Rotating speed evaluation method and device based on sound wave signal

Abstract

The invention relates to a rotating speed evaluation method and device based on a sound wave signal. The method comprises the steps that sound wave parameters of target equipment in an operation state are acquired; performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; synchronously extracting the time-frequency data to obtain the rotating speed frequency of the target equipment; and evaluating the rotating speed of the target equipment according to the rotating speed frequency. Microphones are arranged around an engine to collect sound signals, and short-time Fourier transform and synchronous extraction transform are utilized to carry out time-frequency analysis on the signals, so that accurate evaluation on the rotating speed of the engine is realized; the method has obvious advantages in the aspects of processing non-stationary signals and improving the time-frequency resolution, the measurement precision and reliability are guaranteed, the requirement for high-performance computing resources is reduced, and the measurement cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of engine technology, and in particular to a rotation speed evaluation method and device based on sound wave signals. Background Art

[0002] Engine speed is one of the key indicators to measure the working state of the engine. It is crucial for monitoring and maintaining vehicle performance. The engine's fault sound signal will change accordingly when it is in different working states (such as low speed, high speed, cold start, hot engine, etc.). As the speed increases, the engine's working cycle accelerates, and the acoustic characteristic frequency of the fault point will also increase; quickly and accurately capturing the characteristics of the engine speed helps to accurately evaluate its working state, thereby preventing diagnostic errors.

[0003] However, traditional speed measurement technology often relies on physical contact sensors, which face problems such as complex equipment, difficult maintenance and high costs in actual operation.

[0004] Therefore, there is an urgent need to develop a rotation speed evaluation method and device based on acoustic wave signals to solve one or more of the above-mentioned problems. Summary of the invention

[0005] In view of this, in order to solve the above technical problems or part of the technical problems, an embodiment of the present invention provides a rotation speed evaluation method and device based on sound wave signals.

[0006] In a first aspect, the present application provides a method for evaluating rotation speed based on an acoustic wave signal, the method comprising: Get the acoustic wave parameters of the target device in the running state; Performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; Synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device; The rotation speed of the target device is evaluated according to the rotation speed frequency.

[0007] In a possible implementation manner, obtaining the acoustic wave parameters of the target device in the running state includes: Acquire the acoustic wave signal of the target device in the running state; Selecting a sampling signal from the sound wave signal; Acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

[0008] In a possible implementation manner, selecting a sampling signal from the sound wave signal includes: Acquire a low-frequency signal in the sound wave signal, and acquire a signal feature of the low-frequency signal; Selecting a sampling signal from the low-frequency signal according to the signal characteristics; The sampling signal includes the same signal characteristics as the low-frequency signal.

[0009] In a possible implementation manner, obtaining the low-frequency signal in the sound wave signal includes: Performing time-frequency analysis on the sound wave signal to obtain the frequency of the sound wave signal; Get the preset sampling frequency threshold; The sound wave signal is screened based on the sampling frequency threshold to obtain a low-frequency signal.

[0010] In a possible implementation, performing a short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters includes: Obtain a preset finite broadband basis function; Based on the finite broadband basis function, a short-time Fourier transform formula is established; The sound wave parameters are input into the short-time Fourier transform formula to obtain time-frequency data corresponding to the sound parameters.

[0011] In a possible implementation, the short-time Fourier transform formula includes: ; Among them, the For time-frequency data, is a finite broadband basis function, is the sound wave parameter.

[0012] In a possible implementation, synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device includes: Obtaining the two-dimensional instantaneous frequency of the time-frequency data; The time-frequency data and the two-dimensional instantaneous frequency corresponding to the time-frequency data are input into a synchronous extraction equation group to determine the rotational speed frequency of the target device.

[0013] In a possible implementation, the synchronous extraction equation group includes: ; Among them, the is the speed frequency, For time-frequency data, is the Dirac function, is the two-dimensional instantaneous frequency.

[0014] In a second aspect, the present application provides a rotation speed estimation device based on an acoustic wave signal, the device comprising: An acquisition module is used to obtain the acoustic wave parameters of the target device in the running state; A transformation module, used for performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; An extraction module, used to synchronously extract the time-frequency data to obtain the rotational speed frequency of the target device; The evaluation module is used to evaluate the rotation speed of the target device according to the rotation speed frequency.

[0015] In a possible implementation, the acquisition module includes: The signal acquisition submodule is used to acquire the acoustic wave signal of the target device in the running state; A selection submodule, used for selecting a sampling signal from the sound wave signal; The parameter acquisition submodule is used to acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

[0016] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application collects sound signals by installing microphones around the engine, and uses short-time Fourier transform and synchronous extraction transform to perform time-frequency analysis on these signals. This method can extract characteristic frequency components, thereby achieving accurate evaluation of the engine speed; it shows significant advantages in processing non-stationary signals and improving time-frequency resolution, while ensuring measurement accuracy and reliability, it reduces the demand for high-performance computing resources and reduces measurement costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0020] Figure 1 A schematic flow chart of a rotation speed estimation method based on acoustic wave signals provided in an embodiment of the present application; Figure 2A schematic diagram of a model of Example 1 provided in an embodiment of the present application; Figure 3 A schematic diagram of a sound source of Example 1 provided in an embodiment of the present application; Figure 4 A schematic diagram of the time domain waveform of an example two-wave sound signal provided in an embodiment of the present application; Figure 5 A schematic diagram of the short-time Fourier transform result of an example two-wave sound signal provided in an embodiment of the present application; Figure 6 A schematic diagram of the synchronous extraction and transformation results of two sound wave signals provided in an example embodiment of the present application; Figure 7 An example diagram of instantaneous frequency trajectory of an example two sound wave signal provided in an embodiment of the present application; Figure 8 A schematic diagram of the time domain waveforms of three sound wave signals provided as examples in an embodiment of the present application; Fig. 9 A schematic diagram of short-time Fourier transform results of three sound wave signals provided in an embodiment of the present application; Fig.10 A schematic diagram of synchronous extraction and transformation results of three sound wave signals provided in an embodiment of the present application; Fig.11 An example diagram of instantaneous frequency trajectories of three sound wave signals provided in an embodiment of the present application; Fig.12 A schematic diagram of the structure of a rotation speed estimation device based on sound wave signals provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0023] In order to solve the limitations of the prior art of measuring the rotational speed through direct physical contact sensors, such as complex equipment, difficult maintenance and high cost, the present application provides a rotational speed evaluation method and device based on acoustic wave signals, which can collect acoustic signals by installing microphones around the engine, and use short-time Fourier transform and synchronous extraction transform to perform time-frequency analysis on the signals, extract characteristic frequency components, and realize engine speed evaluation. It also simplifies the complexity of traditional rotational speed measurement, reduces maintenance costs, and improves measurement accuracy and reliability.

[0024] Figure 1 A flow chart of a method for evaluating rotation speed based on acoustic wave signals provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method specifically includes: S101, obtaining the acoustic wave parameters of the target device in the running state; When the engine is running, its internal mechanical parts such as cylinders, pistons and crankshafts will vibrate, and the vibration will spread through the air to form sound waves. If the engine speed is N RPM (Revolutions Per Minute), each cylinder of the engine will undergo N working cycles per minute; the engine's working cycle includes four strokes: intake, compression, power and exhaust. In each working process, the gas in the cylinder will be subject to different degrees of pressure changes, thus generating sound waves.

[0025] Specifically, during the intake stroke, the intake valve opens, air enters the cylinder, and produces airflow sound; during the compression stroke, the intake valve closes, the piston moves upward to compress the air, and produces compression sound; during the power stroke, the spark plug ignites the mixture, and produces an explosion sound; during the exhaust stroke, the exhaust valve opens, the exhaust gas is discharged, and exhaust sound is produced; in a working cycle, each working process will produce different sound waves, and the superposition of the sound waves constitutes the overall sound wave signal of the engine.

[0026] In this embodiment, the sound wave parameters of the target device are extracted when the operating state is obtained; the sound wave parameters include but are not limited to key information such as frequency, amplitude, waveform, etc., so as to fully understand the sound characteristics of the device when it is running; by analyzing these sound wave parameters, the operating speed of the device can be determined, and then it can be judged whether there is an abnormal situation, thereby ensuring the normal operation and maintenance of the equipment.

[0027] S102, performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; The Fast Fourier Transform (FFT) method converts the sound signal in the time domain into a spectrum in the frequency domain, which can clearly observe the components of the signal at different frequencies, and detect the frequency components and energy distribution in the engine sound signal through spectrum analysis; by analyzing the spectrum, the peak position of the main frequency and its harmonic components can be identified, thereby determining the key frequency components related to the engine speed.

[0028] In addition to the fundamental frequency, the engine sound wave signal also contains a variety of harmonic components. Harmonics are integer multiples of the fundamental frequency, forming rich spectral characteristics. The existence of harmonics can be analyzed through Fourier transform.

[0029] In this embodiment, the sound wave parameters are subjected to short-time Fourier transform to obtain the time-frequency data corresponding to the sound parameters. By performing short-time Fourier transform processing on the described sound wave parameters, the time-frequency data corresponding to the sound parameters are obtained; specifically, short-time Fourier transform is a method of converting a signal from the time domain to the time-frequency domain. It divides the signal into short time periods and performs Fourier transform on each time period, thereby obtaining the frequency distribution of the signal in different time periods.

[0030] S103, synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device; Short-time Fourier transform has limited effect when processing non-stationary signals, and it is difficult to accurately capture frequency changes. In the speed estimation of engine acoustic signals, these limitations make it difficult to accurately identify the details of the frequency components in the signal, affecting the accuracy of speed estimation. In order to solve these problems, the synchronous extraction transform is introduced; the synchronous extraction transform improves the time-frequency resolution by redistributing the energy on the time-frequency plane, and can achieve high time resolution and high frequency resolution in one analysis framework.

[0031] In this embodiment, the rotation speed frequency information of the target device is obtained by performing a synchronous extraction operation on the time-frequency data obtained above.

[0032] S104: Evaluate the rotation speed of the target device according to the rotation speed frequency.

[0033] In this embodiment, the operating state and performance of the target device are determined by performing an in-depth analysis on the rotation speed frequency of the target device.

[0034] Specifically, a comprehensive evaluation is conducted by combining the speed and frequency data of the target equipment with the design parameters and working requirements of the target equipment. This ensures that the equipment operates in the best condition and that potential problems and hidden dangers are discovered in a timely manner, so that corresponding maintenance measures can be taken to ensure the stability and reliability of the equipment, provide strong support for the optimization and improvement of the equipment, and further enhance its overall performance and service life.

[0035] The speed evaluation method based on sound wave signals provided in the embodiment of the present application obtains the sound wave parameters generated by the target device while monitoring its operating state; obtains time-frequency data corresponding to the sound parameters by performing short-time Fourier transform on these sound wave parameters, and then synchronously extracts these time-frequency data to obtain the speed frequency of the target device therefrom; finally, based on this speed frequency, accurately evaluates the speed of the target device, and effectively extracts the characteristic frequency components, thereby achieving accurate evaluation of the engine speed, showing significant advantages in processing non-stationary signals and improving time-frequency resolution; it can not only ensure the accuracy and reliability of the measurement, but also reduce the measurement cost while reducing the demand for high-performance computing resources, and can more efficiently monitor and evaluate the engine speed in a wider range of scenarios, thereby improving the overall production efficiency and equipment operation stability.

[0036] In an optional solution of the embodiment of the present invention, the acquiring of the acoustic wave parameters of the target device in the running state includes: Acquire the acoustic wave signal of the target device in the running state; In this embodiment, in the process of acquiring the operating status, the sound wave signal emitted by the target device is captured and analyzed, and the sound wave signal is recorded and further data analysis and processing are performed to ensure the normal operation of the device and timely discover potential faults.

[0037] Taking the engine as an example, the work of each cylinder is cyclical. The number of cylinders k directly affects the frequency superposition of sound waves. In addition to the fundamental frequency (basic frequency), the engine sound wave signal also contains a variety of harmonic components; these harmonics are based on integer multiples of the fundamental frequency, forming rich spectral characteristics; in the working cycle, each stroke will generate different sound waves, and these sound waves are superimposed to form the overall sound wave signal of the engine.

[0038] Selecting a sampling signal from the sound wave signal; In this embodiment, a specific sampling signal is selected from the sound wave signal through the analysis and processing process as high-quality sampling data, ensuring its representativeness and accuracy, and providing a solid foundation for further analysis and processing. Acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

[0039] In this embodiment, the acoustic wave parameters in the sampled information are obtained and used as the acoustic wave parameters of the target device. Specifically, a series of key acoustic wave characteristics, such as frequency, amplitude, waveform, and phase, are extracted by analyzing and processing the collected acoustic wave signals. The acoustic wave parameters are used to describe and define the acoustic wave performance of the target device under specific conditions, thereby providing an important reference for subsequent acoustic analysis and device optimization.

[0040] In an optional solution of the embodiment of the present invention, the selecting a sampling signal from the sound wave signal includes: Acquire a low-frequency signal in the sound wave signal, and acquire a signal feature of the low-frequency signal; Since the amount of collected engine sound signal data is large, and the information about the engine speed is usually concentrated in the low-frequency band, the original data needs to be downsampled. Low-pass filtering is a commonly used signal processing technology, which aims to allow low-frequency signals to pass through while suppressing high-frequency signals. Through low-pass filtering, the low-frequency part can be separated from the complex sound wave signal for further analysis and processing, and the low-frequency information in the sound wave signal can be better extracted and utilized.

[0041] In this embodiment, the low-frequency component in the sound wave signal is effectively extracted by performing low-pass filtering on the original signal.

[0042] Selecting a sampling signal from the low-frequency signal according to the signal characteristics; The sampling signal includes the same signal characteristics as the low-frequency signal.

[0043] The original signal needs to be downsampled to avoid the spectrum aliasing effect after downsampling. Direct downsampling will cause the high-frequency components to fold back to the low-frequency band, resulting in spectrum aliasing, which will affect the accuracy of the signal. In this embodiment, according to the signal characteristics of the low-frequency signal, a sampling signal that can retain the characteristics of the original low-frequency signal is selected from the low-frequency signal.

[0044] Specifically, for the low-pass filtered signal Downsampling is used to reduce the amount of data while retaining the main characteristics of the signal; it is described by the following mathematical expression: ; In the formula Represents the downsampled signal; by selecting the first sample in every M samples, the sampling points of the signal are effectively reduced, and the computational complexity of signal processing is also reduced.

[0045] In an optional solution of the embodiment of the present invention, the step of obtaining the low-frequency signal in the sound wave signal includes: Performing time-frequency analysis on the sound wave signal to obtain the frequency of the sound wave signal; Get the preset sampling frequency threshold; The sound wave signal is screened based on the sampling frequency threshold to obtain a low-frequency signal.

[0046] In this embodiment, by performing time-frequency analysis on the sound wave signal mentioned above, the frequency components contained in the sound wave signal are effectively extracted; then, a pre-set sampling frequency threshold is used as an important basis for filtering the signal, and based on the sampling frequency threshold, the original sound wave signal is carefully filtered and processed to obtain the required low-frequency signal part.

[0047] Specifically, the Nyquist sampling principle is to find the lower limit of the sampling frequency at which the signal spectrum does not have aliasing. This theorem has proved that in order to ensure that the signal spectrum does not have aliasing, the sampling frequency must be greater than or equal to twice the maximum frequency of the signal to be sampled.

[0048] The Nyquist sampling theorem is defined as follows: ; In the formula, fs is the sampling frequency, t is the sampling interval, is the folding frequency, is the maximum frequency of the sampling signal. The low-pass filter is used to filter out high-frequency components and retain low-frequency information. The frequency response function of an ideal low-pass filter is It is expressed as: ; Wherein, fc is the cutoff frequency. In practical applications, the present application adopts a finite impulse response filter (FIR) to implement low-pass filtering. In specific implementation, other filters can also be used to implement signal filtering. The signal y(t) after the original signal x(t) is low-pass filtered is expressed as: ; In the formula represents the response of the system to the shock, and is the output signal, symbol is the integrating variable and represents the time delay.

[0049] The embodiment of the present application provides a rotation speed evaluation method based on an acoustic wave signal. The sampling frequency threshold determined by the Nyquist sampling theorem ensures that the signal will not be aliased during the sampling process. By setting an appropriate cutoff frequency fc, the low-pass filter can effectively filter out signal components higher than the cutoff frequency, thereby retaining the low-frequency signal portion. In practical applications, in order to ensure the accuracy and efficiency of signal processing, a finite impulse response filter (FIR) is used to implement low-pass filtering. The FIR filter has a linear phase characteristic, which can ensure that the phase distortion of the signal during the filtering process is minimized, which is conducive to maintaining the time domain characteristics of the acoustic wave signal.

[0050] After acquiring the low-frequency signal, downsampling is performed. Specifically, downsampling is a process of reducing the amount of data by reducing the number of sampling points, but at the same time, it is necessary to ensure that the downsampled signal can still retain the main features of the original signal. In this embodiment, by selecting the first sample in every M samples as the downsampled signal, the sampling points of the signal are effectively reduced, and the computational complexity of signal processing is also reduced. This downsampling method improves the efficiency of signal processing while ensuring signal quality, and can effectively extract sound wave parameters related to the speed from the engine sound wave signal, providing reliable technical support for engine performance evaluation and fault diagnosis.

[0051] In an optional solution of the embodiment of the present invention, performing a short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters includes: Obtain a preset finite broadband basis function; Based on the finite broadband basis function, a short-time Fourier transform formula is established; The sound wave parameters are input into the short-time Fourier transform formula to obtain time-frequency data corresponding to the sound parameters.

[0052] In a possible implementation, the short-time Fourier transform formula includes: ; Among them, the For time-frequency data, is a finite broadband basis function, is the sound wave parameter.

[0053] The Fast Fourier Transform (FFT) method converts the sound signal in the time domain into a spectrum in the frequency domain. The spectrum can be used to clearly observe the components of the signal at different frequencies, and the frequency components and energy distribution in the engine sound signal can be detected through spectrum analysis. By analyzing the spectrum, the peak positions of the main frequency and its harmonic components can be identified, thereby determining the key frequency components related to the engine speed.

[0054] In this embodiment, firstly, a preset finite broadband basis function is obtained. The basis function is a key element for subsequent processing, which can help us better analyze and process the signal, ensure that the required frequency range can be covered and meet the specific bandwidth requirements. Then, based on the finite broadband basis function, a short-time Fourier transform (STFT) formula is established to analyze signals with time-varying characteristics. The frequency distribution of the signal at different time points is obtained by dividing the signal into short time segments and performing Fourier transform on each segment. Finally, the sound wave parameters are input into the short-time Fourier transform formula, and the frequency distribution of the sound wave signal in different time periods is calculated to obtain time-frequency data. The changes of the sound signal in time and frequency are obtained through the time-frequency data, which provides an important basis for further analysis and processing of the sound signal.

[0055] Exemplarily, short-time Fourier transform provides an effective method to observe the changes of the signal in both time domain and frequency domain simultaneously by performing Fourier transform on the signal within a time window, especially the changes occurring in a short time period, because it divides the signal into small time periods and applies Fourier transform to each time period, which is more applicable to the analysis of the acoustic signal of the engine.

[0056] In this embodiment, the short-time Fourier transform is defined as follows: ; in, The microphone receives the signal. It is a finite bandwidth basis function that can move in the time-frequency direction. Short-time Fourier transform expands the one-dimensional time series signal to the two-dimensional time-frequency domain, realizing the observation of instantaneous amplitude and instantaneous frequency information and the extraction of signal.

[0057] In a possible implementation, synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device includes: Obtaining the two-dimensional instantaneous frequency of the time-frequency data; The time-frequency data and the two-dimensional instantaneous frequency corresponding to the time-frequency data are input into a synchronous extraction equation group to determine the rotational speed frequency of the target device.

[0058] In a possible implementation, the synchronous extraction equation group includes: ; Among them, the is the speed frequency, For time-frequency data, is the Dirac function, is the two-dimensional instantaneous frequency.

[0059] The short-time Fourier transform uses a fixed-length window function, which means that there is a trade-off between time resolution and frequency resolution. A short window provides high time resolution but low frequency resolution, while a long window provides high frequency resolution but low time resolution. When processing non-stationary signals, the short-time Fourier transform has some limitations, and frequency changes are difficult to capture accurately. This can lead to energy-blurred time-frequency diagrams. ; In the speed estimation of engine acoustic signals, these limitations make it difficult to accurately identify the details of the frequency components in the signal, affecting the accuracy of speed estimation. To solve these problems, the synchronous extraction transform is introduced; the synchronous extraction equation group is a mathematical model used to simultaneously process and analyze time-frequency data and two-dimensional instantaneous frequency.

[0060] In this embodiment, first, by performing detailed analysis and processing on the time-frequency data, the specific information of the two-dimensional instantaneous frequency is extracted from it, and the frequency variation characteristics of the signal are obtained. The two-dimensional instantaneous frequency refers to the instantaneous frequency value at a specific time and frequency point in the two-dimensional time-frequency distribution; then, the time-frequency data and the corresponding two-dimensional instantaneous frequency are input into the synchronous extraction equation group. By inputting these data into the equation group, the algorithm is used to determine the rotational speed frequency of the target device to understand the operating status and performance of the device.

[0061] Exemplarily, the synchronous extraction transform improves the time-frequency resolution by redistributing the energy on the time-frequency plane, and can achieve both high time resolution and high frequency resolution within one analysis framework.

[0062] The synchronous extraction transformation is defined as follows: ; in () represents the Dirac function. Two-dimensional instantaneous frequency estimation Available ; In the above formula, Re() represents the real part, ∂t represents the derivative of the function with respect to time. Synchronous extraction of changes shows higher accuracy when processing non-stationary signals and can more accurately track the instantaneous frequency changes of signals. In the speed estimation of engine acoustic signals, synchronous extraction of changes can more clearly separate the frequency components related to the engine speed and provide more accurate time-frequency analysis results, thereby significantly improving the accuracy and reliability of speed estimation.

[0063] The speed evaluation method based on sound wave signals provided in the embodiment of the present application collects sound signals by installing microphones around the engine, adopts low-pass filtering and downsampling technology, effectively reduces the amount of data, avoids spectrum aliasing, improves signal processing efficiency, and uses short-time Fourier transform and synchronous extraction transform to perform time-frequency analysis on the signal, extract characteristic frequency components, and realize engine speed estimation; it has obvious advantages in processing engine sound signals and improving time-frequency resolution, and can realize accurate estimation of engine speed.

[0064] Figure 2 , Figure 3 They are respectively a model schematic diagram and a sound source schematic diagram of Example 1 provided in an embodiment of the present application; like Figure 2 As shown, in Example 1, the noise generated by the engine mainly comes from two aspects: aerodynamic source and mechanical source. The aerodynamic source involves the noise caused by air disturbance, such as turbulence inside the intake pipe and exhaust pipe; while the noise from the mechanical source comes from the contact and movement between components, including the friction between the shaft and the bracket, the impact between the cylinder and the piston, the vibration of the gear and the chain or belt, and the vibration caused by the flow of the fluid in the pipeline; There are three ways in which noise can be propagated: airborne, structurally transmitted, and mixed. In airborne propagation, sound waves are transmitted directly from the sound source to the receiving point through the air medium. Structural propagation involves sound waves propagating in structural components for a period of time before being transmitted to the receiver. Mixed propagation refers to the propagation of sound waves in both structural and air modes at the same time.

[0065] like Figure 2 As shown in the figure, the noise emitted by the engine is composed of noises from many different sources. Engine noise can be divided into mechanical noise, combustion noise and aerodynamic noise according to the type of excitation source. Most of the mechanical noise and combustion noise are radiated through the surface of the engine structure, so they are also uniformly summarized as engine surface radiation noise; while aerodynamic noise is generated by the internal movement of the airflow or the interaction with objects, mostly from the intake and exhaust system and the engine fan.

[0066] Engine sound signals have unique diagnostic value. They can be collected without direct contact with the engine, and can obtain comprehensive information from multiple directions and positions, intuitively reflecting the working status of the equipment. Engine sound signals with rich acoustic characteristics are collected by installing microphones around the car engine. These microphones convert the vibration of sound waves into electrical signals, which are then transmitted to the data acquisition instrument. The data acquisition instrument is responsible for receiving, converting and storing the sound information, and converting analog signals into digital signals for subsequent analysis.

[0067] In addition, in order to ensure the high quality and accuracy of the data, attention should be paid to its low noise characteristics and stability when selecting the measuring points to ensure that it can effectively reflect the working status of the engine.

[0068] First, the first measuring point is set 1.5 meters in front of the vehicle to capture the overall working characteristics of the engine; the second measuring point is located 50 centimeters in front of the vehicle, close to the engine, and is used to record the slight changes in the engine sound signal in detail; the third measuring point is set 15 centimeters above the engine to capture possible special acoustic information on the top; the fourth and fifth measuring points are located on the left and right sides of the vehicle respectively, at a 45° angle to the engine and 1 meter away, which helps to capture the characteristics of the engine working status from the side and observe the directional changes of the sound signal; the engine speed is estimated through the acoustic signal analysis of these measuring points to achieve comprehensive monitoring and diagnosis of the engine status.

[0069] Figures 4 to 7 A schematic diagram of Example 2 provided in an embodiment of the present application; Specifically, Example 2 can extract important information related to the engine speed through comprehensive analysis of the time domain waveform, STFT results, synchronous extraction transform (SET) results and time-frequency ridges of the engine sound signal.

[0070] like Figure 4 The figure shows the original sound signal of the engine shifting under normal conditions. The sound signal obtained by the speed shifting method is not only closer to the actual usage situation, but also can provide richer information, thus more realistically reflecting the working status of the engine. Figure 4 The time domain waveform of the engine sound signal is shown, with a sampling frequency of 48000Hz and a sampling time of 35 seconds. The waveform shows that the amplitude of the signal fluctuates between -0.6Pa and 0.6Pa. These vibrations reflect the dynamics of internal mechanical components such as cylinders, pistons, and crankshafts during the working cycle. Although the time domain waveform can reveal the overall vibration, it is difficult to directly provide frequency information. Therefore, we low-pass filter and downsample the engine sound signal for frequency domain analysis.

[0071] like Figure 4 As shown in the figure, the original sound signal of the engine speed change under normal operation is presented. The sound signal collected by speed change is not only closer to the actual operating environment, but also can provide more detailed information, thus more accurately revealing the working condition of the engine. Figure 4The time domain waveform of the engine sound signal is described. The sampling frequency is set to 48000Hz and the sampling time lasts for 35 seconds. It can be seen from the waveform that the amplitude of the signal fluctuates between -0.6Pa and 0.6Pa. These fluctuations reflect the dynamic changes of internal mechanical components such as cylinders, pistons and crankshafts during the working cycle. Although the time domain waveform can show the overall vibration characteristics, it cannot directly provide frequency information. Therefore, the engine sound signal is low-pass filtered and down-sampled for more in-depth frequency domain analysis.

[0072] The short-time Fourier transform result of the processed signal is as follows Figure 5 As shown, the horizontal axis represents time, the vertical axis represents frequency, the color depth represents signal strength, and the main frequency components of the signal are concentrated in the range of 0-100Hz, especially in the frequency bands of about 21Hz, 42Hz, and 63Hz, showing obvious frequency characteristics.

[0073] Since the short-time Fourier transform (STFT) uses a fixed-length window function, there is a trade-off between time and frequency resolution, which may result in the inability to accurately capture frequency changes during periods of rapid frequency changes, making the energy distribution unclear. Therefore, the synchronous extraction transform (SET) technique is further adopted, which significantly improves the time-frequency resolution by redistributing the energy on the time-frequency plane, making the frequency components of the signal more concentrated and clear. Figure 6 As shown, the result after allocation not only clearly identifies the main frequency of the engine speed, but also clearly shows the second harmonic, and even higher harmonics can be fuzzily identified, which fully demonstrates the high-precision effect of synchronous extraction transformation when processing non-stationary signals.

[0074] In addition, the instantaneous frequency trajectory in the transformation result is extracted synchronously and plotted on Fig.10 above; such as Figure 7 As shown, the change of the engine rotation frequency is shown. In the first 25 seconds, the engine speed is roughly maintained at 1260 rpm (that is, the rotation frequency is 21 Hz); 25 seconds later, the speed suddenly increases to about 2220 rpm (that is, the rotation frequency is 37 Hz), and then decreases slightly, and finally steadily rises to about 2400 rpm (that is, the rotation frequency is 40 Hz).

[0075] Figures 8 to 11 A schematic diagram of Example 3 provided in an embodiment of the present application; Specifically, Example 3 shows how to estimate the speed using the engine sound signal under different working conditions. Figure 8 The time domain waveform of the engine sound signal is presented. The sampling time is 35 seconds. The amplitude of the signal fluctuates in the range of -0.4Pa to 0.4Pa, reflecting the vibration state of the mechanical parts inside the engine. Fig. 9 As shown, the main frequency components of the signal are concentrated in the low-frequency area (0-200Hz), especially in the frequency bands around 21Hz and 42Hz. These frequency characteristics are closely related to the engine speed.

[0076] like Fig.10 The synchronous extraction transform shown in the figure improves the time-frequency resolution by redistributing the energy on the time-frequency plane, making the frequency components more concentrated and clear, especially near 20Hz and 42Hz, the main frequency of the signal and its harmonic components become more obvious. Compared with the short-time Fourier transform, the synchronous extraction transform can more effectively separate the frequency components related to the engine speed, thereby improving the accuracy and reliability of the speed estimation.

[0077] Fig.11 The figure describes the time-frequency ridges extracted from the synchronous extraction transformation results, as well as the changes in the instantaneous frequency of the signal. During the entire sampling period, the frequency of the engine changes significantly: in the first 4 seconds, the engine speed increases from 1260 RPM (i.e., a rotation frequency of 21 Hz) to 1440 RPM (i.e., a rotation frequency of 24 Hz), and then remains basically stable; then at the 23rd second, the speed rapidly climbs to 3000 RPM (i.e., a rotation frequency of 50 Hz), and although the speed fluctuates slightly afterwards, the overall trend is to slowly rise to 3240 RPM (i.e., a rotation frequency of 54 Hz).

[0078] Fig.12 A schematic diagram of a rotation speed evaluation device based on an acoustic wave signal provided in an embodiment of the present application is shown in FIG. Fig.12 As shown, the device specifically includes: An acquisition module 1201 is used to acquire the acoustic wave parameters of the target device in the running state; A transformation module 1202 is used to perform short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; An extraction module 1203 is used to synchronously extract the time-frequency data to obtain the rotation speed frequency of the target device; The evaluation module 1204 is used to evaluate the rotation speed of the target device according to the rotation speed frequency.

[0079] In a possible implementation, the acquisition module 1201 includes: The signal acquisition submodule 12011 is used to acquire the acoustic wave signal of the target device in the running state; A selection submodule 12012 is used to select a sampling signal from the sound wave signal; The parameter acquisition submodule 12013 is used to acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

[0080] In a possible implementation, the acquisition module 1201 is further used to acquire a sound wave signal of the target device in operation; select a sampling signal from the sound wave signal; and acquire sound wave parameters of the sampling information as sound wave parameters of the target device.

[0081] In a possible implementation, the acquisition module 1201 is also used to acquire a low-frequency signal in the sound wave signal and acquire a signal feature of the low-frequency signal; based on the signal feature, a sampling signal is selected from the low-frequency signal; wherein the sampling signal includes the same signal feature as the low-frequency signal.

[0082] In a possible implementation, the acquisition module 1201 is further used to perform time-frequency analysis on the sound wave signal to obtain the frequency of the sound wave signal; obtain a preset sampling frequency threshold; and filter the sound wave signal based on the sampling frequency threshold to obtain a low-frequency signal.

[0083] In a possible implementation, the transformation module 1202 is also used to obtain a preset finite broadband basis function; based on the finite broadband basis function, establish a short-time Fourier transform formula; input the sound wave parameters into the short-time Fourier transform formula to obtain time-frequency data corresponding to the sound parameters.

[0084] In a possible implementation, the extraction module 1203 is also used to obtain the two-dimensional instantaneous frequency of the time-frequency data; input the time-frequency data and the two-dimensional instantaneous frequency corresponding to the time-frequency data into the synchronous extraction equation group to determine the rotational speed frequency of the target device.

[0085] The rotation speed evaluation device based on the acoustic wave signal provided in this embodiment can be as follows: Fig.12 The rotation speed evaluation device based on the acoustic wave signal shown in can be performed as follows Figures 1 to 11 All steps of the speed evaluation device based on acoustic wave signals are implemented, thereby achieving Figures 1 to 11 The technical effect of the speed evaluation device based on the sound wave signal is shown in FIG. Figures 1 to 11 For the sake of brevity, the relevant description is not repeated here.

[0086] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0088] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0089] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A rotation speed evaluation method based on acoustic wave signals, characterized in that: include: Get the acoustic wave parameters of the target device in the running state; Performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; Synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device; The rotation speed of the target device is evaluated according to the rotation speed frequency.

2. The method according to claim 1, characterized in that The obtaining of the acoustic wave parameters of the target device when in operation state includes: Acquire the acoustic wave signal of the target device in the running state; Selecting a sampling signal from the sound wave signal; Acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

3. The method according to claim 2, characterized in that The selecting a sampling signal from the sound wave signal comprises: Acquire a low-frequency signal in the sound wave signal, and acquire a signal feature of the low-frequency signal; Selecting a sampling signal from the low-frequency signal according to the signal characteristics; The sampling signal includes the same signal characteristics as the low-frequency signal.

4. The method according to claim 3, characterized in that The step of obtaining the low-frequency signal in the sound wave signal comprises: Performing time-frequency analysis on the sound wave signal to obtain the frequency of the sound wave signal; Get the preset sampling frequency threshold; The sound wave signal is screened based on the sampling frequency threshold to obtain a low-frequency signal.

5. The method according to claim 1, characterized in that The performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters includes: Obtain a preset finite broadband basis function; Based on the finite broadband basis function, a short-time Fourier transform formula is established; The sound wave parameters are input into the short-time Fourier transform formula to obtain time-frequency data corresponding to the sound parameters.

6. The method according to claim 5, characterized in that The short-time Fourier transform formula includes: Wherein, G(t,ω) is time-frequency data, and g(ut)e -iω(u-t) is a finite broadband basis function, and x(u) is an acoustic wave parameter.

7. The method according to claim 1, characterized in that The synchronously extracting the time-frequency data to obtain the rotational speed frequency of the target device includes: Obtaining the two-dimensional instantaneous frequency of the time-frequency data; The time-frequency data and the two-dimensional instantaneous frequency corresponding to the time-frequency data are input into a synchronous extraction equation group to determine the rotational speed frequency of the target device.

8. The method according to claim 7, characterized in that The synchronous extraction equation group includes: Wherein, T(t,ω) is the rotational speed frequency, G(t,ω) is the time-frequency data, is the Dirac function, is the two-dimensional instantaneous frequency.

9. A rotation speed evaluation device based on acoustic wave signals, characterized in that: include: An acquisition module is used to obtain the acoustic wave parameters of the target device in the running state; A transformation module, used for performing short-time Fourier transform on the sound wave parameters to obtain time-frequency data corresponding to the sound parameters; An extraction module, used to synchronously extract the time-frequency data to obtain the rotational speed frequency of the target device; The evaluation module is used to evaluate the rotation speed of the target device according to the rotation speed frequency.

10. The device according to claim 9, characterized in that The acquisition module comprises: The signal acquisition submodule is used to acquire the acoustic wave signal of the target device in the running state; A selection submodule, used for selecting a sampling signal from the sound wave signal; The parameter acquisition submodule is used to acquire the sound wave parameters of the sampling information as the sound wave parameters of the target device.

Images