Power transformation equipment fault detection method and device and electronic equipment

Abstract

The embodiment of the invention discloses a power transformation equipment fault detection method and device and electronic equipment. The method comprises the steps that operation audio data and operation vibration data of to-be-detected power transformation equipment in a target time period are acquired; dividing the running audio data into a plurality of pieces of audio sub-data according to a preset time interval, and determining the stationary attribute of the running audio data based on the similarity among the plurality of pieces of audio sub-data; under the condition that the stable attribute of the operation audio data meets the preset condition, the operation audio data and the operation vibration data are input into the pre-trained fault detection model, the fault type of the to-be-detected power transformation equipment is determined, most of signals of the power transformation equipment in the stable operation state can be abandoned, and the fault detection accuracy is improved. And through conjoint analysis of audio and vibration signals, fault features of more dimensions can be captured, and comprehensiveness, detection efficiency and accuracy of fault identification of the power transformation equipment are improved.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method and device for detecting faults of substation equipment, and electronic equipment. Background Art

[0002] The operation status of substation substation equipment directly affects the economic production of society and people's daily life. Therefore, the working condition monitoring of substation equipment is an important work content.

[0003] At present, in order to ensure the safe and stable operation of substations, manual inspection is the conventional way to detect power equipment faults. The existing method, on the one hand, relies heavily on manual supervision, which requires a lot of manpower and material costs; on the other hand, it cannot achieve uninterrupted detection, and is relatively subjective and heavily dependent on the experience of the implementer, that is, there are problems such as low efficiency, poor comprehensiveness, and low accuracy in fault detection of substation equipment. As a result, it is impossible to locate and warn the fault problems of substation equipment in a timely manner, which is very likely to cause safety problems of power equipment. Summary of the invention

[0004] The present invention provides a method, device and electronic device for detecting faults of substation equipment, so as to discard most of the signals of the substation equipment in a stable operating state, and capture fault characteristics in more dimensions through joint analysis of audio and vibration signals, thereby improving the comprehensiveness, detection efficiency and accuracy of fault identification of substation equipment.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting a fault in a substation, the method comprising:

[0006] Obtaining the operating audio data and operating vibration data of the substation to be tested within the target time period;

[0007] Dividing the running audio data into a plurality of audio sub-data according to a preset time interval, so as to determine a stationary property of the running audio data based on similarities between the plurality of audio sub-data;

[0008] When the stationary property of the operating audio data meets a preset condition, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested.

[0009] In a second aspect, an embodiment of the present invention further provides a device for detecting a fault in a power substation, the device comprising:

[0010] An operation data acquisition module is used to acquire the operation audio data and operation vibration data of the substation to be tested within a target time period;

[0011] A stationary attribute division module, used for dividing the running audio data into a plurality of audio sub-data according to a preset time interval, so as to determine the stationary attribute of the running audio data based on the similarity between the plurality of audio sub-data;

[0012] The fault category determination module is used to input the operating audio data and the operating vibration data into a pre-trained fault detection model to determine the fault category of the substationary equipment to be tested when the smooth attribute of the operating audio data meets a preset condition.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When one or more programs are executed by one or more processors, the one or more processors implement a method for detecting faults of a substation equipment as described in any one of the embodiments of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a method for detecting faults in a substation as described in any one of the embodiments of the present invention.

[0018] The technical solution of the embodiment of the present invention can obtain the operating audio data and operating vibration data of the substation to be tested within the target time period during the operation of the substation to be tested. Through the joint analysis of audio and vibration signals, more dimensional fault characteristics can be captured, and some hidden faults that are difficult to detect by sound or vibration alone can be found, which improves the comprehensiveness of substation fault identification and improves the efficiency and accuracy of substation fault detection. Further, the operating audio data is divided into multiple audio sub-data according to a preset time interval, and the stationary attribute of the operating audio data is determined based on the similarity between the multiple audio sub-data. Then, when the stationary attribute of the operating audio data meets the preset conditions, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested. The technical solution of this embodiment determines whether to start fault detection of the substation through the stationary attribute of the operating audio data, and can discard most of the signals of the substation in a stable operating state, without missing the complete monitoring of the equipment working condition, which not only greatly reduces the data processing volume, but also achieves the effect of uninterrupted detection, further improving the comprehensiveness of substation fault identification, detection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of a flow chart of a method for detecting a fault in a power substation provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of a flow chart of another method for detecting a fault in a power substation provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of a data processing device for operating a substation according to an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of a housing of a data processing device for operating a power transformation device according to an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of the structure of a substation fault detection device provided by an embodiment of the present invention;

[0025] Figure 6 The present invention is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] Figure 1 A flow chart of a method for detecting faults in substation equipment provided in an embodiment of the present invention is provided. This embodiment is applicable to situations where fault detection of substation equipment is required. The method can be executed by a fault detection device for substation equipment. The device can be implemented in the form of software and / or hardware. The hardware can be an electronic device, such as a mobile terminal, a PC or a server.

[0027] like Figure 1 As shown, the substation equipment fault detection method includes:

[0028] S110, obtaining operating audio data and operating vibration data of the substation to be tested within a target time period.

[0029] Among them, substation equipment refers to power facilities used to transform voltage, receive and distribute electric energy. Substation equipment will make sounds when operating normally, and the sounds made by substation equipment will also change as the operating state changes (such as when a fault occurs or when overloaded). The substation equipment to be tested is the substation equipment for which fault detection is to be performed.

[0030] The target time period may be a time period corresponding to a preset time length. The operating audio signal is an audio signal generated by the substation to be tested during operation. The operating vibration data is data of various parameters and indicators of vibration of the substation to be tested. For example, the operating audio data includes multiple discrete operating sound signals within the target time period. Specifically, the operating vibration data may include vibration velocity, vibration acceleration and / or vibration displacement parameters.

[0031] Exemplarily, the operation audio data may be the operation audio values ​​corresponding to each sampling point in a certain time period. For example, the operation audio data may be represented as {x1, x2, x3, ..., xn}, wherein x1 is the operation audio value corresponding to time t1, x2 is the operation audio value corresponding to time t2, x3 is the operation audio value corresponding to time t3, and xn is the operation audio value corresponding to time tn. The operation vibration data may be the vibration velocity, vibration acceleration, and vibration displacement corresponding to each sampling point in a certain time period. For example, the operation vibration data may be represented as {(v1, a1, s1), (v2, a2, s2), (v3, a3, s3) ... (vn, an, sn)}, wherein v1 is the vibration velocity corresponding to time t1, a1 is the vibration acceleration corresponding to time t1, s1 is the vibration displacement corresponding to time t1, v2 is the vibration velocity corresponding to time t2, a2 ​​is the vibration acceleration corresponding to time t2, s2 is the vibration displacement corresponding to time t2, ..., and so on.

[0032] Specifically, the operating audio data corresponding to the substation under test can be collected based on the audio sensor configured within the detection range of the substation under test, and the operating vibration data corresponding to the substation under test can be collected based on the vibration sensor configured within the detection range of the substation under test. Thus, based on the pre-set timing task, the operating audio data and operating vibration data of the substation under test within the target time period can be periodically obtained.

[0033] Exemplarily, the audio sensor and the vibration sensor may be configured at the associated position of the substation to be tested, for example, the audio sensor and the vibration sensor may be configured at the set position of the side wall of the substation to be tested, for real-time collection of the operation audio data and operation vibration data of the substation to be tested during operation. The scheduled task is pre-set to obtain the operation audio data and operation vibration data within the past 5 minutes (i.e., the target time period) every 5 minutes.

[0034] S120: Divide the running audio data into a plurality of audio sub-data according to a preset time interval, and determine a stationary property of the running audio data based on similarities between the plurality of audio sub-data.

[0035] The preset time interval is a preset time length. The audio sub-data is a part of the running audio data, and the multiple audio sub-data do not overlap with each other.

[0036] Among them, the similarity of audio data refers to the similarity of audio sub-data features. For example, the larger the similarity value of two audio sub-data, the higher the similarity of the features of the two audio sub-data. The specific representation form of similarity can be similarity in the frequency domain, for example, the similarity can be spectrum similarity, amplitude similarity, etc. The stable attribute is used to characterize the stability of the entire running audio data. The stable attribute includes a signal stable attribute and a signal unsteady attribute. In this embodiment, the purpose of determining the stable attribute of the running audio data is that in practical applications, the operating conditions of the transformer equipment need to be continuously detected, and the operating condition data during the operation process need to be saved. If all the data are recorded, the amount of data is very large and requires a lot of storage space. Based on the fact that the operating conditions of the transformer equipment are basically stable in a short period of time, when the equipment operating conditions change greatly, the corresponding audio signal and vibration signal will also change greatly. Therefore, for unstable conditions, that is, when the stable attribute is a signal unsteady attribute, the running audio data and the running vibration data can be further analyzed and processed to determine the possible fault categories of the transformer equipment to be tested. For stable working conditions, that is, when the stable attribute is a signal stable attribute, there is no need to judge the fault category, and only the data generated during the operation process needs to be stored.

[0037] Specifically, on the basis of dividing the running audio data into a plurality of audio sub-data, a reference audio sub-data can be determined from the plurality of audio sub-data (for example, the last audio sub-data can be determined as the reference audio sub-data), and each audio sub-data except the reference audio sub-data is determined as the comparison audio sub-data, and then, the similarity between each comparison audio sub-data and the reference audio sub-data is calculated respectively, thereby obtaining the similarity corresponding to each comparison audio sub-data. Further, if all similarities are less than or equal to the similarity threshold, the stability attribute of the running audio data is the signal stability attribute; otherwise, the stability attribute of the running audio data is the signal non-stationary attribute.

[0038] Exemplarily, the preset time interval is 30 seconds, and the running audio data includes 5 minutes of running audio values. Then, the running audio data can be divided into 10 non-overlapping audio sub-data segments in chronological order, specifically including: audio sub-data A1, audio sub-data A2, audio sub-data A3, ..., audio sub-data A10. Audio sub-data A10 can be determined as reference audio sub-data, and the remaining audio sub-data can be determined as comparison audio sub-data. Then, the similarity value between audio sub-data A10 and audio sub-data A1 is calculated, for example, the spectrum similarity value Y1; the spectrum similarity value Y2 between audio sub-data A10 and audio sub-data A2 is calculated, ..., and the spectrum similarity value Y9 between audio sub-data A10 and audio sub-data A9 is calculated. The preset similarity threshold is δ. If Y1, Y2, ..., Y9 are all greater than Y9, the stability attribute of the running audio data is the signal stability attribute; otherwise, the stability attribute of the running audio data is the signal non-stationary attribute.

[0039] S130. When the stationary property of the operating audio data meets a preset condition, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested.

[0040] In this embodiment, the preset condition includes that the stationary attribute of the running audio data is a signal non-stationary attribute.

[0041] Among them, the fault detection model is a pre-trained neural network model. Generally speaking, for a certain substation equipment, if the "buzzing" sound is louder and sharper than usual, and the sound is uniform, it is generally caused by excessive power supply voltage; the "buzzing" sound is sometimes high and sometimes low, but there is no noise, which is generally caused by large load changes; the "buzzing" sound is loud and heavy, but there is no noise, which is generally overloaded; the "buzzing" sound is loud and noisy, and sometimes there will be a "ding-dong" beating sound, which is generally caused by loose internal structure; if there is a "hissing" sound, it is generally caused by discharge caused by dirty high-voltage bushings; if there is a "gurgling" sound, this situation may be caused by a short circuit between transformer turns. Based on this, historical operation audio data and historical operation vibration data including these faults can be obtained in advance as training samples, and the fault detection model to be trained is trained through a large number of training samples to obtain a trained fault detection model. In this embodiment, corresponding to the training samples determined above, the fault attributes may include at least one of the following: the fault category includes at least one of the following: overvoltage fault category, overload fault category, excessive load change fault category, loose accessories fault category, partial discharge fault category, and conductor turn-to-turn short circuit fault category.

[0042] Specifically, when it is determined that the operating audio data of the substation to be tested corresponds to an unstable signal attribute, the operating audio data and the operating vibration data can be input into a pre-trained fault detection model, and the fault detection model can output the fault category of the substation to be tested.

[0043] The technical solution of the embodiment of the present invention can obtain the operating audio data and operating vibration data of the substation to be tested within the target time period during the operation of the substation to be tested. Through the joint analysis of audio and vibration signals, more dimensional fault characteristics can be captured, and some hidden faults that are difficult to detect by sound or vibration alone can be found, which improves the comprehensiveness of substation fault identification and improves the efficiency and accuracy of substation fault detection. Further, the operating audio data is divided into multiple audio sub-data according to a preset time interval, and the stationary attribute of the operating audio data is determined based on the similarity between the multiple audio sub-data. Then, when the stationary attribute of the operating audio data meets the preset conditions, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested. The technical solution of this embodiment determines whether to start fault detection of the substation through the stationary attribute of the operating audio data, and can discard most of the signals of the substation in a stable operating state, without missing the complete monitoring of the equipment working condition, which not only greatly reduces the data processing volume, but also achieves the effect of uninterrupted detection, further improving the comprehensiveness of substation fault identification, detection efficiency and accuracy.

[0044] Embodiment 2

[0045] Figure 2 This is a schematic diagram of a method for detecting a fault in a substation provided by an embodiment of the present invention. Based on the above embodiment, S120 is further refined. The specific implementation method can refer to the technical solution of this embodiment. The technical terms that are the same or corresponding to the above embodiment are not repeated here.

[0046] like Figure 2 As shown, the method specifically comprises the following steps:

[0047] S210: Acquire operating audio data and operating vibration data of the substation to be tested within a target time period.

[0048] S220, dividing the running audio data into a plurality of audio sub-data according to a preset time interval.

[0049] S230: Determine the Mel-cepstral coefficient vector corresponding to each audio sub-data.

[0050] In this embodiment, the audio sub-data includes multiple discrete running audio signals. The Mel-frequency cepstral coefficient is a characteristic parameter that can simulate the structure of the human cochlea. Therefore, by calculating the Mel-frequency cepstral coefficient vector corresponding to the audio sub-data, data preparation can be provided for the subsequent calculation of the spectrum similarity between the audio sub-data.

[0051] Specifically, the specific implementation steps of determining the Mel-cepstral coefficient vector corresponding to each audio sub-data may include:

[0052] S2301. For each audio sub-data, perform modal decomposition processing on the current audio sub-data to obtain a frequency value of at least one modal component included in the current audio sub-data.

[0053] In this embodiment, the processing process for each audio sub-data is the same. Here, any one of the audio sub-data is taken as the current audio sub-data, and the current audio sub-data is taken as an example for exemplary description.

[0054] Specifically, the target modal decomposition algorithm can be used to perform modal decomposition processing on the current audio sub-data to obtain at least one modal component corresponding to the current audio sub-data. Each modal component corresponds to a different frequency value, thereby obtaining the frequency value of at least the modal component corresponding to the current audio sub-data. Exemplarily, the empirical modal decomposition algorithm can be used to perform modal decomposition processing on the current audio sub-data to obtain 8 modal components, namely the first modal component, the second modal component, ..., the eighth modal component, wherein the frequency value corresponding to the first modal component is H1, the frequency value corresponding to the second modal component is H2, ..., and the frequency value corresponding to the eighth modal component is H8.

[0055] S2302: For each frequency value, determine the Mel frequency value corresponding to the current frequency value based on a preset frequency threshold conversion function, and determine the cepstral coefficient value corresponding to the Mel frequency value to obtain the Mel cepstral coefficient value corresponding to the current frequency value.

[0056] In this embodiment, the processing process for each frequency value is the same. Here, any frequency value is taken as the current frequency value, and the current frequency value is taken as an example for exemplary description.

[0057] Among them, the expression corresponding to the preset frequency threshold conversion function is:

[0058]

[0059] Where m is the Mel frequency and f is the frequency value in Hz.

[0060] Specifically, for each frequency value, the frequency value is substituted into formula (1) to calculate the Mel frequency value corresponding to the frequency value, and then cepstrum analysis is performed in the Mel frequency domain, including operations such as taking logarithms and inverse transformation, to finally obtain the Mel frequency cepstrum value.

[0061] S2303. Determine a Mel-cepstral coefficient vector corresponding to the current audio sub-data based on the Mel-cepstral coefficient value corresponding to each frequency value.

[0062] In this embodiment, a set of all Mel-cepstral coefficient values ​​corresponding to each frequency value may be used as a Mel-cepstral coefficient vector corresponding to the current audio sub-data.

[0063] S240: Determine the last audio sub-data among the multiple audio sub-data as the first audio sub-data, and determine each audio sub-data except the first audio sub-data as the second audio sub-data.

[0064] In this embodiment, the running audio data can be divided into multiple non-overlapping audio sub-data according to the time sequence. For example, 5 minutes of running audio data can be divided into 10 audio sub-data including 30 seconds of data, the 10th audio sub-data is the first audio sub-data, and the remaining audio sub-data are the second audio sub-data.

[0065] S250 : Determine frequency spectrum similarity between the first audio sub-data and each second audio sub-data based on the first Mel-cepstral coefficient vector of the first audio sub-data and the second Mel-cepstral coefficient vector of each second audio sub-data.

[0066] In this embodiment, the specific implementation method of determining the spectral similarity can be: for each second Mel-cepstral coefficient vector, calculating the distance information between the first Mel-cepstral coefficient vector and the current second Mel-cepstral coefficient vector; based on the distance information, determining the spectral similarity between the first audio sub-data and the current second audio sub-data.

[0067] In this embodiment, the processing process of each second Mel-cepstral coefficient vector is the same. Here, any one of the second Mel-cepstral coefficient vectors is taken as the current second Mel-cepstral coefficient vector, and the current second Mel-cepstral coefficient vector is taken as an example for exemplary description.

[0068] Exemplarily, the current second audio sub-data X2 m The corresponding current second Mel-frequency cepstral coefficient vector can be expressed as C2(n), the first audio sub-data X1 S The corresponding first Mel cepstral coefficient vector can be expressed as C1(n), then the distance information between the first Mel cepstral coefficient vector and the current second Mel cepstral coefficient vector can be expressed as Based on this, since the smaller the value of the distance information is, the closer the two vectors are in the spatial dimension, the distance information can be converted into a numerical value to obtain the frequency spectrum similarity between the first audio sub-data and the current second audio sub-data.

[0069] S260: Determine the stationary property of the running audio data based on the similarities of the respective frequency spectra and a preset similarity threshold.

[0070] In this embodiment, the stability attribute includes: a signal stability attribute and a signal non-stationary attribute. Specifically, if all spectrum similarities are greater than a preset similarity threshold, the running audio data is determined to have a signal stability attribute; if there is at least one spectrum similarity less than or equal to the preset similarity threshold, the running audio data is determined to have a signal non-stationary attribute.

[0071] S270. When the stationary property of the operating audio data meets a preset condition, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested.

[0072] Furthermore, on the basis of the above technical solution, when the fault type is determined, the target user can be warned of equipment faults. For example, the target user can be reminded of possible faults in the substation to be tested through instant messaging methods such as text messages, emails, and phone calls, so that the target user can further confirm on-site and take corresponding measures in advance to avoid negative consequences.

[0073] S280. If the smoothness property of the operating audio data does not meet the preset condition, at least one audio sub-data and an operating vibration data sub-segment corresponding to the audio sub-data time information are stored in a preset storage unit for reviewing the operating status of the substation to be tested.

[0074] In this embodiment, if the operating audio data has a signal stability attribute, an audio sub-data can be arbitrarily selected from all audio sub-data as the audio sub-data to be stored, and the operating vibration data sub-segment corresponding to the audio sub-data to be stored and the time information of the audio sub-data to be stored is stored in a preset storage unit. This is because, in an actual production environment, the working condition of the transformer equipment needs to be continuously detected, and the operating condition data of the transformer equipment needs to be fully recorded in order to prepare for the operating status review of the transformer equipment to be tested. However, if all data are recorded, the amount of data is very large, and a large amount of storage resources are required. In this embodiment, when the operating audio data has a signal stability attribute, a certain audio sub-data can represent a whole section of operating audio data, so this section of operating condition data can be stored, and most of the redundant signals are not saved. By focusing on recording the signals of the working condition change process, discarding most of the signals in the stable operating state, and not missing the complete monitoring of the equipment working condition, not only can the storage amount of audio data be greatly reduced, but also the effect of uninterrupted detection is achieved.

[0075] The technical solution of the embodiment of the present invention, when determining the stationary attribute of the operating audio data based on the similarity between multiple audio sub-data, can determine the Mel-cepstral coefficient vector corresponding to each audio sub-data, and then determine the last audio sub-data in the multiple audio sub-data as the first audio sub-data, and determine each audio sub-data other than the first audio sub-data as the second audio sub-data, and further, based on the first Mel-cepstral coefficient vector of the first audio sub-data and the second Mel-cepstral coefficient vector of each second audio sub-data, determine the spectrum similarity between the first audio sub-data and each second audio sub-data, thereby determining the stationary attribute of the operating audio data based on each spectrum similarity and a preset similarity threshold. The technical solution provided by this embodiment improves the accuracy of the stationary attribute by determining the Mel-cepstral coefficient vector of the audio sub-data, and further improves the detection efficiency and accuracy of the fault identification of the substationary equipment. In addition, in the case where the operating audio data has a signal stationary attribute, most of the redundant signals are not saved, and by focusing on recording the signals of the working condition change process and discarding most of the signals in the stable operating state, not only the storage amount of the audio data is greatly reduced, but also the effect of uninterrupted detection is achieved.

[0076] Embodiment 3

[0077] Next, a specific example is used to illustrate the implementation of the substation equipment fault detection method, which may specifically include:

[0078] The operation audio data and the operation vibration data can be collected by the substation equipment operation data processing device, and the stable property of the operation audio data can be determined. The schematic diagram of the substation equipment operation data processing device can be found in Figure 3.like Figure 3 As shown, the substation operation data processing device is based on a data processing unit (e.g., a single-chip microcomputer) as the core, and is configured with buttons, a vibration information acquisition module, an audio processing module, a power module (this device can use a 5000mA / h power module), a liquid crystal display, an LED array, an SD memory card and other peripheral circuits.

[0079] The data processing unit can use STM series microcontrollers, which have high compatibility of pin-to-pin, peripherals and software, and high flexibility. The application can be upgraded to require more storage space or streamlined to use less storage space / or use different packaging specifications without modifying the original framework and software.

[0080] The audio processing module is used to collect and run audio data. For example, the sound collection module can use an audio decoding chip, which has corresponding audio decoders and encoders. It is a single-chip Ogg Vorbis / MP3 / AAC / WMA / MIDI audio decoder, an IMA ADPCM encoder, and a user-loaded Ogg Vorbis encoder. It contains a high-performance, patented low-power DSP processor core VS_DSP4, working data memory, serial control and input data interface, up to 8 available general-purpose I / O pins, a UART, and a high-quality variable sampling rate stereo ADC ("mic", "line", "line + mic" or "line * 2") and stereo DAC, and a headphone amplifier and a common voltage buffer. The module supports decoding of audio formats such as MP3 / WMA / OGG / WAV / FLAC / MIDI / AAC and recording of OGG / WAV audio formats, and supports high and low bass adjustment and EarSpeaker space effect settings.

[0081] The vibration information acquisition module is used to collect operating vibration data. For example, the vibration information acquisition module can use a three-axis acceleration sensor, which can capture the acceleration changes of an object in three-dimensional space, provide a complete detection signal for detecting the vibration information of the transformer equipment, and provide a reliable basis for equipment fault diagnosis, performance optimization and reliability evaluation.

[0082] In order to be able to display the status of the audio recording and set the recording time, the substation operation data processing equipment is also equipped with a screen that can display. For example, a liquid crystal display can be used, and the liquid crystal display can be a thin film transistor liquid crystal display, that is, "true color" (TFT). TFT liquid crystal has a semiconductor switch for each pixel, and each pixel can be directly controlled by a dot pulse, so each node is relatively independent and can be controlled continuously, which not only improves the response speed of the display, but also can accurately control the display color level, so the color of TFT liquid crystal is more true. The characteristics of TFT liquid crystal display are good brightness, clear display, high contrast, strong layering, bright colors, and moderate power consumption.

[0083] In addition to the above hardware, the substation equipment operation data processing device includes a housing. Figure 4 .like Figure 4 As shown, the shell adopts a design concept of bevels and right angles. The bevels on the front and top prevent rainwater from flowing into the core components inside the shell. The right-angle design on the back ensures that the substation operation data processing equipment is conveniently placed. There is also a groove on the back, which can be used to place magnets or clips to fix the substation operation data processing equipment.

[0084] In a specific application process, during the operation of the substation to be tested, the operation audio data and the operation vibration data can be obtained through the audio processing module and the vibration information acquisition module in the substation operation data processing device. After the data processing unit performs a stationarity analysis on the operation audio data, it determines the operation audio data and the operation vibration data that need to be stored in the SD memory card. In the case where the stationarity attribute does not meet the preset conditions, the server side (i.e., the computer side) can read the operation audio data and the operation vibration data of the substation to be tested from the SD memory card, and apply the fault detection model deployed in the computer to process the operation audio data and the operation vibration data to obtain the fault category of the substation to be tested.

[0085] The substation operation data processing device provided in this example uses low-cost sensors and corresponding data processing algorithms to remove a large amount of redundant data and reduce the production and maintenance costs of the detection equipment. In addition, audio processing can be effectively deployed in the data processing unit to save computing resources as much as possible.

[0086] Embodiment 4

[0087] Figure 5 The present invention provides a schematic structural diagram of a substation fault detection device provided by an embodiment of the present invention. The device includes: an operation data acquisition module 410 , a stationary attribute classification module 420 , and a fault category determination module 430 .

[0088] The operation data acquisition module 410 is used to acquire the operation audio data and operation vibration data of the substation to be tested within the target time period;

[0089] A stationary attribute division module 420, configured to divide the operation audio data into a plurality of audio sub-data according to a preset time interval, so as to determine a stationary attribute of the operation audio data based on similarities between the plurality of audio sub-data;

[0090] The fault category determination module 430 is used to input the operating audio data and the operating vibration data into a pre-trained fault detection model to determine the fault category of the substationary equipment to be tested when the smooth attribute of the operating audio data meets a preset condition.

[0091] Based on the above device, optionally, the stationary attribute division module 420 includes:

[0092] A cepstrum vector determining unit, used to determine the Mel-cepstrum coefficient vector corresponding to each of the audio sub-data;

[0093] an audio data dividing unit, configured to determine the last audio sub-data among the plurality of audio sub-data as the first audio sub-data, and determine each of the audio sub-data except the first audio sub-data as the second audio sub-data;

[0094] a similarity determination unit, configured to determine a frequency spectrum similarity between the first audio sub-data and each of the second audio sub-data based on a first Mel-cepstral coefficient vector of the first audio sub-data and a second Mel-cepstral coefficient vector of each of the second audio sub-data;

[0095] The stationary attribute determining unit is used to determine the stationary attribute of the running audio data based on each of the frequency spectrum similarities and a preset similarity threshold.

[0096] On the basis of the above device, optionally, the cepstrum vector determining unit includes:

[0097] A modal decomposition subunit, configured to perform modal decomposition processing on each of the audio sub-data and the current audio sub-data to obtain a frequency value of at least one modal component contained in the current audio sub-data;

[0098] A coefficient value determination subunit is used to determine, for each of the frequency values, a Mel frequency value corresponding to a current frequency value based on a preset frequency threshold conversion function, and determine a cepstral coefficient value corresponding to the Mel frequency value, to obtain a Mel cepstral coefficient value corresponding to the current frequency value;

[0099] The cepstral vector determining subunit is used to determine the Mel-cespectral coefficient vector corresponding to the current audio sub-data based on the Mel-cespectral coefficient values ​​corresponding to each of the frequency values.

[0100] Based on the above device, optionally, the similarity determination unit is specifically used to calculate the distance information between the first Mel-cepstral coefficient vector and the current second Mel-cepstral coefficient vector for each of the second Mel-cepstral coefficient vectors, so as to determine the spectral similarity between the first audio sub-data and the current second audio sub-data based on the distance information.

[0101] Based on the above-mentioned device, optionally, the smoothness attribute includes: a signal smoothness attribute and a signal non-smoothness attribute, and the smoothness attribute determination unit is specifically used to determine that the running audio data has a signal smoothness attribute if all the spectrum similarities are greater than a preset similarity threshold; if there is at least one spectrum similarity that is less than or equal to the preset similarity threshold, then determine that the running audio data has a signal non-smoothness attribute.

[0102] Based on the above device, optionally, the preset condition includes that the stability attribute of the running audio data is a signal non-stationary attribute.

[0103] Based on the above device, optionally, the fault category includes at least one of the following: overvoltage fault category, overload fault category, excessive load change fault category, loose accessories fault category, partial discharge fault category, and conductor turn-to-turn short circuit fault category.

[0104] On the basis of the above device, optionally, the substation fault detection device further includes: a data storage module;

[0105] A data storage module is used to store at least one of the audio sub-data and the operating vibration data sub-segment corresponding to the audio sub-data time information in a preset storage unit if the smooth attribute of the operating audio data does not meet the preset conditions, so as to prepare for the operating status review of the substation equipment to be tested.

[0106] The technical solution of the embodiment of the present invention can obtain the operating audio data and operating vibration data of the substation to be tested within the target time period during the operation of the substation to be tested. Through the joint analysis of audio and vibration signals, more dimensional fault characteristics can be captured, and some hidden faults that are difficult to detect by sound or vibration alone can be found, which improves the comprehensiveness of substation fault identification and improves the efficiency and accuracy of substation fault detection. Further, the operating audio data is divided into multiple audio sub-data according to a preset time interval, and the stationary attribute of the operating audio data is determined based on the similarity between the multiple audio sub-data. Then, when the stationary attribute of the operating audio data meets the preset conditions, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested. The technical solution of this embodiment determines whether to start fault detection of the substation through the stationary attribute of the operating audio data, and can discard most of the signals of the substation in a stable operating state, without missing the complete monitoring of the equipment working condition, which not only greatly reduces the data processing volume, but also achieves the effect of uninterrupted detection, further improving the comprehensiveness of substation fault identification, detection efficiency and accuracy.

[0107] The substation fault detection device provided in the embodiment of the present invention can execute the substation fault detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0108] It is worth noting that the various units and modules included in the above system are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0109] Embodiment 5

[0110] Figure 6 The present invention is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 6 A block diagram of an exemplary electronic device 50 suitable for implementing exemplary embodiments of the present invention is shown. Figure 6 The electronic device 50 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0111] like Figure 6 As shown, the electronic device 50 is in the form of a general computing device. The components of the electronic device 50 may include but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 connecting different system components (including the system memory 502 and the processing unit 501).

[0112] Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0113] The electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0114] System memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 504 and / or cache memory 505. Electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 506 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 503 via one or more data medium interfaces. The memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0115] A program / utility 508 having a set (at least one) of program modules 507 may be stored, for example, in the memory 502, such program modules 507 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 507 generally perform the functions and / or methods of the embodiments described herein.

[0116] The electronic device 50 may also communicate with one or more external devices 509 (e.g., keyboards, pointing devices, displays 810, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 50, and / or may communicate with any device that enables the electronic device 50 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 511. Furthermore, the electronic device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 512. As shown, the network adapter 512 communicates with other modules of the electronic device 50 through the bus 503. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0117] The processing unit 501 executes various functional applications and page processing by running the programs stored in the system memory 502, for example, implementing the substation fault detection method provided in the embodiment of the present invention.

[0118] Embodiment 6

[0119] An embodiment of the present invention further provides a storage medium containing computer executable instructions, and when the computer executable instructions are executed by a computer processor, they are used to execute a method for detecting a fault of a substation, the method comprising:

[0120] Obtaining the operating audio data and operating vibration data of the substation to be tested within the target time period;

[0121] Dividing the running audio data into a plurality of audio sub-data according to a preset time interval, so as to determine a stationary property of the running audio data based on similarities between the plurality of audio sub-data;

[0122] When the stationary property of the operating audio data meets a preset condition, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested.

[0123] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0124] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0125] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0126] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0127] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for detecting faults in substation equipment, characterized in that: include: Obtaining the operating audio data and operating vibration data of the substation to be tested within the target time period; Dividing the running audio data into a plurality of audio sub-data according to a preset time interval, so as to determine a stationary property of the running audio data based on similarities between the plurality of audio sub-data; When the stationary property of the operating audio data meets a preset condition, the operating audio data and the operating vibration data are input into a pre-trained fault detection model to determine the fault category of the substation to be tested.

2. The method according to claim 1, characterized in that The similarity includes spectrum similarity, and determining the stationary property of the running audio data based on the similarity between the plurality of audio sub-data includes: Determine the Mel-cepstral coefficient vector corresponding to each of the audio sub-data; Determine the last audio sub-data among the plurality of audio sub-data as the first audio sub-data, and determine each of the audio sub-data except the first audio sub-data as the second audio sub-data; determining, based on a first Mel-cepstral coefficient vector of the first audio sub-data and a second Mel-cepstral coefficient vector of each of the second audio sub-data, a frequency spectrum similarity between the first audio sub-data and each of the second audio sub-data; Based on the frequency spectrum similarities and a preset similarity threshold, a stationary property of the running audio data is determined.

3. The method according to claim 2, characterized in that The audio sub-data includes a plurality of discrete running audio signals, and the step of determining a Mel-cepstral coefficient vector corresponding to each of the audio sub-data includes: For each of the audio sub-data, a modal decomposition process is performed on the current audio sub-data to obtain a frequency value of at least one modal component contained in the current audio sub-data; For each of the frequency values, determine the Mel frequency value corresponding to the current frequency value based on a preset frequency threshold conversion function, and determine the cepstral coefficient value corresponding to the Mel frequency value, to obtain the Mel cepstral coefficient value corresponding to the current frequency value; Based on the Mel-cepstral coefficient values ​​corresponding to the frequency values, a Mel-cepstral coefficient vector corresponding to the current audio sub-data is determined.

4. The method according to claim 2, characterized in that: The determining, based on the first Mel-cepstral coefficient vector of the first audio sub-data and the second Mel-cepstral coefficient vector of each second audio sub-data, the frequency spectrum similarity between the first audio sub-data and each second audio sub-data includes: For each of the second Mel-cepstral coefficient vectors, calculating distance information between the first Mel-cepstral coefficient vector and the current second Mel-cepstral coefficient vector; Based on the distance information, a frequency spectrum similarity between the first audio sub-data and the current second audio sub-data is determined.

5. The method according to claim 2, characterized in that: The stationary attribute includes: a signal stationary attribute and a signal unstationary attribute. The determining of the stationary attribute of the running audio data based on each of the spectrum similarities and a preset similarity threshold includes: If all the frequency spectrum similarities are greater than a preset similarity threshold, determining that the running audio data has a signal stability attribute; If there is at least one frequency spectrum similarity that is less than or equal to the preset similarity threshold, it is determined that the running audio data has an unsteady signal attribute.

6. The method according to claim 1, characterized in that The preset condition includes that the stationary attribute of the running audio data is a signal non-stationary attribute.

7. The method according to claim 1, characterized in that The method further comprises: If the smooth attribute of the operating audio data does not meet the preset conditions, at least one of the audio sub-data and the operating vibration data sub-segment corresponding to the audio sub-data time information is stored in a preset storage unit for the operating status review of the substation to be tested.

8. The method according to claim 1, characterized in that The fault category includes at least one of the following: an overvoltage fault category, an overload fault category, an excessive load change fault category, a loose accessories fault category, a partial discharge fault category, and a conductor turn-to-turn short circuit fault category.

9. A substation fault detection device, characterized in that: include: An operation data acquisition module is used to acquire the operation audio data and operation vibration data of the substation to be tested within a target time period; a stationary attribute division module, configured to divide the running audio data into a plurality of audio sub-data according to a preset time interval, so as to determine the stationary attribute of the running audio data based on the similarity between the plurality of audio sub-data; A fault category determination module is used to input the operating audio data and the operating vibration data into a pre-trained fault detection model to determine the fault category of the substationary equipment to be tested when the smooth attribute of the operating audio data meets a preset condition.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for detecting faults in substation equipment according to any one of claims 1 to 8.

Images