Automobile expected working condition noise analog simulation method and system based on reference noise matching

Abstract

The invention provides an automobile expected working condition noise simulation method and system based on reference noise matching, and relates to the technical field of noise simulation. The method provided by the invention comprises the steps of performing feature extraction on reference noise data to obtain reference noise features of each reference vehicle type under each original working condition; inputting the sound field influence factors of the vehicle type to be detected into a pre-trained target model to obtain predicted noise features output by the target model; comparing the predicted noise feature with each reference noise feature to obtain a target reference vehicle model matched with the to-be-detected vehicle model; and in a noise playback cavity matched with the to-be-tested vehicle model, playing back reference noise data of the target reference vehicle model under the expected working condition. According to the method, a main engine plant can simulate and evaluate noise characteristics in an early stage, so that design changes caused by noise problems are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of noise simulation, and in particular to a method and system for simulating noise of expected automobile working conditions based on reference noise matching. Background Art

[0002] With the development of intelligent connected vehicles, cars have evolved from simple modes of transportation into a "third living space" that integrates transportation, information, and entertainment. This transformation not only enhances the user experience but also places higher demands on various in-cabin acoustic systems (such as voice interaction systems, emergency call systems, hands-free calling systems, and audio entertainment systems). The quality and performance of in-vehicle acoustic systems have become a key factor influencing consumers' driving experience and even car purchasing decisions. Currently, to ensure smooth communication between the vehicle and the Public Safety Answering Point (PSAP), better utilize social resources, and save lives, even higher standards are placed on call voice quality. Furthermore, the performance of in-vehicle acoustic systems is closely linked to driving safety. Research by the U.S. National Highway Traffic Safety Administration (NHTSA) indicates that poor in-vehicle acoustic system performance increases driver distraction, thereby increasing the risk of traffic accidents. In stark contrast to the relatively quiet listening environment of a home or professional audio studio, in-vehicle acoustic systems must perform in a diverse and noisy environment. The intensity and frequency of vehicle driving noise and wind noise vary depending on vehicle speed and vehicle design. Furthermore, the enclosed interior and reflective properties of materials cause multiple reflections and absorption of sound, creating a reverberation effect that further complicates the sound field. Therefore, integrating an in-vehicle acoustic system into a car is fraught with challenges. The placement of microphones and speakers, as well as noise reduction algorithms, significantly impact the system's performance.

[0003] To analyze the performance of vehicle acoustic systems during actual user use, the impact of interior noise must be considered when conducting vehicle acoustic system tests. In the early stages of vehicle acoustic system development, testers often sat inside the vehicle and conducted subjective evaluations of the system while the vehicle was operating under specific operating conditions. This method suffers from high costs and time constraints. Furthermore, due to difficulties in quantification, poor repeatability, and objectivity, it can easily mislead product tuning. With the advancement of testing technology, vehicle acoustic system testing now uses standardized acoustic dummies (equipped with artificial ears and mouths to receive and transmit test audio signals) in a full-vehicle noise test chamber. This testing method uses objective physical quantities to test the vehicle acoustic system, offering high objectivity and repeatability. To test the performance of vehicle acoustic systems under actual user use, a vehicle operating noise simulation system is required to simulate the interior noise environment. When the vehicle-mounted acoustic system is working, car noise has the greatest impact on the user and the vehicle-mounted microphone. Therefore, the vehicle operating noise simulation system needs to accurately restore the sound field at the user's ear point and the vehicle-mounted microphone point.

[0004] The sequence of automotive development is concept development, detailed design, engineering development, prototyping, testing and verification, and pre-production. While the layout of onboard speakers and microphones often occurs in the early stages of concept development and detailed design, vehicle operating noise cannot be collected until prototyping and pre-production. The automotive industry urgently needs a system for simulating operating noise early in vehicle development to address this conflict. Summary of the Invention

[0005] To address the above issues, the present invention proposes a method and system for simulating automobile expected operating condition noise based on reference noise matching, which is used to simulate and evaluate noise characteristics at an early stage, thereby reducing design changes caused by noise problems.

[0006] In a first aspect, an embodiment of the present invention provides a method for simulating noise in expected vehicle operating conditions based on reference noise matching, comprising: Collect reference noise data of various reference models under various original working conditions; Performing feature extraction on the reference noise data to obtain reference noise features for each reference vehicle model under each original operating condition; Input the sound field influencing factors of the vehicle model to be tested into a pre-trained target model to obtain the predicted noise characteristics output by the target model; Obtaining a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise signature with each reference noise signature; In a noise playback chamber that matches the vehicle type to be tested, reference noise data of the target reference vehicle type under expected operating conditions is played back.

[0007] Optionally, collect reference noise data for various reference vehicle models under various original operating conditions, including: Control each reference vehicle model to operate under each original working condition; When the reference vehicle model is driving under any original working condition, reference noise data is collected through multi-point microphones inside the reference vehicle model.

[0008] Optionally, before inputting the sound field influencing factors of the vehicle to be tested into the pre-trained target model, the following steps are also included: Collecting training samples, wherein the training samples include samples of sound field influencing factors of multiple reference vehicle models and noise feature labels; The target model is trained using the training samples.

[0009] Optionally, the target model is a multilayer perceptron.

[0010] Optionally, obtaining a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise signature with each reference noise signature includes: Calculating a difference vector between the predicted noise feature and each reference noise feature; Obtaining a matching probability between the predicted noise feature and each reference noise feature according to the difference vector and a normalized exponential function; The reference vehicle model from which the reference noise feature with the highest matching probability originates is determined as the target reference vehicle model.

[0011] Optionally, before replaying the reference noise data of the target reference vehicle under expected operating conditions in a noise playback chamber that matches the vehicle to be tested, the method further includes: Summarize a reference noise data set under each original working condition, wherein the reference noise data set includes reference noise data of multiple vehicle models, recorded by multiple microphone positions, and in multiple frequency bands; Clustering the reference noise data sets under various original working conditions to obtain various typical working conditions and a typical reference noise data set under each typical working condition; The expected operating condition is any typical operating condition.

[0012] Optionally, replaying reference noise data of the target reference vehicle under expected operating conditions in a noise playback chamber that matches the vehicle to be tested includes: Determine the preset microphone layout for the vehicle model to be tested; screening reference noise data of the target reference vehicle model under expected operating conditions according to the preset microphone arrangement; The filtered reference noise data is played back using a power amplifier and a speaker group that are consistent with the preset microphone arrangement.

[0013] Optionally, the method further includes: when collecting reference noise in a reference vehicle model, and when playing back reference noise data in a noise playback cavity, using a noise equalization front end to perform sound field equalization in the noise playback cavity and in the reference vehicle model.

[0014] In a second aspect, an embodiment of the present invention provides a system for simulating and emulating automobile expected operating noise based on reference noise matching, comprising: Microphone, used to collect reference noise data of various reference vehicle models under various original working conditions; A controller is configured to extract features from the reference noise data to obtain reference noise features for each reference vehicle model under each original operating condition; input the sound field influencing factors of the vehicle model to be tested into a pre-trained target model to obtain predicted noise features output by the target model; and obtain a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise features with each reference noise feature; The noise playback system is used to play back the reference noise data of the target reference vehicle model under the expected working conditions in a noise playback cavity matched with the vehicle model to be tested.

[0015] Optionally, the noise playback cavity is a completely enclosed space having a resonance frequency that matches the vehicle model to be tested; the noise data in the noise playback cavity is reflected multiple times to form a reverberation effect, and noise data of different frequencies are filtered.

[0016] During vehicle development, the layout of onboard speakers and microphones often occurs in the early stages of concept development and detailed design. However, vehicle operating noise collection requires the initial phase of prototyping and pre-production. Traditional solutions, if the acoustic system of a vehicle prototype fails to meet expected performance, require rewriting the early design, increasing development costs and extending the development cycle.

[0017] Therefore, the present invention collects noise data under different working conditions of the vehicle during the prototype manufacturing to pre-production stage of vehicle development, uses a noise playback system to play back the noise, and simulates the vehicle working condition noise. The beneficial effects are: 1. Early Noise Simulation: Traditionally, noise collection is performed only during the vehicle prototyping and pre-production stages. Discovering acoustic system issues can necessitate rewriting early designs, increasing development costs and lead times. This new approach collects noise data during the prototyping phase and simulates it using a noise playback system. This allows OEMs to simulate and evaluate noise characteristics at an early stage, reducing design changes caused by noise issues.

[0018] 2. Establishing a Reference Noise Database and Optimizing Scenarios: A reference noise database consisting of reference noise data was established by recording real-world noise from various vehicle models under various operating conditions. Clustering methods were then used to simplify the operating conditions into a small number of typical ones. This not only reduced the number of scenarios to be processed, improving testing efficiency, but also ensured that the key noise characteristics under different vehicle operating conditions were covered.

[0019] 3. Multilayer Perceptron (MLP) Modeling: MLP is used to model the relationship between multiple sound field influencing factors (such as structure, power, material, and size) and noise characteristics. This machine learning method accurately captures complex nonlinear relationships, enhancing the accuracy of noise signature predictions for the tested vehicle and making the development process more scientific and data-driven.

[0020] 4. Probability Matching and Noise Replay: A normalized exponential function (Softmax function) is used to calculate the probability of the tested vehicle belonging to a target reference vehicle model. This probability is then matched against existing reference noise data. For successfully matched vehicles, the corresponding noise from the reference noise library is replayed to simulate the in-vehicle noise environment. This process not only improves the accuracy of noise assessment but also provides OEMs with a more flexible design verification method.

[0021] 5. Reduced development costs and cycle time: By simulating and predicting noise characteristics in advance, this project significantly reduced potential design changes later in the process, lowered development costs, and shortened development cycles. This has significant economic benefits and enhanced market competitiveness for automotive developers.

[0022] 6. By setting up a noise playback cavity, the sound field environment can be simulated before the vehicle model is manufactured. At the same time, the noise playback cavity is a completely enclosed space with a resonant frequency that matches the vehicle model to be tested. The noise data is reflected multiple times to form a reverberation effect, and noise data of different frequencies are filtered. The noise equalization front end is used to equalize the sound field in the noise playback cavity, improving the authenticity of the noise field restoration inside the vehicle.

[0023] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above description and other purposes, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are specifically cited and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: Figure 1 A flowchart of a method for simulating noise in expected vehicle operating conditions based on reference noise matching provided by an embodiment of the present invention; Figure 2 A schematic diagram of the 16 microphone locations provided in an embodiment of the present invention and their arrangement within a reference vehicle model; Figure 3 A schematic diagram of the structure of a vehicle expected operating condition noise simulation system based on reference noise matching provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0026] In the description of the present invention, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood in a broad sense. For example, they may refer to connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0027] Example 1 The embodiment of the present invention provides a method for simulating the noise of an automobile under expected working conditions based on reference noise matching, which is applicable to the situation where the noise sound field is simulated in a noise playback cavity simulating the vehicle model to be tested in the early stage when the vehicle model to be tested has not yet been manufactured. Figure 1 The method for simulating the expected operating noise of an automobile based on reference noise matching provided in this embodiment includes the following steps: S110. Collect reference noise data of various reference vehicle models under various original working conditions.

[0028] Reference vehicle models are commercially available. Specifically, each reference vehicle model is controlled to operate under each original operating condition. While the reference vehicle model is operating under each original operating condition, reference noise data is collected using microphones located at multiple points within the reference vehicle model. The collected reference noise data is stored in a reference noise library.

[0029] In some examples, to ensure that the reference noise library comprehensively covers noise scenarios in various vehicle operating conditions, 16 original operating conditions were set. These original operating conditions include combinations of vehicle speeds (0, 60, 80, and 120 km / h) and air conditioning volume settings (off, low, medium, and high).

[0030] Table 1 Information of original working condition Under all original working conditions, the air conditioner is set to external circulation, only the face-blowing air duct is open and the other air ducts are closed, the air outlet direction is adjusted to the middle angle between the horizontal and vertical angles of the air duct, the sunroof is closed, and all side windows are closed.

[0031] Reference vehicle status: No unusual noises during driving, normal vehicle operation, and no warning signals. The tires must be factory models with no noticeable tread wear or uneven wear. The cold tire inflation pressure must meet the vehicle's specifications. The fuel, lubricant, brake fluid, ignition timing, and injection timing used in the vehicle must meet the vehicle's specifications or current national standards. The engine coolant temperature must be within the normal range during noise recording / collection. It is recommended to drive the vehicle at a moderate speed for a short distance before recording. During noise recording / collection, the vehicle must be unloaded except for the driver, a noise recorder (one person, seated in the passenger seat), and necessary test equipment. No occupants should make any noise. When driving under any operating conditions, the vehicle must be in the highest gear for the corresponding speed in manual transmissions; manual gear changes in automatic transmissions must not be made. Windshield wipers, turn signals, automatic sounding devices, or any other devices that could affect the test must be inoperative.

[0032] 100 vehicles with significant differences were selected, including different body structures, power, sizes, and materials, covering all reference models available on the market. Multiple points of real vehicle noise were recorded for the aforementioned 16 working conditions of more than 100 different models. Microphones were placed at the recording points. Figure 2 The diagram shows the locations of 16 microphones and their placement within a reference vehicle. Each microphone is numbered from 1 to 16. The specific locations are described as follows: Microphones 1 and 2 are located on the upper left and upper right sides of the central control screen. They face upward.

[0033] Microphones 3-5 are located on the edge of the front dome light module, near the passenger seat. Microphone 3 is on the left side, 4 is in the middle, and 5 is on the right side. The microphones face rearward.

[0034] Microphones 6 through 9 are located on the passenger-side edge of the sun visor, with microphone 6 located on the left side of the left sun visor, microphone 7 located in the center of the left sun visor, microphone 8 located in the center of the right sun visor, and microphone 9 located on the right side of the right sun visor. The microphones face rearward.

[0035] Microphones 10 and 11 are located on the upper ends of the left and right B-pillars, facing upward.

[0036] Microphones 12 and 13 are located directly above the driver and front passenger's heads, respectively. If the sunroof prevents placement of the microphones directly above the driver and front passenger's heads, place them on the left and right edges of the sunroof, as close as possible to the driver and front passenger's heads. The microphones face rearward.

[0037] Microphone 14: Located directly above the center rear passenger's head. If the sunroof prevents placement of the microphone directly above the center rear passenger's head, place the microphone at the rear edge of the sunroof, as close as possible to the center rear passenger's head. The microphone faces rearward.

[0038] Microphones 15 and 16 are located directly above the heads of the left and right second-row passengers, respectively. If the sunroof prevents placement of the microphones directly above the heads of the left and right second-row passengers, place the microphones on the left and right edges of the sunroof, as close as possible to the heads of the left and right second-row passengers. The microphones face rearward.

[0039] S120 , performing feature extraction on the reference noise data to obtain reference noise features for each reference vehicle model under each original working condition.

[0040] For each vehicle, under each operating condition, and from each microphone, the reference noise data (essentially a segment of audio) is collected. The octave sound pressure level (10 frequency bands in total) in the range of 31.5 to 16,000 Hz is extracted as the reference noise feature.

[0041] X represents the set of reference noise features. Each row represents a row vector of reference noise features for a specific operating condition, including m features, where m = number of vehicles × number of noise recording points × number of frequency bands. This data is stored in a matrix X with dimensions of 16 (number of operating conditions) × m (number of features).

[0042] ; S130 , inputting the sound field influencing factors of the vehicle type to be tested into a pre-trained target model to obtain predicted noise characteristics output by the target model.

[0043] The vehicle model to be tested is a vehicle model that has not yet been manufactured, but its sound field influencing factors that affect the sound field inside the vehicle are known, including but not limited to: vehicle structure, power, material and size.

[0044] Optionally, the target model is a multilayer perceptron (MLP), which maps input sound field influencing factors to noise characteristics, such as octave-band sound pressure levels. This means predicting the internal noise characteristics of the vehicle under test based on its characteristics. Before using the target model, you must build and train the MLP.

[0045] The multilayer perceptron consists of an input layer, a hidden layer, and an output layer. The factors affecting the sound field are set as input features, including vehicle structure, power, material, and size. Assume that the input vector composed of these factors is A. The MLP contains one or more hidden layers. In the hidden layer, the output of the neurons can be represented by weighted summation without using an activation function. l The output of the hidden layer is h l , and its calculation formula is: ; in: Indicates the l The weight matrix of the layer. Indicates the l The bias vector of the layer. h0=A represents the input vector.

[0046] The output layer is used to calculate the noise characteristics of the vehicle , and its calculation formula is: ; in: Represents the weight matrix of the output layer. Represents the bias vector of the output layer. is the output of the last hidden layer. represents the calculated noise characteristics.

[0047] Collect training samples: including samples of sound field influencing factors of various reference models and noise feature labels; use the training samples to train the target model. Through the trained MLP model, for the sound field influencing factor A of the given tested model, test , we can get the corresponding noise characteristics , called the prediction noise feature.

[0048] ; S140 , obtaining a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise feature with each reference noise feature.

[0049] The predicted noise characteristics output by the model are compared with the reference noise characteristics of the reference vehicle model. Through logistic regression, the probability value of the tested vehicle matching the existing model is obtained, and then the tested vehicle is matched with the reference vehicle model with existing noise data.

[0050] Optionally, a similarity score between the predicted noise feature and each reference noise feature is calculated; based on the similarity score and a normalized exponential function, a matching probability between the predicted noise feature and each reference noise feature is obtained; the reference vehicle model from which the reference noise feature with the highest matching probability originates is determined as the target reference vehicle model; and then the reference noise data of the target reference vehicle model under various original working conditions is determined in the reference noise library for playback use.

[0051] Optionally, a similarity score between the predicted noise feature and each reference noise feature is calculated using the following formula: ; in, is the score of the i-th vehicle type category. m is Number of features. is the kth feature data under the i-th reference noise feature.

[0052] The Softmax function is used to calculate the matching probability between the predicted noise feature and each reference noise feature. The Softmax calculation formula is: Where: C is the number of vehicle type categories, 100. Indicates that the tested vehicle belongs to the i-th vehicle type category probability.

[0053] S150 : Playing back reference noise data of the target reference vehicle model under expected operating conditions in a noise playback chamber that matches the vehicle model to be tested.

[0054] The noise playback chamber is a completely enclosed space (used to simulate a cockpit) with a resonant frequency that matches the vehicle under test. When the frequency of external sound matches the cavity's resonant frequency, it causes strong resonance within the chamber, amplifying the sound. The noise data within the noise playback chamber undergoes multiple reflections, creating a reverberation effect. The duration of the reverberation period is affected by factors such as the chamber's size, shape, material, and internal sound absorption. The noise playback chamber filters noise data of different frequencies. Some frequencies may be absorbed or reflected by the chamber, while others can pass through smoothly. The resonant frequency, reverberation effect, and filtering capability of the noise playback chamber should match the vehicle under test.

[0055] To cover a wide range of reference vehicle models, this embodiment uses up to 16 microphones to collect noise data. In reality, the test vehicle typically has fewer than 16 microphones. To recreate the realistic noise field, the reference noise data must be filtered based on the microphone layout of the test vehicle. Optionally, a preset microphone layout is determined for the test vehicle (e.g., on both sides of the seats). Based on this preset microphone layout, the reference noise data for the target reference vehicle under expected operating conditions is filtered. Specifically, the 16 microphones are first filtered for the target microphone that is closest to or overlaps with the preset microphone layout. The reference noise data collected by the target microphone is then filtered from the 16 reference noise data sets under expected operating conditions for the target reference vehicle. The filtered reference noise data is then played back using an amplifier and speaker set that matches the preset microphone layout. Preferably, the amplifier and speaker set utilize eight full-range speakers and one subwoofer to simulate the vehicle's interior background noise. Interference in the sound transmission path between the speakers, the test vehicle's terminal microphones, and the test system should be minimized, and the speakers should avoid resonance.

[0056] Furthermore, when collecting reference noise within a reference vehicle model and replaying the reference noise data in a noise playback chamber, a noise equalization front-end is used to equalize the sound field within the noise playback chamber and the reference vehicle model. Specifically, sound field equalization can eliminate the effects of errors in speaker frequency response, placement, and directivity. Sound field equalization ensures that each playback sound field and the recorded noise sound field meet the following requirements: (a) The level difference should be within ±1dB; (b) The amplitude of the complex coherence (normalized cross-correlation spectrum) in the frequency range of 100 Hz to 1000 Hz should be greater than 0.9 (measured in 1 / 3 octave bands); (c) The phase of the complex coherence should be accurate to within ±10 degrees in the frequency range of 100 Hz to 1000 Hz and to within ±30 degrees in the frequency range of 1000 Hz to 1500 Hz (measured in 1 / 3 octave bands); (d) The difference between the original reference noise octave band sound pressure level and the simulated noise octave band sound pressure level for each microphone shall be within ±3 dB in the frequency range of 50 Hz to 10,000 Hz and within ±6 dB in the frequency range of 10,000 Hz to 16,000 Hz (measured in 1 / 3 octave bands); (e) In the frequency range of 50 Hz to 20,000 Hz, the average spectrum accuracy of all microphones should be within ±3 dB.

[0057] Optionally, the expected operating condition may be any original operating condition, so that after determining the target reference vehicle model, reference noise data of the target reference vehicle model under a certain original operating condition is selected from the reference noise library for playback.

[0058] Example 2 In some embodiments, testing the noise environment of the vehicle under test by only testing a small number of representative operating conditions in a noise playback chamber can improve testing efficiency. Therefore, before replaying the reference noise data of the target reference vehicle under the expected operating conditions in a noise playback chamber that matches the vehicle under test, a small number of representative operating conditions are selected from a variety of original operating conditions.

[0059] Preferably, a reference noise data set under each original operating condition is aggregated, the reference noise data set including reference noise data from multiple vehicle models, recorded by multiple microphone locations, and in multiple frequency bands; the reference noise data sets under the multiple original operating conditions are clustered to obtain multiple typical operating conditions and a typical reference noise data set under each typical operating condition. The number of typical operating conditions is less than the number of original operating conditions.

[0060] Optionally, this embodiment uses the k-means clustering method to obtain multiple typical operating conditions. First, the elbow method is used to automatically determine k (the number of clusters). The clustering cost (the sum of squared errors within clusters, abbreviated as SSE) is calculated for different k values. For each possible k value (for example, any number from 1 to 10), the corresponding SSE is calculated: ; Where: k is the current number of clusters. C i is the ith cluster. x j is assigned to cluster C i The jth characteristic vector in , the characteristic vector is a reference noise data set under a certain original working condition, that is, the row vector in the above X matrix. μ i It is a cluster C i The center of mass.

[0061] Then, plot the change of SSE under different k values ​​and find the elbow point (the point where the SSE decreases significantly slower). The k value corresponding to the elbow point is the optimal number of clusters. The present invention applies the elbow rule to select = 4, that is, the optimal number of clusters obtained by the elbow rule is = 4. Next, randomly select A reference noise dataset is taken as the initial centroid, and this The initial centroid is For each feature vector x j(j = 1, 2,..., 100), calculate its distance to all centroids, find the nearest centroid in Euclidean order, and assign the feature vector to the corresponding cluster C i The Euclidean distance between the feature vector and the centroid is calculated as: ; Among them, k is a variable. is the kth characteristic data under the jth working condition.

[0062] According to the following rules, the characteristic vector x j Assigned to cluster C i : ; For each cluster , calculate the new center of mass , which is the centroid after t+1 iterations. This centroid is the mean of all feature vectors in the cluster: in, Represents cluster C i The number of feature vectors in .

[0063] Check if the centroid has changed. If the centroid change is less than a preset threshold ε (usually set to a very small value, such as ε = 10 -6 ), or the maximum number of iterations is reached, the algorithm stops, otherwise it continues to iterate. After several iterations, the final Cluster Heart . Assume that four cluster centers are finally calculated: . Calculate each feature vector The Euclidean distance from each cluster center, select the feature vector closest to each cluster center The corresponding working condition is a typical working condition, and As a typical reference noise data set.

[0064] This embodiment selects 4 typical working conditions from the aforementioned 16 working conditions through a clustering algorithm, covering typical vehicle driving noise collection scenarios.

[0065] After determining typical operating conditions, the reference noise data of various reference models under these typical operating conditions, recorded by multiple microphones at multiple locations, and in multiple frequency bands can be stored in the reference noise library. The reference noise data of the target reference model under any typical operating condition can then be replayed in the noise playback chamber.

[0066] Example 3 This embodiment provides a vehicle expected operating noise simulation system based on reference noise matching, see Figure 3 , including: microphone, controller and noise playback system, the noise playback system includes noise equalization front end, noise playback cavity and power amplifier and speaker group.

[0067] The microphone is used to collect reference noise data from multiple reference vehicle models under multiple original operating conditions to construct a reference noise library. The controller is used to extract features from the reference noise data to obtain reference noise characteristics for each reference vehicle model under each original operating condition. The sound field influencing factors of the vehicle model to be tested are input into a pre-trained target model to obtain the predicted noise characteristics output by the target model. By comparing the predicted noise characteristics with each reference noise characteristic, a target reference vehicle model matching the vehicle model to be tested is obtained. The noise playback system is used to replay the reference noise data of the target reference vehicle model under the expected operating conditions in a noise playback chamber matching the vehicle model to be tested.

[0068] When collecting reference noise in a reference vehicle model and when playing back reference noise data in a noise playback cavity, a noise equalization front end is used to equalize the sound field in the noise playback cavity and in the reference vehicle model.

[0069] The foregoing description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed herein are intended to be encompassed within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for simulating the expected working condition noise of an automobile based on reference noise matching, characterized in that: Collect reference noise data of various reference models under various original working conditions; Performing feature extraction on the reference noise data to obtain reference noise features of each reference vehicle model under each original working condition; Inputting the sound field influencing factors of the vehicle model to be tested into a pre-trained target model to obtain the predicted noise characteristics output by the target model; Obtaining a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise feature with each reference noise feature; In a noise playback chamber that matches the vehicle type to be tested, reference noise data of the target reference vehicle type under expected operating conditions are played back.

2. The method according to claim 1, characterized in that Collect reference noise data of various reference models under various original working conditions, including: Control each reference vehicle model to operate under each original working condition; When the reference vehicle model is driving under any original working condition, reference noise data is collected through multi-point microphones in the reference vehicle model.

3. The method according to claim 1, characterized in that Before inputting the sound field influencing factors of the vehicle model to be tested into the pre-trained target model, it also includes: Collecting training samples, wherein the training samples include samples of sound field influencing factors of multiple reference vehicle models and noise feature labels; The target model is trained using the training samples.

4. The method according to claim 3, characterized in that: The target model is a multi-layer perceptron.

5. The method according to claim 1, characterized in that By comparing the predicted noise feature with each reference noise feature, a target reference vehicle model matching the vehicle model to be tested is obtained, including: Calculating a difference vector between the predicted noise feature and each reference noise feature; Obtaining a matching probability between the predicted noise feature and each reference noise feature according to the difference vector and the normalized exponential function; The reference vehicle model from which the reference noise feature with the highest matching probability comes is determined as the target reference vehicle model.

6. The method according to claim 1, characterized in that Before replaying the reference noise data of the target reference vehicle model under the expected working condition in the noise replay cavity matched with the vehicle model to be tested, the method further includes: Summarize a reference noise data set under each original working condition, wherein the reference noise data set includes reference noise data of multiple vehicle models, recorded by microphones at multiple locations, and in multiple frequency bands; Clustering the reference noise data sets under various original working conditions to obtain various typical working conditions and a typical reference noise data set under each typical working condition; The expected operating condition is any typical operating condition.

7. The method according to claim 1, characterized in that In a noise playback chamber that matches the vehicle type to be tested, reference noise data of the target reference vehicle type under expected operating conditions is played back, including: Determine the preset microphone arrangement for the vehicle model to be tested; Screening reference noise data of the target reference vehicle model under expected operating conditions according to the preset microphone arrangement; The screened reference noise data is played back using a power amplifier and a speaker group that are consistent with the preset microphone arrangement.

8. The method according to claim 1, characterized in that The method further comprises: When collecting reference noise in a reference vehicle model and when playing back reference noise data in a noise playback cavity, a noise equalization front end is used to perform sound field equalization in the noise playback cavity and in the reference vehicle model.

9. A vehicle expected operating noise simulation system based on reference noise matching, characterized in that: include: Microphone, used to collect reference noise data of various reference vehicle models under various original working conditions; A controller is used to extract features from the reference noise data to obtain reference noise features of each reference vehicle model under each original working condition; input the sound field influencing factors of the vehicle model to be tested into a pre-trained target model to obtain predicted noise features output by the target model; and obtain a target reference vehicle model that matches the vehicle model to be tested by comparing the predicted noise features with each reference noise feature; The noise playback system is used to play back the reference noise data of the target reference vehicle model under the expected working conditions in a noise playback cavity matched with the vehicle model to be tested.

10. The system according to claim 9, characterized in that The noise playback cavity is a completely enclosed space and has a resonance frequency that matches the vehicle model to be tested; The noise data in the noise playback cavity is reflected multiple times to form a reverberation effect, and the noise data of different frequencies are filtered.

Images