Intelligent Detection Method and System for the Static and Dynamic Noise Reduction of Automobile Sunroofs Integrating Acoustic Imaging

Abstract

The present invention discloses an intelligent detection method and system for the dynamic and static noise of a vehicle sunroof integrating acoustic imaging, which relates to the technical field of acoustic measurement. The method includes: obtaining the internal space structure information of the target vehicle, determining the optimal installation position based on the analysis of the layout points of the acoustic imager, and collecting the noise data during the opening and closing process of the vehicle sunroof in real time; building a dual-channel for acoustic data processing, extracting the multi-dimensional feature set and spatial feature set of the sunroof noise; constructing a dynamic and static noise detection task set for the sunroof, mapping the multi-dimensional feature set to the spatial feature set for fusion evaluation, generating a dynamic and static noise detection report for the vehicle sunroof, and realizing the accurate detection and quantitative analysis of dynamic noise. It solves the technical problem that the prior art cannot perform real-time and high-precision spatial detection and quantitative evaluation on the dynamic noise during the opening and closing process of the vehicle sunroof, and achieves the technical effect of improving the detection accuracy and efficiency.

Description

Technical Field

[0001] This application relates to the field of acoustic measurement technologies, and particularly to an intelligent detection method and system for the static and dynamic noise of automotive sunroofs integrating acoustic imaging. Background Art

[0002] With the improvement of the performance requirements for automotive NVH (Noise, Vibration, and Harshness), the problem of dynamic noise generated during the opening and closing of sunroofs has become increasingly prominent. Traditional detection methods mainly rely on wind tunnel tests and numerical simulations that couple CFD and acoustic software, but there are significant limitations: on the one hand, sensors such as single-point microphones are difficult to capture the transient change characteristics of noise during the opening and closing of sunroofs in real time, resulting in low accuracy of noise source localization; on the other hand, existing technologies cannot synchronously obtain noise signal and spatial distribution information, and can only infer the resonance region through experimental data. The optimization process requires repeated trial and error and is inefficient. In addition, the generation of sunroof wind-induced noise is closely related to the Helmholtz resonance mechanism, and its frequency is affected by factors such as the sunroof opening area and the volume of the vehicle interior cavity. However, existing methods have insufficient adaptability to dynamic conditions (such as changes in vehicle speed and adjustment of sunroof opening), and it is difficult to quantify the noise propagation path and resonance region. The above defects make it difficult for sunroof noise detection to meet the requirements of real-time, spatial analysis, and efficient optimization in engineering practice.

[0003] In the current related technologies, there is a technical problem that it is impossible to perform real-time and high-precision spatial detection and quantitative evaluation of the dynamic noise during the opening and closing of automotive sunroofs. Summary of the Invention

[0004] This application solves the technical problem that existing technologies cannot perform real-time and high-precision spatial detection and quantitative evaluation of the dynamic noise during the opening and closing of automotive sunroofs by providing an intelligent detection method and system for the static and dynamic noise of automotive sunroofs integrating acoustic imaging.

[0005] This application provides an intelligent detection method for the static and dynamic noise of automotive sunroofs integrating acoustic imaging, including:

[0006] Obtain the internal space structure information of the target vehicle and the acoustic imager to be applied. Based on the internal space structure information, conduct a layout point analysis on the acoustic imager to be applied to determine the acoustic imager layout point information; install the acoustic imager to be applied according to the acoustic imager layout point information, and start the installed acoustic imager to perform real-time dynamic acquisition of the noise data during the opening and closing process of the automobile sunroof, so as to obtain a sunroof noise signal set and a sunroof noise image set; build a dual-channel acoustic data processing system, and synchronously analyze and process the sunroof noise signal set and the sunroof noise image set based on the dual-channel acoustic data processing system to obtain a sunroof noise multi-dimensional feature set and a sunroof noise spatial feature set; construct a sunroof quiet and noisy detection task set, and map the sunroof noise multi-dimensional feature set to the sunroof noise spatial feature set based on the sunroof quiet and noisy detection task set for fusion evaluation, and generate an automobile sunroof quiet and noisy detection report.

[0007] The present application provides an intelligent detection system for the quiet and noisy state of an automobile sunroof integrating acoustic imaging, including:

[0008] A layout point analysis module, which is used to obtain the internal space structure information of the target vehicle and the acoustic imager to be applied, conduct a layout point analysis on the acoustic imager to be applied based on the internal space structure information, and determine the acoustic imager layout point information; a real-time dynamic acquisition module, which is used to install the acoustic imager to be applied according to the acoustic imager layout point information, and start the installed acoustic imager to perform real-time dynamic acquisition of the noise data during the opening and closing process of the automobile sunroof, so as to obtain a sunroof noise signal set and a sunroof noise image set; a feature set acquisition module, which is used to build a dual-channel acoustic data processing system, and synchronously analyze and process the sunroof noise signal set and the sunroof noise image set based on the dual-channel acoustic data processing system to obtain a sunroof noise multi-dimensional feature set and a sunroof noise spatial feature set; a fusion evaluation module, which is used to construct a sunroof quiet and noisy detection task set, and map the sunroof noise multi-dimensional feature set to the sunroof noise spatial feature set based on the sunroof quiet and noisy detection task set for fusion evaluation, and generate an automobile sunroof quiet and noisy detection report.

[0009] The intelligent detection method and system for the dynamic and static noise of automotive sunroofs integrating acoustic imaging proposed in this application first obtain the internal space structure information of the target vehicle, determine the optimal installation position based on the analysis of the layout points of the acoustic imager, and collect the noise data during the opening and closing process of the automotive sunroof in real time to obtain the sunroof noise signal set and image set. A dual-channel for acoustic data processing is built to synchronously analyze the noise signal and the image, and extract the multi-dimensional feature set and spatial feature set of the sunroof noise. A task set for the dynamic and static noise detection of the sunroof is constructed, and the multi-dimensional feature set is mapped to the spatial feature set for fusion evaluation. Finally, a detection report for the dynamic and static noise of the automotive sunroof is generated, realizing the accurate detection and quantitative analysis of dynamic noise. Through the optimization of the layout of the acoustic imager and dual-channel data processing, the real-time spatial detection and quantitative evaluation of dynamic noise during the opening and closing process of the automotive sunroof are realized, achieving the technical effects of improving the detection accuracy and efficiency. Brief Description of the Drawings

[0010] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0011] Figure 1 It is a schematic flowchart of the intelligent detection method for the dynamic and static noise of automotive sunroofs integrating acoustic imaging provided by the embodiments of the present application;

[0012] Figure 2 It is a schematic structural diagram of the intelligent detection system for the dynamic and static noise of automotive sunroofs integrating acoustic imaging provided by the embodiments of the present application.

[0013] Description of the reference numerals: Layout point analysis module 10, real-time dynamic acquisition module 20, feature set acquisition module 30, fusion evaluation module 40. Detailed Embodiments

[0014] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specifically illustrates the detailed embodiments of this application.

[0015] In order to make the purpose, technical solutions and advantages of this application clearer, the following will further describe this application in detail with reference to the drawings. The described embodiments should not be regarded as limitations of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0016] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0017] The embodiments of this application provide an intelligent detection method for the static and dynamic noise of a car sunroof integrating acoustic imaging, as Figure 1 shown, the method includes:

[0018] Step S100, obtain the internal space structure information of the target vehicle and the acoustic imager to be applied, and based on the internal space structure information, perform layout point analysis on the acoustic imager to be applied to determine the layout point information of the acoustic imager. Specifically, to determine the layout point information of the acoustic imager in the target vehicle, it is necessary to first collect basic information, measure on-site with measuring tools and combine with technical documents to master the internal space structure of the vehicle, and at the same time investigate the parameters and performance of the imager. Then clarify the detection target and extract acoustic detection influencing factors such as the coverage range, overlapping area, measurement accuracy, and sensitivity. Subsequently, use modeling software to construct an internal space model of the vehicle. After verification and calibration, perform acoustic analysis and marking on it, divide the monitoring area, and plan points within the area with the influencing factors and device attributes as constraints to generate an optional layout point set. Finally, use finite element simulation technology to simulate the noise propagation, determine the noise source capture effectiveness parameters, and through an iterative optimization algorithm, optimize the initial point information based on this parameter until the parameter reaches the optimal standard to determine the final layout point information of the acoustic imager, covering the precise coordinates, orientation, and the positional relationship with surrounding components, and record the optimized parameters.

[0019] In a possible implementation, obtain the internal space structure information of the target vehicle and the acoustic imager to be applied, perform a layout point analysis on the acoustic imager to be applied based on the internal space structure information, and determine the acoustic imager layout point information. Step S100 further includes step S110, obtain the quiet and noisy detection target of the automobile sunroof, extract the acoustic influence factors based on the quiet and noisy detection target of the automobile sunroof, and determine the acoustic detection influence factor set. The acoustic detection influence factor set includes the coverage range, the overlapping area, the measurement accuracy, and the sensitivity. Specifically, to achieve accurate quiet and noisy detection of the automobile sunroof, the detection target needs to be clarified first. By communicating with automobile manufacturers, testing institutions, component suppliers, and research teams, determine the detection content, such as identifying types of mechanical noise, wind noise, air leakage noise, etc., quantifying the noise intensity, positioning, and frequency detection accuracy, and clarifying the goals for design optimization, quality control, and after-sales service. Based on this, extract the acoustic influence factors. When determining the coverage range, comprehensively cover the sunroof and the surrounding potential noise source areas, and consider different working conditions; when multiple devices are used for detection, set a reasonable overlapping area ratio to improve the accuracy of noise source positioning; based on the detection target and combined with environmental factors, determine the noise intensity, source positioning, and frequency measurement accuracy; adopt high-sensitivity sensors and optimized circuits, etc., to balance the sensitivity and the dynamic range to meet the needs of weak noise detection. Finally, construct an acoustic detection influence factor set including the coverage range, the overlapping area, the measurement accuracy, and the sensitivity.

[0020] Step S120, generate a vehicle internal space model according to the internal space structure information, and at the same time obtain the device attribute information of the acoustic imager to be applied. Specifically, in the quiet and noisy detection scheme of the automobile sunroof, generating a vehicle internal space model and obtaining the device attribute information of the acoustic imager are important preliminary tasks. First, collect the internal space structure information, measure the length, width, height of the vehicle and the position and size of each component on-site, disassemble and analyze the structural materials of the roof, doors, etc., and consult technical documents to obtain acoustic design parameters. Then use professional software such as 3ds_Max and SolidWorks to construct the model, create a framework based on the measurement information, and set the material attributes and acoustic parameters. After the preliminary construction is completed, compare and test with the actual vehicle and the acoustic measurement equipment, and adjust the model according to the measurement data to ensure that it accurately reflects the in-vehicle acoustic environment. At the same time, obtain the device attribute information of the acoustic imager, study the technical manual to understand parameters such as the microphone array layout, frequency response range, etc., as well as the imaging principle and technical characteristics, and consult third-party evaluation reports and actual application cases to comprehensively master its performance in different scenarios, providing strong support for subsequent detection work.

[0021] Step S130: Based on the set of acoustic detection influencing factors and the device attribute information, conduct a preliminary point layout planning for the vehicle interior space model to obtain the initial layout point information. Specifically, after completing the construction of the vehicle interior space model and obtaining relevant information, it is necessary to plan the points based on the set of acoustic detection influencing factors and the device attribute information. First, integrate and analyze the two to clarify the relationships between factors such as the coverage range and overlapping areas and the attributes of the imager's effective detection distance, resolution, etc., and determine the coverage area and overlapping ratio according to the imager's performance. Then, conduct an acoustic analysis of the vehicle interior space model, define the skylight area and its surroundings, analyze the internal obstacles and acoustic wave propagation characteristics, and accordingly divide the key and extended monitoring areas. After that, within the monitoring areas, search for points with the influencing factors and device attributes as constraints to generate an optional layout point set containing three-dimensional coordinates, orientations, and the surrounding position relationships. Finally, set evaluation indicators such as noise source coverage and positioning accuracy, comprehensively evaluate the points according to the indicator weights, sort and screen them according to the scores, and determine the initial layout point information with detailed information, laying a foundation for subsequent acoustic detection.

[0022] Step S140: Conduct simulation and layout optimization on the initial layout point information to determine the acoustic imager layout point information. Specifically, after obtaining the initial layout point information, in order to achieve the best detection effect, it is necessary to conduct simulation and layout optimization on it to determine the final points. First, select professional simulation software such as COMSOL_Multiphysics, import the vehicle interior space model and the initial layout point information, and set simulation parameters covering the frequency range, noise source characteristics, etc. Then, run the software to simulate the noise propagation and analyze the detection effects of the imager at each initial point, such as positioning accuracy and image quality. Determine the optimization direction based on the detection effects, select a suitable algorithm such as the genetic algorithm and set the key parameters. Then, use the optimization algorithm to adjust the points, and through multiple iterations and simulation verification after each iteration, make the algorithm converge to the point combination with the best detection effect. Finally, comprehensively evaluate the optimization plan considering multiple factors, select the best plan, and record and output in detail the final acoustic imager layout point information containing three-dimensional coordinates, orientations, and the relative position relationships with key components, providing guarantee for the precise detection of the dynamic and static noise of the automotive skylight.

[0023] In a possible implementation, based on the set of acoustic detection influencing factors and the device attribute information, a preliminary point layout plan is carried out for the vehicle interior space model to obtain the initial layout point information. Step S130 further includes step S131, where an acoustic analysis and marking is performed on the vehicle interior space model to determine the skylight area information, the set of internal obstacles, and the acoustic wave propagation and reflection characteristics. Specifically, the acoustic analysis and marking of the vehicle interior space model is an important basis for the acoustic detection scheme. First, in a high-precision model, professional software is used to accurately define the geometry and dimensions of the skylight, such as the length and width of a rectangular skylight, the radius and arc length of an arc-shaped skylight, etc., and its position in the vehicle is determined based on the three-dimensional coordinate system. At the same time, the movement trajectories of the skylight opening and closing and the position information in different states are clarified. Next, the model is scanned comprehensively to identify internal obstacles such as seats and the center console, and classified and marked using a layer management tool, and the key characteristics such as the length, width, height, and inclination angle of each obstacle are recorded in detail to build an information database. Finally, by referring to the acoustic characteristic data to obtain the acoustic parameters of different materials, such as the reflection coefficient of metal, the sound absorption coefficient of soft materials, the transmittance and reflectance of glass, etc., with the help of professional acoustic simulation software, a simulation scenario is set up to observe the propagation path, reflection angle, attenuation degree of the acoustic wave in the vehicle, and the scattering situation around the obstacles, so as to comprehensively master the acoustic wave propagation and reflection characteristics and provide rich and accurate data support for the subsequent work.

[0024] Step S132, based on the skylight area information, the set of internal obstacles, and the acoustic wave propagation and reflection characteristics, perform a monitoring area division to obtain the acoustic monitoring area information. Specifically, after clarifying the relevant information, dividing the monitoring area and obtaining the acoustic monitoring area information is extremely crucial for the quiet operation detection of the automotive skylight. First, with the skylight area as the core, determine the key monitoring areas, covering the 5-10 cm extensions on both sides of the skylight guide rail and the entire sealing strip area, and at the same time consider the 20-30 cm roof area around the skylight when it is opened, because it is prone to generate aerodynamic noise due to the influence of air flow. Next, combine the internal obstacles and acoustic wave characteristics to determine the extended monitoring areas, and set areas around obstacles such as 15-20 cm extensions around the seats, 10-15 cm around the center console and 20-30 cm behind, because the acoustic wave is disturbed here; also include the areas 20 cm before and after and 15 cm on both the left and right of the rear seats and the area 30-50 cm from the skylight edge on the roof, because they are affected by the propagation and diffusion of the acoustic wave. Finally, integrate to form the acoustic monitoring area information, use different colors or symbols in the model to identify the key and extended areas, accurately define the boundary range, record the main monitoring targets of each area and the expected noise type and intensity range, and provide a solid foundation and clear guidance for the subsequent detection work.

[0025] Step S133: Using the set of acoustic detection influencing factors and the device attribute information as constraint information, conduct a preliminary site planning within the acoustic monitoring area information to obtain a set of optional installation sites. Specifically, after mastering the set of acoustic detection influencing factors, device attribute information, and acoustic monitoring area information, it is necessary to conduct a preliminary site planning to obtain a set of optional installation sites. First, clarify the constraint information. In the set of acoustic detection influencing factors, the coverage range should comprehensively cover potential noise sources in the monitoring area, and a 20%-30% overlapping area is set to improve the noise source localization accuracy. The measurement accuracy requires that the noise intensity, source localization, and frequency measurement within a specific frequency reach a certain precision, and the sensitivity should be able to capture weak noises. In terms of device attributes, the microphone array layout, frequency response range, resolution, detection sensitivity, and effective detection distance and angle range, etc., all affect the performance of the imager. Then, search for sites within the acoustic monitoring area and screen according to the effective detection range of the imager to ensure coverage of the monitoring area and its boundaries; at the junction of adjacent monitoring areas, adjust the sites so that the monitoring ranges of the imagers overlap by 20%-30%; in areas with high accuracy and sensitivity requirements, select sites that can give full play to the advantages of the imager. Finally, for the generated set of optional installation sites, record the three-dimensional coordinates, orientations, and relative position relationships with surrounding components, laying a solid foundation for subsequent work.

[0026] Step S134: Set the imager quantity threshold, and based on the imager quantity threshold, optimize the layout effect of the set of optional installation sites to obtain the initial installation site information. Specifically, after obtaining the set of optional installation sites, it is necessary to set the imager quantity threshold and optimize the layout effect accordingly to determine the initial installation site information. When setting the threshold, comprehensively consider the project's requirements for detection accuracy and comprehensiveness, as well as the cost limitations of purchasing, maintaining imagers, and data processing. At the same time, refer to the detection effects of different numbers of imagers in the previous simulation experiments and the empirical data of past similar projects. After determining the threshold, establish an evaluation index system including the noise source coverage effect, positioning accuracy, and matching degree with device performance, and assign weights to each index according to the key requirements of the project. For example, if positioning is emphasized, increase the weight of the positioning accuracy index. Then, calculate the comprehensive score of each site combination according to the formula. On the premise of meeting the imager quantity threshold, sort the site combinations according to the scores, select the ones with high scores for in-depth analysis and comparison, and determine the best combination. Finally, record the initial installation site information in detail, including the three-dimensional coordinates, orientations of the imagers, and relative position relationships with key components, providing a reliable basis for subsequent work.

[0027] In a possible implementation, the initial layout point information is subjected to simulation and layout optimization to determine the layout point information of the acoustic imager. Step S140 further includes step S141 of importing and running a simulation on the vehicle interior space model and the initial layout point information using finite element simulation technology to establish a vehicle acoustic simulation model. Specifically, to establish a vehicle acoustic simulation model using finite element simulation technology, it is necessary to first evaluate and select from numerous software, such as COMSOL Multiphysics and LMS_Virtual.Lab, and select according to project requirements and team capabilities. Then, the vehicle interior space model is imported after format conversion and preprocessing, and mechanical and acoustic parameters are set for each component according to the actual material. At the same time, the coordinates of the initial layout point information and the device parameters of the acoustic imager are accurately entered to determine the interaction relationship between the imager and the model. Subsequently, the model is meshed, with fine meshes set in key areas, an appropriate element type is selected, and parameters such as the acoustic analysis type and solver are set before running the simulation. After completion, the simulation results are compared and verified with theoretical or actual test data. If there are deviations, the model is adjusted, and after multiple adjustments, it is ensured that the model can accurately reflect the vehicle interior acoustic environment.

[0028] Step S142, perform a simulation of the opening and closing of the automotive sunroof and monitor the noise propagation using the vehicle acoustic simulation model to obtain noise propagation simulation information. Specifically, to carry out a simulation of the opening and closing of the automotive sunroof and monitor the noise propagation using the vehicle acoustic simulation model to obtain noise propagation simulation information, the following steps are required. First, check and optimize the model to ensure that the geometric shapes, dimensions, positions, and material acoustic parameters of each component are accurate. Subsequently, for the sunroof opening and closing simulation, accurately set the motion parameters of the translating or rotating sunroof, such as speed, stroke, angle, etc., and set the noise source position, intensity, and type. After the parameter setting is completed, start the simulation, reasonably set the time step and total duration, and during the simulation, the software calculates phenomena such as the propagation of sound waves according to acoustic principles. At the same time, reasonably arrange monitoring points inside the vehicle, covering the periphery of the sunroof, areas where people are easily perceptible, and key parts, and collect and record data such as sound pressure level, frequency components, and phase in real time. Finally, use data processing software to organize the data, convert it into a visual chart, and based on an in-depth analysis of the characteristics such as the propagation attenuation, reflection, and scattering of noise between different materials and the propagation differences under different working conditions, provide a basis for vehicle acoustic optimization.

[0029] Step S143: Based on the noise propagation simulation information, evaluate the effectiveness of the initial layout point information and determine the noise source capture effectiveness parameter. Specifically, after obtaining the noise propagation simulation information, evaluating the effectiveness of the initial layout point information and determining the noise source capture effectiveness parameter are of great significance for optimizing the layout of the acoustic imager. First, establish an evaluation index system. By comparing the actual position of the simulated noise source with the estimated position of the imager, calculate the positioning error using the Euclidean distance formula, and use the statistical mean and standard deviation to measure the positioning accuracy. Calculate the error between the measured value and the simulated noise intensity at the monitoring point using the root mean square error formula to evaluate the signal intensity detection accuracy. With the help of an image recognition algorithm, calculate the edge clarity and contrast of the noise source area, and construct an acoustic imaging clarity index. Then, extract relevant data from the simulation information and organize it, and calculate the effectiveness parameter according to the index system. Finally, deeply analyze the parameter, compare the performance of different points, find the gap with the ideal value. If the index of a certain point is not good, analyze the reasons such as being far from the noise source or having a complex acoustic environment around, and propose improvement measures such as adjusting the position or optimizing the parameter, so as to improve the effectiveness of the initial layout point and lay a solid foundation for determining the accurate layout point.

[0030] Step S144: Based on the noise source capture effectiveness parameter, perform iterative simulation optimization on the initial layout point information through the vehicle acoustic simulation model to determine the layout point information of the acoustic imager. Specifically, to determine the accurate layout point of the acoustic imager, with the help of the vehicle acoustic simulation model, perform iterative optimization on the initial layout point information based on the noise source capture effectiveness parameter. First, clarify the goal of improving the noise source capture effectiveness, such as reducing the positioning error and root mean square error, and improving the imaging clarity, etc. At the same time, sort out the constraint conditions such as the vehicle space limitation and the upper limit of the number of imagers. After analysis, due to the complexity of the model and the need for multi-parameter optimization, choose the genetic algorithm as the main one and combine it with the local search algorithm to improve the performance. Then, generate an initial population containing 50 point combinations according to the initial layout information using the genetic algorithm, ensuring compliance with the constraint conditions. Import each combination into the model, obtain the noise propagation information through simulation, calculate the fitness value according to the effectiveness parameter, and then perform genetic operations such as selection, crossover, and mutation on the population to generate a new population. Repeat the operation until the termination conditions such as the maximum number of iterations or the fitness value change threshold are met, and determine the optimal point combination. Finally, verify it with actual vehicle testing or high-precision physical model simulation. If it meets the standard, determine it as the final layout point. Otherwise, analyze the reasons, improve the model, adjust the algorithm, and then optimize it again until the requirements are met.

[0031] Step S200: Install the acoustic imager to be applied according to the layout point information of the acoustic imager, and start the installed acoustic imager to be applied to collect the noise data in real time and dynamically during the opening and closing process of the car sunroof, so as to obtain the sunroof noise signal set and the sunroof noise image set. Specifically, when using the acoustic imager to collect the noise data of the car sunroof opening and closing, it is necessary to do the preparations before installation first, check the acoustic imager, accessories and tools, park the vehicle in a quiet place, turn off the irrelevant equipment and clean the interior. Then, according to the layout point information, accurately position with a tape measure, etc., and firmly install the imager through brackets, screws and shock pads. After installation, connect the device to the data acquisition terminal, turn on the power supply, and set parameters such as sampling frequency, image resolution, sensitivity and storage path in the supporting software according to the detection requirements. Then, test the operation status of the sunroof, confirm that the imager is working properly, operate the sunroof according to the predetermined plan, and the imager collects the noise signals and images in real time to generate a noise signal set and an image set. Finally, preliminarily check the data, classify and organize it according to the test conditions, and store it in a reliable device to provide accurate data support for subsequent analysis.

[0032] Step S300: Build a dual-channel for acoustic data processing, and synchronously analyze and process the sunroof noise signal set and the sunroof noise image set based on the dual-channel for acoustic data processing to obtain the sunroof noise multi-dimensional feature set and the sunroof noise spatial feature set. Specifically, to build a dual-channel for acoustic data processing, it is necessary to first select a suitable network. For the acoustic signal processing network, select RNN or LSTM to process the sunroof noise signal, and adjust the received signal format of the input layer during adaptation; for the acoustic image processing network, select CNN architectures such as AlexNet, VGG or ResNet, and adapt the input size and number of channels. Use TensorFlow or PyTorch to build an integrated framework, define parallel sub-models and set the data flow direction. When processing the sunroof noise signal set, first perform preprocessing such as denoising, normalization and feature engineering, and then input it into the network. The LSTM and other layers extract the time series features, and the fully connected layer integrates and outputs the multi-dimensional feature set. When processing the sunroof noise image set, first perform preprocessing such as image enhancement, filtering, normalization and possible segmentation, and then input it into the network. The convolutional layer and the pooling layer extract the features, and the fully connected layer outputs the spatial feature set. Finally, splice and integrate the multi-dimensional and spatial feature sets, and verify by inputting into the classification model and combining the actual situation to ensure that the feature set is accurate and reliable, providing strong support for the study of car sunroof noise.

[0033] In a possible implementation, an acoustic data processing dual-channel is built, and based on the acoustic data processing dual-channel, the skylight noise signal set and the skylight noise image set are synchronously analyzed and processed to obtain a skylight noise multi-dimensional feature set and a skylight noise spatial feature set. Step S300 further includes step S310, which mines and collects the skylight historical noise signal set and the skylight historical noise image set, and performs filtering preprocessing on the skylight historical noise signal set and the skylight historical noise image set to obtain an available skylight noise signal set and an available skylight noise image set. Specifically, to obtain an available skylight noise data set, first collect skylight historical noise data from multiple channels such as automobile manufacturers, laboratory simulations, and road tests, and sort and summarize them according to sources, time, working conditions, etc., and add detailed annotations. Then, screen out abnormal signals and images and label data features. Subsequently, for the noise signal set, select low-pass, high-pass, or band-pass filtering algorithms according to the noise characteristics to remove interference; for the noise image set, use Gaussian and median filtering algorithms to smooth the images and remove noise points. After the preprocessing is completed, verify the effect by comparing spectrograms, time-domain waveforms, and using indicators such as PSNR and SSIM. If it is not ideal, adjust the algorithm and reprocess. Finally, classify and organize the data according to vehicle models, skylight types, etc., add metadata, and store it in a reliable device to provide high-quality data support for subsequent analysis.

[0034] Step S320, respectively perform noise feature annotation training on the available skylight noise signal set and the available skylight noise image set to generate an acoustic signal processing network and an acoustic image processing network. Specifically, to generate an acoustic signal processing and an acoustic image processing network, noise feature annotation training needs to be carried out on the available skylight noise signal set and the image set respectively. First, clean and preprocess the data in the early stage, remove outliers in the signal set and images with poor quality in the image set, and then determine the annotation rules, such as the frequency, amplitude, and time-domain characteristics of the signal, and the annotation content such as the position, shape, and visual intensity of the noise source in the image. When training the acoustic signal processing network, professionals annotate the signal set according to the rules using signal analysis software, select appropriate neural network architectures such as RNN, LSTM, and CNN, divide the annotation set according to a certain proportion and input it into the network, set parameters such as the learning rate, and train using the backpropagation algorithm. Use the validation set to prevent overfitting and the test set to evaluate the network performance. In terms of training the acoustic image processing network, professionals use annotation tools to annotate the image set according to the rules, select CNN architectures such as AlexNet, VGG, and ResNet, divide the annotation set and input it for training, set parameters such as the convolutional kernel size, and train using the cross-entropy loss function and the backpropagation algorithm. Monitor the network with the validation set and evaluate the network with the test set. Finally, two networks are successfully generated, laying a solid foundation for subsequent skylight noise analysis and processing.

[0035] Step S330: Integrate the acoustic signal processing network and the acoustic image processing network in parallel to build the dual-channel acoustic data processing system. Specifically, to build the dual-channel acoustic data processing system, it is necessary to first sort out the characteristics of the acoustic signal processing and image processing networks, clarify the types of noise, frequency responses, image feature recognition capabilities, and input requirements that each is good at processing. At the same time, evaluate the performance of both, calculate the accuracy rate, recall rate of the acoustic signal processing network, and the mAP value of the acoustic image processing network. Then, design a unified input interface to convert the acoustic signal into a similar image format, adjust the image size and number of channels, and build a compatible output interface to integrate different output information with a structure. Subsequently, select TensorFlow or PyTorch to build an integration framework, define parallel sub-models and control the data flow direction, and reasonably allocate computing resources. Finally, debug the function by inputting diverse acoustic data, identify the reasons for unexpected results, and optimize from two aspects: computational efficiency (such as model pruning, quantization) and accuracy (such as adjusting training parameters, increasing the amount of data), successfully building a dual-channel foundation for efficient acoustic data processing.

[0036] In a possible implementation, perform noise feature annotation training on the available skylight noise signal set and the available skylight noise image set respectively to generate an acoustic signal processing network and an acoustic image processing network. Step S320 further includes step S321: perform noise feature annotation on the available skylight noise signal set and the available skylight noise image set respectively to obtain a skylight noise signal sample set and a skylight noise image sample set. Specifically, to obtain the skylight noise signal sample set and the image sample set, it is necessary to carry out noise feature annotation work on the available skylight noise signal set and the image set respectively. For the noise signal set, form an acoustic professional annotation team, equip with signal analysis software such as MATLAB and LabVIEW and high-performance computers, and according to rules such as frequency range, amplitude, and time-domain characteristics, the annotators operate the software to measure and record the signal characteristics, and after review and verification, organize them into a sample set. For the noise image set, organize annotators familiar with image processing, select annotation tools such as LabelImg and configure them reasonably. According to rules such as the position, shape, and visual intensity of the noise source, the annotators box, describe, and quantify the noise information in the tool, and after quality inspection and correction, form an image sample set, laying a solid foundation for subsequent deep learning model training and acoustic analysis.

[0037] Step S322: Use a deep neural network to perform feature recognition training on the skylight noise signal sample set to generate an initial signal processing network. Specifically, to generate an initial signal processing network, first, according to the characteristics of the skylight noise signal such as the time series, refer to successful cases in the field of acoustic signal processing, and select a suitable deep neural network architecture such as RNN and its variants or MLP. Then, perform normalization processing on the skylight noise signal sample set, enhance the data by adding noise, adjusting the amplitude and time domain scale, etc., and divide it into a training set, a validation set, and a test set according to the ratios of 70%-80%, 10%-15%, and 10%-15%. After that, determine the number of input layer nodes according to the signal feature dimension, try different numbers of layers and node settings for the hidden layer structure through experiments, select a suitable activation function such as ReLU, and determine the number of output layer nodes and the activation function according to the task type. During training, select an optimization algorithm such as Adam, set the learning rate, define a loss function such as cross-entropy or mean squared error according to the task, input the training set in batches for iterative training, and use the validation set to monitor the performance. After training is completed, evaluate the model using the test set. If the performance is not good, analyze the reasons in aspects such as the network architecture, data preprocessing, and hyperparameters, adjust the architecture and parameters, and retrain until an initial signal processing network that meets the requirements is generated.

[0038] Step S323: Use a convolutional neural network to perform feature recognition training on the skylight noise image sample set to generate an initial image processing network. Specifically, to generate an initial signal processing network, first conduct a secondary review of the skylight noise signal sample set, correct mislabeled data, and process missing data, and build a computing environment with TensorFlow or PyTorch as the framework and configured with GPU acceleration. According to the characteristics of the noise signal and the task requirements, select an architecture such as LSTM, GRU, or MLP, determine the number of layers and nodes through experiments, and select an activation function such as ReLU. Normalize the sample set, extract and filter time domain and frequency domain features, and divide it into training, validation, and test sets according to the ratios of 70%-80%, 10%-15%, and 10%-15%. During training, select an optimization algorithm such as Adam, set hyperparameters such as the learning rate, batch size, and number of iterations, define a loss function such as cross-entropy or mean squared error according to the task, and use the validation set to monitor the performance. After training is completed, evaluate using the test set. If the performance meets the standard, apply it; otherwise, analyze the reasons for overfitting or underfitting, adjust the network complexity, hyperparameters, etc., retrain and evaluate until an initial image processing network that meets the requirements is generated.

[0039] Step S324: Perform cross-validation tuning on the initial signal processing network and the initial image processing network respectively to generate the acoustic signal processing network and the acoustic image processing network. Specifically, to generate the acoustic signal and image processing network, cross-validation tuning needs to be performed on the initial network. In the preparation stage, the signal sample set and the image sample set are divided using the K-fold (K is usually 5 or 10) cross-validation method. Determine the evaluation metrics according to the task characteristics. For example, the signal network uses accuracy, recall rate, and F1 value to evaluate the classification performance, and the image network uses mAP to evaluate the object detection performance. When tuning the initial signal processing network, cycle through training with 4 subsets and validating with 1 subset, analyze the K group of metric values. If there is overfitting, add a regularization term or Dropout. If there is underfitting, increase the network complexity and adjust the hyperparameters, and determine the final network according to the comprehensive performance. For the initial image processing network, perform the same operations. If the mAP value is not good, adjust the convolution kernel size, prune, or perform data augmentation, and determine the final network according to the results. Finally, comprehensively evaluate the two networks, jointly test the collaborative performance, and apply them to the actual acoustic data processing task after meeting the standards.

[0040] Step S400: Construct a skylight static and dynamic noise detection task set, and map the skylight noise multi-dimensional feature set to the skylight noise spatial feature set based on the skylight static and dynamic noise detection task set for fusion evaluation to generate an automobile skylight static and dynamic noise detection report. Specifically, to construct a skylight static and dynamic noise detection task set and generate a detection report, it is necessary to first clarify the detection task types such as static and dynamic noise caused by normal opening, specific working conditions, and faults, collect data from the manufacturer's test database, laboratory simulation, and road tests, and label and organize them into a standard format according to the task type, noise intensity, etc. Then, analyze the relationship between the multi-dimensional and spatial feature sets, establish a mapping relationship through regression analysis, etc., select methods such as weighted fusion or neural network fusion, perform fusion evaluation on the feature sets according to the task set, and judge the static and dynamic noise abnormality according to the threshold. Finally, design a report framework including an introduction, an overview of the task set, etc., fill in the evaluation data, analyze with charts, and generate a comprehensive and accurate automobile skylight static and dynamic noise detection report that can provide valuable information for relevant personnel after expert review and improvement.

[0041] In a possible implementation, a skylight dynamic and static noise detection task set is constructed. Based on the skylight dynamic and static noise detection task set, the skylight noise multi-dimensional feature set is mapped to the skylight noise spatial feature set for fusion evaluation to generate an automobile skylight dynamic and static noise detection report. Step S400 further includes step S410 of constructing a skylight acoustic distribution space according to the skylight noise spatial feature set. Specifically, to construct a skylight acoustic distribution space, first, data of the skylight noise spatial feature set from multiple sources such as automobile manufacturer tests, laboratory simulations, and road tests are widely collected. After sorting out and removing defects, communicate with relevant parties to clarify requirements such as construction objectives, accuracy, and dimensions. Then, determine the three-dimensional or two-dimensional space dimension according to the features and requirements, select the Cartesian coordinate system, establish a coordinate system with a certain fixed point of the skylight as the origin, and divide the space into appropriately sized grids according to the accuracy. Subsequently, formulate rules to map features such as the position and intensity of the noise source to the grid cells, fill and quantify them so that each cell has a clear acoustic feature value, and visually present it with visualization software. Finally, select the comparison or simulation method for verification, analyze the reasons for errors and correct them, and continuously optimize and update according to technological development and demand changes, so as to construct a practical skylight acoustic distribution space.

[0042] Step S420 is to map the skylight noise multi-dimensional feature set to the skylight acoustic distribution space according to the spatial distribution information for feature matching and fusion to obtain a skylight noise fusion feature set. Specifically, to obtain a skylight noise fusion feature set, first, review the data of the multi-dimensional feature set and the acoustic distribution space, preprocess the numerical features, and clarify the mapping rules and matching criteria according to the physical characteristics and requirements. Then, according to the rules, locate the multi-dimensional features in the acoustic distribution space region according to the noise source position, calculate the matching degree with the standard and screen the feature pairs. Subsequently, select fusion methods such as weighted average, PCA, or deep learning according to the noise characteristics, operate on the screened feature pairs, organize the fusion features and store them as a set, and add information. Finally, determine verification indicators such as accuracy to evaluate the fusion feature set. If there are problems, analyze reasons such as the mapping rules and optimize them accordingly to complete the construction of the feature set.

[0043] Step S430 is to perform noise analysis and evaluation on the skylight noise fusion feature set in sequence based on the skylight dynamic and static noise detection task set to generate an automobile skylight dynamic and static noise detection report. Specifically, to generate an automobile skylight dynamic and static noise detection report, first, clarify the details of the skylight dynamic and static noise detection task set and the corresponding evaluation criteria, and adapt and preprocess the data of the skylight noise fusion feature set. Subsequently, according to the order of the task set, extract relevant features for each task, and use statistical analysis and machine learning algorithms to compare with the standard for evaluation, and record in detail the actual values of the tasks, comparison situations, evaluation conclusions and other results. Finally, design a report framework covering parts such as introduction and task overview, fill in the evaluation data and display it with charts, and after expert review and improvement, correct errors and supplement information to form a high-quality detection report, providing valuable reference for relevant personnel.

[0044] In a possible implementation, the skylight noise multi-dimensional feature set is mapped to the skylight acoustic distribution space according to the spatial distribution information for feature matching and fusion, and a skylight noise fusion feature set is obtained. Step S420 further includes step S421 of mapping the skylight noise multi-dimensional feature set to the skylight acoustic distribution space according to the spatial distribution information for feature matching to obtain a skylight noise matching feature set. Specifically, first, analyze the composition of the skylight noise multi-dimensional feature set (including time domain, frequency domain, energy and other features) and the skylight acoustic distribution space, unify and preprocess the data, and remove outliers and normalize the numerical features. Then, formulate mapping rules. Based on the noise source position, infer the corresponding spatial region according to coordinates or signal attenuation; according to the frequency characteristics, map the high-frequency noise features to a small area near the noise source, and map the low-frequency noise features to a larger area; comprehensively map in combination with other features such as energy, for example, a higher energy corresponds to a larger area. Finally, extract the feature values according to the rules, calculate the matching degree with the spatial region by methods such as Euclidean distance, set a threshold for screening, and organize the successfully matched information into a skylight noise matching feature set.

[0045] Step S422 is to perform weighted fusion on each matching signal feature and spatial feature in the skylight noise matching feature set to obtain the skylight noise fusion feature set. Specifically, deeply analyze the roles of the matching signal and spatial features in describing the skylight noise characteristics, and determine the weights of each feature according to the actual application requirements and the experience of acoustic experts. For example, when focusing on the judgment of noise intensity, the amplitude feature weight is relatively high. Subsequently, perform weighted summation on each group of matching signal features (such as amplitude, frequency, energy, etc.) in the matching feature set according to the weights, and perform the same operation on the spatial features (such as noise source position coordinates, regional area, shape parameters, etc., and the coordinates are normalized first). Then, splice the weighted signal and spatial feature values into a fusion feature vector, and finally organize all the fusion feature vectors in order into a set. This set combines the two types of feature information and can provide strong support for subsequent tasks such as noise analysis.

[0046] In a possible implementation, based on the skylight static and dynamic noise detection task set, noise analysis and evaluation are sequentially performed on the skylight noise fusion feature set to generate a vehicle skylight static and dynamic noise detection report. Step S430 further includes step S431, where noise analysis and evaluation are sequentially performed on the skylight noise fusion feature set based on each detection task in the skylight static and dynamic noise detection task set to obtain a skylight noise detection task information set. Specifically, comprehensively sort out the skylight static and dynamic noise detection task set, clarify the conditions and objectives of each task, and at the same time be familiar with the noise fusion feature set. Check and adapt the data format, preprocess the data, remove outliers, and normalize the features. Then, in the order of the task set, extract relevant data from the fusion feature set for each task, compare it with the preset standard, and comprehensively evaluate using statistical analysis and machine learning algorithms. Finally, design a structured table to record in detail the evaluation information of each task, including task name, actual feature value, standard range, conclusion, abnormal type, and speculation on the reason, etc., and summarize the table to form an information set, providing key data for subsequent analysis and report generation.

[0047] Step S432, record and integrate the skylight noise detection task information set to generate the vehicle skylight static and dynamic noise detection report. Specifically, when generating the vehicle skylight static and dynamic noise detection report, first build a framework including core sections such as introduction and task details according to the detection requirements and specifications, and plan the internal structure of each section. Then, extract data such as task name and actual feature value from the skylight noise detection task information set, organize it according to the framework requirements, and at the same time write the text description of each section. Subsequently, invite acoustic experts and automotive engineers to review and proofread, check the accuracy, integrity, and logic, make visual charts such as bar charts and line charts and insert them into the report. Finally, improve the report according to the review opinions and chart situation, adjust the content order and structure, optimize the coordination between the charts and the text, and generate a final report that can provide strong reference for relevant parties.

[0048] In the embodiment of the present application, by obtaining the internal space structure information of the target vehicle, determining the optimal installation position based on the analysis of the acoustic imager layout points, and real-time collecting the noise data during the opening and closing process of the vehicle skylight, a skylight noise signal set and an image set are obtained; an acoustic data processing dual channel is built to synchronously analyze the noise signal and the image, and a skylight noise multi-dimensional feature set and a spatial feature set are extracted; a skylight static and dynamic noise detection task set is constructed, and the multi-dimensional feature set is mapped to the spatial feature set for fusion evaluation, and finally a vehicle skylight static and dynamic noise detection report is generated, realizing the accurate detection and quantitative analysis of dynamic noise. Through the optimization of the acoustic imager layout and dual-channel data processing, the real-time spatial detection and quantitative evaluation of dynamic noise during the opening and closing process of the vehicle skylight are realized, achieving the technical effect of improving the detection accuracy and efficiency.

[0049] In the above text, with reference to Figure 1A method for intelligent detection of dynamic and static noise of automotive sunroofs integrating acoustic imaging according to an embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 Describe an intelligent detection system for dynamic and static noise of automotive sunroofs integrating acoustic imaging according to an embodiment of the present invention.

[0050] The intelligent detection system for dynamic and static noise of automotive sunroofs integrating acoustic imaging according to an embodiment of the present invention is used to solve the technical problem that the prior art cannot perform real-time, high-precision spatial detection and quantitative evaluation of dynamic noise during the opening and closing process of automotive sunroofs. Through the optimization of the layout of acoustic imagers and dual-channel data processing, real-time spatial detection and quantitative evaluation of dynamic noise during the opening and closing process of automotive sunroofs are achieved, and the technical effects of improving detection accuracy and efficiency are achieved. The intelligent detection system for dynamic and static noise of automotive sunroofs integrating acoustic imaging includes: a layout point analysis module 10, a real-time dynamic acquisition module 20, a feature set acquisition module 30, and a fusion evaluation module 40.

[0051] The layout point analysis module 10 is used to obtain the internal space structure information of the target vehicle and the acoustic imager to be applied, and based on the internal space structure information, perform layout point analysis on the acoustic imager to be applied to determine the layout point information of the acoustic imager.

[0052] The real-time dynamic acquisition module 20 is used to install the acoustic imager to be applied according to the layout point information of the acoustic imager, and start the installed acoustic imager to be applied to perform real-time dynamic acquisition of noise data during the opening and closing process of the automotive sunroof, obtaining a sunroof noise signal set and a sunroof noise image set.

[0053] The feature set acquisition module 30 is used to build a dual-channel for acoustic data processing, and based on the dual-channel for acoustic data processing, synchronously analyze and process the sunroof noise signal set and the sunroof noise image set to obtain a sunroof noise multi-dimensional feature set and a sunroof noise spatial feature set.

[0054] The fusion evaluation module 40 is used to construct a sunroof dynamic and static noise detection task set, and based on the sunroof dynamic and static noise detection task set, map the sunroof noise multi-dimensional feature set to the sunroof noise spatial feature set for fusion evaluation, generating a detection report on the dynamic and static noise of the automotive sunroof.

[0055] Next, the specific configuration of the layout point analysis module 10 will be described in detail. As described above, the internal space structure information of the target vehicle is obtained and the acoustic imager to be applied is obtained. Based on the internal space structure information, the layout point analysis of the acoustic imager to be applied is carried out to determine the acoustic imager layout point information. The layout point analysis module 10 further includes: a detection target acquisition unit, which is used to acquire the dynamic and static noise detection target of the automobile sunroof, extract the acoustic influence factors based on the dynamic and static noise detection target of the automobile sunroof, and determine the acoustic detection influence factor set, where the acoustic detection influence factor set includes the coverage range, the overlapping area, the measurement accuracy, and the sensitivity; a device attribute information acquisition unit, which is used to generate a vehicle internal space model according to the internal space structure information and simultaneously acquire the device attribute information of the acoustic imager to be applied; a point position preliminary planning unit, which is used to carry out point position preliminary planning on the vehicle internal space model based on the acoustic detection influence factor set and the device attribute information to obtain the initial layout point information; and an acoustic imager layout point information determination unit, which is used to perform simulation and layout optimization on the initial layout point information to determine the acoustic imager layout point information.

[0056] Among them, based on the acoustic detection influence factor set and the device attribute information, the point position preliminary planning is carried out on the vehicle internal space model to obtain the initial layout point information. The point position preliminary planning unit further includes: an acoustic analysis marking subunit, which is used to perform acoustic analysis marking on the vehicle internal space model to determine the sunroof area information, the internal obstacle set, and the acoustic wave propagation and reflection characteristics; a monitoring area division subunit, which is used to divide the monitoring area based on the sunroof area information, the internal obstacle set, and the acoustic wave propagation and reflection characteristics to obtain the acoustic monitoring area information; a constraint information determination subunit, which is used to use the acoustic detection influence factor set and the device attribute information as constraint information to carry out point position preliminary planning within the acoustic monitoring area information to obtain an optional layout point set; and an imager number threshold setting subunit, which is used to set the imager number threshold and optimize the layout effect of the optional layout point set based on the imager number threshold to obtain the initial layout point information.

[0057] Among them, the initial layout point information is simulated and optimized for layout to determine the layout point information of the acoustic imager. The layout point information determination unit of the acoustic imager further includes: an operation simulation subunit, which is used to import and run a simulation of the vehicle interior space model and the initial layout point information by using the finite element simulation technology to establish a vehicle acoustic simulation model; a propagation monitoring subunit, which is used to perform a simulation of the opening and closing of the automobile sunroof and monitor the noise propagation by using the vehicle acoustic simulation model to obtain noise propagation simulation information; a validity evaluation subunit, which is used to evaluate the validity of the initial layout point information based on the noise propagation simulation information to determine the noise source capture validity parameter; an iterative simulation optimization subunit, which is used to perform iterative simulation optimization of the initial layout point information based on the noise source capture validity parameter through the vehicle acoustic simulation model to determine the layout point information of the acoustic imager.

[0058] Next, the specific configuration of the feature set acquisition module 30 will be described in detail. As described above, a dual-channel acoustic data processing channel is built, and the skylight noise signal set and the skylight noise image set are analyzed and processed synchronously based on the dual-channel acoustic data processing channel to obtain a skylight noise multi-dimensional feature set and a skylight noise spatial feature set. The feature set acquisition module 30 further includes: a filtering preprocessing unit, which is used to mine and collect the skylight historical noise signal set and the skylight historical noise image set, and perform filtering preprocessing on the skylight historical noise signal set and the skylight historical noise image set to obtain an available skylight noise signal set and an available skylight noise image set; a processing network generation unit, which is used to perform noise feature annotation training on the available skylight noise signal set and the available skylight noise image set respectively to generate an acoustic signal processing network and an acoustic image processing network; a parallel integration unit, which is used to parallelly integrate the acoustic signal processing network and the acoustic image processing network to build the dual-channel acoustic data processing channel.

[0059] Among them, noise feature annotation training is respectively performed on the available skylight noise signal set and the available skylight noise image set to generate an acoustic signal processing network and an acoustic image processing network. The processing network generation unit further includes: a sample set acquisition subunit, which is used to perform noise feature annotation on the available skylight noise signal set and the available skylight noise image set respectively to obtain a skylight noise signal sample set and a skylight noise image sample set; an initial signal processing network generation subunit, which is used to perform feature recognition training on the skylight noise signal sample set using a deep neural network to generate an initial signal processing network; an initial image processing network generation subunit, which is used to perform feature recognition training on the skylight noise image sample set using a convolutional neural network to generate an initial image processing network; a cross-validation tuning subunit, which is used to perform cross-validation tuning on the initial signal processing network and the initial image processing network respectively to generate the acoustic signal processing network and the acoustic image processing network.

[0060] Next, the specific configuration of the fusion evaluation module 40 will be described in detail. As described above, a skylight static and dynamic noise detection task set is constructed, and based on the skylight static and dynamic noise detection task set, the skylight noise multi-dimensional feature set is mapped to the skylight noise spatial feature set for fusion evaluation to generate an automotive skylight static and dynamic noise detection report. The fusion evaluation module 40 further includes: a skylight acoustic distribution space construction unit, which is used to construct a skylight acoustic distribution space according to the skylight noise spatial feature set; a feature matching and fusion unit, which is used to map the skylight noise multi-dimensional feature set to the skylight acoustic distribution space according to the spatial distribution information for feature matching and fusion to obtain a skylight noise fusion feature set; a static noise detection report generation unit, which is used to perform noise analysis and evaluation on the skylight noise fusion feature set in sequence based on the skylight static and dynamic noise detection task set to generate an automotive skylight static and dynamic noise detection report.

[0061] Among them, mapping the skylight noise multi-dimensional feature set to the skylight acoustic distribution space according to the spatial distribution information for feature matching and fusion to obtain a skylight noise fusion feature set, the feature matching and fusion unit further includes: a distribution information mapping subunit, which is used to map the skylight noise multi-dimensional feature set to the skylight acoustic distribution space according to the spatial distribution information for feature matching to obtain a skylight noise matching feature set; a weighted fusion subunit, which is used to perform weighted fusion on each matching signal feature and spatial feature in the skylight noise matching feature set to obtain the skylight noise fusion feature set.

[0062] Among them, based on the skylight static and dynamic noise detection task set, noise analysis and evaluation are sequentially performed on the skylight noise fusion feature set to generate an automobile skylight static and dynamic noise detection report. The static noise detection report generation unit further includes: a skylight noise detection task information set acquisition subunit, which is used to perform noise analysis and evaluation on the skylight noise fusion feature set based on each detection task in the skylight static and dynamic noise detection task set to obtain a skylight noise detection task information set; a recording and integration subunit, which is used to record and integrate the skylight noise detection task information set to generate the automobile skylight static and dynamic noise detection report.

[0063] The intelligent detection system for the static and dynamic noise of an automobile skylight integrating acoustic imaging provided by the embodiments of the present invention can execute the intelligent detection method for the static and dynamic noise of an automobile skylight integrating acoustic imaging provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0064] Although various references are made to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0065] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An intelligent detection method for automobile sunroof dynamic and static noises integrating acoustic imaging, characterized in that: The method comprises: Acquiring the internal space structure information of the target vehicle and the acoustic imager to be used, and performing a layout point analysis on the acoustic imager to be used based on the internal space structure information to determine the layout point information of the acoustic imager; The acoustic imager to be used is installed according to the acoustic imager arrangement point information, and the installed acoustic imager to be used is started to perform real-time dynamic collection of noise data during the opening and closing process of the automobile sunroof to obtain a sunroof noise signal set and a sunroof noise image set; Building a dual channel for acoustic data processing, and synchronously analyzing and processing the skylight noise signal set and the skylight noise image set based on the dual channel for acoustic data processing to obtain a skylight noise multidimensional feature set and a skylight noise spatial feature set; Constructing a sunroof dynamic and static sound detection task set, mapping the sunroof noise multidimensional feature set to the sunroof noise spatial feature set for fusion evaluation based on the sunroof dynamic and static sound detection task set, and generating a car sunroof dynamic and static sound detection report; The dual-channel acoustic data processing system includes: Mining and collecting skylight historical noise signal sets and skylight historical noise image sets, performing filtering preprocessing on the skylight historical noise signal sets and skylight historical noise image sets, and obtaining available skylight noise signal sets and available skylight noise image sets; Performing noise feature labeling training on the available skylight noise signal set and the available skylight noise image set respectively to generate an acoustic signal processing network and an acoustic image processing network; Integrate the acoustic signal processing network and the acoustic image processing network in parallel to build the acoustic data processing dual channel; The generating of the acoustic signal processing network and the acoustic image processing network comprises: Respectively annotating the available skylight noise signal set and the available skylight noise image set with noise features to obtain a skylight noise signal sample set and a skylight noise image sample set; Using a deep neural network to perform feature recognition training on the skylight noise signal sample set to generate an initial signal processing network; Using a convolutional neural network to perform feature recognition training on the skylight noise image sample set to generate an initial image processing network; The initial signal processing network and the initial image processing network are cross-validated and tuned respectively to generate the acoustic signal processing network and the acoustic image processing network.

2. The intelligent detection method for automobile sunroof dynamic and static noises integrating acoustic imaging as claimed in claim 1 is characterized in that: The step of determining the acoustic imager deployment point information includes: Acquire a vehicle sunroof dynamic and static sound detection target, extract acoustic influencing factors based on the vehicle sunroof dynamic and static sound detection target, and determine an acoustic detection influencing factor set, wherein the acoustic detection influencing factor set includes coverage, overlapping area, measurement accuracy, and sensitivity; Generate a vehicle interior space model according to the interior space structure information, and simultaneously obtain device attribute information of the acoustic imager to be applied; Performing preliminary point planning on the vehicle interior space model based on the acoustic detection influencing factor set and the equipment attribute information to obtain initial layout point information; The initial layout point information is simulated and optimized to determine the layout point information of the acoustic imager.

3. The intelligent detection method for automobile sunroof dynamic and static noises fused with acoustic imaging as claimed in claim 2, characterized in that: The obtaining of initial deployment point information includes: Performing acoustic analysis and marking on the vehicle interior space model to determine the skylight area information, the internal obstacle set, and the sound wave propagation and reflection characteristics; Based on the skylight area information, the internal obstacle set and the sound wave propagation and reflection characteristics, the monitoring area is divided to obtain the acoustic monitoring area information; Using the acoustic detection influencing factor set and the equipment attribute information as constraint information, preliminary planning of points is performed within the acoustic monitoring area information to obtain a set of optional deployment points; A threshold value for the number of imagers is set, and based on the threshold value for the number of imagers, the optional deployment point set is optimized for deployment effects to obtain the initial deployment point information.

4. The intelligent detection method for automobile sunroof dynamic and static sound integrating acoustic imaging as claimed in claim 3 is characterized in that: The step of determining the acoustic imager deployment point information includes: Using finite element simulation technology to import the vehicle interior space model and the initial layout point information for simulation, and establish a vehicle acoustic simulation model; The vehicle acoustic simulation model is used to simulate the opening and closing of the automobile sunroof and monitor noise propagation to obtain noise propagation simulation information; Based on the noise propagation simulation information, the effectiveness of the initial deployment point information is evaluated to determine the noise source capture effectiveness parameter; The initial layout point information is iteratively simulated and optimized based on the noise source capture effectiveness parameter by using the vehicle acoustic simulation model to determine the layout point information of the acoustic imager.

5. The intelligent detection method for automobile sunroof dynamic and static noises fused with acoustic imaging as claimed in claim 1, characterized in that: The generating of the automobile sunroof dynamic and static sound detection report comprises: Constructing a skylight acoustic distribution space according to the skylight noise spatial feature set; Mapping the skylight noise multidimensional feature set to the skylight acoustic distribution space according to the spatial distribution information to perform feature matching and fusion to obtain a skylight noise fusion feature set; Based on the sunroof dynamic and static sound detection task set, noise analysis and evaluation are performed on the sunroof noise fusion feature set in sequence to generate a car sunroof dynamic and static sound detection report.

6. The intelligent detection method for automobile sunroof dynamic and static noises fused with acoustic imaging as claimed in claim 5, characterized in that: The step of obtaining a skylight noise fusion feature set comprises: Mapping the skylight noise multidimensional feature set to the skylight acoustic distribution space according to the spatial distribution information to perform feature matching to obtain a skylight noise matching feature set; The matching signal features and spatial features in the skylight noise matching feature set are weightedly fused to obtain the skylight noise fusion feature set.

7. The intelligent detection method for automobile sunroof dynamic and static noises fused with acoustic imaging as claimed in claim 6, characterized in that: The generating of the automobile sunroof dynamic and static sound detection report comprises: Based on each detection task in the sunroof dynamic and static detection task set, noise analysis and evaluation are performed on the sunroof noise fusion feature set in turn to obtain a sunroof noise detection task information set; The sunroof noise detection task information set is recorded and integrated to generate the automobile sunroof dynamic and static noise detection report.

8. The intelligent detection system for automobile sunroof movement and stillness combined with acoustic imaging is characterized by: The system is used to implement the intelligent detection method for automobile sunroof movement and stillness by integrating acoustic imaging as described in any one of claims 1 to 7, and the system comprises: A layout point analysis module, the layout point analysis module is used to obtain the internal space structure information of the target vehicle and the acoustic imager to be applied, and perform layout point analysis on the acoustic imager to be applied based on the internal space structure information to determine the layout point information of the acoustic imager; A real-time dynamic acquisition module, wherein the real-time dynamic acquisition module is used to install the acoustic imager to be used according to the acoustic imager layout point information, and start the installed acoustic imager to be used to perform real-time dynamic acquisition of noise data during the opening and closing process of the automobile sunroof, so as to obtain a sunroof noise signal set and a sunroof noise image set; A feature set acquisition module, wherein the feature set acquisition module is used to build a dual channel for acoustic data processing, and based on the dual channel for acoustic data processing, the skylight noise signal set and the skylight noise image set are analyzed and processed synchronously to obtain a skylight noise multidimensional feature set and a skylight noise spatial feature set; A fusion evaluation module is used to construct a sunroof dynamic and static sound detection task set, and based on the sunroof dynamic and static sound detection task set, the multi-dimensional feature set of sunroof noise is mapped to the sunroof noise spatial feature set for fusion evaluation to generate a car sunroof dynamic and static sound detection report.

Images