Vehicle abnormal sound identification method, system and device and computer readable storage medium

Abstract

A vehicle abnormal sound identification method, system and device and a computer readable storage medium relate to the technical field of vehicle abnormal sound detection, and comprise the following steps: performing frequency range analysis on each segment of vehicle noise data to obtain a plurality of target noise characteristic curves and non-target noise characteristic curves of 1 / 3 frequency bands, and obtaining a first weighting coefficient and a second weighting coefficient; acquiring a first noise amplitude of the target noise characteristic curve and a second noise amplitude of a non-target noise characteristic curve; determining a second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient and the second weighting coefficient; determining a first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve; and target vehicle abnormal sound identification is carried out based on the position relation between the target noise characteristic curve and the target upper limit curve and the position relation between the non-target noise characteristic curve and the first upper limit curve. The problem that the abnormal sound with low sound power and narrow frequency band cannot be effectively identified in the prior art can be solved.

Description

Technical Field

[0001] This application relates to the field of vehicle abnormal noise detection technology, specifically to a vehicle abnormal noise identification method, system, device, and computer-readable storage medium. Background Technology

[0002] Currently, with the continuous advancement of vehicle technology, the performance of vehicles in detecting abnormal noises has become a key focus for customers. To improve the performance of vehicles in detecting abnormal noises, many automated (non-manual) noise detection methods have been applied to various noise detection scenarios. Since low-power and narrow-band noises such as transmission knocking do not significantly affect the total sound pressure level, traditional methods for detecting total sound pressure level cannot effectively identify these noises. As a result, vehicles with these noises enter the market, leading to a poor user experience.

[0003] Therefore, it is urgent to develop new methods for detecting these abnormal noises, to prevent vehicles with abnormal noises from entering the market, and to improve the user experience. Summary of the Invention

[0004] This application provides a method, system, device, and computer-readable storage medium for identifying abnormal noises in vehicles, which can solve the technical problem in the prior art that it is impossible to effectively identify abnormal noises with low sound power and narrow frequency band.

[0005] In a first aspect, embodiments of this application provide a method for identifying abnormal vehicle noises, the method comprising: Frequency band analysis is performed on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and weighting coefficients corresponding to each 1 / 3 octave band are obtained. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. Obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve; The second distance is determined based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve. The first upper limit curve of the non-target noise characteristic curve is determined based on the second distance and the non-target noise characteristic curve. Abnormal noises of target vehicles are identified based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

[0006] In conjunction with the first aspect, in one embodiment, the first noise amplitude is the noise amplitude at any point on a first straight line obtained by fitting the target noise characteristic curve, and the second noise amplitude is the noise amplitude at a target point on a second straight line obtained by fitting the non-target noise characteristic curve, wherein the x-coordinate of the target point is the same as the x-coordinate of any point on the first straight line.

[0007] In conjunction with the first aspect, in one implementation, determining the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient includes: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows:

[0008] In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

[0009] In conjunction with the first aspect, in one implementation, determining the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve includes: The second straight line is translated upwards by a second distance to obtain the third straight line, and the third straight line is used as... The first upper limit curve of the non-target noise characteristic curve.

[0010] In conjunction with the first aspect, in one implementation, the identification of abnormal noises from a target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, includes: Determine whether the target noise characteristic curve is below the target upper limit curve and whether the non-target noise characteristic curve is below the first upper limit curve; If so, then the target vehicle is determined to have no abnormal noises; If not, then the target vehicle is determined to have abnormal noises.

[0011] In conjunction with the first aspect, in one embodiment, prior to the step of performing frequency band analysis on the vehicle noise data for each segment, the method further includes: Vehicle noise data is collected and short-time Fourier transform is performed on the noise data to obtain multiple segments of vehicle noise data.

[0012] Secondly, embodiments of this application provide a vehicle abnormal noise recognition system, the vehicle abnormal noise recognition system comprising: The first processing module is used to perform frequency band analysis on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and to obtain the weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The second processing module is used to obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve; The third processing module is used to determine the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve. The fourth processing module is used to determine the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve; The fifth processing module is used to identify abnormal noises of the target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

[0013] In conjunction with the second aspect, in one implementation, the third processing module is specifically used for: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows:

[0014] In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

[0015] Thirdly, embodiments of this application provide a vehicle abnormal noise identification device, the vehicle abnormal noise identification device including a processor, a memory, and a vehicle abnormal noise identification program stored in the memory and executable by the processor, wherein when the vehicle abnormal noise identification program is executed by the processor, it implements the steps of the vehicle abnormal noise identification method as described in any of the preceding claims.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a vehicle abnormal noise recognition program, wherein when the vehicle abnormal noise recognition program is executed by a processor, it implements the steps of the vehicle abnormal noise recognition method as described in any of the preceding claims.

[0017] The beneficial effects of the technical solutions provided in this application include: By performing frequency band analysis on vehicle noise data for each segment, multiple target noise characteristic curves and non-target noise characteristic curves corresponding to 1 / 3 octave bands are obtained, and weighting coefficients are acquired for each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The 1 / 3 octave band helps to identify noise problems with narrow frequency bands and low amplitudes. The first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve are acquired. Based on the first distance between the target upper limit curve and the target noise characteristic curve, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient, a second distance is determined. Based on the second distance and the non-target noise characteristic curve, the first upper limit curve of the non-target noise characteristic curve is determined. Based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, abnormal noises of the target vehicle are identified. This application analyzes the noise data of the target vehicle in frequency bands, and analyzes the noise signal in a finer-grained frequency band to obtain the noise characteristics in each frequency band. This avoids the problem of not being able to identify abnormal noises with narrow frequency bands and low sound power in traditional methods, prevents vehicles with abnormal noises from entering the market, and improves the driving experience. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an embodiment of the vehicle abnormal noise identification method of this application; Figure 2 This is a schematic diagram of the noise characteristic curve of an embodiment of the vehicle abnormal noise identification method of this application; Figure 3 This is a schematic diagram of the target upper limit curve and the first straight line in an embodiment of the vehicle abnormal noise identification method of this application; Figure 4 This is a schematic diagram of the first upper limit curve and the second straight line in an embodiment of the vehicle abnormal noise identification method of this application; Figure 5 This is a schematic diagram illustrating the abnormal noise identification method for vehicles according to this application. Figure 6 This is a schematic diagram of the functional modules of an embodiment of the vehicle abnormal noise recognition system of this application; Figure 7 This is a schematic diagram of the hardware structure of the vehicle abnormal noise recognition device involved in the embodiments of this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] In a first aspect, embodiments of this application provide a method for identifying abnormal noises in vehicles.

[0022] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the vehicle abnormal noise identification method of this application. Figure 1 As shown, the vehicle abnormal noise identification method includes: Step S10: Perform frequency band analysis on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and obtain the weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve.

[0023] Exemplary and common frequency band analyses include octave band analysis, 1 / 3 octave band analysis, and 1 / 6 octave band analysis. In this embodiment, 1 / 3 octave band analysis is preferred for noise data analysis. A-weighted 1 / 3 octave band analysis is used to simulate the human ear's sensitivity to sound frequencies and divides the signal spectrum into multiple refined frequency bands to analyze the sound pressure level of certain specific frequency bands. That is, when performing frequency domain analysis on a sound signal, an A-weighted filter is first used to simulate human auditory perception, and then the spectrum is divided into multiple refined frequency bands (i.e., multiple 1 / 3 octave bands) to accurately analyze the sound power or noise amplitude of each frequency band. The bandwidth of each 1 / 3 octave band is (2π / 3) of its center frequency. 1 / 3 -1) / 2 1 / 6 The advantage of using a 1 / 3 octave band is that it allows for more refined spectrum analysis, making it suitable for noise assessment with narrow bandwidth and low sound power, such as noise from vehicle transmission knocking.

[0024] It should be noted that before performing 1 / 3 octave band analysis on the vehicle noise data for each segment, the vehicle noise data needs to be collected and segmented. The noise data collection is for vehicles that may have abnormal noises. Based on the components associated with the abnormal noise, the abnormal noise components of the vehicle can be divided into two categories. The first category is components related to rotating parts (such as the engine, transmission, drive motor, half shaft, drive shaft, tires, etc.), and the second category is components unrelated to rotation (such as abnormal noises from the shock absorbers, main instrument panel, and control arm). For the first category of abnormal noises, it is necessary to collect the rotational speed signal of the relevant rotating parts; for the second category of abnormal noises, it is not necessary to collect the rotational speed signal.

[0025] Specifically, noise signals can be collected by placing microphones inside the vehicle, and whether to collect engine speed signals depends on the type of abnormal noise component. It's important to note that the start and end points of data collection must be under the potential operating conditions where the abnormal noise occurs. For example, in a gasoline-powered vehicle, the engine speed range corresponding to an abnormal noise is 2500-3500 rpm. Therefore, when the engine speed is below 2500 rpm or above 3500 rpm, noise data collection is unnecessary. The collected noise data is segmented, and A-weighted 1 / 3 octave band analysis is performed on each segment to obtain the noise amplitude data for each 1 / 3 octave band, along with the corresponding engine speed and time data. Connecting the segmented data yields the curves showing the change in noise amplitude of each 1 / 3 octave band with engine speed (type 1 abnormal noise) and time (type 2 abnormal noise), known as noise characteristic curves. Figure 2 As shown.

[0026] Specifically, Figure 2 The diagram contains four typical noise characteristic curves for cases without any abnormal noise. (a) and (b) represent the first type of abnormal noise, with the horizontal axis representing rotational speed and the vertical axis representing the noise amplitude in a certain 1 / 3 octave band. (a) shows that the noise amplitude increases with increasing rotational speed, while (b) shows that the noise amplitude decreases with increasing rotational speed. (c) and (d) represent the second type of abnormal noise, with the horizontal axis representing time and the vertical axis representing the noise amplitude in a certain 1 / 3 octave band. (c) shows that the noise amplitude increases with increasing time, while (d) shows that the noise amplitude decreases with increasing time.

[0027] It should be noted that since both speech and hearing are frequency-dependent, and only sounds between 200 and 6300 Hz are considered, the concept of weighting coefficient W(f) from the whole-vehicle speech intelligibility test is introduced. The weighting coefficient is different at different frequencies. In this embodiment, the preferred frequency range is the 1 / 3 octave band data within the range of the frequency band where the human ear is more sensitive to hearing (e.g., 200 Hz-6300 Hz). Specifically, refer to the weighting coefficients corresponding to the 16 1 / 3 octave bands shown in Table 1. Among them, the 1 / 3 octave band with a center frequency of 1600 Hz has the largest weighting coefficient, that is, this 1 / 3 octave band is the most sensitive to the smooth transmission of sound. The target noise characteristic curve refers to the noise characteristic curve corresponding to the 1 / 3 octave band with a center frequency of 1600 Hz. The non-target noise characteristic curve refers to the noise characteristic curve corresponding to other 1 / 3 octave bands other than the center frequency of 1600 Hz, such as the noise characteristic curve of the 1 / 3 octave band with a center frequency of 4000 Hz.

[0028] Table 1 shows the center frequency and weighting coefficients for each 1 / 3 octave band.

[0029] It should be understood that, as shown in Table 1, the 1 / 3 octave band with a center frequency of 1600Hz has the largest weighting factor; the 1 / 3 octave band with a center frequency of 4000Hz has a weighting factor of 7.75%.

[0030] Specifically, by performing 1 / 3 octave band analysis on the vehicle noise data of each segment, the distribution of noise in each frequency band can be obtained in detail, and the noise characteristic curves of each 1 / 3 octave band can be obtained, which can then be used for subsequent identification and analysis of abnormal noises in the target vehicle based on these data.

[0031] Step S20: Obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve.

[0032] As an example, in this embodiment of the application, the target noise characteristic curve is processed to obtain a straight line, and the noise amplitude at any point on the straight line is obtained, which is the first noise amplitude corresponding to the target noise characteristic curve (i.e., the 1 / 3 octave band with a center frequency of 1600Hz); similarly, the non-target noise characteristic curve (e.g., the 1 / 3 octave band with a center frequency of 4000Hz) is processed to obtain a straight line, and the noise amplitude at any point on the straight line with the same x-coordinate as the target noise characteristic curve is obtained, which is the second noise amplitude corresponding to the non-target noise characteristic curve.

[0033] Step S30: Determine the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve.

[0034] As an example, in this embodiment, an upper envelope can be plotted by analyzing the collected noise data. This line represents the highest point of the noise, reflecting the maximum noise of the vehicle under normal operating conditions. By setting a curve higher than the upper envelope (i.e., the upper limit curve) as a safety limit for noise fluctuation, then referring to... Figure 3 As shown, the upper limit curve corresponding to the target noise characteristic curve is the target upper limit curve.

[0035] It's important to note that improperly set upper limit curves can lead to both missed and false alarms. A missed alarm occurs when the upper limit curve is set too high, causing actual abnormal noises to be incorrectly identified as not occurring. A false alarm occurs when the upper limit curve is set too low, causing the characteristic curve's normal fluctuations to exceed the upper limit even when no abnormal noise is present, thus incorrectly identifying it as an abnormal noise. In vehicle abnormal noise detection, missed alarms have more serious consequences than false alarms because they can lead to vehicles with abnormal noises entering the market and causing customer complaints. While false alarms increase the time required for staff to reconfirm, they do not necessarily result in vehicles with abnormal noises entering the market. Therefore, when determining the upper limit curve, prioritizing the prevention of missed alarms is crucial; the upper limit curve should not be set too high.

[0036] It should be understood that the first distance refers to the distance between the target upper limit curve and the target noise characteristic curve. In other words, the first distance is the difference between the noise amplitude at any point on the target upper limit curve and the noise amplitude at the corresponding point on the straight line obtained after fitting the target noise characteristic curve. It can be obtained by statistical analysis of noise data from numerous vehicles, and is not limited here. For example, the first distance can preferably be 3 dBA. The upper limit curve is an indicator curve for judging whether a certain type of noise has reached the target value, and there are multiple methods to obtain the upper limit curve. In this embodiment, the least squares method is preferably used to fit the target noise characteristic curve to obtain a straight line, and then the target upper limit curve is obtained by shifting the straight line up by the first distance. It should be noted that in this embodiment, the first distance corresponding to the 1 / 3 octave band with a center frequency of 1600Hz is obtained through statistical analysis, while the distances corresponding to other 1 / 3 octave bands are not obtained based on statistical analysis. Instead, the first distance of the 1 / 3 octave band is used as a benchmark to calculate the distances of other 1 / 3 octave bands, that is, the second distance is calculated using the first distance.

[0037] Specifically, let's assume the first distance corresponding to the target noise characteristic curve is L. 21 , sound power is and The power difference is E 21 The first noise amplitude is The first weighting coefficient is w1, and the second distance corresponding to the non-target noise characteristic curve is L. 43 , sound power is and The power difference is E 43 The second noise amplitude is The second weighting coefficient is w2, where the power difference is the difference between the sound power at any point on the upper limit curve and the sound power at the corresponding point on the straight line obtained after fitting the noise characteristic curve, and the first distance is the difference between the noise amplitude at any point on the target upper limit curve and the noise amplitude at the corresponding point on the straight line obtained after fitting the target noise characteristic curve. For example, the power difference... First distance Therefore, according to the principle of equal weighted power difference, we can conclude that... ,at the same time, , Therefore, it can be based on the first distance. Difference between power , The relationship between the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient is used to replace the sound power. Finally, the second distance is obtained based on the relationship between the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient, which provides a new safe distance for subsequent noise assessment.

[0038] Step S40: Determine the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve.

[0039] In an exemplary embodiment of this application, after processing the non-target noise characteristic curve to obtain a straight line, the first upper limit curve can be determined by the second distance and the straight line, thus obtaining the upper limit curve corresponding to the non-target noise characteristic curve. In this embodiment, the non-target noise characteristic curve refers to the noise characteristic curve of the other 1 / 3 octave bands besides the 1 / 3 octave band with a center frequency of 1600Hz. That is, the upper limit curves of the other 1 / 3 octave bands can be calculated based on the data of the 1 / 3 octave band with a center frequency of 1600Hz, so as to identify the abnormal noise of the target vehicle based on the first upper limit curve.

[0040] Step S50: Identify abnormal noises of the target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

[0041] In this exemplary embodiment, the target vehicle refers to the vehicle under test. Under normal circumstances, the target noise characteristic curve should be located below the target upper limit curve, meaning that noise fluctuations will not exceed the safety limit. Therefore, abnormal noises in the vehicle can be identified by judging the positional relationship between the target noise characteristic curve and the target upper limit curve. Similarly, non-target noise characteristic curves should also be located below the first upper limit curve, indicating that these noise fluctuations are within the normal range. Therefore, abnormal noises in the target vehicle can be identified by judging the positional relationship between the non-target noise characteristic curve and the first upper limit curve. It should be understood that the above judgment strategy can not only help to detect abnormal noise problems in a timely manner, but also improve the accuracy of fault prediction and maintenance efficiency.

[0042] This application obtains multiple target noise characteristic curves and non-target noise characteristic curves corresponding to 1 / 3 octave bands by performing frequency band analysis on vehicle noise data of each segment, and obtains weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The 1 / 3 octave band helps to identify noise problems with narrow frequency bands and low amplitudes. The application obtains the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve. Based on the first distance between the target upper limit curve and the target noise characteristic curve, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient, the application determines the second distance. Based on the second distance and the non-target noise characteristic curve, the application determines the first upper limit curve of the non-target noise characteristic curve. Based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, the application identifies abnormal noises from the target vehicle. This application analyzes the noise data of the target vehicle in a frequency band, and analyzes the noise signal in a finer-grained frequency band to obtain the noise characteristics of each frequency band. This avoids the problem of not being able to identify abnormal noises with narrow frequency bands and low sound power in traditional methods, prevents vehicles with abnormal noises from entering the market, and improves the driving experience.

[0043] Furthermore, in one embodiment, the first noise amplitude is the noise amplitude at any point on a first straight line obtained by fitting the target noise characteristic curve, and the second noise amplitude is the noise amplitude at a target point on a second straight line obtained by fitting the non-target noise characteristic curve, wherein the x-coordinate of the target point is the same as the x-coordinate of any point on the first straight line.

[0044] In this embodiment, as an example, various fitting methods are used. Preferably, the least squares method is used to fit the noise characteristic curves to obtain the median line corresponding to the noise characteristic curves, namely the first straight line and the second straight line. The least squares method can minimize fitting errors, allowing the obtained straight line to more accurately represent the average trend of the noise data. The least squares method is existing technology and is not limited here for the sake of simplicity. Specifically, after obtaining multiple 1 / 3 octave band noise characteristic curves, the target noise characteristic curve is fitted using the least squares method to obtain a straight line, namely the first straight line. Alternatively, a straight line can be obtained by connecting the start and end points of the noise characteristic curves. The noise data at any point on the first straight line is selected as the first noise amplitude. Similarly, the non-target noise characteristic curve is fitted using the least squares method to obtain the second straight line, and the noise data at the point on the second straight line with the same x-coordinate as any point on the first straight line (i.e., the target point) is selected as the second noise amplitude. It is understood that by selecting the noise amplitude at one point from the first and second straight lines, a more stable and consistent noise assessment result can be provided.

[0045] Further, in one embodiment, determining the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient includes: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows:

[0046] In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

[0047] As an example, in the embodiments of this application, the first distance is... First noise amplitude Second noise amplitude First weighting coefficient Second weighting coefficient Substituting into the following calculation formula, we obtain the second distance. The calculation formula is as follows:

[0048] Specifically, refer to Figure 3 and Figure 4As shown, assuming points A on the first straight line and C on the second straight line are selected, then the point on the target upper limit curve corresponding to the first straight line is point B, and the point on the first upper limit curve corresponding to the second straight line is point D. Assume the noise amplitude at point A is L1 and the sound power is E1, the noise amplitude at point B is L2 and the sound power is E2, the noise amplitude at point C is L3 and the sound power is E3, and the noise amplitude at point D is L4 and the sound power is E4. The derivation of the calculation formula is as follows:

[0049]

[0050] In the formula, Let the power difference between two points on the target upper limit curve and the first straight line be the sum of the above two equations:

[0051] According to the principle of equal weighted power difference, ,in, After sorting, we get:

[0052]

[0053] When L 21 Once confirmed, Let be a constant, let Substituting into the above formula, we get: Therefore, as long as we get The value can be obtained. The value of , i.e., the second distance.

[0054] Specifically, and The relationship is: Similarly, and The relationship is Where Eref is the reference power, subtracting the two equations yields: After deformation, it becomes Substitute this formula into the above From the expression, we can obtain .

[0055] Further, in one embodiment, determining the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve includes: The second straight line is translated upwards by a second distance to obtain the third straight line, and the third straight line is used as... The first upper limit curve of the non-target noise characteristic curve.

[0056] As an example, in the embodiments of this application, reference is made to Figure 4 As shown, after obtaining the second straight line and the second distance, the first upper limit curve of the non-target noise characteristic curve can be obtained by shifting the second straight line upward by the second distance. The first upper limit curve can effectively prevent equipment failure or performance degradation that may be caused by noise fluctuations exceeding the safe range, thereby improving the overall stability and durability of the vehicle. The upper limit curve can also serve as a standard for daily maintenance and inspection, helping engineers to quickly identify potential problems and extend the service life of components.

[0057] Further, in one embodiment, the identification of abnormal noises from the target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, includes: Determine whether the target noise characteristic curve is below the target upper limit curve and whether the non-target noise characteristic curve is below the first upper limit curve; If so, then the target vehicle is determined to have no abnormal noises; If not, then the target vehicle is determined to have abnormal noises.

[0058] As an example, in the embodiments of this application, both the target upper limit curve and the first upper limit curve are safety limits for noise fluctuations, with reference to... Figure 5 As shown in (e) and (f), if the target noise characteristic curve is below the target upper limit curve and the non-target noise characteristic curve is also below the first upper limit curve, in other words, if the noise characteristic curves of all 16 1 / 3 octave bands are below their corresponding upper limit curves, it means that the vehicle noise is within the allowable noise range, and the target vehicle is determined to have no abnormal noise. If the target noise characteristic curve is above the target upper limit curve or the non-target noise characteristic curve is above the first upper limit curve, it means that the vehicle noise has exceeded the allowable noise range, and the target vehicle is determined to have abnormal noise, and the target vehicle needs to be adjusted or repaired.

[0059] Furthermore, in one embodiment, prior to the step of performing frequency band analysis on the vehicle noise data for each segment, the method further includes: Vehicle noise data is collected and short-time Fourier transform is performed on the noise data to obtain multiple segments of vehicle noise data.

[0060] As an example, in the embodiments of this application, the Short-Time Fourier Transform (STFT) is an effective tool for frequency domain analysis of time signals. It can describe the characteristics of a signal simultaneously in both time and frequency dimensions. STFT divides the signal into multiple small time windows and then performs a Fourier transform on the signal within each time window to obtain the spectrum of the signal within that time period. The spectrum of different time periods can reflect different noise sources, helping to identify the location and cause of abnormal noises.

[0061] Specifically, this application embodiment collects noise data from normal vehicles and converts the vehicle noise data into multiple time-frequency domain features, which can effectively reveal the time and frequency characteristics of the noise signal. Each feature corresponds to the noise information within a time period, and finally multiple segments of vehicle noise data are obtained. Each segment of vehicle noise data includes time, frequency and noise amplitude information. It can be understood that the above processing helps to accurately locate the noise source, diagnose the fault, and provide data support for subsequent noise optimization and noise reduction measures.

[0062] Secondly, embodiments of this application also provide a vehicle abnormal noise recognition system.

[0063] In one embodiment, reference is made to Figure 6 , Figure 6 This is a schematic diagram of the functional modules of an embodiment of the vehicle abnormal noise recognition system of this application. Figure 6 As shown, the vehicle noise detection system includes: The first processing module is used to perform frequency band analysis on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and to obtain the weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The second processing module is used to obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve; The third processing module is used to determine the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve. The fourth processing module is used to determine the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve; The fifth processing module is used to identify abnormal noises of the target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

[0064] Furthermore, in one embodiment, the second processing module is specifically used for: The first noise amplitude is the noise amplitude at any point on the first straight line obtained by fitting the target noise characteristic curve, and the second noise amplitude is the noise amplitude at the target point on the second straight line obtained by fitting the non-target noise characteristic curve. The x-coordinate of the target point is the same as the x-coordinate of any point on the first straight line.

[0065] Furthermore, in one embodiment, the third processing module is specifically used for: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows:

[0066] In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

[0067] Furthermore, in one embodiment, the fourth processing module is specifically used for: The second straight line is translated upwards by a second distance to obtain the third straight line, and the third straight line is used as... The first upper limit curve of the non-target noise characteristic curve.

[0068] Furthermore, in one embodiment, the fifth processing module is specifically used for: Determine whether the target noise characteristic curve is below the target upper limit curve and whether the non-target noise characteristic curve is below the first upper limit curve; If so, then the target vehicle is determined to have no abnormal noises; If not, then the target vehicle is determined to have abnormal noises.

[0069] Furthermore, in one embodiment, the first processing module is specifically used for: Vehicle noise data is collected and short-time Fourier transform is performed on the noise data to obtain multiple segments of vehicle noise data.

[0070] This application obtains multiple target noise characteristic curves and non-target noise characteristic curves corresponding to 1 / 3 octave bands by performing frequency band analysis on vehicle noise data of each segment, and obtains weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The 1 / 3 octave band helps to identify noise problems with narrow frequency bands and low amplitudes. The application obtains the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve. Based on the first distance between the target upper limit curve and the target noise characteristic curve, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient, the application determines the second distance. Based on the second distance and the non-target noise characteristic curve, the application determines the first upper limit curve of the non-target noise characteristic curve. Based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, the application identifies abnormal noises from the target vehicle. This application analyzes the noise data of the target vehicle in a frequency band, and analyzes the noise signal in a finer-grained frequency band to obtain the noise characteristics of each frequency band. This avoids the problem of not being able to identify abnormal noises with narrow frequency bands and low sound power in traditional methods, prevents vehicles with abnormal noises from entering the market, and improves the driving experience.

[0071] The functions of each module in the above-mentioned vehicle noise recognition system correspond to the steps in the above-mentioned vehicle noise recognition method embodiment, and their functions and implementation processes will not be described in detail here.

[0072] Thirdly, this application provides a vehicle noise recognition device, which can be a personal computer (PC), laptop computer, server or other device with data processing capabilities.

[0073] Reference Figure 7 , Figure 7 This is a schematic diagram of the hardware structure of the vehicle noise recognition device involved in the embodiments of this application. In this embodiment, the vehicle noise recognition device may include a processor, a memory, a communication interface, and a communication bus.

[0074] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0075] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the vehicle noise detection device, as well as interfaces used for interconnecting the vehicle noise detection device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0076] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0077] The processor can be a general-purpose processor, which can call the vehicle abnormal noise recognition program stored in the memory and execute the vehicle abnormal noise recognition method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the vehicle abnormal noise recognition program is called can be referred to in the various embodiments of the vehicle abnormal noise recognition method of this application, and will not be repeated here.

[0078] Those skilled in the art will understand that Figure 7 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0079] Fourthly, embodiments of this application also provide a readable storage medium.

[0080] The present application has a readable storage medium storing a vehicle abnormal noise recognition program, wherein when the vehicle abnormal noise recognition program is executed by a processor, it implements the steps of the vehicle abnormal noise recognition method as described above.

[0081] The method implemented when the vehicle abnormal noise recognition program is executed can be referred to in various embodiments of the vehicle abnormal noise recognition method of this application, and will not be repeated here.

[0082] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0083] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0084] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0085] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0086] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0087] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, 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 storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0088] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for identifying abnormal noises in vehicles, characterized in that, The vehicle abnormal noise identification method includes: Frequency band analysis is performed on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and weighting coefficients corresponding to each 1 / 3 octave band are obtained. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. Obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve; The second distance is determined based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve. The first upper limit curve of the non-target noise characteristic curve is determined based on the second distance and the non-target noise characteristic curve. Abnormal noises of target vehicles are identified based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

2. The vehicle abnormal noise identification method as described in claim 1, characterized in that, The first noise amplitude is the noise amplitude at any point on the first straight line obtained by fitting the target noise characteristic curve, and the second noise amplitude is the noise amplitude at the target point on the second straight line obtained by fitting the non-target noise characteristic curve. The x-coordinate of the target point is the same as the x-coordinate of any point on the first straight line.

3. The vehicle abnormal noise identification method as described in claim 2, characterized in that, The determination of the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient includes: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows: In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

4. The vehicle abnormal noise identification method as described in claim 2, characterized in that, The determination of the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve includes: The second straight line is translated upwards by a second distance to obtain the third straight line, and the third straight line is used as... The first upper limit curve of the non-target noise characteristic curve.

5. The vehicle abnormal noise identification method as described in claim 1, characterized in that, The method of identifying abnormal noises from a target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve, includes: Determine whether the target noise characteristic curve is below the target upper limit curve and whether the non-target noise characteristic curve is below the first upper limit curve; If so, then the target vehicle is determined to have no abnormal noises; If not, then the target vehicle is determined to have abnormal noises.

6. The vehicle abnormal noise identification method as described in claim 1, characterized in that, Before the step of performing frequency band analysis on the vehicle noise data for each segment, the method further includes: Vehicle noise data is collected and short-time Fourier transform is performed on the noise data to obtain multiple segments of vehicle noise data.

7. A vehicle abnormal noise recognition system, characterized in that, The vehicle abnormal noise detection system includes: The first processing module is used to perform frequency band analysis on the vehicle noise data of each segment to obtain target noise characteristic curves and non-target noise characteristic curves corresponding to multiple 1 / 3 octave bands, and to obtain the weighting coefficients corresponding to each 1 / 3 octave band. The first weighting coefficient corresponding to the target noise characteristic curve is greater than the second weighting coefficient corresponding to the non-target noise characteristic curve. The second processing module is used to obtain the first noise amplitude corresponding to the target noise characteristic curve and the second noise amplitude corresponding to the non-target noise characteristic curve; The third processing module is used to determine the second distance based on the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient. The first distance is the distance between the target upper limit curve of the target noise characteristic curve and the target noise characteristic curve. The fourth processing module is used to determine the first upper limit curve of the non-target noise characteristic curve based on the second distance and the non-target noise characteristic curve; The fifth processing module is used to identify abnormal noises of the target vehicle based on the positional relationship between the target noise characteristic curve and the target upper limit curve, and the positional relationship between the non-target noise characteristic curve and the first upper limit curve.

8. The vehicle abnormal noise recognition system as described in claim 7, characterized in that, The third processing module is specifically used for: Substituting the first distance, the first noise amplitude, the second noise amplitude, the first weighting coefficient, and the second weighting coefficient into the first calculation formula, we obtain the second distance. The first calculation formula is as follows: In the formula, This is the first distance; This is the first noise amplitude; This is the second noise amplitude; This is the first weighting factor; This is the second weighting factor; This is the second distance.

9. A vehicle abnormal noise identification device, characterized in that, The vehicle noise identification device includes a processor, a memory, and a vehicle noise identification program stored in the memory and executable by the processor, wherein when the vehicle noise identification program is executed by the processor, it implements the steps of the vehicle noise identification method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle noise identification program, wherein when the vehicle noise identification program is executed by a processor, it implements the steps of the vehicle noise identification method as described in any one of claims 1 to 6.

Images