Substation emission noise separation method, device, equipment and storage medium

Abstract

The application discloses a substation emission noise separation method, device, equipment and storage medium, the method comprises the following steps: measuring total noise signals around the substation; first filtering processing is performed on the total noise signals in the time domain, non-stationary noise is removed, and a first noise separation signal is obtained; the first noise separation signal is converted to the frequency domain through Fourier transform, second filtering processing is performed on the first noise separation signal in the frequency domain, stationary noise is removed, and a second noise separation signal is obtained; the second noise separation signal is converted to the time domain through inverse Fourier transform, and a substation emission noise signal is obtained. The application introduces time-frequency domain joint filtering into the noise monitoring process of the substation, effectively improves the accuracy of noise monitoring, and reduces the interference of environmental background noise on the noise monitoring result. The technical problems that the prior information required by the current substation emission noise separation method is much, the calculation amount is large, and the separation effect is not ideal are solved.

Description

Technical Field

[0001] This invention relates to the field of substation noise treatment technology, and in particular to a method, apparatus, equipment and storage medium for separating substation emission noise. Background Technology

[0002] Obtaining the pure noise level of a substation is crucial for noise monitoring and control in urban substations. Effective monitoring of substation noise pollution requires accurate measurements of noise levels within the substation and surrounding designated areas. However, in urban environments, significant background noise from traffic and other environmental sources interferes with measurements, affecting not only the substation noise but also the accuracy of the measurements and increasing the difficulty of noise control.

[0003] Existing technologies typically employ acoustic signal separation techniques to obtain clean substation noise. These include traditional methods such as blind source separation, empirical mode decomposition, and wavelet decomposition, as well as more recently developed deep learning-based methods. While traditional methods can achieve good separation results in specific scenarios, their performance deteriorates when there is limited prior information about the noise and the frequency components of the mixed noise signals are similar. Deep learning-based methods require a large amount of training data and consume significant computational resources.

[0004] From the perspective of practical engineering applications, existing noise separation technologies each have some problems. First, for traditional acoustic signal separation methods, algorithms such as wavelet analysis and Kalman filtering require a lot of prior information, which is difficult to meet the conditions for use in actual noise measurement environments. When applying blind source separation algorithms such as independent component analysis, it is difficult to determine the number of noise sources, thus also having the problem of applicability. For signal separation methods based on deep learning, a large amount of training data needs to be collected in advance, and the computational load in practical applications is also large. In the scenario of substation noise monitoring, portable devices are often used to receive and process relevant signals. Due to the limitations of hardware computing power, it is usually impossible to embed complex signal processing algorithms, and thus it is impossible to achieve ideal signal separation results. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, equipment, and storage medium for separating noise emitted from substations, aiming to solve the technical problems of current substation noise separation methods requiring a large amount of prior information, involving a large amount of computation, and having unsatisfactory separation effects.

[0006] To achieve the above objectives, the present invention provides a method for separating noise emitted from a substation, the method comprising the following steps:

[0007] S1: Noise measurement is performed at preset locations around the substation to obtain the total noise signal;

[0008] S2: Perform a first filtering process on the total noise signal in the time domain to remove non-stationary noise and obtain the first noise separation signal;

[0009] S3: The first noise separation signal is converted to the frequency domain by Fourier transform, and the first noise separation signal is subjected to the second filtering process in the frequency domain to remove stationary noise and obtain the second noise separation signal;

[0010] S4: The second noise separation signal is converted to the time domain by inverse Fourier transform to obtain the substation emission noise signal.

[0011] Optionally, the expression for the total noise signal is specifically as follows:

[0012] y(t) = y1(t) + n1(t)

[0013] Where y(t) is the total noise signal, y1(t) is the first noise separation signal, and n1(t) is the non-stationary noise.

[0014] Optionally, in step S2, the first filtering process specifically includes: taking the envelope of the amplitude of the total noise signal and calculating the mean, and removing data points other than the mean.

[0015] Optionally, the expression for the first noise separation signal is as follows:

[0016] y1(t) = s(t) + n2(t)

[0017] Where y1(t) is the first noise separation signal, s(t) is the substation emission noise signal, and n2(t) is the stationary noise.

[0018] Optionally, in step S3, the second filtering process specifically includes: constructing a frequency Wiener filter to filter the first noise separation signal and remove noise signals in the non-target signal frequency band.

[0019] Furthermore, to achieve the above objectives, the present invention also provides a substation emission noise separation device, the device comprising:

[0020] The noise measurement module is used to measure noise at preset locations around the substation to obtain the total noise signal.

[0021] The first filtering module is used to perform a first filtering process on the total noise signal in the time domain to remove non-stationary noise and obtain a first noise separation signal.

[0022] The second filtering module is used to convert the first noise separation signal to the frequency domain through Fourier transform, and to perform a second filtering process on the first noise separation signal in the frequency domain to remove stationary noise and obtain the second noise separation signal.

[0023] The noise separation module is used to convert the second noise separation signal to the time domain through inverse Fourier transform to obtain the substation emission noise signal.

[0024] In addition, to achieve the above objectives, the present invention also provides a substation emission noise separation device, the device comprising: a memory, a processor, and a substation emission noise separation program stored in the memory and executable on the processor, wherein the substation emission noise separation program, when executed by the processor, implements the steps of the above-described substation emission noise separation method.

[0025] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a substation emission noise separation program, which, when executed by a processor, implements the steps of the substation emission noise separation method described above.

[0026] This invention proposes a method, apparatus, equipment, and storage medium for separating substation emission noise. The method includes measuring noise at predetermined locations around the substation to obtain a total noise signal; performing a first filtering process on the total noise signal in the time domain to remove non-stationary noise, obtaining a first noise separation signal; converting the first noise separation signal to the frequency domain using a Fourier transform; performing a second filtering process on the first noise separation signal in the frequency domain to remove stationary noise, obtaining a second noise separation signal; and converting the second noise separation signal back to the time domain using an inverse Fourier transform to obtain the substation emission noise signal. This invention effectively improves the accuracy of noise monitoring and reduces the interference of environmental background noise on the noise monitoring results by introducing joint time-frequency domain filtering into the substation noise monitoring process. It solves the technical problems of current substation emission noise separation methods requiring a large amount of prior information, involving large computational loads, and achieving unsatisfactory separation results. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the structure of a substation emission noise separation device according to an embodiment of the present invention.

[0028] Figure 2 This is a schematic flowchart of an embodiment of the substation emission noise separation method of the present invention.

[0029] Figure 3This is a schematic diagram of peak shaving in the substation emission noise separation method of the present invention.

[0030] Figure 4 This is a comparison chart of peak reduction results in the substation emission noise separation method of the present invention.

[0031] Figure 5 This is a spectrum diagram of the observed signal in the substation emission noise separation method of the present invention.

[0032] Figure 6 This is the Wiener filtering result in the substation emission noise separation method of the present invention.

[0033] Figure 7 This is a spectrum diagram of the filtered signal in the substation emission noise separation method of the present invention.

[0034] Figure 8 This is a structural block diagram of a substation emission noise separation device according to an embodiment of the present invention.

[0035] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0036] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0037] Currently, in the relevant technical fields, substation emission noise separation methods require a lot of prior information, involve a large amount of computation, and have unsatisfactory separation effects.

[0038] To address this problem, various embodiments of the substation emission noise separation method of the present invention are proposed. The substation emission noise separation method provided by the present invention divides noise separation into two steps based on the types of background noise frequently present in actual scenarios. First, for occasional, non-stationary noise, such as dog barking and bird calls, time-domain filtering methods are used to remove it. Then, for stationary noise, such as traffic noise, frequency-domain filtering methods are used to remove it. Thus, a combined time-frequency domain method is used to remove background noise and extract a relatively clean substation emission noise measurement signal.

[0039] Reference Figure 1 , Figure 1 This is a schematic diagram of the substation emission noise separation device involved in the embodiment of the present invention.

[0040] The device can be a user equipment (UE) such as a mobile phone, smartphone, laptop, digital broadcast receiver, personal digital assistant (PDA), tablet computer (PAD), handheld device, in-vehicle device, wearable device, computing device or other processing device connected to a wireless modem, mobile station (MS), etc. The device may be referred to as a user terminal, portable terminal, desktop terminal, etc.

[0041] Typically, the device includes: at least one processor 301, a memory 302, and a substation emission noise separation program stored in the memory and executable on the processor, the substation emission noise separation program being configured to implement the steps of the substation emission noise separation method as described above.

[0042] Processor 301 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 301 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 301 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 301 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. Processor 301 may also include an AI (Artificial Intelligence) processor, which processes information related to substation emission noise separation operations, enabling the substation emission noise separation model to train and learn autonomously, improving efficiency and accuracy.

[0043] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 302 are used to store at least one instruction, which is executed by the processor 301 to implement the substation emission noise separation method provided in the method embodiments of this application.

[0044] In some embodiments, the terminal may also optionally include a communication interface 303 and at least one peripheral device. The processor 301, memory 302, and communication interface 303 can be connected via a bus or signal line. Each peripheral device can be connected to the communication interface 303 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0045] The communication interface 303 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 301 and the memory 302. The communication interface 303 is used to receive movement trajectories and other data uploaded by the user from multiple mobile terminals via the peripheral device. In some embodiments, the processor 301, memory 302, and communication interface 303 are integrated on the same chip or circuit board; in other embodiments, any one or two of the processor 301, memory 302, and communication interface 303 can be implemented on separate chips or circuit boards, and this embodiment is not limited to this.

[0046] The radio frequency (RF) circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 304 communicates with communication networks and other communication devices via electromagnetic signals, thereby acquiring the movement trajectories and other data of multiple mobile terminals. The RF circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 304 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 304 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0047] Display screen 305 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 305 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 301 for processing. In this case, display screen 305 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, display screen 305 can be a single screen, the front panel of an electronic device; in other embodiments, display screen 305 can be at least two screens, respectively disposed on different surfaces of the electronic device or in a folded design; in still other embodiments, display screen 305 can be a flexible display screen, disposed on a curved or folded surface of the electronic device. Furthermore, display screen 305 can also be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. Display screen 305 can be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0048] Power supply 306 is used to supply power to various components in an electronic device. Power supply 306 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 306 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0049] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on substation emission noise separation equipment, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] This invention provides a method for separating noise emitted from a substation, referring to... Figure 2 , Figure 2 This is a schematic flowchart of an embodiment of the substation emission noise separation method of the present invention.

[0051] In this embodiment, the substation emission noise separation method includes the following steps:

[0052] Step 1: Collect noise signals at sensitive points around the substation. Since there is usually some background noise around the substation, the measured signal is not the pure emission signal from the substation, which complicates subsequent noise analysis and control. Assuming the measured signal is s(t), it can be expressed as:

[0053] y(t) = s(t) + n1(t) + n2(t)

[0054] In the formula, s(t) represents the emission noise of the substation itself, n1(t) represents the non-stationary environmental noise around the substation, such as dog barking and bird calls, and n2(t) represents the stationary environmental noise around the substation, such as traffic noise. The purpose of noise signal separation is to remove n1(t) and n2(t) from y(t) to extract s(t).

[0055] Step 2: First, perform time-domain filtering on the non-stationary noise signal. For the measured signal s(t), take the envelope of its amplitude, calculate its mean, and remove data points outside the mean to perform peak clipping in the time domain, reducing the interference of occasional non-stationary signals on the observed data values. After this step, the influence of n1(t) is removed, resulting in the following equation:

[0056] y1(t) = s(t) + n2(t)

[0057] In the formula, y1(t) represents the mixed signal after time-domain filtering.

[0058] Step 3: Perform a Fourier transform on y1(t) to convert the signal to the frequency domain, and then perform frequency domain filtering. This step is represented as:

[0059] Y(ω)=F[y1(t)]

[0060] Step 4: Construct a frequency-domain Wiener filter for the frequency domain signal to filter the observed signal, removing noise signals in the non-target signal frequency band and retaining only the signal with the same frequency as the substation's own noise. After this step, the influence of n2(t) is effectively removed, resulting in the following equation:

[0061] y2(t)=s(t)

[0062] In the formula, y2(t) represents the mixed signal after time-domain filtering.

[0063] Step 5: Perform an inverse Fourier transform on the obtained frequency domain signal. The resulting signal is the substation noise signal after removing environmental noise.

[0064] In a specific example, let the observed signal be...

[0065] y(t)=s(t)+n1(t)+n2(t)(0.1)

[0066] In the formula, s(t) represents the target signal, n1(t) represents non-stationary environmental noise around the substation, such as dog barking or bird calls, and n2(t) represents stationary environmental noise around the substation, such as traffic noise. In the directly observed signal, there will be occasional non-stationary environmental noise, such as human speech, which will exhibit a significant peak in the time domain. To remove this peak, the envelope of the observed signal is first calculated, and the mean of the envelope is used to clip the peak, retaining only the observations within the mean, thus achieving time-domain filtering. A schematic diagram is attached. Figure 3 The peak-shaving results are compared with the original observed signals in the appendix. Figure 4 .

[0067] A spectral analysis was performed on the above results, and the results are attached. Figure 5 As shown, although occasional peak noise signals have been removed from the observed signal, significant noise interference still exists over a large frequency range, except for the 100Hz frequency range and its harmonics of the target signal. Clearly, this noise interference cannot be removed using time-domain methods.

[0068] Let s(t) represent the waveform of the signal to be estimated. The purpose of this invention is to obtain a signal with environmental background noise removed by observing the signal y(t) and using Wiener filtering. This process can be represented as:

[0069]

[0070] In the formula, y(k) is the sampled value at time k, and h(t,k) is the weighting coefficient. The above formula shows that if the random signal y(t) is input into the h(t,k) filter with a time-varying impulse response, its output is an estimate of s(t).

[0071] Using the relevant functions, we can obtain

[0072]

[0073] Transforming it to the frequency domain yields

[0074] P xg (ω)=H(ω)P x (ω)(0.4)

[0075] Therefore, its transfer function is Where P xg (ω) is the Fourier transform of the cross-correlation function between the observed signal y(t) and the waveform s(t) to be estimated, P x (ω) is the Fourier transform of the autocorrelation function of the observed signal y(t).

[0076] After obtaining the transfer function H(ω), multiply it by the Fourier transform of the observed signal, and then perform an inverse Fourier transform on the result to obtain the time-domain waveform of the estimated signal after removing background noise interference. The filtered signal result is shown in the appendix. Figure 6 As shown, its spectrum is attached. Figure 7 As can be seen, after filtering by this invention, not only are occasional non-stationary noise signals removed, but also noise signals in non-target frequency bands are removed in the frequency domain, retaining only the substation body noise at 100Hz and its harmonics.

[0077] This embodiment proposes a method for separating substation emission noise. Based on the types of background noise commonly found in real-world scenarios, noise separation is divided into two steps. First, intermittent, non-stationary noises, such as dog barks and bird calls, are removed using time-domain filtering. Then, stationary noises, such as traffic noise, are removed using frequency-domain filtering. This combined time- and frequency-domain approach effectively removes background noise and extracts a relatively clean substation emission noise measurement signal. Through the filtering process described in this application, interference from urban background noise on substation noise monitoring can be effectively removed, resulting in valid substation noise data, which is of significant importance for subsequent substation noise pollution control.

[0078] Reference Figure 8 , Figure 8 This is a structural block diagram of an embodiment of the substation emission noise separation device of the present invention.

[0079] like Figure 8 As shown, the substation emission noise separation device proposed in this embodiment of the invention includes:

[0080] The noise measurement module 10 is used to measure noise at preset locations around the substation to obtain the total noise signal.

[0081] The first filtering module 20 is used to perform a first filtering process on the total noise signal in the time domain to remove non-stationary noise and obtain a first noise separation signal.

[0082] The second filtering module 30 is used to convert the first noise separation signal to the frequency domain through Fourier transform, and to perform a second filtering process on the first noise separation signal in the frequency domain to remove stationary noise and obtain the second noise separation signal.

[0083] The noise separation module 40 is used to convert the second noise separation signal to the time domain through inverse Fourier transform to obtain the substation emission noise signal.

[0084] Other embodiments or specific implementations of the substation emission noise separation device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0085] Furthermore, embodiments of the present invention also propose a storage medium storing a substation emission noise separation program. When executed by a processor, the substation emission noise separation program implements the steps of the substation emission noise separation method described above. Therefore, it will not be repeated here. Additionally, the beneficial effects of using the same method will not be repeated here either. For technical details not disclosed in the computer-readable storage medium embodiments related to this application, please refer to the description of the method embodiments of this application. As an example, program instructions may be deployed to execute on a single computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0086] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0087] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0088] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware, and of course, it can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memory, special components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for the present invention, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, portable hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

Claims

1. A method for separating noise emitted from a substation, characterized in that, The method includes the following steps: S1: Noise measurement is performed at preset locations around the substation to obtain the total noise signal; S2: Perform a first filtering process on the total noise signal in the time domain to remove non-stationary noise and obtain a first noise separation signal. The first filtering process specifically includes: calculating the envelope of the total noise signal and performing peak clipping on the total noise signal using the envelope mean, retaining the observation values ​​within the envelope mean. S3: The first noise separation signal is converted to the frequency domain by Fourier transform, and the first noise separation signal is subjected to a second filtering process in the frequency domain to remove stationary noise and obtain the second noise separation signal. The second filtering process specifically includes: constructing a frequency Wiener filter to filter the first noise separation signal and remove noise signals in non-target signal frequency bands. The expression for the total noise signal is as follows: y(t) = s(t) + n2(t) + n1(t) Where y(t) is the total noise signal, s(t) is the substation emission noise signal, n2(t) is the stationary noise, n1(t) is the non-stationary noise, and s(t)+n2(t) is the first noise separation signal; The expression for the noise signal in the target signal frequency band is as follows: Where y(k) is the sampled value at time k, and h(t,k) is the weighting coefficient; S4: The second noise separation signal is converted to the time domain by inverse Fourier transform to obtain the substation emission noise signal.

2. A substation emission noise separation device, characterized in that, The device includes: The noise measurement module is used to measure noise at preset locations around the substation to obtain the total noise signal. The first filtering module is used to perform a first filtering process on the total noise signal in the time domain to remove non-stationary noise and obtain a first noise separation signal. The first filtering process specifically includes: calculating the envelope of the total noise signal and performing peak clipping on the total noise signal with the mean of the envelope, and retaining the observation values ​​within the mean of the envelope. The second filtering module is used to convert the first noise separation signal to the frequency domain through Fourier transform, and to perform a second filtering process on the first noise separation signal in the frequency domain to remove stationary noise and obtain the second noise separation signal. The second filtering process specifically includes: constructing a frequency Wiener filter to filter the first noise separation signal and remove noise signals in non-target signal frequency bands. The expression for the total noise signal is as follows: y(t) = s(t) + n2(t) + n1(t) Where y(t) is the total noise signal, s(t) is the substation emission noise signal, n2(t) is the stationary noise, n1(t) is the non-stationary noise, and s(t)+n2(t) is the first noise separation signal; The expression for the noise signal in the target signal frequency band is as follows: Where y(k) is the sampled value at time k, and h(t,k) is the weighting coefficient; The noise separation module is used to convert the second noise separation signal to the time domain through inverse Fourier transform to obtain the substation emission noise signal.

3. A substation noise separation device, characterized in that, The substation emission noise separation device includes: a memory, a processor, and a substation emission noise separation program stored in the memory and executable on the processor. When the substation emission noise separation program is executed by the processor, it implements the steps of the substation emission noise separation method as described in claim 1.

4. A storage medium, characterized in that, The storage medium stores a substation emission noise separation program, which, when executed by a processor, implements the steps of the substation emission noise separation method as described in claim 1.

Images