourier transform, and the specified sound signal is converted from the time domain to the frequency domain, so as to obtain the spectrum of the specified sound signal. The basic frequency of the specified sound signal is obtained in the spectrum, which is recorded as P. The amplitude of each harmonic component is squared to obtain the harmonic power, which is recorded as D. Thus, the formula is used to calculate Get the total harmonic distortion corresponding to the specified sound signal; The designated sound signal is compared point by point at each set time point to detect whether the designated sound signal crosses the zero point between each adjacent time point. When the sign of the designated sound signal changes between certain adjacent time points, a zero crossing is recorded to obtain the number of zero crossings and the total number of times. The number of zero crossings is divided by the total number of times, and the result is recorded as the zero crossing rate corresponding to the designated sound signal.