Electrical performance test method, device and equipment of high-order computing power automatic driving FPC sensing module and storage medium

Abstract

The invention relates to an electrical performance test method, device and equipment for a high-order computing power automatic driving FPC sensing module and a storage medium, and the method comprises the following steps: collecting an initial electrical signal of the FPC sensing module, and obtaining electrical signal collection data; performing spectrum analysis on the electric signal acquisition data through fast Fourier transform to obtain spectrum characteristic data; performing dynamic response analysis on the FPC sensing module based on the frequency spectrum characteristic data to obtain a dynamic response curve; carrying out probability distribution analysis on the FPC sensing module based on the dynamic response curve to obtain an electrical property probability distribution diagram; and performing performance trend prediction on the FPC sensing module based on the electrical performance probability distribution diagram to obtain a performance trend curve, and generating an electrical performance test report based on the performance trend curve. The technical problem that the traditional testing means always focuses on performance evaluation under the static condition and cannot comprehensively reflect the change of dynamic response under the actual driving condition is solved.

Description

Technical Field

[0001] The present invention relates to the field of FPC sensor module technology, and in particular to an electrical performance testing method, device, equipment and storage medium for a high-order computing power autonomous driving FPC sensor module. Background Art

[0002] With the rapid development of autonomous driving technology, accurate perception of the vehicle's surrounding environment has become essential. High-level computing power autonomous driving systems rely on a variety of sensors to collect data to ensure a safe and efficient driving experience. Flexible printed circuit (FPC) sensor modules, as a lightweight, compact and high-performance sensor solution, play a key role in autonomous vehicles. However, traditional electrical performance testing methods are difficult to meet the requirements of these advanced sensor modules. On the one hand, traditional testing methods often focus on performance evaluation under static conditions and cannot fully reflect the changes in dynamic response under actual driving conditions; on the other hand, due to the lack of effective analysis tools for spectral characteristics, it is difficult to deeply understand the subtle differences in the signal, which limits the accurate grasp of the working status of the FPC sensor module.

[0003] In the existing test process, although the initial electrical signal acquisition of the FPC sensor module can provide certain basic information, the subsequent data processing and analysis are insufficient. Fast Fourier Transform (FFT) is a powerful method to convert time domain signals into frequency domain representation. It can help engineers identify the frequency components in the signal, thereby more clearly understanding the dynamic characteristics of the system. However, in practice, many test schemes do not fully utilize the advantages of FFT for spectrum analysis, resulting in failure to fully explore the deep information behind the electrical signal. In addition, dynamic response analysis usually only focuses on transient behavior under specific operating conditions, while ignoring the probability distribution of performance changes under long-term operation, which makes it more difficult to predict the long-term stability of the sensor module.

[0004] In order to overcome the above challenges, it is necessary to develop a new electrical performance test method that can not only efficiently collect and process complex electrical signals from FPC sensor modules, but also reveal hidden patterns in the signals through advanced spectrum analysis technology, and conduct detailed dynamic response analysis based on this. More importantly, through the probability distribution analysis of the dynamic response curve, the performance of the sensor module in different usage scenarios can be evaluated more scientifically, thereby achieving an accurate prediction of its performance trend. This method can not only improve the reliability and accuracy of the test results, but also provide an important basis for optimizing design and fault diagnosis, and ultimately promote autonomous driving technology to a higher level. Summary of the invention

[0005] The main purpose of the present invention is to provide an electrical performance testing method, device, equipment and storage medium for a high-order computing power autonomous driving FPC sensor module, which solves the technical problem that traditional testing methods often focus on performance evaluation under static conditions and cannot fully reflect the changes in dynamic response under actual driving conditions.

[0006] To achieve the above object, the present invention provides an electrical performance testing method for a high-order computing power autonomous driving FPC sensor module, comprising the following steps: The initial electrical signal of the FPC sensor module is collected by a preset electrical signal sensor to obtain electrical signal collection data; Performing spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum characteristic data; Performing dynamic response analysis on the FPC sensor module based on the frequency spectrum characteristic data to obtain a dynamic response curve; Performing probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; Based on the electrical performance probability distribution diagram, a performance trend prediction is performed on the FPC sensor module to obtain a performance trend curve, and an electrical performance test report is generated based on the performance trend curve.

[0007] Furthermore, the initial electrical signal of the FPC sensor module is collected by a preset electrical signal sensor to obtain electrical signal collection data, including: Applying an electrical signal to the input end of the FPC sensor module, and performing multi-point synchronous electrical signal sampling on the FPC sensor module through a preset electrical signal sensor to obtain initial sampling data; wherein the electrical signal includes a voltage signal and a current signal, and the applied electrical signal is used to test the electrical performance of the FPC sensor module; Performing multi-source signal separation on the initial sampling data, extracting independent signal sources, and obtaining independent signal features; Performing dynamic sampling point interpolation on the independent signal feature to obtain an interpolated independent signal; The interpolated independent signal is amplified to obtain an amplified electrical signal, and the amplified electrical signal data is used as electrical signal acquisition data.

[0008] Furthermore, the spectrum analysis of the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data includes: Performing frequency domain transformation on the electrical signal acquisition data by fast Fourier transform to obtain a spectrum intensity distribution diagram, and extracting harmonic components from the spectrum intensity distribution diagram to obtain a harmonic component data set; Performing power spectrum estimation based on the harmonic component data set to obtain a signal power distribution curve, and performing peak detection on the signal power distribution curve to obtain a characteristic frequency point sequence; Performing phase correlation analysis on the characteristic frequency point sequence to obtain a phase coupling matrix, and performing frequency band segmentation based on the phase coupling matrix to obtain a multi-band characteristic graph; Spectral features are extracted from the multi-band feature graph to obtain spectral feature data.

[0009] Further, the dynamic response analysis of the FPC sensor module is performed based on the frequency spectrum feature data to obtain a dynamic response curve, including: Performing unit pulse excitation conversion on the frequency spectrum feature data to obtain a pulse excitation sequence, and performing pulse response feature extraction based on the pulse excitation sequence to obtain a pulse feature set; Calculating an impulse response function for the pulse feature set, and deriving a transfer function based on the impulse response function to obtain a transfer function vector, wherein the transfer function vector includes zero-pole distribution, amplitude-frequency characteristics, and phase-frequency characteristics; Performing a unit step response analysis based on the transfer function vector to obtain a step response space, and performing a pulse convolution operation on the step response space to obtain a convolution response sequence; Performing dynamic space modeling based on the convolution response sequence to obtain a state space graph, and performing feature trajectory extraction on the state space graph to obtain a trajectory feature set; A response curve is drawn for the trajectory feature set to obtain a dynamic response curve.

[0010] Furthermore, the derivation of the transfer function based on the impulse response function to obtain the transfer function vector includes: Performing frequency domain conversion on the impulse response function by Laplace transform to obtain a complex frequency domain function; Performing zero-pole decomposition on the complex frequency domain function to obtain a zero-pole distribution diagram, wherein the zero-pole distribution diagram is used to characterize the response sensitivity of the FPC sensor module at different frequencies; Performing transfer function approximation on the zero-pole distribution diagram by polynomial fitting to obtain a polynomial coefficient matrix; Based on the polynomial coefficient matrix, a state space equation is constructed to obtain state space data of the FPC sensor module; wherein the state space data includes a state matrix, an input matrix, an output matrix and a transfer matrix; A transfer function is derived based on the state space data to obtain a transfer function vector; wherein the transfer function vector is used to describe the electrical signal transmission capability of the FPC sensor module at different frequencies.

[0011] Furthermore, the probability distribution analysis of the FPC sensor module is performed based on the dynamic response curve to obtain an electrical performance probability distribution diagram, including: The dynamic response curve is sampled in sections to obtain a response characteristic sequence, and the FPC sensor module is subjected to state switching analysis based on the response characteristic sequence to obtain a voltage-current state mapping set; wherein the voltage-current state mapping set includes a voltage fluctuation boundary value, a current response critical point, and a signal switching time point; Dividing the voltage-current state mapping set into density intervals to obtain electrical signal distribution density data, and performing voltage-current correlation calculation based on the electrical signal distribution density data to obtain a state coupling degree sequence, wherein the state coupling degree sequence includes a voltage following characteristic value, a current response delay value, and a signal transmission stability value; Based on the state coupling degree sequence, a performance fluctuation range set of the FPC sensor module is calculated, and interval probability statistics are performed on the performance fluctuation range set to obtain a performance interval probability density diagram; Through a preset component mapping space algorithm, the FPC sensor module is spatially transformed and mapped based on the performance interval probability density map to obtain an electrical performance probability distribution map; wherein the electrical performance probability distribution map is used to reflect the electrical performance probability distribution of each component of the FPC sensor module under different working conditions, and the size of the probability density is represented by color depth or height.

[0012] Further, the performance trend prediction of the FPC sensor module is performed based on the electrical performance probability distribution diagram to obtain a performance trend curve, and an electrical performance test report is generated based on the performance trend curve, including: Performing time series decomposition on the electrical performance probability distribution diagram to obtain a time series feature sequence, and extracting feature points from the time series feature sequence to obtain a key performance feature point set, wherein the key performance feature point set includes a voltage mutation point, a current jump point, and a signal distortion point; Based on the key performance feature point set, the FPC sensor module is subjected to trend analysis to obtain a multi-dimensional trend vector, and based on the multi-dimensional trend vector, trend extrapolation is performed to obtain a performance prediction sequence. Performing multi-dimensional space mapping on the performance prediction sequence to obtain a trend feature space, and reconstructing a trajectory based on the trend feature space to obtain a performance trend curve; Performing critical point analysis based on the performance trend curve to obtain a performance warning threshold set, and performing hierarchical mapping on the performance warning threshold set to obtain a hierarchical warning map; An electrical performance test report is generated based on the graded warning map.

[0013] The present invention also provides an electrical performance testing device for a high-order computing power autonomous driving FPC sensor module, comprising: The acquisition module is used to acquire the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal acquisition data; A first analysis module is used to perform spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data; A second analysis module is used to perform dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve; A third analysis module is used to perform probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; The prediction module is used to predict the performance trend of the FPC sensor module based on the electrical performance probability distribution diagram, obtain a performance trend curve, and generate an electrical performance test report based on the performance trend curve.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The electrical performance test method of the high-order computing power autonomous driving FPC sensor module provided by the present invention includes the following steps: collecting the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal collection data; performing spectrum analysis on the electrical signal collection data through fast Fourier transform to obtain spectrum feature data; performing dynamic response analysis on the FPC sensor module based on the spectrum feature data to obtain a dynamic response curve; performing probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; performing performance trend prediction on the FPC sensor module based on the electrical performance probability distribution diagram to obtain a performance trend curve, and generating an electrical performance test report based on the performance trend curve. It solves the problem that traditional testing methods often focus on performance evaluation under static conditions and cannot fully reflect the changes in dynamic response under actual driving conditions. The generated performance trend curve provides a basis for long-term performance prediction of the FPC sensor module. Based on these predictions, manufacturers and service providers can plan ahead and take preventive measures to extend product life, reduce unexpected downtime, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1It is a schematic diagram of the steps of a method for testing the electrical performance of a high-order computing power autonomous driving FPC sensor module in one embodiment of the present invention; Figure 2 It is a structural block diagram of an electrical performance testing device for a high-order computing power autonomous driving FPC sensor module in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 This is a schematic diagram of the steps of a method for testing the electrical performance of a high-order computing power autonomous driving FPC sensor module in one embodiment of the present invention; In one embodiment of the present invention, a method for testing the electrical performance of a high-order computing power autonomous driving FPC sensor module is provided, comprising the following steps: Step S1, collecting the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal collection data.

[0021] Specifically, in the step of "collecting the initial electrical signal of the FPC sensor module through the preset electrical signal sensor to obtain the electrical signal acquisition data" mentioned above, it should be made clear that the electrical signal sensors are pre-set, which means that they are configured to accurately match the FPC (flexible printed circuit) sensor module. These sensors usually have specific sensitivity, frequency response range and anti-interference ability to ensure that the initial electrical signal emitted by the FPC sensor module can be accurately captured. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module may be installed in different parts of the vehicle, such as around the camera module or inside the lidar, to sense environmental changes and transmit information to the autonomous driving system. When the vehicle starts and starts running, these FPC sensor modules will continue to generate electrical signals reflecting their working status and changes in external conditions. At this time, the preset electrical signal sensors will come into play. They are connected to the key contacts of the FPC sensor module, monitor the electrical signals from the module in real time, and convert these signals into digital data streams, which are the so-called electrical signal acquisition data. In order to ensure the effectiveness of the acquisition process, the design of the sensor must take into account the complex situations in actual applications. For example, in an autonomous driving environment, the vehicle may experience different speeds, accelerations, vibrations and other dynamic factors, all of which will affect the performance of the FPC sensor module. Therefore, the preset electrical signal sensor must not only provide reliable measurement results under static conditions, but also be able to maintain stability and accuracy in dynamic environments. This involves selecting appropriate materials and technologies to ensure that the sensor can work normally over a wide temperature range, while also having good electromagnetic compatibility to avoid interference from other electronic devices. In addition, the quality of the collected data is crucial for subsequent analysis. In an autonomous driving system, every subtle change may be critical information, so the electrical signal sensor must be able to distinguish very weak signal differences. This requires the sensor to have a sufficiently high resolution and signal-to-noise ratio to extract useful features from complex background noise. Once the initial electrical signal is successfully collected, the data can be further processed using technologies such as fast Fourier transform, but all of this is based on an efficient and accurate electrical signal acquisition process, which is achieved through the careful design and configuration of the preset electrical signal sensor.

[0022] Step S2, performing spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data.

[0023] Specifically, in the step of "performing spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data" mentioned above, we deeply explore its specific implementation method and its importance in the electrical performance test of the FPC sensor module of high-order computing power autonomous driving. Fast Fourier transform (FFT) is an efficient algorithm that can convert complex signals in the time domain into frequency domain representation, thereby revealing the various frequency components contained in the signal. This method is crucial to understanding the working status of the FPC sensor module because it allows engineers to identify periodic and non-periodic features in the signal, as well as any abnormal conditions that may affect the performance of the system. For example, in the application scenario of autonomous driving, when the vehicle is running, the FPC sensor module will continue to generate electrical signals that reflect environmental changes and its own working conditions. These signals contain rich information, but they are often wrapped in a complex noise background. By applying fast Fourier transform, we can extract key spectrum feature data from the collected electrical signal data. This means that we convert the original time series data into a series of frequency-amplitude pairs, each of which represents the energy level of a specific frequency in the original signal. This process not only simplifies data analysis, but also makes potential problems easier to detect. Suppose in one instance, the FPC sensor module installed on the autonomous vehicle began to experience intermittent performance fluctuations. To diagnose the problem, technicians first collected the initial electrical signals over a period of time using the preset electrical signal sensor. Then, they applied the fast Fourier transform to process the data. The results showed that abnormally high energy peaks appeared at certain specific frequencies, which may be due to external interference or aging of the internal components of the module. With these spectral feature data, engineers can more accurately locate the source of the fault and take appropriate measures to solve the problem. In addition, the fast Fourier transform can also help predict future performance trends. Through trend analysis of historical spectral feature data, engineers can assess the possibility of long-term stability of the FPC sensor module. For example, if the energy of a certain frequency component is observed to increase gradually over a period of time, this may indicate that the module may face the risk of performance degradation in the future. Therefore, the spectral feature data obtained by the fast Fourier transform is not only a snapshot of the current health status, but also a predictive tool for future behavior, which is of irreplaceable value in ensuring the safety and reliability of the autonomous driving system. In this process, fast Fourier transform plays the role of a bridge, connecting the original electrical signal acquisition data with the subsequent more in-depth dynamic response analysis, thereby providing a solid foundation for optimized design, fault diagnosis and performance improvement.

[0024] Step S3, performing dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve.

[0025] Specifically, in the process of "analyzing the dynamic response of the FPC sensor module based on the spectral feature data to obtain a dynamic response curve" mentioned above, we further explore how to use the spectral feature data obtained after the fast Fourier transform (FFT) to deeply understand the behavior of the FPC sensor module. Once the electrical signal acquisition data is converted into a frequency domain representation through FFT processing and the key spectral feature data is extracted from it, the next step is to use this data to perform dynamic response analysis. The core of this step is to evaluate the reaction characteristics of the FPC sensor module at different frequencies, that is, how it responds to changes in external excitation signals. For example, in the application scenario of high-order computing power autonomous driving, when the vehicle is in a driving state, the FPC sensor module will continuously receive input signals caused by changes in the surrounding environment. These input signals may include data from other sensors, vibrations generated by vehicle movement, and environmental factors such as temperature and humidity. By analyzing the spectral feature data, we can simulate the impact of these external conditions on the performance of the FPC sensor module, thereby constructing its dynamic response model. Specifically, we will draw a dynamic response curve that reflects the response characteristics of the FPC sensor module at different frequencies based on the frequency components and their corresponding amplitude information in the spectral feature data. Take a specific example: suppose an autonomous vehicle is driving on a highway, and the FPC sensor module installed on the vehicle begins to record changes in the surrounding environment. Due to the high speed of the vehicle, the sensor module may experience frequent acceleration, deceleration and steering operations, resulting in rich frequency components in the input signal. By applying the fast Fourier transform, we first obtain the spectral feature data of these signals. Next, when performing dynamic response analysis, we will pay special attention to the data points in the frequency range that are directly related to the vehicle movement. If the response at certain specific frequencies is found to be abnormally strong or unstable, this may indicate potential problems with the FPC sensor module, such as design defects or component aging. In addition, the dynamic response curve not only helps us identify current problems, but also can be used to predict future performance trends. As the vehicle mileage increases, the materials and components of the FPC sensor module may gradually wear out, causing its response characteristics to change. By comparing the spectral feature data collected at different times, we can observe the changes in the corresponding positions on the dynamic response curve. For example, if the response intensity of a certain frequency component gradually weakens over time, this may indicate that the module may be at risk of performance degradation in the future. Therefore, the dynamic response curve is not only a snapshot of the current health status, but also a predictive tool for future behavior, which is crucial to ensure the safety and reliability of autonomous driving systems. In summary, dynamic response analysis based on spectral feature data is an important bridge connecting frequency domain analysis results with actual physical phenomena. It enables engineers to have a deeper understanding of the working principle of the FPC sensor module and provide valuable guidance for its optimized design.In this process, the dynamic response curve, as an intuitive form of expression, not only reveals the response characteristics of the module at different frequencies, but also lays a solid foundation for subsequent probability distribution analysis and performance trend prediction.

[0026] Step S4, performing probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram.

[0027] Specifically, in the process of "performing a probability distribution analysis of the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram" mentioned above, we deeply explore how to use the previously obtained dynamic response curve to further analyze the electrical performance characteristics of the FPC sensor module. After the dynamic response curve is constructed through the spectrum feature data, the next key step is to perform a probability distribution analysis on these response characteristics. The purpose of this step is to quantify the probability of occurrence of response intensity at different frequencies, so as to generate an electrical performance probability distribution diagram that can intuitively reflect the working state of the FPC sensor module. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously records the input signal caused by changes in the surrounding environment. Since the vehicle will experience various complex road conditions and environmental conditions during operation, such as different speeds, acceleration and deceleration, steering, and temperature and humidity changes, these factors will affect the dynamic response of the sensor module. Therefore, through the dynamic response curve, we can see how the response amplitude of the sensor module changes over time at different frequencies. However, in order to more comprehensively evaluate its performance stability, we need to consider the frequency of occurrence of a specific response intensity during long-term use, that is, the probability distribution. Specifically, suppose an autonomous vehicle is driving on a city road, frequently encountering complex traffic conditions caused by traffic lights, pedestrians, and other vehicles. The data collected by the FPC sensor module installed on the vehicle in this environment may show significant volatility. By statistically analyzing the dynamic response curves over a period of time (such as a month or a quarter), we can calculate the proportion of each response intensity value in all measurement points. If certain response intensity values ​​appear frequently, it means that the response at that frequency is relatively stable; on the contrary, if certain response intensity values ​​appear rarely, it indicates that the response at that frequency may be abnormal or unstable. This analysis method helps to identify potential problem areas and provide guidance for subsequent maintenance. In addition, the electrical performance probability distribution diagram not only provides information about the current performance stability, but also lays the foundation for predicting future performance trends. As the vehicle mileage increases, the materials and components of the FPC sensor module may gradually age, causing changes in its response characteristics. By comparing the probability distribution diagrams in different time periods, we can observe the trend of these changes. For example, if it is found that the probability distribution of response intensity in a certain frequency range gradually shifts to a lower value over time, this may indicate that the module may have a risk of performance degradation in the future. Therefore, the probability distribution diagram, as a visualization tool for performance changes, is of great significance for ensuring the safety and reliability of the autonomous driving system. In summary, the probability distribution analysis based on the dynamic response curve is an important link, which converts quantitative data into a visual electrical performance probability distribution diagram, allowing engineers to more clearly understand the working status of the FPC sensor module and its long-term development trend.This method not only improves the accuracy of fault diagnosis, but also provides strong support for optimized design and preventive maintenance, thereby ensuring the stable operation of the autonomous driving system in various complex environments.

[0028] Step S5, predicting the performance trend of the FPC sensor module based on the electrical performance probability distribution diagram to obtain a performance trend curve, and generating an electrical performance test report based on the performance trend curve.

[0029] Specifically, in the process of "predicting the performance trend of the FPC sensor module based on the electrical performance probability distribution map, obtaining a performance trend curve, and generating an electrical performance test report based on the performance trend curve" mentioned above, we explore how to use the previously obtained probability distribution map to predict the future performance changes of the FPC sensor module and finally generate a detailed electrical performance test report. After the electrical performance probability distribution map is obtained through probability distribution analysis, the next step is to use these data to infer the behavior pattern of the FPC sensor module in long-term use. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors changes in the vehicle's surrounding environment and transmits information to the autonomous driving system. Over time, the performance of the sensor module may gradually change due to external conditions (such as temperature, humidity, vibration) and internal aging. Therefore, by analyzing the probability distribution map collected over a period of time, we can identify the trend of changes in the response intensity over time at different frequencies. This trend can be manifested as the response at certain frequencies becoming more stable or more unstable, reflecting the improvement or degradation of module performance. Specifically, suppose an autonomous vehicle experiences a variety of driving conditions over a quarter, including different road conditions on highways and urban roads. The FPC sensor module installed on the vehicle records a large amount of data generated under these conditions. After analyzing the spectral feature data and constructing the dynamic response curve, and further analyzing the probability distribution, we obtain the probability distribution diagram of the electrical performance during this period. Next, we arrange these distribution diagrams in chronological order to observe the development of the response intensity over time in each frequency range. If the response intensity at a certain frequency is found to gradually weaken over time, this may mean that the sensing function corresponding to this frequency is degrading; on the contrary, if the response intensity remains stable or even increases, it indicates that the performance of this part is good. Based on these observations, we can draw a performance trend curve that reflects the long-term performance changes of the FPC sensor module. This curve not only shows the data points in the past, but also extends to the future to predict the performance of the module in the future. For example, if we notice that the response intensity in a certain frequency range has a clear downward trend, it is reasonable to infer that at some point in the future, the response at this frequency may be lower than the acceptable threshold, thereby affecting the reliability of the entire sensing system. At this point, the performance trend curve becomes an early warning tool, reminding engineers to take measures in advance, such as replacing components or adjusting design parameters, to avoid potential problems. Finally, the electrical performance test report generated based on the performance trend curve is a summary and presentation of the entire test process. This report not only contains raw data, spectrum feature analysis, dynamic response curves, and probability distribution diagrams, but more importantly, it provides professional interpretations and suggestions for future performance trends.For autonomous driving applications, such a detailed test report can help manufacturers and service providers better understand the actual working status of the FPC sensor module, and provide an important basis for optimizing product design, improving system reliability and formulating preventive maintenance plans. At the same time, it also provides valuable information for subsequent quality control and fault diagnosis, ensuring that the autonomous driving system can operate safely and reliably in various complex environments. In summary, the process from the electrical performance probability distribution diagram to the performance trend prediction and finally generating the electrical performance test report is a scientific decision-making process driven by data. It not only deepens the understanding of the working characteristics of the FPC sensor module, but also lays a solid foundation for achieving more efficient and safer autonomous driving technology.

[0030] In a specific embodiment, the initial electrical signal of the FPC sensor module is collected by a preset electrical signal sensor to obtain electrical signal collection data, including: Applying an electrical signal to the input end of the FPC sensor module, and performing multi-point synchronous electrical signal sampling on the FPC sensor module through a preset electrical signal sensor to obtain initial sampling data; wherein the electrical signal includes a voltage signal and a current signal, and the applied electrical signal is used to test the electrical performance of the FPC sensor module; Performing multi-source signal separation on the initial sampling data, extracting independent signal sources, and obtaining independent signal features; Performing dynamic sampling point interpolation on the independent signal feature to obtain an interpolated independent signal; The interpolated independent signal is amplified to obtain an amplified electrical signal, and the amplified electrical signal data is used as electrical signal acquisition data.

[0031] Specifically, the process of "collecting the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain the electrical signal acquisition data" mentioned above involves a series of precise operations and analysis steps. The process starts with applying specific electrical signals to the input end of the FPC sensor module, including voltage signals and current signals, and performing multi-point synchronous sampling of the FPC sensor module through a preset electrical signal sensor to obtain a series of initial sampling data. These data are the basis for all subsequent analysis work, and they directly reflect the response characteristics of the FPC sensor module when it is stimulated by external stimuli. For example, in a high-order computing power autonomous driving system, the FPC sensor module is used to monitor the environmental changes around the vehicle in real time and feed back to the autonomous driving control system. In order to ensure that the module can perform tasks accurately and without error, it must first be subjected to rigorous electrical performance testing. In this process, engineers will apply a set of carefully designed electrical signals to the FPC sensor module, which is designed to simulate various situations that may be encountered in actual application scenarios. In this way, the module's responsiveness and stability can be fully evaluated. At the same time, the method of multi-point synchronous sampling can obtain electrical signal information at multiple different positions at the same time point, making the collected data richer and more detailed, which helps to understand the working mechanism inside the module more accurately. Next, the initial sampling data obtained needs to be further processed to extract independent signal features. Since in actual operation, the information recorded at each sampling point is often the result of a mixture of multiple signals, it is necessary to apply multi-source signal separation technology to decompose these complex data. This process is similar to unraveling a tangled ball of thread, with the goal of finding each independent clue - that is, each independent signal source. Doing so not only improves the accuracy of data analysis, but is also crucial for identifying and eliminating interference factors. For example, during the driving of an autonomous vehicle, signals from multiple sources such as the engine, tire friction, and external electromagnetic fields may be superimposed on each other to affect the normal operation of the FPC sensor module. Through multi-source signal separation, we can accurately distinguish these different signal components, so as to better grasp the true performance of the module. Once the independent signal features are obtained, the next step is to perform dynamic sampling point interpolation on them. This step involves estimating the signal values ​​at time or spatial positions that are not directly measured based on known sampling points. Simply put, it is like drawing a smooth curve between two known points, making the entire signal change process look more coherent. This processing method is particularly suitable for signals with nonlinear change trends, because they are often difficult to fully describe with traditional uniformly spaced sampling. For FPC sensor modules, dynamic sampling point interpolation can help us understand more carefully its behavior patterns when facing rapidly changing input signals, such as when the vehicle suddenly accelerates or decelerates, how the module quickly adjusts its state to adapt to new working conditions.After the above steps, the interpolated independent signals obtained need to be amplified. This is because the original signal strength may not be sufficient to support subsequent detailed analysis or direct application in certain application scenarios. By properly amplifying the signal, it can be ensured that even very weak changes can be clearly displayed. This is especially important for detecting subtle defects in FPC sensor modules, because it allows technicians to find small problems that may have been overlooked. The amplified electrical signal ultimately constitutes the complete electrical signal acquisition data, which becomes one of the important bases for evaluating module performance. For example, in an autonomous driving system, any small error may lead to serious consequences, so it is crucial to ensure the data quality and accuracy of each link. In summary, the entire process of "collecting the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal acquisition data" is a highly specialized and technical operation process. It is closely linked and indispensable from applying electrical signals, multi-point synchronous sampling to multi-source signal separation, dynamic sampling point interpolation to signal amplification. It is through such a set of systematic testing methods that we can deeply understand the internal working principle of the FPC sensor module and provide a solid foundation for its optimization and improvement. In addition, this also provides a strong guarantee for ensuring the safety and reliability of key application areas such as autonomous driving. Throughout the process, every detail is carefully designed and strictly controlled to ensure the authenticity and effectiveness of the final result.

[0032] In a specific embodiment, the spectrum analysis of the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data includes: Performing frequency domain transformation on the electrical signal acquisition data by fast Fourier transform to obtain a spectrum intensity distribution diagram, and extracting harmonic components from the spectrum intensity distribution diagram to obtain a harmonic component data set; Performing power spectrum estimation based on the harmonic component data set to obtain a signal power distribution curve, and performing peak detection on the signal power distribution curve to obtain a characteristic frequency point sequence; Performing phase correlation analysis on the characteristic frequency point sequence to obtain a phase coupling matrix, and performing frequency band segmentation based on the phase coupling matrix to obtain a multi-band characteristic graph; Spectral features are extracted from the multi-band feature graph to obtain spectral feature data.

[0033] Specifically, in the process of "performing spectrum analysis on the electrical signal acquisition data through fast Fourier transform to obtain spectrum feature data" mentioned above, a series of complex and precise operation steps are involved. The process starts with converting the electrical signal acquisition data into a frequency domain representation, that is, by applying fast Fourier transform (FFT) to these data, we can obtain a spectrum intensity distribution diagram and further extract a harmonic component data set from it. This step is the basis of the entire spectrum analysis, which allows us to intuitively see the energy distribution of each frequency component in the signal. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors environmental changes around the vehicle and transmits information to the autonomous driving system. In order to ensure the accuracy and reliability of this information, the electrical signals generated by the sensor module must be deeply analyzed. After engineers obtain preliminary electrical signal acquisition data from the FPC sensor module, they first use the fast Fourier transform algorithm to convert the original signal in the time domain into a frequency domain representation. Doing so can reveal the periodic and non-periodic components in the signal, as well as any abnormal conditions that may affect system performance. In this example, suppose an autonomous vehicle is driving on a highway, and the FPC sensor module installed on the vehicle begins to record changes in the surrounding environment. Due to the high speed of the vehicle, the sensor module may experience frequent acceleration, deceleration and steering operations, resulting in a rich frequency component in the input signal. By applying the fast Fourier transform, we first obtain the spectrum intensity distribution map of these signals, which provides a basis for the subsequent harmonic component extraction. Next, based on the obtained spectrum intensity distribution map, we will extract the harmonic components. This is because the actual signal is often composed of multiple sine waves of different frequencies, and some components at specific frequencies may be key information. Therefore, identifying and separating these harmonic components is crucial to understanding the nature of the signal. Specifically, we will determine the main harmonic components based on the peak position in the spectrum intensity distribution map and form them into a data set. This process is similar to distinguishing the sound of each instrument from a complex background music, allowing us to more clearly understand each independent frequency component. In the example of an autonomous vehicle, if the response at certain specific frequencies is found to be abnormally strong or unstable, this may indicate potential problems with the FPC sensor module, such as design defects or component aging. Once the harmonic component data set is obtained, the next step is to perform power spectrum estimation to generate a signal power distribution curve. The purpose of this stage is to quantify the energy level of each frequency component and then evaluate its importance in the entire signal. By calculating the power value at different frequencies, we can draw a trend line that reflects the change of signal energy with frequency - the signal power distribution curve. Next, peak detection will be performed on this curve to identify those frequency points with significant energy contribution, which is the so-called characteristic frequency point sequence.These characteristic frequency points not only represent the main components of the signal, but may also be key clues for diagnosing problems. For example, during the driving of an autonomous vehicle, if the power in a certain frequency range suddenly increases, this may indicate that a new interference source has appeared in the area or that some changes have occurred inside the module. Subsequently, we will perform phase correlation analysis on the characteristic frequency point sequence and construct a phase coupling matrix. This is because in addition to amplitude information, the phase relationship also has an important impact on the signal characteristics. The phase coupling matrix reflects the interaction between different frequency components and helps us better understand the intrinsic relationship between them. Based on this matrix, we can further implement frequency band segmentation to obtain multi-band feature maps. This segmentation method allows us to divide complex spectral data into several manageable small parts, and each multi-band feature map focuses on the characteristics of the signal in a specific frequency range. For example, in the application of autonomous vehicles, by analyzing the characteristics in different frequency bands, we can more accurately locate those frequency components that are directly related to vehicle movement, such as engine speed, tire rotation, etc., thereby improving the response accuracy of the system. Finally, spectrum feature extraction is performed on the multi-band feature map to obtain comprehensive spectrum feature data. This step aims to summarize all the existing information and extract the core features that best represent the working status of the FPC sensor module. This method can not only simplify the data analysis process, but also enhance the explanatory power and operability of the results. For example, when the performance of an autonomous vehicle fluctuates after a long period of operation, engineers can quickly find out the cause of the performance degradation by comparing the new and old spectrum feature data, and take corresponding measures to solve it. In summary, the whole process of "spectral analysis of electrical signal acquisition data through fast Fourier transform to obtain spectrum feature data" is a scientific exploration journey from shallow to deep and progressive. It starts from the initial frequency domain transformation, through harmonic component extraction, power spectrum estimation, characteristic frequency point sequence identification, phase correlation analysis to frequency band segmentation and spectrum feature extraction, each link is closely connected and indispensable. It is through such a systematic analysis method that we can deeply explore the electrical performance secrets behind the FPC sensor module and provide solid data support for its optimization and improvement. In addition, this also lays an important technical foundation for ensuring the safety and reliability of the autonomous driving system. Throughout the process, every detail is carefully designed and strictly controlled to ensure the authenticity and effectiveness of the final result.

[0034] In a specific embodiment, the dynamic response analysis of the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve includes: Performing unit pulse excitation conversion on the frequency spectrum feature data to obtain a pulse excitation sequence, and performing pulse response feature extraction based on the pulse excitation sequence to obtain a pulse feature set; Calculating an impulse response function for the pulse feature set, and deriving a transfer function based on the impulse response function to obtain a transfer function vector, wherein the transfer function vector includes zero-pole distribution, amplitude-frequency characteristics, and phase-frequency characteristics; Performing a unit step response analysis based on the transfer function vector to obtain a step response space, and performing a pulse convolution operation on the step response space to obtain a convolution response sequence; Performing dynamic space modeling based on the convolution response sequence to obtain a state space graph, and performing feature trajectory extraction on the state space graph to obtain a trajectory feature set; A response curve is drawn for the trajectory feature set to obtain a dynamic response curve.

[0035] Specifically, in the process of "analyzing the dynamic response of the FPC sensor module based on the spectral feature data to obtain a dynamic response curve", we explored how to use the spectral feature data to reveal the behavior pattern of the FPC sensor module under different excitation conditions. The process starts with the unit pulse excitation conversion of the spectral feature data, and finally generates a dynamic response curve that can intuitively reflect the working state of the module through a series of complex and precise operation steps. This process not only provides an important basis for understanding the performance of the module, but also lays a solid foundation for optimizing the design and fault diagnosis. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors the environmental changes around the vehicle and transmits the information to the autonomous driving system. In order to ensure the accuracy and reliability of this information, the electrical signals generated by the sensor module must be deeply analyzed for dynamic response. When engineers obtain the spectral feature data, they first perform unit pulse excitation conversion on these data to simulate various transient situations that may occur in actual applications. Specifically, unit pulse excitation is an ideal input signal that can excite all frequency components of the system in an instant, so that we can observe the response characteristics at each frequency. In this way, a pulse excitation sequence can be obtained, which contains all the frequency information that may affect the operation of the module. Then, based on this pulse excitation sequence, the pulse response feature is extracted to obtain the pulse feature set. This step is similar to using a fine comb to comb out the response details at each frequency point, making the subsequent analysis more accurate. Next, for the obtained pulse feature set, the impulse response function needs to be calculated, and the transfer function vector is further derived. This is because the impulse response function describes how the system responds to an idealized input (such as a unit pulse), while the transfer function provides a more general mathematical model for representing the relationship between input and output. The transfer function vector includes key parameters such as zero-pole distribution, amplitude-frequency characteristics, and phase-frequency characteristics, which together determine the dynamic behavior of the system. In the example of an autonomous vehicle, suppose a car is driving on a highway. At this time, the FPC sensor module installed on the vehicle will continuously receive input signals caused by changes in the surrounding environment. By converting these signals into unit pulse excitation and extracting the pulse feature set, we can calculate the impulse response function and then derive the transfer function vector. If the response at certain specific frequencies is found to be abnormally strong or unstable, this may indicate potential problems with the FPC sensor module, such as design defects or component aging. After obtaining the transfer function vector, the next step is to perform a unit step response analysis on it to obtain the step response space. Step response refers to the behavior of a system when a constant input is suddenly applied. It is one of the common methods for evaluating the stability and rapidity of a system. By performing a unit step response analysis on the transfer function vector, we can construct a step response space that reflects the dynamic changes of the system.Then, pulse convolution is performed on this space to obtain a convolution response sequence. This convolution operation allows us to combine the previously obtained pulse excitation sequence with the step response to simulate a more realistic dynamic response process. For example, during the driving of an autonomous vehicle, if the response in a certain frequency range shows significant delay or oscillation, this may indicate the emergence of a new interference source in the area or some changes have occurred inside the module. By performing pulse convolution operations on the step response space, we can more accurately predict the impact of these changes on future performance. Subsequently, dynamic space modeling is performed based on the convolution response sequence to obtain a state space diagram. A state space diagram is a graphical representation method that shows the changes of various state variables in the system over time. By extracting features from the trajectories of these variables, we can obtain trajectory feature sets that focus on the behavior patterns of the FPC sensor module under different working conditions. For example, in the application of autonomous vehicles, by analyzing the response characteristics of the module under different states, we can more accurately locate those frequency components that are directly related to vehicle motion, such as engine speed, tire rotation, etc., thereby improving the response accuracy of the system. In addition, the state space diagram can also help us identify any factors that may cause performance degradation, such as component aging or external interference. Finally, the response curve is drawn based on the trajectory feature set to obtain the dynamic response curve. This curve not only summarizes all the existing information, but also presents the performance of the FPC sensor module in the entire test process in an intuitive way. The dynamic response curve is the final result of the entire analysis process, and it provides engineers with a valuable reference. For example, when the performance of an autonomous vehicle fluctuates after a long period of operation, technicians can quickly find out the cause of the performance degradation by comparing the new and old dynamic response curves, and take corresponding measures to solve it. In addition, the dynamic response curve can also be used to guide future design improvements to ensure that the module can maintain stable and reliable performance in various complex environments. In summary, the entire process of "analyzing the dynamic response of the FPC sensor module based on the spectral feature data to obtain the dynamic response curve" is a scientific exploration journey from shallow to deep and progressive. It starts from the initial unit pulse excitation conversion, through pulse response feature extraction, impulse response function calculation, transfer function derivation, unit step response analysis, pulse convolution operation, and dynamic space modeling and response curve drawing. Each link is closely connected and indispensable. It is through such a systematic analysis method that we can deeply explore the electrical performance secrets behind the FPC sensor module and provide solid data support for its optimization and improvement. In addition, this also lays an important technical foundation for ensuring the safety and reliability of the autonomous driving system. Throughout the process, every detail is carefully designed and strictly controlled to ensure the authenticity and effectiveness of the final result.

[0036] In a specific embodiment, the derivation of the transfer function based on the impulse response function to obtain the transfer function vector includes: Performing frequency domain conversion on the impulse response function by Laplace transform to obtain a complex frequency domain function; Performing zero-pole decomposition on the complex frequency domain function to obtain a zero-pole distribution diagram, wherein the zero-pole distribution diagram is used to characterize the response sensitivity of the FPC sensor module at different frequencies; Performing transfer function approximation on the zero-pole distribution diagram by polynomial fitting to obtain a polynomial coefficient matrix; Based on the polynomial coefficient matrix, a state space equation is constructed to obtain state space data of the FPC sensor module; wherein the state space data includes a state matrix, an input matrix, an output matrix and a transfer matrix; A transfer function is derived based on the state space data to obtain a transfer function vector; wherein the transfer function vector is used to describe the electrical signal transmission capability of the FPC sensor module at different frequencies.

[0037] Specifically, in the process of "deriving the transfer function based on the impulse response function to obtain the transfer function vector" mentioned above, we have explored in depth how to use the impulse response function to construct the mathematical model of the FPC sensor module and finally obtain the transfer function vector that describes its transmission capability. This process starts with the frequency domain conversion of the impulse response function through Laplace transform, and gradually goes deep into zero-pole decomposition, polynomial fitting, state space equation construction and the final transfer function derivation. Each step is closely linked and indispensable, and together they constitute a complete analysis chain, allowing us to fully and accurately understand the working characteristics of the FPC sensor module. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors environmental changes around the vehicle and transmits information to the autonomous driving system. In order to ensure the accuracy and reliability of this information, it is necessary to conduct in-depth dynamic response analysis of the electrical signals generated by the sensor module. When engineers obtain the impulse response function, they first apply Laplace transform to the function to convert it from the time domain to the complex frequency domain representation. Laplace transform is a powerful mathematical tool that can reveal the relationship between time delay and frequency components in a signal. Through this transformation, we can obtain the complex frequency domain function, which is similar to converting a complex map into a more easily interpreted topographic map, making subsequent analysis more intuitive and efficient. Next, for the obtained complex frequency domain function, zero-pole decomposition is required to generate a zero-pole distribution diagram. This is because each complex frequency domain function can be decomposed into several simple components, namely zeros and poles. These zeros and poles not only determine the stability of the system, but also affect its response sensitivity to different frequency inputs. The zero-pole distribution diagram is like an internal structure diagram of the system, which clearly shows the response characteristics of the FPC sensor module at various frequencies. In the example of an autonomous vehicle, suppose a car is driving on the highway. At this time, the FPC sensor module installed on the vehicle will continuously receive input signals caused by changes in the surrounding environment. By converting these signals to unit pulse excitation and extracting the impulse response function, and then applying Laplace transform and zero-pole decomposition, we can draw a zero-pole distribution diagram. If the response at certain specific frequencies is found to be abnormally strong or unstable, this may indicate potential problems with the FPC sensor module, such as design defects or component aging. After obtaining the zero-pole distribution diagram, the next step is to approximate the transfer function of the diagram through polynomial fitting to obtain the polynomial coefficient matrix. This method aims to find the mathematical expression that best represents the characteristics of the zero-pole distribution in order to more accurately describe the dynamic behavior of the system. Polynomial fitting is like fitting a set of smooth curves to the data points in the scatter plot, allowing us to summarize complex phenomena in a concise form. Specifically, we will construct a polynomial expression based on the position information in the zero-pole distribution diagram and calculate the corresponding coefficient matrix.This matrix contains all the necessary parameters to reconstruct the original transfer function. For example, in the application of self-driving cars, polynomial fitting can better capture those frequency components that are directly related to vehicle motion, such as engine speed, tire rotation, etc., thereby improving the response accuracy of the system. Subsequently, the state space equation is constructed based on the polynomial coefficient matrix to obtain the state space data of the FPC sensor module. The state space equation is a general mathematical model that can simultaneously describe the internal state of the system and its response to external inputs. In this way, we can have a more comprehensive understanding of the behavior mode of the FPC sensor module under different working conditions. The state space data includes the state matrix, input matrix, output matrix and transfer matrix, which together form a complete mathematical framework for simulating and predicting the performance of the module. For example, during the driving of an autonomous vehicle, if the response within a certain frequency range shows significant delay or oscillation, this may indicate that a new interference source has appeared in the area or some changes have occurred inside the module. By analyzing the state space data, we can more accurately predict the impact of these changes on future performance and take appropriate measures to address them. Finally, the transfer function is derived based on the state space data to obtain the transfer function vector. The transfer function vector is a key result that describes the ability of the FPC sensor module to transmit electrical signals at different frequencies. This vector not only summarizes all the existing information, but also presents the working characteristics of the module in mathematical form. For example, when the performance of an autonomous vehicle fluctuates after a long period of operation, technicians can quickly find out the cause of the performance degradation by comparing the old and new transfer function vectors, and take corresponding measures to solve it. In addition, the transfer function vector can also be used to guide future design improvements to ensure that the module can maintain stable and reliable performance in various complex environments. In summary, the entire process of "deriving the transfer function based on the impulse response function to obtain the transfer function vector" is a scientific exploration journey from shallow to deep and layer by layer. It starts from the initial Laplace transform, through zero-pole decomposition, polynomial fitting, to state space equation construction and transfer function derivation, each link is closely connected and indispensable. It is through such a systematic analysis method that we can deeply explore the electrical performance secrets behind the FPC sensor module and provide solid data support for its optimization and improvement. In addition, this also lays an important technical foundation for ensuring the safety and reliability of the autonomous driving system. Throughout the entire process, every detail is carefully designed and strictly controlled to ensure the authenticity and effectiveness of the final result.

[0038] In a specific embodiment, the probability distribution analysis of the FPC sensor module based on the dynamic response curve is performed to obtain an electrical performance probability distribution diagram, including: The dynamic response curve is sampled in sections to obtain a response characteristic sequence, and the FPC sensor module is subjected to state switching analysis based on the response characteristic sequence to obtain a voltage-current state mapping set; wherein the voltage-current state mapping set includes a voltage fluctuation boundary value, a current response critical point, and a signal switching time point; Dividing the voltage-current state mapping set into density intervals to obtain electrical signal distribution density data, and performing voltage-current correlation calculation based on the electrical signal distribution density data to obtain a state coupling degree sequence, wherein the state coupling degree sequence includes a voltage following characteristic value, a current response delay value, and a signal transmission stability value; Based on the state coupling degree sequence, a performance fluctuation range set of the FPC sensor module is calculated, and interval probability statistics are performed on the performance fluctuation range set to obtain a performance interval probability density diagram; Through a preset component mapping space algorithm, the FPC sensor module is spatially transformed and mapped based on the performance interval probability density map to obtain an electrical performance probability distribution map; wherein the electrical performance probability distribution map is used to reflect the electrical performance probability distribution of each component of the FPC sensor module under different working conditions, and the size of the probability density is represented by color depth or height.

[0039] Specifically, in the process of "performing probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain the electrical performance probability distribution diagram" mentioned above, we have deeply explored how to use the dynamic response curve to evaluate the electrical performance of the FPC sensor module, and finally generate an electrical performance probability distribution diagram that can reflect the probability distribution of the electrical performance of each component under different working conditions. This process starts with segmented sampling of the dynamic response curve, and gradually goes deep into state switching analysis, construction of voltage-current state mapping set, density interval division, calculation of electrical signal distribution density data, voltage and current correlation calculation, establishment of state coupling degree sequence, calculation of performance fluctuation range set, interval probability statistics, and space conversion and mapping. Each step is closely linked and indispensable. Together, they constitute a complete analysis chain, allowing us to fully and accurately understand the electrical performance of the FPC sensor module. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors environmental changes around the vehicle and transmits information to the autonomous driving system. In order to ensure the accuracy and reliability of this information, it is necessary to conduct an in-depth probability distribution analysis of the dynamic response curve generated by the sensor module. When engineers get the dynamic response curve, they first sample the curve in segments to obtain a series of response feature sequences. These sequences not only record the voltage and current changes of the FPC sensor module at various time points, but also provide a basis for subsequent state switching analysis. By performing state switching analysis on the response feature sequence, a voltage-current state mapping set can be obtained. This set includes key parameters such as voltage fluctuation boundary value, current response critical point and signal switching time point, which together describe the characteristics of the module under different working states. For example, during the driving of an autonomous vehicle, if the response within a certain frequency range shows significant changes or instability, this may indicate that a new interference source has appeared in the area or that some changes have occurred inside the module. Through state switching analysis, we can more accurately identify the time and location of these potential problems. With the voltage-current state mapping set, the next step is to divide the set into density intervals to obtain electrical signal distribution density data. This is because different voltage-current state mapping sets reflect the performance of the module under different working conditions, and density interval division helps us better understand the distribution law of these states. Based on the electrical signal distribution density data, voltage and current correlation calculations can be further performed to obtain a state coupling degree sequence. The state coupling degree sequence is an important concept. It includes data in multiple dimensions, such as voltage following characteristic value, current response delay value and signal transmission stability value, to measure the correlation between voltage and current.For example, if we notice that the change in voltage within a certain frequency range does not cause a corresponding change in current, it is reasonable to infer that there may be a low correlation between voltage and current at this frequency, which may be caused by the failure of some components inside the module or external interference. By establishing the state coupling degree sequence, we can more accurately capture the relationship between voltage and current, providing support for further performance analysis. Subsequently, based on the state coupling degree sequence, the performance fluctuation range set of the FPC sensor module can be calculated, and the interval probability statistics of these fluctuation range sets can be performed to obtain the performance interval probability density map. The performance fluctuation range set describes the magnitude of the performance change of the module under different working conditions, and the interval probability statistics estimates the probability of its occurrence based on these change magnitudes. The performance interval probability density map provides an intuitive form of expression, which not only shows the past data points, but also indicates the size of the probability density by color depth or height. For example, if we notice that the performance fluctuations within a certain frequency range are large and occur frequently, it is reasonable to infer that the performance at this frequency is unstable, which may affect the reliability of the entire sensor system. At this time, the performance interval probability density map becomes an early warning tool, reminding engineers to take measures in advance, such as replacing components or adjusting design parameters, to avoid potential problems. Finally, the FPC sensor module is spatially transformed and mapped based on the performance interval probability density map through the preset component mapping space algorithm to obtain the electrical performance probability distribution map. The component mapping space algorithm is a technology used to convert abstract probability data into specific spatial expressions, which allows us to visualize complex performance analysis results for easy understanding and application. The electrical performance probability distribution map not only summarizes all existing information, but also provides valuable information for subsequent quality control and fault diagnosis. For example, in the application of self-driving cars, by analyzing the electrical performance probability distribution map, engineers can identify those frequency components or working conditions that are prone to problems and take preventive measures in advance. This not only improves the overall safety of the system, but also provides a valuable reference for optimizing the design. In summary, the whole process of "performing a probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution map" is a scientific exploration journey from shallow to deep and progressive. It starts from the initial segmented sampling, through state switching analysis, construction of voltage-current state mapping set, density interval division, calculation of electrical signal distribution density data, voltage and current correlation calculation, establishment of state coupling degree sequence, calculation of performance fluctuation range set, interval probability statistics, and finally space conversion and mapping. Each link is closely connected and indispensable. It is through such a set of systematic analysis methods that we can deeply explore the electrical performance secrets behind the FPC sensor module and provide solid data support for its optimization and improvement. In addition, this also lays an important technical foundation for ensuring the safety and reliability of the autonomous driving system.Throughout the entire process, every detail is carefully designed and strictly controlled to ensure the authenticity and validity of the final results. The resulting electrical performance probability distribution map not only summarizes all the existing information, but also provides valuable information for subsequent quality control and fault diagnosis, ensuring that the autonomous driving system can operate safely and reliably in various complex environments.

[0040] In a specific embodiment, the performance trend prediction of the FPC sensor module is performed based on the electrical performance probability distribution diagram to obtain a performance trend curve, and an electrical performance test report is generated based on the performance trend curve, including: Performing time series decomposition on the electrical performance probability distribution diagram to obtain a time series feature sequence, and extracting feature points from the time series feature sequence to obtain a key performance feature point set, wherein the key performance feature point set includes a voltage mutation point, a current jump point, and a signal distortion point; Based on the key performance feature point set, the FPC sensor module is subjected to trend analysis to obtain a multi-dimensional trend vector, and based on the multi-dimensional trend vector, trend extrapolation is performed to obtain a performance prediction sequence. Performing multi-dimensional space mapping on the performance prediction sequence to obtain a trend feature space, and reconstructing a trajectory based on the trend feature space to obtain a performance trend curve; Performing critical point analysis based on the performance trend curve to obtain a performance warning threshold set, and performing hierarchical mapping on the performance warning threshold set to obtain a hierarchical warning map; An electrical performance test report is generated based on the graded warning map.

[0041] Specifically, in the process of "predicting the performance trend of the FPC sensor module based on the electrical performance probability distribution map, obtaining a performance trend curve, and generating an electrical performance test report based on the performance trend curve" mentioned above, we have deeply explored how to use the electrical performance probability distribution map to predict the future performance changes of the FPC sensor module, and finally generate a detailed electrical performance test report. This process starts with the time series decomposition of the electrical performance probability distribution map, and gradually goes deep into feature point extraction, trend analysis, trend extrapolation, multi-dimensional space mapping, trajectory reconstruction, critical point analysis, and the generation of graded warning maps. Each step is closely linked and indispensable. Together, they constitute a complete prediction chain, allowing us to comprehensively and accurately evaluate the long-term performance of the FPC sensor module. For example, in the application scenario of high-order computing power autonomous driving, the FPC sensor module continuously monitors environmental changes around the vehicle and transmits information to the autonomous driving system. In order to ensure the accuracy and reliability of this information, in-depth trend prediction and performance evaluation of the electrical signals generated by the sensor module must be performed. When engineers get the electrical performance probability distribution map, they first perform time series decomposition on the map to capture the response characteristics in different time periods. Specifically, by performing time series decomposition on the electrical performance probability distribution map, a series of time series feature sequences can be obtained, which record the voltage and current changes of the FPC sensor module at various time points. Based on these time series feature sequences, feature point extraction can be further performed to obtain a set of key performance feature points. This set includes important parameters such as voltage mutation points, current jump points, and signal distortion points, which together describe the abnormal behavior of the module under different working conditions. For example, during the driving of an autonomous vehicle, if the response within a certain frequency range shows significant delay or oscillation, this may indicate that a new source of interference has appeared in the area or that some changes have occurred inside the module. Through feature point extraction, we can more accurately identify the time and location of these potential problems. With the set of key performance feature points, the next step is to perform trend analysis on the FPC sensor module based on these feature points to obtain a multi-dimensional trend vector. This is because each feature point not only reflects the current state, but also contains the possibility of future changes. With this approach, we can construct a multidimensional space where each dimension represents a specific performance indicator (such as voltage stability, current response speed, etc.), and the trend vector describes the change trend of these indicators over time. Based on the multidimensional trend vector, trend extrapolation can be performed to obtain a performance prediction sequence, that is, the expected value of module performance changes in the future. This prediction method allows us to detect possible problems in advance and take corresponding preventive measures. For example, when an autonomous vehicle experiences performance fluctuations after a long period of operation, technicians can quickly find out the cause of the performance degradation by comparing the old and new performance prediction sequences, and take corresponding measures to solve it.Subsequently, the performance prediction sequence is mapped in a multidimensional space to obtain a trend feature space, and the trajectory is reconstructed based on the space to obtain a performance trend curve. The trend feature space is an abstract concept that integrates performance data from multiple dimensions to form a more intuitive form of expression. Through trajectory reconstruction, we can draw a dynamic curve that reflects the performance changes of the FPC sensor module. This curve not only shows the past data points, but also extends to the future to predict the performance of the module in the future. For example, if we notice that the response intensity in a certain frequency range has a significant downward trend, it can be reasonably inferred that at some point in the future, the response at this frequency may be lower than the acceptable threshold, thereby affecting the reliability of the entire sensor system. At this point, the performance trend curve becomes an early warning tool, reminding engineers to take measures in advance, such as replacing components or adjusting design parameters, to avoid potential problems. Finally, critical point analysis is performed based on the performance trend curve to obtain a set of performance warning thresholds, and these threshold sets are hierarchically mapped to obtain a hierarchical warning map. Critical point analysis aims to identify critical moments that may cause a sharp deterioration in system performance, while hierarchical mapping classifies these critical points according to different risk levels. The graded warning map provides a clear risk view, allowing users to understand at a glance which components have a higher risk of failure or performance uncertainty in a specific state. For example, in the application of autonomous vehicles, by analyzing the graded warning map, engineers can identify those frequency components or working conditions that are prone to problems and take preventive measures in advance. This not only improves the overall safety of the system, but also provides a valuable reference for optimizing the design. In summary, the entire process of "predicting the performance trend of the FPC sensor module based on the electrical performance probability distribution map, obtaining the performance trend curve, and generating the electrical performance test report based on the performance trend curve" is a scientific exploration journey from shallow to deep and progressive. It starts from the initial time series decomposition, through feature point extraction, trend analysis, trend extrapolation, multi-dimensional space mapping, trajectory reconstruction to critical point analysis and the generation of graded warning maps. Each link is closely connected and indispensable. It is through such a set of systematic prediction methods that we can deeply explore the electrical performance secrets behind the FPC sensor module and provide solid data support for its optimization and improvement. In addition, this also lays an important technical foundation for ensuring the safety and reliability of autonomous driving systems. Throughout the entire process, every detail is carefully designed and strictly controlled to ensure the authenticity and validity of the final results. The final electrical performance test report not only summarizes all the existing information, but also provides valuable information for subsequent quality control and fault diagnosis, ensuring that the autonomous driving system can operate safely and reliably in various complex environments.

[0042] The above describes the electrical performance test method of the high-order computing power autonomous driving FPC sensor module in the embodiment of the present invention. The following describes the electrical performance test device of the high-order computing power autonomous driving FPC sensor module in the embodiment of the present invention. Please refer to Figure 2 , an embodiment of the electrical performance testing device of the high-order computing power autonomous driving FPC sensor module in the embodiment of the present invention includes: The acquisition module 21 is used to acquire the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal acquisition data; A first analysis module 22 is used to perform spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data; A second analysis module 23 is used to perform a dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve; A third analysis module 24 is used to perform probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; The prediction module 25 is used to predict the performance trend of the FPC sensor module based on the electrical performance probability distribution diagram, obtain a performance trend curve, and generate an electrical performance test report based on the performance trend curve.

[0043] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0044] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0045] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0046] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0047] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0048] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0049] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for testing the electrical performance of a high-order computing power autonomous driving FPC sensor module, characterized in that: The following steps are involved: The initial electrical signal of the FPC sensor module is collected by a preset electrical signal sensor to obtain electrical signal collection data; Performing spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum characteristic data; Performing dynamic response analysis on the FPC sensor module based on the frequency spectrum characteristic data to obtain a dynamic response curve; Performing probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; Based on the electrical performance probability distribution diagram, a performance trend prediction is performed on the FPC sensor module to obtain a performance trend curve, and an electrical performance test report is generated based on the performance trend curve; The performing dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve includes: Performing unit pulse excitation conversion on the frequency spectrum feature data to obtain a pulse excitation sequence, and performing pulse response feature extraction based on the pulse excitation sequence to obtain a pulse feature set; Calculating an impulse response function for the pulse feature set, and deriving a transfer function based on the impulse response function to obtain a transfer function vector, wherein the transfer function vector includes zero-pole distribution, amplitude-frequency characteristics, and phase-frequency characteristics; Performing a unit step response analysis based on the transfer function vector to obtain a step response space, and performing a pulse convolution operation on the step response space to obtain a convolution response sequence; Performing dynamic space modeling based on the convolution response sequence to obtain a state space graph, and performing feature trajectory extraction on the state space graph to obtain a trajectory feature set; A response curve is drawn for the trajectory feature set to obtain a dynamic response curve.

2. The electrical performance testing method of the high-order computing power autonomous driving FPC sensor module according to claim 1 is characterized in that: The initial electrical signal of the FPC sensor module is collected by a preset electrical signal sensor to obtain electrical signal collection data, including: Applying an electrical signal to the input end of the FPC sensor module, and performing multi-point synchronous electrical signal sampling on the FPC sensor module through a preset electrical signal sensor to obtain initial sampling data; wherein the electrical signal includes a voltage signal and a current signal, and the applied electrical signal is used to test the electrical performance of the FPC sensor module; Performing multi-source signal separation on the initial sampling data, extracting independent signal sources, and obtaining independent signal features; Performing dynamic sampling point interpolation on the independent signal feature to obtain an interpolated independent signal; The interpolated independent signal is amplified to obtain an amplified electrical signal, and the amplified electrical signal data is used as electrical signal acquisition data.

3. The electrical performance testing method of the high-order computing power autonomous driving FPC sensor module according to claim 1 is characterized in that: The spectrum analysis of the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data includes: Performing frequency domain transformation on the electrical signal acquisition data by fast Fourier transform to obtain a spectrum intensity distribution diagram, and extracting harmonic components from the spectrum intensity distribution diagram to obtain a harmonic component data set; Performing power spectrum estimation based on the harmonic component data set to obtain a signal power distribution curve, and performing peak detection on the signal power distribution curve to obtain a characteristic frequency point sequence; Performing phase correlation analysis on the characteristic frequency point sequence to obtain a phase coupling matrix, and performing frequency band segmentation based on the phase coupling matrix to obtain a multi-band characteristic graph; Spectral features are extracted from the multi-band feature graph to obtain spectral feature data.

4. The electrical performance testing method of the high-order computing power autonomous driving FPC sensor module according to claim 1 is characterized in that: The step of deriving a transfer function based on the impulse response function to obtain a transfer function vector includes: Performing frequency domain conversion on the impulse response function by Laplace transform to obtain a complex frequency domain function; Performing zero-pole decomposition on the complex frequency domain function to obtain a zero-pole distribution diagram, wherein the zero-pole distribution diagram is used to characterize the response sensitivity of the FPC sensor module at different frequencies; Performing transfer function approximation on the zero-pole distribution diagram by polynomial fitting to obtain a polynomial coefficient matrix; Based on the polynomial coefficient matrix, a state space equation is constructed to obtain state space data of the FPC sensor module; wherein the state space data includes a state matrix, an input matrix, an output matrix and a transfer matrix; A transfer function is derived based on the state space data to obtain a transfer function vector; wherein the transfer function vector is used to describe the electrical signal transmission capability of the FPC sensor module at different frequencies.

5. The electrical performance testing method of the high-order computing power autonomous driving FPC sensor module according to claim 1 is characterized in that: The probability distribution analysis of the FPC sensor module based on the dynamic response curve is performed to obtain an electrical performance probability distribution diagram, including: The dynamic response curve is sampled in sections to obtain a response characteristic sequence, and the FPC sensor module is subjected to state switching analysis based on the response characteristic sequence to obtain a voltage-current state mapping set; wherein the voltage-current state mapping set includes a voltage fluctuation boundary value, a current response critical point, and a signal switching time point; Dividing the voltage-current state mapping set into density intervals to obtain electrical signal distribution density data, and performing voltage-current correlation calculation based on the electrical signal distribution density data to obtain a state coupling degree sequence, wherein the state coupling degree sequence includes a voltage following characteristic value, a current response delay value, and a signal transmission stability value; Based on the state coupling degree sequence, a performance fluctuation range set of the FPC sensor module is calculated, and interval probability statistics are performed on the performance fluctuation range set to obtain a performance interval probability density diagram; Through a preset component mapping space algorithm, the FPC sensor module is spatially transformed and mapped based on the performance interval probability density map to obtain an electrical performance probability distribution map; wherein the electrical performance probability distribution map is used to reflect the electrical performance probability distribution of each component of the FPC sensor module under different working conditions, and the size of the probability density is represented by color depth or height.

6. The electrical performance testing method of the high-order computing power autonomous driving FPC sensor module according to claim 1 is characterized in that: The method of predicting the performance trend of the FPC sensor module based on the electrical performance probability distribution diagram to obtain a performance trend curve, and generating an electrical performance test report based on the performance trend curve, includes: Performing time series decomposition on the electrical performance probability distribution diagram to obtain a time series feature sequence, and extracting feature points from the time series feature sequence to obtain a key performance feature point set, wherein the key performance feature point set includes a voltage mutation point, a current jump point, and a signal distortion point; Based on the key performance feature point set, the FPC sensor module is subjected to trend analysis to obtain a multi-dimensional trend vector, and based on the multi-dimensional trend vector, trend extrapolation is performed to obtain a performance prediction sequence. Performing multi-dimensional space mapping on the performance prediction sequence to obtain a trend feature space, and reconstructing a trajectory based on the trend feature space to obtain a performance trend curve; Performing critical point analysis based on the performance trend curve to obtain a performance warning threshold set, and performing hierarchical mapping on the performance warning threshold set to obtain a hierarchical warning map; An electrical performance test report is generated based on the graded warning graph.

7. An electrical performance test device for a high-order computing power autonomous driving FPC sensor module, characterized in that: include: The acquisition module is used to acquire the initial electrical signal of the FPC sensor module through a preset electrical signal sensor to obtain electrical signal acquisition data; A first analysis module is used to perform spectrum analysis on the electrical signal acquisition data by fast Fourier transform to obtain spectrum feature data; A second analysis module is used to perform dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve; A third analysis module is used to perform probability distribution analysis on the FPC sensor module based on the dynamic response curve to obtain an electrical performance probability distribution diagram; A prediction module, used to predict the performance trend of the FPC sensor module based on the electrical performance probability distribution diagram, obtain a performance trend curve, and generate an electrical performance test report based on the performance trend curve; The performing dynamic response analysis on the FPC sensor module based on the frequency spectrum feature data to obtain a dynamic response curve includes: Performing unit pulse excitation conversion on the frequency spectrum feature data to obtain a pulse excitation sequence, and performing pulse response feature extraction based on the pulse excitation sequence to obtain a pulse feature set; Calculating an impulse response function for the pulse feature set, and deriving a transfer function based on the impulse response function to obtain a transfer function vector, wherein the transfer function vector includes zero-pole distribution, amplitude-frequency characteristics, and phase-frequency characteristics; Performing a unit step response analysis based on the transfer function vector to obtain a step response space, and performing a pulse convolution operation on the step response space to obtain a convolution response sequence; Performing dynamic space modeling based on the convolution response sequence to obtain a state space graph, and performing feature trajectory extraction on the state space graph to obtain a trajectory feature set; A response curve is drawn for the trajectory feature set to obtain a dynamic response curve.

8. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images