Voiceprint signal processing method and device of power transformation equipment, equipment and storage medium

Abstract

The invention provides a voiceprint signal processing method and device for power transformation equipment, equipment and a storage medium, and the method comprises the steps: carrying out the discretization of a to-be-processed voiceprint signal of the power transformation equipment, and obtaining a discrete signal; calculating a first wavelet coefficient of the discrete signal; performing low-pass filtering processing on the discrete signal based on the first wavelet coefficient to obtain a target discrete signal; calculating a second wavelet coefficient of the target discrete signal; performing wavelet inverse transformation on the target discrete signal based on the second wavelet coefficient to obtain a target voiceprint signal; the inverse wavelet transform is used for restoring the target discrete signal into an original voiceprint signal format. According to the invention, noise reduction is carried out on the voiceprint signal generated during actual operation of the power transformation equipment through the wavelet algorithm and the low-pass filtering method, so that the voiceprint features are clearer and more accurate, and the voiceprint signal recognition rate of the power transformation equipment is improved.

Description

Technical Field

[0001] The present application relates to the field of voiceprint recognition technology, and in particular to a method, device, equipment and storage medium for processing voiceprint signals of a substation. Background Art

[0002] Against the backdrop of increasingly intelligent power system operation and maintenance, voiceprint signal noise reduction technology has emerged. As the core of power transmission and distribution, the stability of the substation equipment's operating state is directly related to the safety and stability of the entire power system. However, in actual operation, due to the influence of complex factors such as environmental noise and electromagnetic interference, substation equipment will generate a large amount of useless noise information, which will lead to a decrease in the recognition accuracy of voiceprint signals. At the same time, the processing speed is difficult to meet the real-time requirements, limiting the practical level of voiceprint signal noise reduction technology.

[0003] The current voiceprint signal processing of substation equipment faces two major challenges: First, traditional filtering methods are limited to a fixed frequency range, making it difficult to effectively distinguish and filter out noise in non-stationary signals. At the same time, useful signals may be lost, and they lack the ability to adaptively adjust filtering parameters, making them ineffective when processing complex signals. Second, although Fourier transform can reveal frequency domain characteristics, it lacks local information in the time domain, and has limitations when processing non-stationary signals and overlapping signals in the frequency domain. In addition, the amount of calculation for long signals is large, affecting real-time processing performance. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a voiceprint signal processing method, device, equipment and storage medium for substation equipment.

[0005] As one aspect of the present application, a method for processing a voiceprint signal of a substation is provided, comprising:

[0006] Discretize the to-be-processed voiceprint signal of the power substation to obtain a discrete signal;

[0007] Calculating a first wavelet coefficient of the discrete signal;

[0008] Based on the first wavelet coefficient, low-pass filtering is performed on the discrete signal to obtain a target discrete signal;

[0009] Calculating a second wavelet coefficient of the target discrete signal;

[0010] Based on the second wavelet coefficient, the target discrete signal is subjected to an inverse wavelet transform to obtain a target voiceprint signal; the inverse wavelet transform is used to restore the target discrete signal to an original voiceprint signal format.

[0011] Optionally, the first wavelet coefficient satisfies the following expression:

[0012]

[0013] Among them, W f1 is the first wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0014] Optionally, the target discrete signal satisfies the following expression:

[0015] S f (j+1,k)=S f (j,k)×h(j,k);

[0016] Among them, S f represents the target discrete signal, and h is a low-pass filter processor.

[0017] Optionally, the second wavelet coefficient satisfies the following expression:

[0018]

[0019] Among them, W f2 is the second wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0020] Optionally, the voiceprint signal to be processed and the target voiceprint signal are respectively input into a neural network model to obtain a defect detection result; the neural network model is used to perform voiceprint defect detection on the voiceprint signal to be processed and the target voiceprint signal.

[0021] Optionally, the voiceprint signal to be processed is collected.

[0022] Optionally, the voiceprint signal to be processed satisfies the Nyquist sampling theorem.

[0023] As a second aspect of the present application, a voiceprint signal processing device for a substation is provided, comprising: a processing module and a calculation module;

[0024] The processing module is used to discretize the voiceprint signal to be processed of the substation equipment to obtain a discrete signal;

[0025] The calculation module is used to calculate the first wavelet coefficient of the discrete signal;

[0026] The processing module is further used to perform low-pass filtering on the discrete signal based on the first wavelet coefficient to obtain a target discrete signal;

[0027] The calculation module is also used to calculate the second wavelet coefficient of the target discrete signal;

[0028] The processing module is also used to perform an inverse wavelet transform on the target discrete signal based on the second wavelet coefficient to obtain a target voiceprint signal; the inverse wavelet transform is used to restore the target discrete signal to the original voiceprint signal format.

[0029] Optionally, the first wavelet coefficient satisfies the following expression:

[0030]

[0031] Among them, W f1 is the first wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0032] Optionally, the target discrete signal satisfies the following expression:

[0033] S f (j+1,k)=S f (j,k)×h(j,k);

[0034] Among them, S f represents the target discrete signal, and h is a low-pass filter processor.

[0035] Optionally, the second wavelet coefficient satisfies the following expression:

[0036]

[0037] Among them, W f2 is the second wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0038] Optionally, the processing module is also used to input the voiceprint signal to be processed and the target voiceprint signal into a neural network model respectively to obtain a defect detection result; the neural network model is used to perform voiceprint defect detection on the voiceprint signal to be processed and the target voiceprint signal.

[0039] Optionally, the voiceprint signal processing device of the power transformation equipment further includes a collection module;

[0040] The acquisition module is used to acquire the voiceprint signal to be processed.

[0041] Optionally, the voiceprint signal to be processed satisfies the Nyquist sampling theorem.

[0042] As a third aspect of the present application, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a voiceprint signal processing method for the above-mentioned substation when executing the program.

[0043] As a fourth aspect of the present application, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the voiceprint signal processing method of the above-mentioned substation equipment provided in the present application.

[0044] From the above, it can be seen that the voiceprint signal processing method, device, equipment and storage medium of the substation equipment provided by the present application can convert the continuous analog signal into a discrete digital signal by discretizing the voiceprint signal of the substation equipment, which not only simplifies the representation of the signal, but also facilitates the subsequent digital processing. Then, the wavelet transform is used to calculate the wavelet coefficients of the discrete signal. The wavelet transform has good localization characteristics in both the time domain and the frequency domain, and can effectively extract the high-frequency and low-frequency parts of the signal. Furthermore, the discrete signal is low-pass filtered based on the wavelet coefficients to remove the high-frequency noise and unnecessary detail information generated by the substation equipment in actual operation, thereby obtaining a purer target discrete signal, making the voiceprint feature clearer and more accurate. Finally, the target discrete signal is inversely transformed by wavelet to restore the target voiceprint signal that is closer to the original voiceprint signal format, ensuring the integrity of the voiceprint signal during the processing process, thereby realizing accurate monitoring and evaluation of the status of the substation equipment, and facilitating early warning and accurate diagnosis of substation equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A schematic diagram of an application scenario of a voiceprint signal processing method for a substation provided in an embodiment of the present application;

[0047] Figure 2 A flow chart of a voiceprint signal processing method for a substation provided in an embodiment of the present application;

[0048] Figure 3A flow chart of a voiceprint signal processing method for a substation provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram of voiceprint signal sampling for a substation provided in an embodiment of the present application;

[0050] Figure 5 A flow chart of a voiceprint signal processing method for a substation provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the composition of a voiceprint signal processing device for a substation provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0054] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a concrete way. Unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meaning understood by people with ordinary skills in the field to which the present application belongs. SUMMARY OF THE INVENTION

[0056] Among the related technologies, voiceprint signal noise reduction technology is one of the key technologies for intelligent operation and maintenance management of power system substation equipment. This technology accurately collects the voiceprint signals generated during the operation of substation equipment, and uses signal processing technology for preprocessing and noise reduction to eliminate the interference of background noise, thereby significantly improving the signal-to-noise ratio and clarity of the voiceprint signal. On this basis, combined with voiceprint recognition technology, key voiceprint features are extracted to achieve accurate monitoring and evaluation of equipment status. When abnormal conditions such as mechanical wear and electrical faults are detected in the equipment, early warning and accurate diagnosis of the fault are achieved to ensure the safe and stable operation of the power system. The existing technologies mainly include traditional filtering methods and noise reduction technologies based on Fourier transform. These technologies have their own characteristics, but they also have some shortcomings.

[0057] The inventors of the present application have found that traditional filtering methods, such as low-pass, high-pass and band-pass filtering, mainly reduce noise by setting a specific frequency range. These methods have limitations when processing non-stationary signals because they are difficult to distinguish between noise and useful signals, especially when the frequency ranges of these signals overlap. In addition, the parameters of traditional filtering are usually fixed and are not suitable for adaptive adjustment according to the specific characteristics of the signal, which is not effective when processing complex and changeable voiceprint signals. On the other hand, Fourier transform, as a classic tool in the field of signal processing, although it realizes the conversion of signals from time domain to frequency domain, it is convenient for noise analysis in the frequency domain, but its global transformation characteristics limit its application in non-stationary signal processing. Fourier transform cannot simultaneously reveal the local characteristics of the signal in time and frequency, that is, it lacks time-frequency analysis capabilities, which is particularly difficult when processing the situation where the frequency domain of noise and useful signals overlap, and it is easy to cause signal distortion in the noise reduction process. Furthermore, for longer voiceprint signals, the computational complexity of Fourier transform increases significantly, affecting the real-time processing, and it is difficult to meet the data processing speed requirements of modern power systems or other application scenarios with high real-time requirements.

[0058] In order to solve the above problems, the present application provides a voiceprint signal processing method for a substation equipment. By discretizing the voiceprint signal of the substation equipment, a continuous analog signal can be converted into a discrete digital signal, which not only simplifies the representation of the signal, but also facilitates subsequent digital processing. Then, a wavelet transform is used to calculate the wavelet coefficients of the discrete signal. The wavelet transform has good localization characteristics in both the time domain and the frequency domain, and can effectively extract the high-frequency and low-frequency parts of the signal. Furthermore, based on the wavelet coefficients, the discrete signal is low-pass filtered to remove the high-frequency noise and unnecessary detail information generated by the substation equipment in actual operation, thereby obtaining a purer target discrete signal, making the voiceprint feature clearer and more accurate. Finally, the target discrete signal is inversely transformed by wavelet to restore the target voiceprint signal that is closer to the original voiceprint signal format, thereby ensuring the integrity of the voiceprint signal during the processing process, thereby realizing accurate monitoring and evaluation of the status of the substation equipment, and facilitating early warning and accurate diagnosis of substation equipment failures.

[0059] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application are described in detail below.

[0060] Application Scenario Overview

[0061] Figure 1 A schematic diagram of an application scenario of a voiceprint signal processing method for a substation provided in an embodiment of the present application. Figure 1 As shown, the application scenario includes a transformer 101, an audio acquisition device 102 and a voiceprint signal processing device 103. The transformer 101 is connected to the audio acquisition device 102 via a wired or wireless communication network, and the audio acquisition device 102 is connected to the voiceprint signal processing device 103 via a wired or wireless communication network.

[0062] The voiceprint signal processing device 103 mentioned here can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Optionally, the server can also be implemented on a cloud platform. For example, the cloud platform can include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, inter-clouds, and multi-clouds, etc., or any combination thereof. The embodiments of the present application are not limited to this.

[0063] In some embodiments, the substation equipment 101 is a key component in the power system, responsible for the conversion and distribution of electric energy. They will generate sounds with specific spectral characteristics when running, and these sounds can reflect the health of the equipment. The substation equipment 101 includes but is not limited to transformers, switch cabinets, circuit breakers, etc. These devices will have different soundprint characteristics when operating normally and when they fail. By monitoring these soundprints, the abnormal state of the equipment can be discovered in time, so as to perform maintenance and repair.

[0064] In some embodiments, the audio acquisition device 102 is responsible for capturing the voiceprint signal generated by the substation during operation. These devices include a highly sensitive microphone and a corresponding signal conditioning circuit, which can convert the voiceprint signal into an electrical signal and perform preliminary amplification and filtering. In addition, the audio acquisition device 102 will forward the collected voiceprint signal to the voiceprint signal processing device 103 for subsequent signal processing and analysis.

[0065] In some embodiments, the voiceprint signal processing device 103 is a device specifically used to process and analyze the voiceprint signal collected by the audio collection device. The voiceprint signal processing device 103 can perform preprocessing, feature extraction, pattern recognition and other processing on the sound signal through a series of complex algorithms and technologies to extract useful information from the sound signal, such as the operating status of the equipment, the type of fault, etc. The voiceprint signal processing device 103 contains special algorithms and models that can identify and distinguish different voiceprint features, so as to determine whether the substation equipment is operating normally or has potential faults.

[0066] The above example is described by taking the audio acquisition device 102 and the voiceprint signal processing device 103 as different devices. In some scenarios, the audio acquisition device 102 and the voiceprint signal processing device 103 can be the same device, that is, the device can simultaneously realize the function of collecting voiceprint signals and the voiceprint signal processing method of the substation of the present application.

[0067] It should be understood that Figure 1 is an exemplary structural diagram, Figure 1 The number of devices included in the application scenario shown is not limited, for example, the number of power conversion devices 101 is not limited and the number of audio acquisition devices 102 is not limited. Figure 1 In addition to the equipment shown, Figure 1 The application scenario shown may also include other devices, which is not limited to this.

[0068] Combine the following Figure 1The voiceprint signal processing method of the substation according to the exemplary embodiment of the present application is described by using the application scenario. It should be noted that the above application scenario is only shown to facilitate the understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this respect. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0069] Figure 2 A flow chart of a voiceprint signal processing method for a substation provided in an embodiment of the present application. Figure 2 As shown, the voiceprint signal processing method for substation equipment provided in the present application can be implemented by the above-mentioned voiceprint signal processing device 103, and specifically includes the following steps:

[0070] S201, discretize the voiceprint signal to be processed of the substation equipment to obtain a discrete signal.

[0071] In some embodiments, the collected voiceprint signal is a continuous analog signal, which is converted into a digital signal through an analog-to-digital converter (ADC). At this time, the continuous time signal will be converted into a series of discrete numerical points to obtain a discrete signal to simplify subsequent digital processing.

[0072] In some embodiments, Figure 3 As shown, before S201, the voiceprint signal processing method of the substation equipment provided by the embodiment of the present application further includes the following S200:

[0073] S200: Collect voiceprint signals to be processed.

[0074] Among them, the voiceprint signal to be processed satisfies the Nyquist sampling theorem.

[0075] In some embodiments, the voiceprint signal generated by the substation equipment during operation is collected by a microphone or other high-precision audio collection device, and the collected original audio signal is stored as a digital file for subsequent processing. The voiceprint signal is an analog signal, which represents the voiceprint feature of the substation equipment, and the voiceprint signal satisfies the following expression:

[0076] f(t)=s(t)+n(t);

[0077] Among them, f(t) is the collected signal, s(t) is the original signal, n(t) is the white noise signal, and t is time.

[0078] It should be noted that if Figure 4 As shown, according to the Nyquist-Shannon sampling theorem, the sampling frequency of the voiceprint signal to be processed should be at least twice the highest frequency component of the signal to avoid frequency aliasing and ensure that the signal is restored without distortion.

[0079] S202, calculating the first wavelet coefficient of the discrete signal.

[0080] In some embodiments, the noise signals in the voiceprint signal are mostly concentrated in the high-frequency area, and only a few noise signals are distributed on the wavelet coefficients. The corresponding discrete signal obtained after the voiceprint signal f(t) is discretized is represented as f(n), and the selected wavelet function, such as the scaling function Transform the discrete signal to obtain the first wavelet coefficient, which satisfies the following expression:

[0081]

[0082] Among them, W f1 is the first wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0083] It should be noted that wavelet transform is an effective tool for analyzing non-stationary signals. It can provide signal information in both time and frequency domains. It transforms signals through wavelet functions of different scales to reveal the characteristics of signals at different scales.

[0084] S203 . Based on the first wavelet coefficient, perform low-pass filtering on the discrete signal to obtain a target discrete signal.

[0085] In some embodiments, low-pass filtering is a signal processing method that removes high-frequency noise and retains low-frequency useful information. In digital signal processing, low-pass filtering can be implemented by discretization methods, such as using backward difference transformation. The filtered signal will be smoother, which is helpful for identifying and analyzing the state of substation equipment. By using recursive processing based on the calculated first wavelet coefficient, the discrete signal is low-pass filtered to obtain the target discrete signal, which can further reduce the noise interference in the discrete signal and improve the signal-to-noise ratio and purity of the signal. The target discrete signal satisfies the following expression:

[0086] S f (j+1,k)=S f (j,k)×h(j,k);

[0087] Among them, S f represents the target discrete signal, and h is a low-pass filter processor.

[0088] It should be understood that the recursive process can achieve accurate filtering processing by iteratively updating the output value of the filter.

[0089] S204, calculating the second wavelet coefficients of the target discrete signal.

[0090] In some embodiments, as in S202 above, the target discrete signal is transformed to obtain a second wavelet coefficient, and the second wavelet coefficient satisfies the following expression:

[0091]

[0092] Among them, W f2 is the second wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0093] S205. Based on the second wavelet coefficient, perform an inverse wavelet transform on the target discrete signal to obtain a target voiceprint signal.

[0094] Among them, the inverse wavelet transform is used to restore the target discrete signal to the original voiceprint signal format.

[0095] In some embodiments, the inverse wavelet transform is the inverse process of the wavelet transform, which restores the signal from its wavelet domain representation to a time domain signal by combining the wavelet coefficients and the scaling function. Based on the calculated second wavelet coefficients, the target discrete signal is subjected to an inverse wavelet transform to reconstruct the original signal, i.e., obtain the target voiceprint signal.

[0096] The voiceprint signal processing method of the substation equipment provided in the present application can convert the continuous analog signal into a discrete digital signal by discretizing the voiceprint signal of the substation equipment, which not only simplifies the representation of the signal, but also facilitates the subsequent digital processing. Then, the wavelet transform is used to calculate the wavelet coefficients of the discrete signal. The wavelet transform has good localization characteristics in both the time domain and the frequency domain, and can effectively extract the high-frequency and low-frequency parts of the signal. Furthermore, the discrete signal is low-pass filtered based on the wavelet coefficients to remove the high-frequency noise and unnecessary detail information generated by the substation equipment in actual operation, thereby obtaining a purer target discrete signal, making the voiceprint feature clearer and more accurate. Finally, the target discrete signal is inversely transformed by wavelet to restore the target voiceprint signal that is closer to the original voiceprint signal format, thereby ensuring the integrity of the voiceprint signal during the processing process, thereby realizing accurate monitoring and evaluation of the status of the substation equipment, and facilitating early warning and accurate diagnosis of substation equipment failures.

[0097] In some embodiments, Figure 5 As shown, the voiceprint signal processing method for a substation provided in the embodiment of the present application further includes the following S206:

[0098] S206. Input the voiceprint signal to be processed and the target voiceprint signal into the neural network model respectively to obtain a defect detection result.

[0099] Among them, the neural network model is used to perform voiceprint defect detection on the processed voiceprint signal and the target voiceprint signal.

[0100] In some embodiments, the voiceprint signal to be processed and the target voiceprint signal are input into a pre-trained neural network model. The neural network model can learn the features extracted from the voiceprint signal and identify whether there are problems, which can then be used to detect whether there are defects or other abnormal conditions.

[0101] In some embodiments, a neural network-based voiceprint defect detection algorithm is used to perform defect detection analysis on the original voiceprint signal (voiceprint signal to be processed), and the detection results are shown in Table 1; then, the same neural network voiceprint defect detection method is used to perform defect detection on the voiceprint signal (target voiceprint signal) that has completed noise reduction based on wavelet analysis, and the detection results are shown in Table 2.

[0102] Table 1

[0103] Fault type Recognition accuracy Fault type Recognition accuracy DC bias 85.2％ Loose parts 83.3％ Traditional Kasser 87.6％ Partial Discharge 82.1％ Heavy overload 90.8％ Anomaly Detection 85.3％

[0104] Table 2

[0105] Fault type Recognition accuracy Fault type Recognition accuracy DC bias 91.3％ Loose parts 89.2％ Traditional Kasser 92.8％ Partial Discharge 86.9％ Heavy overload 94.6％ Anomaly Detection 88.2％

[0106] As shown in Table 1, when the fault type of the voiceprint signal to be processed is DC bias magnetization, the recognition accuracy is 85.2%; when the fault type of the voiceprint signal to be processed is traditional jamming, the recognition accuracy is 87.6%; when the fault type of the voiceprint signal to be processed is heavy overload, the recognition accuracy is 90.8%; when the fault type of the voiceprint signal to be processed is loose components, the recognition accuracy is 83.3%; when the fault type of the voiceprint signal to be processed is partial discharge, the recognition accuracy is 82.1%; when the fault type of the voiceprint signal to be processed is abnormal detection, the recognition accuracy is 85.3%. As shown in Table 2, when the fault type of the target voiceprint signal is DC bias magnetization, the recognition accuracy is 91.3%; when the fault type of the target voiceprint signal is traditional jamming, the recognition accuracy is 92.8%; when the fault type of the target voiceprint signal is heavy overload, the recognition accuracy is 94.6%; when the fault type of the target voiceprint signal is loose components, the recognition accuracy is 89.2%; when the fault type of the target voiceprint signal is partial discharge, the recognition accuracy is 86.9%; when the fault type of the target voiceprint signal is abnormal detection, the recognition accuracy is 88.2%.

[0107] It should be noted that the voiceprint detection result data in Table 1 and Table 2 above show that the accuracy of voiceprint defect detection has been significantly improved after noise reduction using wavelet analysis, with an average increase of 5%. According to the above experimental results, it can be shown that the voiceprint noise reduction algorithm based on wavelet analysis can effectively improve the accuracy of voiceprint defect detection and improve detection efficiency, providing strong technical support for intelligent monitoring and fault diagnosis of substation equipment.

[0108] The voiceprint signal processing method for substation equipment provided in this application satisfies the Nyquist sampling theorem, can avoid aliasing, and ensure the integrity and accuracy of the signal. In addition, by using a neural network model to detect defects in the voiceprint signal before and after processing, it is possible to identify and locate anomalies and defects in the signal, improve the accuracy of voiceprint defect detection, and improve detection efficiency, providing strong technical support for intelligent monitoring and fault diagnosis of substation equipment.

[0109] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0110] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a voiceprint signal processing device for a substation.

[0112] refer to Figure 6 , the voiceprint signal processing device of the substation equipment includes: a processing module 601 and a calculation module 602;

[0113] The processing module 601 is used to discretize the voiceprint signal to be processed of the substation equipment to obtain a discrete signal;

[0114] The calculation module 602 is used to calculate the first wavelet coefficient of the discrete signal;

[0115] The processing module 601 is further configured to perform low-pass filtering on the discrete signal based on the first wavelet coefficient to obtain a target discrete signal;

[0116] The calculation module 602 is also used to calculate the second wavelet coefficient of the target discrete signal;

[0117] The processing module 601 is further used to perform an inverse wavelet transform on the target discrete signal based on the second wavelet coefficient to obtain a target voiceprint signal; the inverse wavelet transform is used to restore the target discrete signal to the original voiceprint signal format.

[0118] In some embodiments, the first wavelet coefficients satisfy the following expression:

[0119]

[0120] Among them, W f1 is the first wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0121] In some embodiments, the target discrete signal satisfies the following expression:

[0122] S f (j+1,k)=S f (j,k)×h(j,k);

[0123] Among them, S f represents the target discrete signal, and h is a low-pass filter processor.

[0124] In some embodiments, the second wavelet coefficients satisfy the following expression:

[0125]

[0126] Among them, W f2 is the second wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

[0127] In some embodiments, the processing module 601 is also used to input the voiceprint signal to be processed and the target voiceprint signal into a neural network model respectively to obtain a defect detection result; the neural network model is used to perform voiceprint defect detection on the voiceprint signal to be processed and the target voiceprint signal.

[0128] In some embodiments, the voiceprint signal processing device of the power conversion equipment further includes a collection module 603;

[0129] The acquisition module 603 is used to acquire the voiceprint signal to be processed.

[0130] In some embodiments, the voiceprint signal to be processed satisfies the Nyquist sampling theorem.

[0131] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0132] The device of the above embodiment is used to implement the voiceprint signal processing method of the corresponding substation equipment in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0133] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the voiceprint signal processing method of the substation equipment described in any of the above embodiments is implemented.

[0134] Figure 7 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1060. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1060 in the device.

[0135] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0136] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0137] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0138] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0139] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0140] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0141] The electronic device of the above embodiment is used to implement the voiceprint signal processing method of the corresponding substation equipment in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0142] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the voiceprint signal processing method of the substation equipment as described in any of the above embodiments.

[0143] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0144] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the voiceprint signal processing method of the substation equipment as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0145] Based on the same inventive concept, corresponding to the voiceprint signal processing method of the substation equipment described in any of the above embodiments, the present disclosure also provides a computer program product, which includes a computer program. In some embodiments, the computer program is executable by one or more processors so that the processor executes the voiceprint signal processing method of the substation equipment. Corresponding to the execution subject corresponding to each step in each embodiment of the voiceprint signal processing method of the substation equipment, the processor that executes the corresponding step may belong to the corresponding execution subject.

[0146] The computer program product of the above embodiment is used to enable the processor to execute the voiceprint signal processing method of the substation equipment as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0147] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0148] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0149] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0150] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for processing voiceprint signals of a substation, characterized in that: The method comprises: Discretize the to-be-processed voiceprint signal of the power substation to obtain a discrete signal; Calculating a first wavelet coefficient of the discrete signal; Based on the first wavelet coefficient, low-pass filtering is performed on the discrete signal to obtain a target discrete signal; Calculating a second wavelet coefficient of the target discrete signal; Based on the second wavelet coefficient, the target discrete signal is subjected to an inverse wavelet transform to obtain a target voiceprint signal; the inverse wavelet transform is used to restore the target discrete signal to an original voiceprint signal format.

2. The method according to claim 1, characterized in that The first wavelet coefficients satisfy the following expression: Among them, W f1 is the first wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

3. The method according to claim 2, characterized in that The target discrete signal satisfies the following expression: S f (j+1,k)=S f (j,k)×h(j,k); Among them, S f represents the target discrete signal, and h is a low-pass filter processor.

4. The method according to claim 1, characterized in that: The second wavelet coefficients satisfy the following expression: Among them, W f2 is the second wavelet coefficient, j is the signal discrete processing scale, N is the number of discrete signals, f(n) is the discrete signal, n is a natural number, is the scaling function, and k is the signal approximation coefficient.

5. The method according to claim 1, characterized in that The method further comprises: The voiceprint signal to be processed and the target voiceprint signal are respectively input into a neural network model to obtain a defect detection result; the neural network model is used to perform voiceprint defect detection on the voiceprint signal to be processed and the target voiceprint signal.

6. The method according to claim 1, characterized in that Before the voiceprint signal to be processed is discretized to obtain a discrete signal, the method further includes: The voiceprint signal to be processed is collected.

7. The method according to any one of claims 1 to 6, characterized in that: The voiceprint signal to be processed satisfies the Nyquist sampling theorem.

8. A voiceprint signal processing device for a substation, characterized in that: The device comprises: a processing module and a computing module; The processing module is used to discretize the voiceprint signal to be processed of the substation equipment to obtain a discrete signal; The calculation module is used to calculate the first wavelet coefficient of the discrete signal; The processing module is further used to perform low-pass filtering on the discrete signal based on the first wavelet coefficient to obtain a target discrete signal; The calculation module is also used to calculate the second wavelet coefficient of the target discrete signal; The processing module is also used to perform an inverse wavelet transform on the target discrete signal based on the second wavelet coefficient to obtain a target voiceprint signal; the inverse wavelet transform is used to restore the target discrete signal to the original voiceprint signal format.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program. 10 . A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to claim 1 .

Images