Power transformer sound level detection method and system

Abstract

The invention discloses a power transformer sound level detection method and system, and relates to the technical field of power detection, and the system comprises a sound pressure level conversion unit, a background noise analysis unit, a transformer sound pressure level analysis unit and a sound power level calculation unit. Analyzing the sound pressure level of the transformer before operation and the sound pressure level of the transformer after operation measured by each wireless microphone so as to calculate the average A-weighted sound pressure level of the background noise of the power transformer; and the transformer sound pressure level analysis unit is used for analyzing the sound pressure level of each wireless sound measurement sensor and calculating the A-weighted sound power level of the power transformer in operation. Data support is provided for design and optimization of the transformer, and noise emission is reduced. The device replaces manual handheld sound level measurement equipment to approach the transformer, and the electric shock risk is effectively avoided; and the sound level can be quickly and accurately obtained through automatic calculation. The method is suitable for measuring the sound power levels of power transformers, reactors, prefabricated substations (box substations) and installed cooling equipment, operation is easy, convenient and efficient, and the process is safe and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power detection, and in particular to a method and system for detecting sound levels of electric power transformers. Background Art

[0002] With the rapid development of the electric power industry, power transformers are indispensable key equipment in the power system. The monitoring and evaluation of their operating status are of great significance to ensure the stability and reliability of the system. Although traditional mechanical and electrical detection methods can meet basic needs to a certain extent, they are obviously insufficient in refined monitoring and early fault diagnosis. Therefore, acoustic detection technology has gradually received attention and applied to the sound level detection and fault diagnosis of power transformers. When designing and installing transformers, reactors, prefabricated substations (box transformers) and the cooling equipment installed, many parameters should be considered, one of which is the noise emitted by the equipment under normal operating conditions on site. The humming sound emitted by the transformer is a low-frequency sound, and the size of its sound power is an important factor affecting the noise level of the substation plant boundary. The transformer contributes most of the plant boundary noise. The sound sources of the transformer include magnetostriction of the core, axial and lateral electromagnetic force vibration in the winding, oil pump noise, fan noise, and vibration transmission of the box or shell.

[0003] In a Chinese invention application with application publication number CN117288209A, a transformer sound level measurement method and system are disclosed, including obtaining transformer sound level measurement site environment information; using a grid method to spatially grid the transformer sound level measurement site environment information and establish a site grid map; initializing the tuna school position in the site grid map through Logistic chaotic mapping to determine the initial position and target position of the transformer sound level measurement device; iteratively optimizing the position of the transformer sound level measurement device through a tuna school optimization algorithm, and the optimal individual position of the tuna school position in each iteration is the position of the transformer sound level measurement device; and performing Bezier curve smoothing to obtain the optimal inspection path of the transformer sound level measurement device.

[0004] In the above invention application, an optimal and smooth transformer sound level measurement route is provided for the intelligent robot for transformer sound level measurement, but the research and development, manufacturing and maintenance costs of the intelligent robot may also be relatively high, especially in the selection and configuration of key components such as high-precision sensors, processors, and navigation systems. And although the intelligent robot can plan the optimal path and avoid obstacles, its navigation and positioning accuracy may be affected under extreme or complex environmental conditions (such as strong winds, heavy rains, heavy snow, etc.), thereby affecting the accuracy and smoothness of the measurement route. The environment of power facilities such as substations is often complex and changeable, and there are factors such as electromagnetic interference and temperature changes. These factors may have an adverse effect on the normal operation of the intelligent robot, resulting in untimely or low-precision transformer sound level measurement.

[0005] To this end, the present invention provides a method and system for detecting the sound level of a power transformer. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the shortcomings of the prior art, the present invention provides a method and system for detecting the sound level of a power transformer. The present invention converts the sound pressure value measured by each wireless microphone into a sound pressure level, analyzes the sound pressure level L before operation of each wireless microphone, and calculates the sound pressure level L before operation of each wireless microphone. bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and And analyze the operating sound pressure level L of each wireless sound sensor pAi , calculate the A-weighted sound power level L of the power transformer WA , the monitoring data is corrected according to the background noise level to improve the accuracy of the data. By monitoring and analyzing the sound pressure level and sound power level data, data support can be provided for the design and optimization of the transformer, noise emissions can be reduced, and operating efficiency can be improved, thereby solving the technical problems recorded in the background technology.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a power transformer sound level detection system, comprising:

[0010] The wireless sound sensor module is used to collect the sound pressure values ​​of the power transformer before, during and after operation, and is composed of multiple wireless sound sensors. The wireless sound sensor has a built-in antenna, and the sound level data is collected through a local area network in multiple channels at the same time. The transmission power, sampling rate or data upload cycle can be set, and the greater the power of the wireless sound sensor, the longer the wireless transmission distance;

[0011] Ethernet gateway module, used to receive and display data from various wireless acoustic sensors in real time, set communication channels and data sampling frequency, including Ethernet gateway, antenna, touch screen, power button, status indicator light, SD card storage; data communication uses HTTP protocol, POST method, RJ45 interface; communication channels can be set to 1 to 32, sensor synchronization words can be set to 1 to 255, server address, dynamic and static IP can be expanded and developed;

[0012] The sound power level analysis module includes a sound pressure level conversion unit, a background noise analysis unit, a transformer sound pressure level analysis unit and a sound power level calculation unit; the sound pressure level conversion unit is used to convert the sound pressure value measured by each wireless microphone into a sound pressure level; after filtering out the strong wave interference in the background noise, the background noise analysis unit analyzes the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and The transformer sound pressure level analysis unit is used to analyze the operating sound pressure level L of each wireless sound sensor. pAi , calculate the A-weighted sound power level L of the power transformer WA .

[0013] Furthermore, before the transformer is powered on, the wireless sound measurement sensor is placed at each sound measurement point. According to the guidance requirements of the national standard "Power Transformer Part 10.1: Application Guidelines for Sound Level Measurement" (GB / T 1094.101), the distribution of each microphone measurement point is determined by placing one at the center point of each side (or the center position of the coil) and at each corner. For distribution transformers, 8 sound measurement points are preferred, and for dry-type transformers, 12 sound measurement points are preferred. 20 sound measurement points can also be arranged, but the total sound level difference is less than 1dB (A).

[0014] Furthermore, if the transformer is a distribution transformer, 8 sound measurement points are distributed on each contour line at a distance of 0.3m from the transformer reference emitting surface, and microphones are placed at the center point of each side of the oil tank and at each corner of the tank; if the transformer is a dry-type transformer, 12 sound measurement points are distributed on each contour line at a distance of 1.0m from the transformer reference emitting surface, and microphones are placed at the position opposite to the center of the core column coil and at each corner of the outer shell.

[0015] Furthermore, when the gateway receives data from each wireless acoustic sensor, it flashes blue; when the gateway is in the setting mode, the yellow light is always on; when data transmission fails, the red light is always on. Data is uploaded through the RJ45 interface or exported to the industrial computer through the SD memory card.

[0016] Furthermore, the average sound pressure bgA of the power transformer before operation measured by each wireless microphone is obtained. i , average sound pressure during operation pA i And the average sound pressure after operation bgB i , converted to sound pressure level L bgAi , L pAi and L bgBi :

[0017]

[0018] Among them, p0 is the weakest sound that a healthy human ear can perceive, and 20μPa at 1kHz is used as a reference value, corresponding to 0dB.

[0019] Furthermore, the sound pressure level L of each wireless sound sensor during operation is obtained. pAi , calculate the uncorrected average A-weighted sound pressure level of the power transformer:

[0020]

[0021] Wherein, i is the serial number of each wireless acoustic sensor, and N is the total number of wireless acoustic sensor locations.

[0022] Further, the sound pressure level L before operation of each wireless microphone is obtained. bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and

[0023]

[0024] The corresponding average A-weighted sound pressure level of the power transformer background noise and The calculation formula is as above.

[0025] Further, the calculation of the environmental correction value K:

[0026]

[0027] Where: α i is the local surface sound absorption coefficient, Sv i is with α i The area of ​​the corresponding local surface of the test chamber, unit: m 2 , S is the surface area of ​​the power transformer.

[0028] Further, the uncorrected average A-weighted sound pressure level of the power transformer is obtained and the average A-weighted sound pressure level of background noise Calculation of Corrected Average A-Weighted Sound Pressure Level for Power Transformers

[0029]

[0030] The corresponding corrected average A-weighted sound pressure level of the power transformer The calculation formula is as above.

[0031] Furthermore, based on the average A-weighted sound pressure level corrected for the power transformer Calculation of the A-weighted sound power level L of a power transformer WA :

[0032]

[0033] Where: S0 is the base reference area.

[0034] Further, the steps of filtering out strong wave interference in the background noise include:

[0035] The sound pressure value spectrum is sparsely processed to remove the strong frequency interference in the background noise, and the amplitude data of the spectrum is smoothed by a low-pass filter, and the offset caused by the low-pass filtering is compensated for the first time; the compensation method is: establish a spectrum offset compensation model, train the spectrum offset compensation model, and obtain the first compensation amount through the trained spectrum offset compensation model;

[0036] The smoothed and compensated spectrum is subjected to primary and secondary differential operations to obtain the spectrum peak position trajectory. The peak position is compensated for a second time using the spectrum offset compensation model, and then a differential operation is performed on the compensated peak trajectory to obtain the spectrum differential value. The differential value is used as the frequency difference between the harmonics of the spectrum, and the mean of each harmonic within the set range is calculated to obtain the intensity trajectory of each harmonic, and the spectrum corresponding to the frequency difference not within the intensity trajectory is eliminated.

[0037] A method for detecting the sound level of a power transformer comprises the following steps:

[0038] Collect the sound pressure values ​​of the power transformer before, during and after operation, and convert the sound pressure value measured by each wireless microphone into sound pressure level;

[0039] Analyze the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and

[0040] Analyze the operating sound pressure level L of each wireless acoustic sensor pAi , calculate the A-weighted sound power level L of the power transformer WA .

[0041] (III) Beneficial effects

[0042] The present invention provides a method and system for detecting sound level of a power transformer, which has the following beneficial effects:

[0043] 1. By collecting the sound pressure values ​​before, during and after the operation of the power transformer, it is crucial to promptly detect abnormal sounds during the operation of the transformer. By continuously monitoring the changes in sound pressure before, during and after the operation of the transformer, a complete data chain can be formed, which is helpful to analyze the operating status and performance changes of the transformer.

[0044] 2. Convert the sound pressure value measured by each wireless microphone into the sound pressure level, and analyze the sound pressure level L before operation of each wireless microphone. bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and And analyze the operating sound pressure level L of each wireless sound sensor pAi , calculate the A-weighted sound power level L of the power transformer WA , the monitoring data can be corrected according to the background noise level to improve the accuracy of the data. By monitoring and analyzing the sound pressure level and sound power level data, data support can be provided for the design and optimization of the transformer, reducing noise emissions and improving operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a structural schematic diagram of a power transformer sound level detection system of the present invention;

[0046] Figure 2 A schematic diagram of a flow chart of a method for detecting sound level of a power transformer according to the present invention;

[0047] Figure 3 Schematic diagram of horizontal distribution of sound measurement points of dry-type transformer of the present invention;

[0048] Figure 4 The control flow chart of the sampling program for the wireless sound transmission gateway;

[0049] Figure 5 It is a schematic diagram of the sound level calculation software window of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] See also Figure 1-5 The present invention provides a power transformer sound level detection system, comprising:

[0052] The wireless sound sensor module is used to collect the sound pressure values ​​of the power transformer before, during and after operation. It is composed of multiple wireless sound sensors. The wireless sound sensor has a built-in antenna. The sound level data is collected through multiple channels through the local area network. The transmission power, sampling rate or data upload cycle can be set. The greater the power of the wireless sound sensor, the longer the wireless transmission distance.

[0053] Before energizing the transformer, place the wireless sound measurement sensor at each sound measurement point. According to the guidance requirements of the national standard "Power Transformer Part 10.1: Application Guidelines for Sound Level Measurement" (GB / T 1094.101), the distribution of each microphone measurement point is determined by placing one at the center point of each side (or the center position of the coil) and at each corner. For distribution transformers, 8 sound measurement points are preferred, and for dry-type transformers, 12 sound measurement points are preferred. 20 sound measurement points can also be arranged, but the total sound level difference is less than 1dB (A).

[0054] The horizontal position distribution of the wireless acoustic sensor is different according to the type of transformer. If the transformer is a distribution transformer, 8 acoustic measurement points are distributed on each contour line at a distance of 0.3m from the transformer reference emission surface, and microphones are placed at the center point of each side of the oil tank and at each corner of the tank. If the transformer is a dry-type transformer, 12 acoustic measurement points are distributed on each contour line at a distance of 1.0m from the transformer reference emission surface, and microphones are placed at the position facing the center of the core column coil and at each corner of the shell, such as Figure 2 The vertical height of the wireless acoustic sensor is determined by the actual height of the transformer and is fixed on a height-adjustable bracket.

[0055] By collecting the sound pressure values ​​before, during and after the operation of the power transformer, it is crucial to promptly detect abnormal sounds during the operation of the transformer. By continuously monitoring the changes in sound pressure before, during and after the operation of the transformer, a complete data chain can be formed, which is helpful to analyze the operating status and performance changes of the transformer.

[0056] The Ethernet gateway module is used to receive and display the data of each wireless acoustic sensor in real time, set the communication channel and data sampling frequency, and includes an Ethernet gateway, antenna, touch screen, power button, status indicator, and SD card storage. Data communication uses HTTP protocol, POST method, and RJ45 interface; the communication channel can be set to 1 to 32, the sensor synchronization word can be set to 1 to 255, and the server address, dynamic and static IP can be expanded and developed.

[0057] When the gateway receives data from each wireless acoustic sensor, it flashes blue; when the gateway is in the setting mode, the yellow light is always on; when data transmission fails, the red light is always on. Data is uploaded through the RJ45 interface or exported to the industrial computer through the SD memory card.

[0058] The sound power level analysis module includes a sound pressure level conversion unit, a background noise analysis unit, a transformer sound pressure level analysis unit and a sound power level calculation unit. The sound pressure level conversion unit is used to convert the sound pressure value measured by each wireless microphone into a sound pressure level. After filtering out the strong wave interference in the background noise, the background noise analysis unit analyzes the pre-operation sound pressure level L of each wireless microphone. bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and The transformer sound pressure level analysis unit is used to analyze the operating sound pressure level L of each wireless sound sensor. pAi , calculate the A-weighted sound power level L of the power transformer WA .

[0059] The steps to filter out strong interference from background noise include:

[0060] At the detection site, the operation of various equipment generates strong wave signal interference. In the collected sound level signal, these strong wave signal interferences will have a great impact on the accuracy of sound level detection. Therefore, it is necessary to remove the strong wave interference in the background noise.

[0061] Firstly, the collected sound pressure value spectrum is sparsely processed to remove the strong frequency interference in the background noise. Specifically, the amplitude data of the spectrum is smoothed by using a low-pass filter. During this processing, the signal will be offset. Therefore, the offset caused by the low-pass filtering is compensated for the first time. The compensation method is: establish a spectrum offset compensation model, train the spectrum offset compensation model, and obtain the first compensation through the trained spectrum offset compensation model.

[0062] Training process: Spectrum samples are collected, and the audio amplifier amplifies the samples to obtain real-time audio data. The real-time audio data is then subjected to mean filtering to obtain filtered data. The audio amplitude offset is obtained by analyzing the real-time audio data and the filtered data. The audio amplitude offset is used as the input of the spectrum offset compensation model for training.

[0063] Subsequently, the smoothed and compensated spectrum graph is subjected to primary and secondary differential operations to obtain the spectrum graph peak position trajectory. The peak position is compensated for the second time through the spectrum offset compensation model, and then a differential operation is performed on the compensated peak trajectory to obtain the spectrum difference value. The differential value is used as the frequency difference between the harmonics in the spectrum graph, and the mean of each harmonic within the set range is calculated to obtain the intensity trajectory of each harmonic. The spectrum corresponding to the frequency difference that is not within the intensity trajectory is eliminated, that is, the strong wave interference in the background signal is eliminated, thereby improving the acquisition accuracy.

[0064] Get the average sound pressure bgA of the power transformer before operation measured by each wireless microphonei , average sound pressure during operation pA i And the average sound pressure after operation bgB i , converted to sound pressure level L bgAi , L pAi and L bgBi :

[0065]

[0066] Among them, p0 is the weakest sound that a healthy human ear can perceive, and 20μPa at 1kHz is used as a reference value, corresponding to 0dB.

[0067] Get the operating sound pressure level L of each wireless sound sensor pAi , calculate the uncorrected average A-weighted sound pressure level of the power transformer:

[0068]

[0069] Where i is the serial number of each wireless acoustic sensor, and N is the total number of wireless acoustic sensors (microphones should be located on the specified contour line, with equal spacing between each other, and the interval should not be greater than 1m).

[0070] Get the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and

[0071]

[0072] The corresponding average A-weighted sound pressure level of the power transformer background noise and The calculation formula is as above.

[0073] Calculation of environmental correction value K:

[0074]

[0075] Where: α i is the local surface sound absorption coefficient, Sv i is with α i The area of ​​the corresponding local surface of the test chamber, unit: m 2 , S is the surface area of ​​the power transformer.

[0076] Get the uncorrected average A-weighted sound pressure level of the power transformer and the average A-weighted sound pressure level of background noise Calculation of Corrected Average A-Weighted Sound Pressure Level for Power Transformers

[0077]

[0078] The corresponding corrected average A-weighted sound pressure level of the power transformer The calculation formula is as above.

[0079] Average A-weighted sound pressure level corrected for power transformers Calculation of the A-weighted sound power level L of a power transformer WA :

[0080]

[0081] Where: S0 is the reference area (1m 2 ).

[0082] The sound pressure value measured by each wireless microphone is converted into the sound pressure level, and the pre-operation sound pressure level L of each wireless microphone is analyzed. bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and And analyze the operating sound pressure level L of each wireless sound sensor pAi , calculate the A-weighted sound power level L of the power transformer WA , the monitoring data can be corrected according to the background noise level to improve the accuracy of the data. By monitoring and analyzing the sound pressure level and sound power level data, data support can be provided for the design and optimization of the transformer, reducing noise emissions and improving operating efficiency.

[0083] See also Figure 2-5 The present invention provides a method for detecting the sound level of a power transformer, comprising the following steps:

[0084] The sound pressure values ​​of the power transformer are collected before, during and after operation, and the sound pressure value measured by each wireless microphone is converted into sound pressure level.

[0085] Analyze the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and

[0086] Analyze the operating sound pressure level L of each wireless acoustic sensor pAi , calculate the A-weighted sound power level L of the power transformer WA .

[0087] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A power transformer sound level detection system, characterized in that: include: The wireless sound sensor module is used to collect the sound pressure values ​​of the power transformer before, during and after operation, and is composed of multiple wireless sound sensors. The wireless sound sensor has a built-in antenna, and the sound level data is collected through a local area network in multiple channels at the same time. The transmission power, sampling rate or data upload cycle can be set, and the greater the power of the wireless sound sensor, the longer the wireless transmission distance; Ethernet gateway module, used to receive and display data from various wireless acoustic sensors in real time, set communication channels and data sampling frequency, including Ethernet gateway, antenna, touch screen, power button, status indicator light, SD card storage; data communication uses HTTP protocol, POST method, RJ45 interface; communication channels can be set to 1 to 32, sensor synchronization words can be set to 1 to 255, server address, dynamic and static IP can be expanded and developed; The sound power level analysis module includes a sound pressure level conversion unit, a background noise analysis unit, a transformer sound pressure level analysis unit and a sound power level calculation unit; the sound pressure level conversion unit is used to convert the sound pressure value measured by each wireless microphone into a sound pressure level; after filtering out the strong wave interference in the background noise, the background noise analysis unit analyzes the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and The transformer sound pressure level analysis unit is used to analyze the operating sound pressure level L of each wireless sound sensor. pAi , calculate the A-weighted sound power level L of the power transformer WA .

2. A power transformer sound level detection system according to claim 1, characterized in that: If the transformer is a distribution transformer, 8 sound measurement points are distributed on each contour line at a distance of 0.3m from the transformer reference emission surface, and microphones are placed at the center point of each side of the oil tank and at each tank corner; If the transformer is a dry-type transformer, 12 sound measurement points are distributed on each contour line 1.0m away from the transformer reference emission surface, and microphones are placed facing the center of the core coil and each corner of the shell.

3. A power transformer sound level detection system according to claim 1, characterized in that: When the gateway receives data from each wireless acoustic sensor, it flashes blue; when the gateway is in the setting mode, the yellow light is always on; when data transmission fails, the red light is always on. Data is uploaded through the RJ45 interface or exported to the industrial computer through the SD memory card.

4. The power transformer sound level detection system according to claim 1, characterized in that: Get the average sound pressure bgA of the power transformer before operation measured by each wireless microphone i , average sound pressure during operation pA i And the average sound pressure after operation bgB i , converted to sound pressure level L bgAi , L pAi and L bgBi : Among them, p0 is the weakest sound that a healthy human ear can perceive, and 20μPa at 1kHz is used as a reference value, corresponding to 0dB.

5. The power transformer sound level detection system according to claim 1, characterized in that: Get the operating sound pressure level L of each wireless sound sensor pAi , calculate the uncorrected average A-weighted sound pressure level of the power transformer: Wherein, i is the serial number of each wireless acoustic sensor, and N is the total number of wireless acoustic sensor locations.

6. A power transformer sound level detection system according to claim 1, characterized in that: Get the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and The corresponding average A-weighted sound pressure level of the power transformer background noise and The calculation formula is as above.

7. The power transformer sound level detection system according to claim 1, characterized in that: Calculation of environmental correction value K: Where: α i is the local surface sound absorption coefficient, Sv i is with α i The area of ​​the corresponding local surface of the test chamber, unit: m 2 , S is the surface area of ​​the power transformer.

8. The power transformer sound level detection system according to claim 1, characterized in that: Get the uncorrected average A-weighted sound pressure level of the power transformer and the average A-weighted sound pressure level of background noise Calculation of Corrected Average A-Weighted Sound Pressure Level for Power Transformers The corresponding corrected average A-weighted sound pressure level of the power transformer The calculation formula is as above; Average A-weighted sound pressure level corrected for power transformers Calculation of the A-weighted sound power level L of a power transformer WA : Where: S0 is the base reference area.

9. A power transformer sound level detection system according to claim 1, characterized in that: The steps to filter out strong wave interference from background noise include: The sound pressure value spectrum is sparsely processed to remove the strong frequency interference in the background noise, and the amplitude data of the spectrum is smoothed by a low-pass filter, and the offset caused by the low-pass filtering is compensated for the first time; the compensation method is: establish a spectrum offset compensation model, train the spectrum offset compensation model, and obtain the first compensation amount through the trained spectrum offset compensation model; The smoothed and compensated spectrum is subjected to primary and secondary differential operations to obtain the spectrum peak position trajectory. The peak position is compensated for a second time using the spectrum offset compensation model, and then a differential operation is performed on the compensated peak trajectory to obtain the spectrum differential value. The differential value is used as the frequency difference between the harmonics of the spectrum, and the mean of each harmonic within the set range is calculated to obtain the intensity trajectory of each harmonic, and the spectrum corresponding to the frequency difference not within the intensity trajectory is eliminated.

10. A method for detecting sound level of a power transformer, characterized in that: The steps include: Collect the sound pressure values ​​of the power transformer before, during and after operation, and convert the sound pressure value measured by each wireless microphone into sound pressure level; Analyze the pre-operation sound pressure level L of each wireless microphone bgAi And the sound pressure level after operation L bgBi , calculate the average A-weighted sound pressure level of the power transformer background noise and Analyze the operating sound pressure level L of each wireless acoustic sensor pAi , calculate the A-weighted sound power level L of the power transformer WA .

Images