Motion envelope rapid generation system of automobile chassis suspension spring

Abstract

The invention relates to the technical field of hardware equipment, in particular to a system for rapidly generating a motion envelope of an automobile chassis suspension spring. The method comprises the following steps: firstly, acquiring multi-modal spring data in real time by using a multi-modal sensor array; secondly, the deviation of the multi-mode spring data is identified; correcting the multi-mode spring data according to the error; and performing multi-dimensional data fusion on the multi-modal spring data to generate fused data. Then, carrying out data processing on the fused data by utilizing edge calculation to obtain time-frequency characteristics; and generating a spring motion envelope by using a motion envelope parallel optimization method based on the time-frequency data. Thirdly, smoothing data in a spring motion envelope window, and removing abnormal fluctuation values; and finally, continuously monitoring the working state of each unit, and evaluating the coordination degree of each unit in real time. And the corrected control parameters are transferred back to each unit through a feedback loop for adjustment. According to the method, computing resources can be reduced, and the spring motion envelope generation efficiency and accuracy can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of hardware equipment, in particular to a system for quickly generating a motion envelope of a suspension spring of an automobile chassis. Background Art

[0002] Automobile chassis suspension springs are usually located in the vehicle's suspension system, connecting the body and wheels. They are mainly arranged between suspension arms, shock absorbers, and wheels and body, with the purpose of buffering the impact and vibration during vehicle driving and absorbing the external force of uneven roads. The springs ensure the smooth driving and comfort of the vehicle by supporting the weight of the vehicle and maintaining the relative position of the wheels and body. Generating the motion envelope of automobile chassis suspension springs can help optimize suspension performance, ensure that the deformation range of the springs under different working conditions is reasonable, avoid overload, and improve the comfort and safety of the vehicle.

[0003] For the generation of the envelope of the spring, traditional methods usually rely on geometric modeling and analysis based on mathematical models. First, by modeling the deformation of the spring under different working conditions, combined with the geometric parameters, load and elastic properties of the spring, finite element analysis or traditional analytical methods are used to calculate the motion trajectory of the spring during compression or tension. Traditional methods usually use simplified mechanical models to describe the dynamic changes and motion envelope of the spring through a series of equations. These calculation processes require detailed input of the physical parameters of the spring, and the results are obtained through theoretical derivation or numerical simulation. However, the calculation process of the traditional method is cumbersome and the accuracy is limited, making it difficult to accurately simulate the dynamic changes of the spring under complex environmental conditions. The real-time monitoring and dynamic adjustment of environmental factors are ignored, and there is a lack of real-time and adaptability.

[0004] The existing technology has introduced more digital tools and intelligent calculation methods to improve the accuracy of the motion envelope of chassis suspension springs. Some advanced solutions use finite element simulation software for dynamic simulation, combining the geometry and loading conditions of the spring to accurately analyze it. These methods can not only simulate the deformation of the spring, but also conduct a comprehensive analysis of the spring under the influence of multiple physical fields. In addition, with the development of sensor technology, modern automobile suspension systems can collect real-time suspension working status data through pressure sensors, acceleration sensors, etc., and combine these real-time data to improve the accuracy of the envelope through model calibration and correction. The existing technology also uses machine learning and optimization algorithms to automatically optimize spring design parameters based on a large amount of data to improve performance. Modern optimization technologies such as particle swarm optimization algorithms and genetic algorithms have also been applied to the design and adjustment of suspension systems, further improving the accuracy of the envelope. However, the existing technology faces the problem of low computational efficiency, especially under complex working conditions, the finite element analysis and multi-physics simulation calculation time is long. In addition, the accuracy of the envelope is still limited, and it is difficult to fully consider the impact of real-time environmental changes on spring performance.

[0005] Therefore, a fast motion envelope generation system for automobile chassis suspension springs is proposed. Summary of the invention

[0006] The object of the present invention is to provide a system for rapidly generating motion envelopes of automobile chassis suspension springs, which is used to improve the efficiency and accuracy of rapidly generating spring motion envelopes. First, a multimodal sensor array is used to collect multimodal spring data in real time. Secondly, the deviation of the multimodal spring data is identified; the multimodal spring data is corrected according to the error; and the multimodal spring data is subjected to multi-dimensional data fusion to generate fused data. Then, edge computing is used to process the fused data to obtain time-frequency features; based on the time-frequency data, the motion envelope is generated using a motion envelope parallel optimization method. Next, the data in the spring motion envelope window is smoothed to remove abnormal fluctuation values. Finally, the working status of each unit is continuously monitored, and the coordination degree of each unit is evaluated in real time; the corrected control parameters are transferred back to each unit through a feedback loop for adjustment.

[0007] To achieve the above object, the present invention provides the following technical solutions: A system for quickly generating motion envelopes of automobile chassis suspension springs, comprising: A sensor data acquisition unit uses a multi-modal sensor array arranged at multiple locations of the suspension to collect multi-modal spring data in real time; The error correction and sensor data fusion unit identifies the deviation of the multi-modal spring data; corrects the multi-modal spring data according to the error; and performs multi-dimensional data fusion on the multi-modal spring data through a data fusion algorithm to generate fused data; A motion envelope generation unit processes the fused data using edge computing to obtain time-frequency features; based on the time-frequency data, a motion envelope parallel optimization method is used to generate a spring motion envelope; the motion envelope parallel optimization method includes the steps of data allocation, initialization, local optimization, information exchange, global convergence and envelope generation; A motion envelope optimization unit is used to smooth the data in the spring motion envelope window and remove abnormal fluctuation values; The feedback and monitoring unit continuously monitors the working status of each unit and evaluates the coordination degree of each unit in real time; based on the real-time evaluation, the corrected control parameters are transmitted back to each unit through a feedback loop for adjustment.

[0008] Specifically, the multimodal sensor array includes pressure, acceleration and fiber optic sensors; the multimodal sensor array is arranged at the two end points of the spring, around the suspension arm and the part where the suspension is connected to the vehicle body; the sensor data includes the deformation, stress and vibration information of the spring.

[0009] Further, the deviation of the multi-modal spring data is identified; and the multi-modal spring data is corrected according to the error, the specific steps are: It includes a principal component analysis method and an autoencoder; using the principal component analysis method to extract key features of the multimodal spring data, inputting the key features into the autoencoder to capture nonlinear errors; A correction weight is calculated based on the error to perform data correction.

[0010] Furthermore, the multi-dimensional data of the multi-modal spring is fused by a data fusion algorithm to generate fused data. The specific steps are as follows: Preprocessing the multi-modal spring data, and performing data alignment and spatiotemporal synchronization; A fusion weight is calculated according to a signal-to-noise ratio of the multi-modal spring data, and the multi-modal spring data is fused based on the fusion weight to generate fused data.

[0011] Furthermore, the processing flow of the edge computing specifically includes: Extracting time domain features from the fused data, including amplitude, periodicity and maximum displacement; Convert the time domain features into the frequency domain, extract the frequency domain features, including frequency components, and corresponding peak frequencies and harmonic information; The periodic information, amplitude characteristics and transient characteristics of the spring motion are extracted from the time domain characteristics; the frequency response characteristics and vibration modes of the spring motion are extracted from the frequency domain characteristics; these characteristics are used as time-frequency characteristics and as inputs of the motion envelope parallel optimization method.

[0012] Furthermore, the specific steps of using the motion envelope parallel optimization method to generate the spring motion envelope are as follows: Data allocation: allocating the time-frequency features to generate multiple different time-frequency data sets; allocating the time-frequency data sets to multiple computing nodes; Initialization: Initialize a part of the particle swarm on each of the computing nodes; each particle represents a potential motion envelope solution, having a position, a velocity, and a fitness value; Local optimization: Each computing node performs particle swarm optimization on the corresponding time-frequency data set, calculates the position and velocity of the particles, and updates the fitness value of the particles; each computing node independently optimizes the corresponding time-frequency data set to obtain a local optimal position.

[0013] Furthermore, the specific steps of using the motion envelope parallel optimization method to generate the spring motion envelope also include: Information exchange: During each round of particle swarm optimization of each computing node, each computing node exchanges the local optimal position of particles with each other, and selects the optimal solution from all the local optimal positions as the global optimal position; Global convergence: updating the particle swarm of each computing node according to the global optimal position and the local optimal position, and gradually converging until the set number of iterations is reached; Envelope generation: In the final iteration, the particle swarm of each computing node finds the optimal solution; all the optimal solutions are summarized to generate the final spring motion envelope.

[0014] Furthermore, a Gaussian kernel function is used to perform weighted smoothing on the data within the spring motion envelope window to remove abnormal fluctuation values, including high-frequency noise.

[0015] Furthermore, the working status of each unit is continuously monitored, and the coordination degree of each unit is evaluated in real time. The specific steps are as follows: Monitor the computing load of each unit, the normal transmission of data flow, the correctness of task execution and time delay, and issue an early warning if an abnormality occurs; Assess the degree of coordination among various units, including the real-time response, accuracy of data, and consistency of processing results, and issue early warnings when abnormalities occur.

[0016] Furthermore, in the feedback and monitoring unit, the feedback loop is PID control.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The data fusion algorithm of the present invention integrates the spring data from multiple sensors into unified fusion data, which can eliminate the local errors, noise and deviations that may exist in each sensor, thereby improving the accuracy and reliability of the data. Multi-dimensional data fusion takes into account the information of different sensors, and can more comprehensively and accurately reflect the actual state of the suspension spring, providing clearer and more comprehensive basic data for subsequent analysis, reducing the errors caused by a single data source, and effectively improving the overall stability and reliability of the system.

[0018] 2. The present invention uses edge computing to push data processing and analysis tasks to the data source end, reducing latency and improving real-time performance. By extracting time domain features and frequency domain features, the key dynamic characteristics of spring motion can be accurately captured. These time-frequency features provide precise input for subsequent spring motion envelope generation, which helps to improve the accuracy and efficiency of the system's envelope generation.

[0019] 3. The present invention can quickly explore different solution spaces by distributing time-frequency feature data to multiple computing nodes for parallel processing, thus avoiding the computational bottleneck of traditional single-node optimization methods. Local optimization and global information exchange mechanisms ensure the gradual convergence of the global optimal solution, accurately capture the dynamic characteristics of the spring and generate an accurate motion envelope. In addition, considering multiple possible solutions at the same time can more effectively handle the nonlinear envelope generation problem and reduce the calculation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A system structure diagram of a system for quickly generating motion envelopes of a vehicle chassis suspension spring according to the present invention; Figure 2 A schematic diagram of the processing flow of edge computing of the present invention; Figure 3 The present invention is a flowchart of the motion envelope parallel optimization method. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] In order to reduce computing resources and improve the efficiency and accuracy of spring motion envelope generation, the present invention provides a fast motion envelope generation system for automobile chassis suspension springs. In order to illustrate the function of the present invention, the effectiveness of the present invention will be illustrated from the following examples.

[0023] Embodiment 1

[0024] In order to improve R&D efficiency, shorten product launch cycle, and ensure that the spring motion performance of the suspension system meets the design requirements under different driving environments, the R&D department of a new energy vehicle A used a motion envelope rapid generation system for the chassis suspension spring. Figure 1 As shown, a system structure diagram of a motion envelope rapid generation system for a vehicle chassis suspension spring is presented.

[0025] Reference Figure 1 ,The system includes a sensor data acquisition unit that uses a ,multimodal sensor array arranged at multiple locations of the suspension to ,acquire multimodal spring data in real time.

[0026] Specifically, the multimodal sensor array includes pressure, acceleration and fiber optic sensors; the multimodal sensor array is arranged at the two end points of the spring, around the suspension arm and the part where the suspension is connected to the vehicle body; the sensor data includes the deformation, stress and vibration information of the spring.

[0027] In this embodiment, the pressure sensor is used to detect the external force and pressure changes applied to the spring and monitor the stress state of the spring. Pressure sensors are installed at the end points of the spring and around the suspension arm to measure the external pressure on the spring in real time. Based on the pressure changes, the deformation amount and corresponding stress of the spring can be calculated.

[0028] The accelerometer measures the acceleration of the spring under stress and detects the spring vibration. The accelerometer is placed at both ends of the spring and on the suspension arm to monitor the motion state of the suspension system under different working conditions. The accelerometer can accurately capture the vibration characteristics of the spring, including the frequency, amplitude and acceleration fluctuations of the spring, and further analyze the dynamic characteristics of the resonant frequency and vibration mode of the spring.

[0029] The optical fiber sensor is used to measure the deformation and stress of the spring with high precision, and detects the deformation by changing the wavelength of the reflected light. When the spring is subjected to force, the deformation of the optical fiber will cause the change of the reflected wavelength, so that the deformation of the spring can be accurately calculated. As shown in Table 1, the relevant data obtained by the pressure, acceleration and optical fiber sensor are shown.

[0030] Table 1 Relevant data obtained by pressure, acceleration and optical fiber sensors

[0031] By combining pressure, acceleration and fiber optic sensors, the deformation, stress and vibration information of the spring can be fully obtained. The combination of these sensors provides a multi-dimensional monitoring solution that can accurately capture the dynamic response of the spring under different working conditions and help improve the accuracy of the spring motion envelope generation.

[0032] Further, refer to Figure 1 The system also includes an error correction and sensor data fusion unit, which identifies the deviation of the multi-modal spring data; corrects the multi-modal spring data according to the error; and fuses the multi-modal spring data in multiple dimensions through a data fusion algorithm to generate fused data. The specific steps of this unit are: The invention comprises a principal component analysis method and an autoencoder; the principal component analysis method is used to extract key features of the multimodal spring data: Calculate the covariance matrix of the multi-modal spring data, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvectors and eigenvalues. In this embodiment, the eigenvalues ​​represent the changing trends between different physical quantities, such as force, deformation, and acceleration. Then, select the previous The eigenvector corresponding to the maximum eigenvalue is used to reduce the dimension of the data, and the data is reconstructed to obtain the key features. In this embodiment, the principal component analysis method helps to remove unnecessary noise and improve calculation efficiency.

[0033] Furthermore, the key features are input into the autoencoder to capture nonlinear errors. The autoencoder includes an encoder and a decoder. The encoder inputs the key features , compressed into a low-dimensional space, using nonlinear transformation ,in represents a nonlinear activation function, represents a low-dimensional feature representation, represents the parameters of the encoder. The decoder represents the low-dimensional features Restore to the original data space: ,in Represents the reconstructed data, Represents the parameters of the decoder. Then based on the key features and the reconstructed data Calculation error , the formula is , where the subscript Indicates sensors.

[0034] Further, based on the error Calculate correction weights , the calculation formula is ,in, represents the control factor, which is used to adjust the effect of the error on the correction weight, Indicates The error of a sensor, represents a natural constant. This formula ensures that data with larger errors will receive more weight, which helps to better correct the data and improve the overall accuracy. Then, according to the correction weight Perform data correction to obtain corrected multi-modal spring data .

[0035] Furthermore, the multimodal spring data is subjected to data preprocessing, including denoising, missing value filling and normalization. Since different types of sensors have different sampling rates and timestamps, time alignment is required, and methods include but are not limited to interpolation and resampling. Furthermore, since different sensors are arranged in different spatial positions, spatial coordinate transformation is required to ensure that different sensor data of the same physical quantity can be compared and fused in the same spatial framework. The method of spatial alignment includes but is not limited to coordinate transformation and sensor calibration method, which will not be elaborated here.

[0036] Furthermore, the signal-to-noise ratio determines the reliability of each sensor data, so the fusion weight is calculated according to the signal-to-noise ratio of the multimodal spring data:

[0037] in, Indicates The signal-to-noise ratio of the sensor data is Indicates The variance of the sensor data, Indicates The expected value of the sensor data.

[0038] Calculate fusion weights based on signal-to-noise ratio : ; in, Indicates the total number of sensors.

[0039] The multi-modal spring data is fused based on the fusion weight to generate fusion data , the calculation formula is: ; Through data preprocessing, alignment, and spatiotemporal synchronization, the consistency and accuracy of multimodal sensor data are ensured, effectively reducing errors caused by sensor delays or data mismatches. Fusion weights are calculated based on the signal-to-noise ratio, and weighted fusion can be performed according to the quality of each sensor data, improving the accuracy and robustness of data fusion, thereby generating more reliable fused data. This not only optimizes computational efficiency, but also improves the accuracy of subsequent spring motion envelope generation.

[0040] Further, refer to Figure 1 The system also includes a motion envelope generation unit, which uses edge computing to process the fused data to obtain time-frequency features; based on the time-frequency data, a motion envelope parallel optimization method is used to generate a spring motion envelope; the motion envelope parallel optimization method includes the steps of data allocation, initialization, local optimization, information exchange, global convergence and envelope generation. Figure 2As shown, a schematic diagram of the processing flow of edge computing is shown.

[0041] Specifically, the processing flow of the edge computing includes: The computing tasks are distributed to the edge devices near the suspension sensor; the fused data is a time series signal, and the time domain features are extracted from the fused data, including amplitude, periodicity and maximum displacement. The amplitude is the difference between the maximum and minimum values ​​in the fused data; the maximum displacement is the maximum offset value of the fused data.

[0042] Furthermore, the Fourier transform formula is used to transform the time domain features into the frequency domain, and the frequency domain features are extracted, including frequency components, and corresponding peak frequencies and harmonic information. The frequency components are represented by discrete values ​​in the frequency domain; the peak frequency is the position with the largest amplitude in the spectrum; and the harmonic information includes the harmonic frequency, which is an integer multiple of the fundamental frequency.

[0043] Furthermore, the periodic information, amplitude characteristics and transient characteristics of the spring motion are extracted from the time domain characteristics. The periodic information is obtained by calculating the periodic changes in the time domain characteristics; the amplitude characteristics are obtained by calculating the mean or peak value of the time domain characteristics; the transient characteristics are characterized by extracting the instantaneous frequency or instantaneous amplitude of the time domain characteristics. The frequency response characteristics and vibration modes of the spring motion are extracted from the frequency domain characteristics. The frequency response characteristics are the amplitude or phase changes in each frequency band in the frequency domain characteristics; the vibration modes are obtained by extracting different vibration modes from different harmonic components in the frequency characteristics.

[0044] These features are used as time-frequency features and as input of the motion envelope parallel optimization method.

[0045] Edge computing extracts time domain and frequency domain features, comprehensively analyzes the periodicity, amplitude, transient and other characteristics of spring motion, improves the ability to accurately identify and analyze motion states, provides effective input for motion envelope parallel optimization methods, and optimizes system response accuracy. In addition, edge computing can process data collected by sensors in real time, avoiding the transmission of large-scale data to remote servers, thereby reducing communication delays and central computing loads.

[0046] Furthermore, based on the time-frequency data, a spring motion envelope is generated using a motion envelope parallel optimization method. Figure 3 As shown, a flow chart of the motion envelope parallel optimization method is shown, and the specific steps are: Data allocation: Allocate the time-frequency features to generate multiple different time-frequency data sets; allocate the time-frequency data sets to multiple computing nodes. computing nodes, each computing node is assigned a part of the time-frequency data set, denoted as ,in , the total time-frequency data set is recorded as ,Right now By dividing the data into multiple subsets, each subset is calculated independently, reducing computing bottlenecks and improving overall performance. In addition, the computing tasks are reasonably allocated, the computing process is optimized, and the time consumption of the intermediate links is reduced.

[0047] Initialization: Initialize a part of the particle swarm on each of the computing nodes; each particle represents a potential motion envelope solution with position, velocity and fitness value. Specifically, for each particle ,in , It is The number of particles on a computing node. The state of is composed of three parts: location : , Dimension index representing the particle position; velocity : ; Fitness value . where the initial position and velocity are usually generated from a random distribution: ; in, and Respectively represent the boundary values ​​of the position; and They represent the boundary values ​​of velocity, and Represents a random number.

[0048] Provide a variety of initial solutions for the optimization algorithm to ensure the breadth of the exploration space and avoid local optimality.

[0049] Local optimization: Each computing node is optimized in the corresponding time-frequency data set. Particle swarm optimization is performed on the particle swarm to calculate the particle position and velocity and update the particle fitness value. The speed is updated by the following formula: ; in, represents the inertia weight; and represents the learning factor; and Represents a random number; Represents particles The local optimal position of represents the global optimal position.

[0050] particle The position is updated by the following formula: ; particle The fitness update is based on the obtained time-frequency data set Calculations are performed to evaluate the quality of the particle position.

[0051] Each computing node independently optimizes the corresponding time-frequency data set, wherein each particle updates its local optimal position according to the fitness function ,Right now .

[0052] Through local optimization search, the quality of the solution can be improved, rough solutions can be avoided, and the solution can be ensured to be close to the optimal state.

[0053] Information exchange: During each round of particle swarm optimization of each computing node, each computing node exchanges the local optimal position of particles with each other. , select the optimal solution from all the local optimal positions as the global optimal position ,Right now ,in, Represents the local optimal solution of each computing node. At the end of each iteration, each computing node sends its local optimal solution to other nodes so that the search of each particle can be adjusted according to the global optimal solution.

[0054] Sharing information between computing nodes helps avoid local optimality and improve global search capabilities. By exchanging solution information, the algorithm can better adjust the search direction and improve global exploration capabilities.

[0055] Global convergence: updating the particle swarm of each computing node according to the global optimal position and the local optimal position, and gradually converging until the set number of iterations is reached.

[0056] Envelope generation: In the final iteration, the particle swarm of each computing node finds its optimal solution , A set of parameters is a mathematical representation of the spring motion envelope, where All the optimal solutions are summarized to generate the final spring motion envelope , expressed as .

[0057] Envelope generation provides an accurate description of the overall behavior of the system by merging local solutions to form a continuous solution space.

[0058] Further, refer to Figure 1The system also includes a motion envelope optimization unit, which smoothes the data in the spring motion envelope window and removes abnormal fluctuation values. Specifically, a moving average algorithm is selected to slide in the data window, gradually calculate and replace the value of each data point, and use the weighted value of the neighboring data to smooth the current data point. Further, a low-pass filter is applied to the spring motion envelope data to remove high-frequency noise, and the low-pass filter includes but is not limited to a Butterworth filter and a Kalman filter. The filtered data is corrected to further smooth the data and ensure the stability of the spring motion envelope.

[0059] Further, refer to Figure 1 The system also includes a feedback and monitoring unit, which continuously monitors the working status of each unit and evaluates the coordination degree of each unit in real time; based on the real-time evaluation, the corrected control parameters are transmitted back to each unit through a feedback loop for adjustment.

[0060] Specifically, the computing load, normal transmission of data flow, correctness of task execution and time delay of each unit are monitored, and an alarm is issued if an abnormality occurs. Use performance monitoring tools to monitor the computing load, such as Prometheus, Grafana or New Relic to collect CPU usage, memory consumption, disk I / O and other indicators of each unit in real time. These data will be continuously monitored in the background, and tasks will be allocated through load balancing algorithms such as weighted polling and minimum number of connections to avoid overloading of a certain unit. Use network delay monitoring tools to monitor the normal transmission of data flow, such as Ping, Traceroute, and Zabbix to monitor the transmission process of data packets to ensure smooth transmission of data between units. If packet loss or delay is detected, the system will trigger an alarm. Use a logging system, such as ELK Stack, or a monitoring service, such as Datadog, to record task execution logs in real time, including input and output data, abnormal errors, etc. Perform unit testing through an automated testing framework to ensure that each unit performs the intended function. Use timestamps and real-time performance analysis tools, such as Apache Kafka's delay monitoring function, to monitor the flow time of data in each processing unit. If a link exceeds the set response time threshold, the system will trigger an alarm.

[0061] Furthermore, the response time of each unit is analyzed by time series analysis method to ensure that each unit responds to the request on time. By setting the threshold alarm, the system will sound an alarm when the response time of a unit is too long. And adopt data verification technology to ensure that the data output by each unit is accurate by comparing with the known standard data set. Combined with the data consistency algorithm to ensure that each module does not produce errors during data processing. Through data integrity check and differential comparison algorithm, check whether the processing results between different modules are consistent. In this embodiment, the methods used in the feedback and monitoring units are all prior art, and no further elaboration is made here.

[0062] Monitor the workload, data flow transmission, task execution correctness and time delay of each unit in real time to ensure the efficient operation of the system. Evaluate the collaborative work effect between units to avoid dysfunction of each unit.

[0063] Evaluation is performed based on real-time monitoring information, and the corrected control parameters are transferred back to each unit through a feedback loop. Specifically, the deviation between the current state and the ideal target is calculated by real-time monitoring of system performance. For example, if the computing load of a unit is too large, the system will calculate the gap between it and the preset standard load. Based on proportional, integral and differential control algorithms, the adjustment value of each unit is calculated. The PID algorithm generates an adjustment output based on the current error, historical error accumulation and error change rate. According to the adjustment value of the PID control output, the configuration parameters of each unit are updated in real time. For example, if the response time of a unit is slow, the PID controller can increase the computing resources of the unit or adjust its task priority. Through automated tuning tools such as Ansible, Chef or Kubernetes' adaptive scheduling method, based on the feedback of PID control, the system's resource allocation, task scheduling, etc. are dynamically adjusted. All adjustments will be optimized again based on the feedback results.

[0064] The operating parameters of each unit are adjusted through PID control to ensure that the system operates efficiently and stably within the target range. The closed-loop control mechanism is used to achieve dynamic optimization of the system, so that the system always remains efficient and stable under the ever-changing workload, thereby generating a highly accurate spring motion envelope.

[0065] The rapid motion envelope generation system for the automobile chassis suspension spring significantly improves the efficiency and accuracy of spring motion envelope generation through multi-modal sensor data acquisition, error correction and data fusion, edge computing processing, and parallel optimization methods. The system can provide real-time feedback and optimize the motion envelope to ensure that the motion performance of the suspension in different driving environments meets the design requirements, shorten the R&D cycle, and improve the R&D efficiency and product performance of new energy vehicles.

[0066] Embodiment 2 In order to analyze the performance of the automobile suspension system and identify potential faults or abnormalities during spring movement, the after-sales department of a certain automobile B used a motion envelope rapid generation system for automobile chassis suspension springs.

[0067] The system includes a sensor data acquisition unit, which uses a multi-modal sensor array arranged at multiple positions of the suspension to collect multi-modal spring data in real time.

[0068] Specifically, the multimodal sensor array includes pressure, acceleration and fiber optic sensors; the multimodal sensor array is arranged at the two end points of the spring, around the suspension arm and the part where the suspension is connected to the vehicle body; the sensor data includes the deformation, stress and vibration information of the spring.

[0069] Furthermore, the system also includes an error correction and sensor data fusion unit, which identifies the deviation of the multi-modal spring data; corrects the multi-modal spring data according to the error; and fuses the multi-modal spring data in multiple dimensions through a data fusion algorithm to generate fused data. The specific steps of this unit are: The invention comprises a principal component analysis method and an autoencoder; the principal component analysis method is used to extract key features of the multimodal spring data: Calculate the covariance matrix of the multi-modal spring data, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvectors and eigenvalues. In this embodiment, the eigenvalues ​​represent the changing trends between different physical quantities, such as force, deformation, and acceleration. Then, select the previous The eigenvector corresponding to the largest eigenvalue is used to reduce the dimension of the data and reconstruct the data to obtain the key features.

[0070] Furthermore, the key features are input into the autoencoder to capture nonlinear errors. The autoencoder includes an encoder and a decoder. The encoder inputs the key features , compressed into a low-dimensional space, using nonlinear transformation ,in represents a nonlinear activation function, represents a low-dimensional feature representation, represents the parameters of the encoder. The decoder represents the low-dimensional features Restore to the original data space: ,in Represents the reconstructed data, Represents the parameters of the decoder. Then based on the key features and the reconstructed data Calculation error , the formula is , where the subscript Indicates sensors.

[0071] Further, based on the error Calculate correction weights , the calculation formula is ,in, represents the control factor, which is used to adjust the effect of the error on the correction weight, Indicates The error of a sensor, represents the natural constant. Then, according to the correction weight Perform data correction to obtain corrected multi-modal spring data .

[0072] Furthermore, the multimodal spring data is subjected to data preprocessing, including denoising, missing value filling and normalization. Since different types of sensors have different sampling rates and timestamps, time alignment is required, including but not limited to interpolation and resampling methods to synchronize the data of all sensors to a unified time axis. Furthermore, since different sensors are arranged in different spatial positions, spatial coordinate transformation is required to ensure that different sensor data of the same physical quantity can be compared and fused in the same spatial framework. The method of spatial alignment includes but is not limited to coordinate transformation and sensor calibration methods.

[0073] Furthermore, the signal-to-noise ratio determines the reliability of each sensor data, so the fusion weight is calculated according to the signal-to-noise ratio of the multimodal spring data: ; in, Indicates The signal-to-noise ratio of the sensor data is Indicates The variance of the sensor data, Indicates The expected value of the sensor data.

[0074] Calculate fusion weights based on signal-to-noise ratio : ; in, Indicates the total number of sensors.

[0075] The multi-modal spring data is fused based on the fusion weight to generate fusion data , the calculation formula is: ; Furthermore, the system also includes a motion envelope generation unit, which uses edge computing to process the fused data to obtain time-frequency features; based on the time-frequency data, a motion envelope parallel optimization method is used to generate a spring motion envelope; the motion envelope parallel optimization method includes the steps of data allocation, initialization, local optimization, information exchange, global convergence and envelope generation. Figure 2 As shown, a schematic diagram of the processing flow of edge computing is shown.

[0076] Specifically, the processing flow of the edge computing includes: The computing tasks are distributed to the edge devices near the suspension sensor; the fused data is a time series signal, and the time domain features are extracted from the fused data, including amplitude, periodicity and maximum displacement. The amplitude is the difference between the maximum and minimum values ​​in the fused data; the maximum displacement is the maximum offset value of the fused data.

[0077] Furthermore, the Fourier transform formula is used to transform the time domain features into the frequency domain, and the frequency domain features are extracted, including frequency components, and corresponding peak frequencies and harmonic information. The frequency components are represented by discrete values ​​in the frequency domain; the peak frequency is the position with the largest amplitude in the spectrum; and the harmonic information includes the harmonic frequency, which is an integer multiple of the fundamental frequency.

[0078] Furthermore, the periodic information, amplitude characteristics and transient characteristics of the spring motion are extracted from the time domain characteristics. The periodic information is obtained by calculating the periodic changes in the time domain characteristics; the amplitude characteristics are obtained by calculating the mean or peak value of the time domain characteristics; the transient characteristics are characterized by extracting the instantaneous frequency or instantaneous amplitude of the time domain characteristics. The frequency response characteristics and vibration modes of the spring motion are extracted from the frequency domain characteristics. The frequency response characteristics are the amplitude or phase changes in each frequency band in the frequency domain characteristics; the vibration modes are obtained by extracting different vibration modes from different harmonic components in the frequency characteristics.

[0079] These features are used as time-frequency features and as input of the motion envelope parallel optimization method.

[0080] Furthermore, based on the time-frequency data, a spring motion envelope is generated using a motion envelope parallel optimization method. Figure 3 As shown, a flow chart of the motion envelope parallel optimization method is shown, and the specific steps are: Data allocation: Allocate the time-frequency features to generate multiple different time-frequency data sets; allocate the time-frequency data sets to multiple computing nodes. computing nodes, each computing node is assigned a part of the time-frequency data set, denoted as ,in , the total time-frequency data set is recorded as ,Right now .

[0081] Initialization: Initialize a part of the particle swarm on each of the computing nodes; each particle represents a potential motion envelope solution with position, velocity and fitness value. Specifically, for each particle ,in , It is The number of particles on a computing node. The state of is composed of three parts: location : , Dimension index representing the particle position; velocity : ; Fitness value . where the initial position and velocity are usually generated from a random distribution: ; in, and Respectively represent the boundary values ​​of the position; and They represent the boundary values ​​of velocity, and Represents a random number.

[0082] Local optimization: Each computing node is optimized in the corresponding time-frequency data set. Particle swarm optimization is performed on the particle swarm to calculate the particle position and velocity and update the particle fitness value. The speed is updated by the following formula: ; in, represents the inertia weight; and represents the learning factor; and Represents a random number; Represents particles The local optimal position of represents the global optimal position.

[0083] particle The position is updated by the following formula: ; particle The fitness update is based on the obtained time-frequency data set Calculations are performed to evaluate the quality of the particle position.

[0084] Each computing node independently optimizes the corresponding time-frequency data set, wherein each particle updates its local optimal position according to the fitness function ,Right now .

[0085] Information exchange: During each round of particle swarm optimization of each computing node, each computing node exchanges the local optimal position of particles with each other. , select the optimal solution from all the local optimal positions as the global optimal position ,Right now ,in, Represents the local optimal solution of each computing node. At the end of each iteration, each computing node sends its local optimal solution to other nodes so that the search of each particle can be adjusted according to the global optimal solution.

[0086] Global convergence: updating the particle swarm of each computing node according to the global optimal position and the local optimal position, and gradually converging until the set number of iterations is reached.

[0087] Envelope generation: In the final iteration, the particle swarm of each computing node finds its optimal solution , A set of parameters is a mathematical representation of the spring motion envelope, where All the optimal solutions are summarized to generate the final spring motion envelope , expressed as .

[0088] Furthermore, the system also includes a motion envelope optimization unit, which smoothes the data in the spring motion envelope window to remove abnormal fluctuation values. Specifically, a moving average algorithm is selected to slide in the data window, gradually calculate and replace the value of each data point, and use the weighted value of the adjacent data to smooth the current data point. Furthermore, a low-pass filter is applied to the spring motion envelope data to remove high-frequency noise, and the low-pass filter includes but is not limited to a Butterworth filter and a Kalman filter. The filtered data is corrected to further smooth the data and ensure the stability of the spring motion envelope.

[0089] Furthermore, the system also includes a feedback and monitoring unit, which continuously monitors the working status of each unit and evaluates the degree of coordination of each unit in real time; based on the real-time evaluation, the corrected control parameters are transmitted back to each unit through a feedback loop for adjustment.

[0090] Specifically, the computing load, normal transmission of data flow, correctness of task execution and time delay of each unit are monitored, and an alarm is issued if an abnormality occurs. Use performance monitoring tools to monitor the computing load, such as Prometheus, Grafana or New Relic to collect CPU usage, memory consumption, disk I / O and other indicators of each unit in real time. These data will be continuously monitored in the background, and tasks will be allocated through load balancing algorithms such as weighted polling and minimum number of connections to avoid overloading of a certain unit. Use network delay monitoring tools to monitor the normal transmission of data flow, such as Ping, Traceroute, and Zabbix to monitor the transmission process of data packets to ensure smooth transmission of data between units. If packet loss or delay is detected, the system will trigger an alarm. Use a logging system, such as ELK Stack, or a monitoring service, such as Datadog, to record task execution logs in real time, including input and output data, abnormal errors, etc. Perform unit testing through an automated testing framework to ensure that each unit performs the intended function. Use timestamps and real-time performance analysis tools, such as Apache Kafka's delay monitoring function, to monitor the flow time of data in each processing unit. If a link exceeds the set response time threshold, the system will trigger an alarm.

[0091] Furthermore, the response time of each unit is analyzed by time series analysis method to ensure that each unit responds to the request on time. By setting the threshold alarm, the system will sound an alarm when the response time of a unit is too long. And adopt data verification technology to ensure that the data output by each unit is accurate by comparing with the known standard data set. Combined with the data consistency algorithm to ensure that each module does not produce errors during data processing. Through data integrity check and differential comparison algorithm, check whether the processing results between different modules are consistent. In this embodiment, the methods used in the feedback and monitoring units are all prior art, and no further elaboration is made here.

[0092] Evaluation is performed based on real-time monitoring information, and the corrected control parameters are transferred back to each unit through a feedback loop. Specifically, the deviation between the current state and the ideal target is calculated by real-time monitoring of system performance. For example, if the computing load of a unit is too large, the system will calculate the gap between it and the preset standard load. Based on proportional, integral and differential control algorithms, the adjustment value of each unit is calculated. The PID algorithm generates an adjustment output based on the current error, historical error accumulation and error change rate. According to the adjustment value of the PID control output, the configuration parameters of each unit are updated in real time. For example, if the response time of a unit is slow, the PID controller can increase the computing resources of the unit or adjust its task priority. Through automated tuning tools such as Ansible, Chef or Kubernetes' adaptive scheduling method, based on the feedback of PID control, the system's resource allocation, task scheduling, etc. are dynamically adjusted. All adjustments will be optimized again based on the feedback results.

[0093] The system effectively improves the efficiency and accuracy of spring motion envelope generation by collecting multimodal sensor data in real time and performing error correction and data fusion. In after-sales department applications, it can quickly identify potential faults or abnormalities in the suspension system. Through edge computing and parallel optimization methods, the system reduces calculation time and improves the accuracy of fault diagnosis. The optimized motion envelope data helps to accurately analyze spring performance, detect problems in a timely manner, improve vehicle safety and reliability, and reduce maintenance costs.

[0094] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A fast motion envelope generation system for automobile chassis suspension springs, characterized in that: include: A sensor data acquisition unit uses a multi-modal sensor array arranged at multiple locations of the suspension to collect multi-modal spring data in real time; The error correction and sensor data fusion unit identifies the deviation of the multi-modal spring data; corrects the multi-modal spring data according to the error; and performs multi-dimensional data fusion on the multi-modal spring data through a data fusion algorithm to generate fused data; A motion envelope generation unit processes the fused data using edge computing to obtain time-frequency features; Based on the time-frequency data, a spring motion envelope is generated using a motion envelope parallel optimization method; the motion envelope parallel optimization method comprises the steps of data allocation, initialization, local optimization, information exchange, global convergence and envelope generation; A motion envelope optimization unit is used to smooth the data in the spring motion envelope window and remove abnormal fluctuation values; A feedback and monitoring unit, which continuously monitors the working status of each unit and evaluates the coordination degree of each unit in real time; Based on the real-time evaluation, the modified control parameters are transmitted back to the various units through the feedback loop for adjustment.

2. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: The multimodal sensor array includes pressure, acceleration and optical fiber sensors; the multimodal sensor array is arranged at the two end points of the spring, around the suspension arm and the part where the suspension is connected to the vehicle body; the sensor data includes the deformation, stress and vibration information of the spring.

3. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: Identify the deviation of the multi-modal spring data; and correct the multi-modal spring data according to the error, the specific steps are: It includes a principal component analysis method and an autoencoder; using the principal component analysis method to extract key features of the multimodal spring data, inputting the key features into the autoencoder to capture nonlinear errors; A correction weight is calculated based on the error to perform data correction.

4. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: Through the data fusion algorithm, the multi-modal spring data is subjected to multi-dimensional data fusion to generate fused data. The specific steps are as follows: Preprocessing the multi-modal spring data, and performing data alignment and spatiotemporal synchronization; A fusion weight is calculated according to a signal-to-noise ratio of the multi-modal spring data, and the multi-modal spring data is fused based on the fusion weight to generate fused data.

5. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: The processing flow of edge computing specifically includes: Extracting time domain features from the fused data, including amplitude, periodicity and maximum displacement; Convert the time domain features into the frequency domain, extract the frequency domain features, including frequency components, and corresponding peak frequencies and harmonic information; The periodic information, amplitude characteristics and transient characteristics of the spring motion are extracted from the time domain characteristics; the frequency response characteristics and vibration modes of the spring motion are extracted from the frequency domain characteristics; these characteristics are used as time-frequency characteristics and as inputs of the motion envelope parallel optimization method.

6. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: The specific steps of using the motion envelope parallel optimization method to generate a spring motion envelope are as follows: Data allocation: allocating the time-frequency features to generate multiple different time-frequency data sets; allocating the time-frequency data sets to multiple computing nodes; Initialization: Initialize a part of the particle swarm on each of the computing nodes; each particle represents a potential motion envelope solution, having a position, a velocity, and a fitness value; Local optimization: Each computing node performs particle swarm optimization on the corresponding time-frequency data set, calculates the position and velocity of the particles, and updates the fitness value of the particles; each computing node independently optimizes the corresponding time-frequency data set to obtain a local optimal position.

7. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 6, characterized in that: The specific steps of using the motion envelope parallel optimization method to generate a spring motion envelope also include: Information exchange: During each round of particle swarm optimization of each computing node, each computing node exchanges the local optimal position of particles with each other, and selects the optimal solution from all the local optimal positions as the global optimal position; Global convergence: updating the particle swarm of each computing node according to the global optimal position and the local optimal position, and gradually converging until the set number of iterations is reached; Envelope generation: In the final iteration, the particle swarm of each computing node finds the optimal solution; all the optimal solutions are summarized to generate the final spring motion envelope.

8. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: The data within the spring motion envelope window is weighted and smoothed using a Gaussian kernel function to remove abnormal fluctuation values, including high-frequency noise.

9. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: Continuously monitor the working status of each unit and evaluate the coordination degree of each unit in real time. The specific steps are: Monitor the computing load of each unit, the normal transmission of data flow, the correctness of task execution and time delay, and issue an early warning if an abnormality occurs; Assess the degree of coordination among various units, including the real-time response, accuracy of data, and consistency of processing results, and issue early warnings when abnormalities occur.

10. The system for quickly generating motion envelope of a vehicle chassis suspension spring according to claim 1, characterized in that: In the feedback and monitoring unit, the feedback loop is PID control.

Images