A method and system for detecting geometric integrity of automobile transmission shaft

Abstract

The present invention provides a method and system for detecting the geometric integrity of an automobile transmission shaft, which relates to the technical field of automobile transmission system detection, including obtaining magnetic field change data of the transmission shaft, and obtaining magnetic field change information related to the torsion and shaft diameter change of the transmission shaft by performing alternating magnetic field excitation on an electromagnetic coil array evenly arranged around the transmission shaft; obtaining resonance frequency and mode data through adaptive resonance analysis processing; performing feature mapping and classification on the extracted quantum features using a quantum convolutional neural network model to obtain key features characterizing the geometric integrity of the transmission shaft; evaluating and processing the key features through a quantum approximate optimization algorithm to obtain a health status evaluation result of the geometric integrity of the transmission shaft; and finally realizing integrity detection of the torsion and shaft diameter change of the transmission shaft. The present invention improves the intelligent level of transmission shaft monitoring and provides a scientific basis for the maintenance and fault prevention of the transmission shaft.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile transmission system detection, and in particular to a method and system for detecting the geometric integrity of an automobile transmission shaft. Background Art

[0002] In the modern automotive industry, the geometric integrity of the drive shaft, as an important component connecting the power source and the drive wheel, is crucial to ensuring transmission efficiency and vehicle driving safety. However, traditional drive shaft detection technologies mostly rely on contact sensors and regular manual inspections, which have many limitations. First, contact detection may cause damage to the surface of the drive shaft, and its application is limited under harsh working conditions such as high temperature and high-speed rotation. Secondly, regular inspections cannot achieve continuous monitoring and it is difficult to capture rapidly changing fault signs. In addition, the data processing capabilities of existing technologies are limited. They are usually based on empirical formulas and simple statistical analysis, and cannot deeply explore the complex patterns behind the data, resulting in insufficient accuracy and timeliness of fault diagnosis.

[0003] With the advancement of science and technology, although some automated and intelligent detection technologies have emerged, most of them are still based on classical computing and traditional signal processing methods, which are difficult to meet the needs of high precision and real-time performance. Especially in extreme environments, such as high cold, high temperature, high humidity and other conditions, the application effect of existing technologies is greatly reduced, and a more advanced and reliable detection method is urgently needed to improve the detection capability of the drive shaft. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for detecting the geometric integrity of an automobile transmission shaft to improve the above-mentioned problem. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides a method for detecting the geometric integrity of an automobile transmission shaft, comprising:

[0006] Obtain the magnetic field change data of the transmission shaft. According to the principle of electromagnetic induction, an alternating magnetic field is excited by an array of electromagnetic coils evenly arranged around the transmission shaft. The induced electromotive force is measured using Faraday's law of electromagnetic induction, thereby obtaining the magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase changes of the induced electromotive force.

[0007] According to the magnetic field change information, after adaptive resonance analysis, the damping ratio and natural frequency are adjusted to match the resonance characteristics of the transmission shaft, and the resonance frequency and mode data reflecting the slight changes in the transmission shaft torsion and shaft diameter are obtained;

[0008] The quantum machine learning algorithm is used to extract and process the features of the resonance frequency and mode data to obtain the extracted quantum features, and the quantum convolutional neural network model is used to perform feature mapping and classification on the extracted quantum features to obtain the key features that characterize the geometric integrity of the transmission shaft. The extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space.

[0009] The key features are evaluated based on the quantum approximate optimization algorithm, and the configuration corresponding to the minimum energy state is found through the evolution of the quantum state, thereby obtaining the health status evaluation result of the geometric integrity of the transmission shaft;

[0010] Based on the health status assessment results, the current geometric integrity status of the drive shaft and the time of potential fault occurrence are obtained through real-time updating and processing of the fault prediction model. Based on the feedback from the machine learning model, the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm are adaptively adjusted to achieve the ultimate integrity detection of the drive shaft torsion and shaft diameter change.

[0011] Preferably, the quantum machine learning algorithm is used to extract and process the features of the resonance frequency and mode data to obtain the extracted quantum features, and the quantum convolutional neural network model is used to perform feature mapping and classification on the extracted quantum features to obtain key features characterizing the geometric integrity of the transmission shaft, including:

[0012] Preprocessing the resonance frequency and mode data obtained by the adaptive resonance analysis, wherein the preprocessing includes normalization, denoising and feature scaling to obtain a preprocessed key data feature set;

[0013] Use quantum machine learning algorithms to identify patterns and correlations between data in a key data feature set, extracting features that reflect the geometric integrity of the drive shaft, including the offset of the resonant frequency, the frequency distribution width, and the shape parameters of the mode;

[0014] The characteristic conditions are mapped into the superposition state of quantum bits to obtain quantized input data. The quantum feature set that can characterize the geometric integrity of the transmission shaft is obtained by using the feature mapping and classification processing of the quantum convolutional neural network model.

[0015] The quantum feature set is optimized by quantum algorithm to obtain the key features of the geometric integrity of the transmission shaft, including the frequency shift and amplitude change of the resonance peak.

[0016] Preferably, the current geometric integrity state of the transmission shaft and the time of potential failure occurrence are obtained through real-time updating and processing of the fault prediction model according to the health status assessment result, including:

[0017] The health status indicators obtained by the quantum approximate optimization algorithm are processed by data fusion and real-time monitoring system to obtain the real-time geometric integrity status of the transmission shaft;

[0018] Combining historical data with machine learning models, the probability and preliminary time estimate of potential drive shaft failures are obtained through processing with a fault prediction algorithm, which includes time series analysis and probability models.

[0019] Based on the probability of occurrence and preliminary time estimation of potential failures of the drive shaft, the predicted time of failure of the drive shaft is obtained through an adaptive adjustment mechanism, and the health status monitoring database of the drive shaft is updated in real time. The adaptive adjustment mechanism includes dynamic threshold adjustment and model parameter optimization.

[0020] In a second aspect, the present application also provides a system for detecting the geometric integrity of an automobile transmission shaft, comprising:

[0021] Acquisition module: used to obtain the magnetic field change data of the transmission shaft. According to the principle of electromagnetic induction, an alternating magnetic field is excited by an array of electromagnetic coils evenly arranged around the transmission shaft, and the induced electromotive force is measured using Faraday's law of electromagnetic induction, thereby obtaining the magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase change of the induced electromotive force;

[0022] The first processing module is used to adjust the damping ratio and natural frequency to match the resonance characteristics of the transmission shaft according to the magnetic field change information through adaptive resonance analysis and processing, so as to obtain the resonance frequency and mode data reflecting the slight changes in the torsion and shaft diameter of the transmission shaft;

[0023] The second processing module is used to extract and process the features of the resonance frequency and mode data using a quantum machine learning algorithm to obtain the extracted quantum features, and use a quantum convolutional neural network model to perform feature mapping and classification on the extracted quantum features to obtain key features that characterize the geometric integrity of the transmission shaft, wherein the extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space;

[0024] The third processing module is used to evaluate and process the key features based on the quantum approximate optimization algorithm, and find the configuration corresponding to the minimum energy state through the evolution of the quantum state, so as to obtain the health status evaluation result of the geometric integrity of the transmission shaft;

[0025] Adjustment detection module: It is used to obtain the current geometric integrity status and potential fault occurrence time of the drive shaft based on the health status assessment results, through real-time updating and processing of the fault prediction model, and adaptively adjust the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm according to the feedback of the machine learning model, so as to achieve the final integrity detection of the drive shaft torsion and shaft diameter change.

[0026] In a third aspect, the present application also provides a device for detecting the geometric integrity of an automobile transmission shaft, comprising:

[0027] Memory for storing computer programs;

[0028] A processor is used to implement the steps of the method for detecting the geometric integrity of a vehicle transmission shaft when executing the computer program.

[0029] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for detecting the geometric integrity of a vehicle drive shaft are implemented.

[0030] The beneficial effects of the present invention are:

[0031] The present invention breaks through the limitations of traditional technology, realizes real-time monitoring of the twist and diameter change of the transmission shaft through non-contact electromagnetic induction technology, avoids the disadvantages of contact detection, and uses adaptive resonance theory to extract the vibration characteristics of the transmission shaft, and then uses quantum machine learning algorithm to deeply mine and intelligently analyze the characteristics, greatly improving the efficiency and accuracy of data processing. Secondly, the present invention also includes a quantum approximate optimization algorithm for quickly and accurately evaluating the health status of the transmission shaft, and combines real-time update and fault prediction models to provide a scientific basis for the maintenance and fault prevention of the transmission shaft. Through the principles of quantum state superposition and quantum entanglement, key features can be quickly extracted, and the quantum approximate optimization algorithm is used to evaluate the health status of the transmission shaft; in addition, the present invention also includes a real-time update and fault prediction model, which can predict potential faults and update the health status of the transmission shaft in time, significantly improving the accuracy and response speed of detection, not only improving the intelligence level of transmission shaft monitoring, but also providing a more reliable guarantee for the safe operation of the automobile transmission system. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 It is a schematic flow chart of a method for detecting the geometric integrity of an automobile transmission shaft according to an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of the structure of a system for detecting the geometric integrity of an automobile transmission shaft according to an embodiment of the present invention;

[0035] Figure 3 It is a schematic diagram of the structure of the device for detecting the geometric integrity of the automobile transmission shaft described in an embodiment of the present invention.

[0036] In the figure: 701, acquisition module; 702, first processing module; 703, second processing module; 704, third processing module; 705, adjustment detection module; 800, equipment for detecting geometric integrity of automobile transmission shaft; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. Embodiment 1:

[0039] In the prior art, the geometric integrity detection of automobile drive shafts usually relies on traditional methods such as vibration analysis, acoustic detection and stress testing. These technologies often use contact sensors to evaluate the health of the drive shaft by measuring the vibration response, sound signal or surface stress distribution during operation. For example, vibration analysis may measure the acceleration or velocity signal of the drive shaft, extract the frequency component through signal processing techniques such as Fourier transform, and then identify abnormal vibration patterns. Acoustic detection captures the sound signal generated by the drive shaft during operation, analyzes the frequency and amplitude changes of the sound, and determines whether there is a fault. Stress testing may involve installing strain gauges on the surface of the drive shaft to measure its stress and strain under different working conditions. However, these traditional detection methods have some significant disadvantages, such as contact measurement limitations, data collection limitations, accuracy and resolution problems, and manual dependence. Therefore, the method proposed in the present invention adopts a series of innovative technologies, including non-contact electromagnetic induction, quantum machine learning algorithm and quantum approximate optimization algorithm, aiming to overcome the limitations of the existing technology and provide a more accurate, efficient and real-time transmission shaft geometric integrity detection solution. Through the application of these advanced technologies, the method can achieve comprehensive monitoring of the transmission shaft state, timely discover and predict potential faults, reduce maintenance costs, and improve the safety and reliability of the automobile transmission system. The embodiments of the present invention are as follows:

[0040] This embodiment provides a method for detecting the geometric integrity of an automobile transmission shaft.

[0041] See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300, step S400 and step S500.

[0042] S100, obtaining magnetic field change data of the transmission shaft, according to the principle of electromagnetic induction, by performing alternating magnetic field excitation on an electromagnetic coil array evenly arranged around the transmission shaft, and measuring the induced electromotive force using Faraday's law of electromagnetic induction, thereby obtaining magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase change of the induced electromotive force.

[0043] It can be understood that the calculation formula for measuring the induced electromotive force using Faraday's law of electromagnetic induction in step S100 is as follows: In the formula, ε represents the induced electromotive force, Φ represents the magnetic flux, t represents time, and dt represents a small change in time.

[0044] It should be noted that a series of electromagnetic coils are evenly arranged around the drive shaft. The design and layout of these coils must ensure that they can fully cover the key monitoring areas of the drive shaft to capture the magnetic field changes of the entire shaft section. The alternating magnetic field is generated by the electromagnetic coil array. This excitation method simulates the dynamic magnetic field environment encountered by the drive shaft in actual operation. It can be periodic or non-periodic to meet different detection needs. The electromagnetic coils and data acquisition system must be able to adapt to various environmental conditions that the car may encounter, such as temperature changes, humidity, vibration, etc. According to Faraday's law of electromagnetic induction, when the magnetic field changes, an induced electromotive force will be generated in the electromagnetic coil. The amplitude and phase changes of the induced electromotive force are recorded in real time by a high-precision data acquisition system. These data are then processed by signal processing, such as filtering, amplification, and analog-to-digital conversion, for further analysis. Key features are extracted from the processed data, such as the amplitude change and phase shift of the induced electromotive force, which are directly related to the physical deformation of the drive shaft.

[0045] S200, according to the magnetic field change information, after adaptive resonance analysis processing, the resonance characteristics of the transmission shaft are matched by adjusting the damping ratio and the natural frequency, and the resonance frequency and mode data reflecting the slight changes in the torsion and shaft diameter of the transmission shaft are obtained.

[0046] It can be understood that the adaptive resonance analysis process in step S200 includes using a nonlinear dynamic equation to simulate the vibration response of the transmission shaft, and the calculation formula is as follows: In the formula, Indicates displacement x About Time t The second derivative of , which is the acceleration, x represents displacement, ζ represents the damping ratio, represents the natural frequency, F ( t ) represents the external excitation force, Indicates displacement x About Time t The first derivative of , that is, the velocity, F ( t ) indicates time t function.

[0047] It should be noted that the magnetic field change information obtained in step S100 is analyzed in depth. This information includes the amplitude and phase changes of the induced electromotive force, which are closely related to the physical deformation of the transmission shaft. Secondly, the vibration mode of the transmission shaft is modeled using the adaptive resonance theory, allowing the system to automatically identify and adapt to the resonant frequency of the transmission shaft, and maintain accurate matching even when external conditions change; by adjusting the damping ζ and natural frequency ωnThe system can simulate the vibration response of the drive shaft under different working conditions, where the damping ratio affects the attenuation rate of the vibration, and the natural frequency corresponds to the natural vibration mode of the drive shaft; by adjusting the damping ratio and natural frequency in real time, the system can match the actual resonance characteristics of the drive shaft, where this matching process is dynamic and can adapt to the changes in the resonance characteristics of the drive shaft due to the twist and shaft diameter changes; after matching, the system records and analyzes the resonant frequency and mode data of the drive shaft. These data include not only the numerical value of the frequency, but also the shape and distribution of the vibration mode, providing rich information for further analysis, which not only improves the accuracy and efficiency of the geometric integrity detection of the drive shaft, but also provides strong technical support for the health management and predictive maintenance of the automotive transmission system.

[0048] S300. Extract and process the features of the resonance frequency and mode data using a quantum machine learning algorithm to obtain the extracted quantum features, and perform feature mapping and classification on the extracted quantum features using a quantum convolutional neural network model to obtain key features that characterize the geometric integrity of the drive shaft, wherein the extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space.

[0049] It can be understood that step S300 includes S301, S302, S303 and S304, wherein:

[0050] S301, preprocessing the resonance frequency and mode data obtained by the adaptive resonance analysis, wherein the preprocessing includes normalization, denoising and feature scaling to obtain a preprocessed key data feature set;

[0051] It should be noted that since the collected resonance frequency and mode data may have different dimensions and numerical ranges, normalization is first performed to scale the data to a uniform scale, such as [0, 1] or [-1, 1], for subsequent processing and analysis; the resonance data may be interfered by various noises, such as electromagnetic interference, sensor noise, etc. The denoising step aims to reduce the impact of these noises and improve data quality, including the use of filters, such as low-pass filters or band-pass filters, to remove high-frequency noise; after denoising, feature scaling is used to adjust the scale of data features to ensure that all features have a balanced influence in feature extraction and machine learning algorithms, including but not limited to minimum-maximum scaling or standardization. Feature scaling makes different features have equal importance in machine learning models, avoiding some features from excessively affecting model training due to their large numerical range.

[0052] S302, using a quantum machine learning algorithm to identify patterns and correlations between data in a key data feature set, and extracting features reflecting the geometric integrity of the drive shaft, wherein the features include an offset of the resonance frequency, a frequency distribution width, and a shape parameter of the mode;

[0053] It should be noted that quantum machine learning algorithms are used to identify patterns in preprocessed data, where quantum algorithms can efficiently process large amounts of data and identify complex patterns in the data. Quantum algorithms can detect correlations between data features, which may be difficult to find in classical algorithms because quantum computers can process multiple calculation paths simultaneously. Features that reflect the geometric integrity of the drive shaft are extracted from the key data feature set, such as the offset of the resonant frequency, the width of the frequency distribution, and the shape parameters of the pattern, and these features are key indicators for evaluating the state of the drive shaft.

[0054] In the actual detection of the geometric integrity of automobile drive shafts, data acquisition technology requires the development of highly sensitive sensors and data acquisition systems to ensure that the resonance data of the drive shaft can be accurately captured; quantum machine learning algorithms need to be implemented on existing quantum computers or quantum simulators and optimized to meet specific data processing needs; quantum algorithms may be used in combination with traditional signal processing technologies to leverage their respective advantages, providing strong technical support for the health management and predictive maintenance of automobile transmission systems.

[0055] Among them, in this scenario, combined with specific data, the specific parameters, working principles, and working processes of the quantum machine learning algorithm used are recorded in detail, as well as an explanation of how to extract characteristic conditions reflecting the geometric integrity of the drive shaft from these processes.

[0056] The specific parameters of the quantum machine learning algorithm are: 1. Data preprocessing parameters: including the normalization range (such as [0,1]), the type and parameters of the denoising filter (such as the cutoff frequency of the low-pass filter), and the method of feature scaling (such as Z-score normalization or minimum-maximum normalization). 2. Quantum bit encoding parameters: involving how to map the normalized data to the amplitude and phase of the quantum state, such as using angle encoding to encode the data into the phase information of the quantum state. 3. Quantum convolutional neural network (QCNN) parameters: including the number of quantum convolution layers, the number of quantum bits in each convolution layer, the type and layout of quantum gates, and the quantum gate parameters during training. 4. Quantum approximate optimization algorithm parameters: such as the number of iterations in QAOA, the angle parameters used in the optimization process, etc.

[0057] Working principle: 1. Quantum state preparation: Encode the preprocessed data features into the superposition state of quantum bits. Each quantum bit can be represented as ,in αand β It is the complex amplitude calculated based on the data features. 2. Quantum feature mapping: The quantum state is transformed by QCNN to extract nonlinear features in the data. QCNN achieves high-dimensional mapping of data through a combination of quantum gates, thereby identifying complex patterns related to the geometric integrity of the drive shaft. 3. Quantum optimization processing: The features extracted by QCNN are further optimized using quantum approximate optimization algorithms (such as QAOA) to extract the most discriminating features.

[0058] Working process: 1. Data input: Input the collected transmission shaft resonance frequency and mode data into the quantum machine learning system to obtain preprocessed data. 2. Quantum state preparation: Prepare the corresponding quantum state according to the preprocessed data, and encode the data into quantum bits to obtain the prepared quantum state. 3. Quantum feature extraction: Based on the prepared quantum state, feature extraction is performed through QCNN to identify patterns and correlations in the data. 4. Quantum optimization processing: Use the quantum approximate optimization algorithm to further optimize the extracted features to extract key features. 5. Result output: Convert the optimized features into classical data to characterize the geometric integrity of the transmission shaft.

[0059] Through the above working process, the quantum machine learning algorithm can extract key features that reflect the geometric integrity of the drive shaft, such as the offset of the resonant frequency, the width of the frequency distribution, and the shape parameters of the mode. These features are obtained through the high-dimensional data processing capabilities of the quantum algorithm and the ability to analyze the complex correlations between data features. The optimization processing of the quantum algorithm further ensures the accuracy and reliability of these features, providing strong data support for the condition assessment of the drive shaft.

[0060] In practical applications, these features will be used to monitor the health of the drive shaft and predict potential failures, thereby achieving predictive maintenance of the drive shaft. Through the application of quantum machine learning algorithms, the accuracy and efficiency of drive shaft geometric integrity detection can be significantly improved, providing an innovative solution for the health management and predictive maintenance of automotive transmission systems.

[0061] S303, mapping the characteristic conditions into a superposition state of quantum bits to obtain quantized input data, and using the feature mapping and classification processing of the quantum convolutional neural network model to obtain a quantum feature set capable of characterizing the geometric integrity of the transmission shaft;

[0062] Among them, in the scenario of automotive drive shaft geometric integrity detection, the application of the quantum convolutional neural network (QCNN) model is to process and analyze the complex vibration data collected from the drive shaft. The specific settings and structural composition of the quantum convolutional neural network model are described as follows:

[0063] Specific settings of the quantum convolutional neural network model:

[0064] The collected resonant frequency and mode data are mapped to the quantum state of the quantum bit through amplitude encoding or angle encoding in preparation for quantum convolution operations. Then, a quantum convolution layer is designed to simulate the function of a traditional convolution layer, and parameterized quantum gates (such as revolving gates) are used to realize feature extraction of the data. Then, through the superposition and entanglement of quantum states, high-dimensional feature mapping of the drive shaft vibration data is realized to extract features related to geometric integrity. Quantum pooling operations are applied to reduce the dimensionality of the quantum state while retaining key geometric integrity features. Finally, a quantum classifier is constructed to determine the geometric integrity state of the drive shaft through quantum measurement to achieve fault diagnosis.

[0065] The structure of the quantum convolutional neural network model is as follows:

[0066] The structure of this application includes: input quantum bits, quantum gates and circuits, parameter optimization, and training and verification, wherein: the number of input quantum bits is determined according to the number of features of the data. For example, if there are multiple resonant frequencies and mode features, each feature can be represented by a quantum bit; quantum gates and circuits: select appropriate quantum gates (such as Hadamard gates, CNOT gates, controlled Z gates, etc.) to construct the various layers of QCNN; circuit design needs to consider the interaction between quantum bits and how to effectively implement convolution and pooling operations; parameter optimization: a classical-quantum hybrid optimization algorithm is used to adjust the parameters of the quantum gates to minimize the loss function and improve the accuracy of the model; training and verification: the QCNN model is trained and verified using a simulated or actual quantum computer to ensure that the model can effectively identify the geometric integrity features of the drive shaft.

[0067] Specifically, the quantum input layer is composed of a group of quantum bits, each of which represents a feature of the transmission shaft data. The hidden layer is composed of multiple quantum convolutional layers and quantum pooling layers, which are used to extract and process complex features in the data. The output layer obtains the final classification result through quantum measurement, which is used to characterize the geometric integrity state of the transmission shaft. Through the classical-quantum feedback mechanism, the parameters of the quantum gate are optimized to improve the accuracy and robustness of the model. Furthermore, the QCNN model can efficiently process and analyze the vibration data of the transmission shaft and extract features related to geometric integrity. Through the quantum measurement results, the QCNN model can accurately diagnose the potential faults of the transmission shaft and improve the accuracy of fault prediction. At the same time, the real-time data processing capability of the QCNN model is used to monitor the geometric integrity of the transmission shaft in real time, thereby realizing predictive maintenance.

[0068] S304. Optimizing the quantum feature set through a quantum algorithm to obtain key features of the geometric integrity of the transmission shaft, wherein the key features include frequency shift and amplitude variation of the resonance peak.

[0069] It should be noted that the geometric integrity features of the drive shaft extracted in step S302 are converted into a superposition state of quantum bits (qubits). This process involves encoding classical data into quantum states, so that each quantum bit can represent multiple possible states at the same time, increasing the dimension of data processing; then, using the principle of quantum superposition, each quantum bit can be in a superposition state of 0 and 1, allowing a large number of combined feature data to be processed simultaneously, which is one of the core advantages of quantum computing; subsequently, the quantized input data is input into the quantum convolutional neural network model. QCNN is able to perform feature mapping and classification at the quantum level, using the high-dimensional characteristics of quantum states to identify complex patterns and associations.

[0070] In step S304, the quantum feature set obtained in step S303 is further optimized using a quantum algorithm to extract the most distinguishing features, and through the optimization of the quantum algorithm, the key features of the geometric integrity of the transmission shaft, such as the frequency shift and amplitude change of the resonance peak, are identified. After the quantum algorithm processing is completed, the quantum state needs to be measured to extract classical data for characterizing the geometric integrity of the transmission shaft. Among them, the technical effect is that the quantum algorithm can accurately extract key features from the quantum feature set, providing reliable data for the state assessment of the transmission shaft; the optimization processing of the quantum algorithm improves the accuracy and efficiency of data processing and ensures the quality of feature extraction; by identifying the frequency shift and amplitude change of the resonance peak, the potential faults and damages of the transmission shaft can be diagnosed more accurately.

[0071] Specifically, in this scenario, the specific implementation of the process is as follows: Preparation of quantum states and feature mapping: First, through quantum state preparation, the quantized input data obtained in step S303 is further mapped to the superposition state of quantum bits, which involves the initialization of quantum bits and the application of quantum gates, such as Hadamard gates, to create superposition states. These quantum states are then input into the quantum convolutional neural network (QCNN) model, which is capable of performing complex feature mapping and classification processing; Quantum convolutional neural network (QCNN): The QCNN model is the core of the quantum algorithm. It processes quantum states through quantum convolution layers, which are capable of identifying and extracting complex patterns in quantum data. The working principle of QCNN is similar to that of traditional CNN, but it operates at the quantum level and uses quantum entanglement and quantum superposition to enhance feature recognition capabilities; After the quantum feature set is processed by QCNN, the feature set is further optimized using a quantum approximate optimization algorithm (such as QAOA), where QAOA is a quantum algorithm that finds the optimal solution to the problem by performing a series of controlled evolution operations on quantum states. This process involves parameterized quantum gates whose parameters are optimized during the execution of the algorithm to minimize or maximize a certain objective function; measurement of quantum states and extraction of classical data: after the quantum algorithm is processed, the quantum state is measured to extract classical data used to characterize the geometric integrity of the drive shaft. The measurement process usually involves the state collapse of the quantum bit, which converts the quantum information into classical information; adaptive adjustment mechanism: finally, based on the measurement results, the parameters of the quantum algorithm are dynamically adjusted through an adaptive adjustment mechanism, including adjusting the rotation angle of the quantum gate, changing the structure of the quantum circuit, or optimizing the number of iterations of the quantum algorithm. This adaptive adjustment helps to improve the accuracy and robustness of the algorithm.

[0072] Further, in the process of "Optimization of quantum algorithms: After the quantum feature set is processed by QCNN, the feature set is further optimized using a quantum approximate optimization algorithm (such as QAOA). QAOA is a quantum algorithm that finds the optimal solution to a problem by performing a series of controlled evolution operations on quantum states. This process involves parameterized quantum gates whose parameters are optimized during the execution of the algorithm to minimize or maximize a certain objective function", the specific application and optimization process of QAOA in this scenario are as follows:

[0073] Quantum circuit construction: First, build a parameterized quantum circuit that contains two types of quantum gates: cost layer and hybrid layer. The cost layer is related to the problem Hamiltonian and is used to encode problem constraints; the hybrid layer is used to explore the solution space.

[0074] Parameterized quantum gates: In QAOA, the quantum gates of the cost layer and the hybrid layer are parameterized, i.e. their angle parameters γ andβ These parameters are constantly updated during the optimization process of the algorithm to minimize or maximize the objective function.

[0075] Quantum state preparation: The quantum circuit starts from an initial uniform superposition state and prepares the initial quantum state on all qubits by applying Hadamard gates.

[0076] Quantum state evolution: By alternately applying quantum gates of the cost layer and the hybrid layer, the quantum adiabatic evolution process is simulated. This process is achieved by parameter γ and β control, they determine the extent to which quantum states are explored in the problem space.

[0077] Expectation value calculation: After the quantum state has evolved, the expectation value of the target Hamiltonian is calculated, which usually involves measuring a specific quantum operator. The expectation value calculation is done by a quantum computer and provides information about the relationship between the quantum state and the target function.

[0078] Classical optimization: Use classical optimizers (such as gradient descent, Nelder-Mead, etc.) to optimize parameters based on expected values γ and β This process involves evaluating the effect of parameter updates on the expected value and iteratively adjusting the parameters to find the combination of parameters that minimizes the objective function.

[0079] Results extraction: After the optimization is completed, the final quantum state is measured to extract classical data used to characterize the geometric integrity of the drive shaft. These data reflect key features such as the resonance peak frequency shift and amplitude change of the drive shaft.

[0080] Adaptive adjustment: After obtaining the optimization results, the parameters of the quantum circuit are adaptively adjusted according to the actual measurement results and the objective function value. This may include adjusting the angle parameters of the quantum gate, changing the structure of the quantum circuit, or the number of iterations of the optimization algorithm.

[0081] Through the above steps, the QAOA algorithm can effectively extract the most discriminative features from the quantum feature set and identify the key features of the geometric integrity of the drive shaft. This approach not only improves the accuracy of fault diagnosis, but also realizes efficient monitoring of the geometric integrity of the drive shaft through real-time updating and fault prediction models. In practical applications, the implementation of the QAOA algorithm requires the support of quantum computing platforms, such as quantum simulators or quantum computers, as well as classical computing resources to perform optimization and data processing. In addition, the successful implementation of the algorithm also relies on a deep understanding of quantum circuit design, parameter optimization techniques, and quantum-classical interfaces.

[0082] In the above, the description of the specific parameters, working principle, and working process of the quantum machine learning algorithm used is inferred from the detailed explanation of steps S300, S301, S302, S303, and S304. These steps describe a series of operations, including data preprocessing, quantum bit encoding, quantum feature mapping, quantum entanglement, quantum algorithm optimization, etc., which are all possible components of the quantum machine learning algorithm.

[0083] S400, based on the quantum approximate optimization algorithm, the key features are evaluated and processed, and the configuration corresponding to the minimum energy state is found through the evolution of the quantum state, so as to obtain the health status evaluation result of the geometric integrity of the transmission shaft.

[0084] It can be understood that in step S400, the evaluation process of the key features by the quantum approximate optimization algorithm includes constructing a Hamiltonian to simulate the health status evaluation problem of the transmission shaft, wherein the calculation formula for constructing the Hamiltonian is as follows:

[0085] In the formula, represents the ground state Hamiltonian or the unperturbed Hamiltonian of the system, Hi Indicates the i The Hamiltonian of the perturbation term, γi represents the penalty weight, H is the Hamiltonian, p represents the total number of disturbance terms.

[0086] S500: Based on the health status assessment result, the current geometric integrity status and potential fault occurrence time of the drive shaft are obtained through real-time updating and processing of the fault prediction model. Based on the feedback of the machine learning model, the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm are adaptively adjusted to achieve the final integrity detection of the drive shaft torsion and shaft diameter change.

[0087] It can be understood that step S500 includes S501, S502 and S503, wherein:

[0088] S501, obtaining the real-time geometric integrity status of the transmission shaft through data fusion and real-time monitoring system processing according to the health status index obtained by the quantum approximate optimization algorithm;

[0089] S502, combining historical data with a machine learning model, and processing the fault prediction algorithm to obtain a probability of occurrence and a preliminary time estimate of a potential fault of the transmission shaft, wherein the processing process includes time series analysis and a probability model;

[0090] S503. Based on the probability of occurrence of potential failure of the transmission shaft and the preliminary time estimation, the predicted time of failure of the transmission shaft is obtained through an adaptive adjustment mechanism, and the health status monitoring database of the transmission shaft is updated in real time, wherein the adaptive adjustment mechanism includes dynamic threshold adjustment and model parameter optimization.

[0091] It should be noted that, first, in step S501, the health status indicators obtained by the quantum approximate optimization algorithm are input into the data fusion and real-time monitoring system as basic data, and the data fusion technology integrates data from different sensors and detection methods to obtain more comprehensive and accurate transmission shaft status information. Among them, the real-time monitoring system processes these fused data to evaluate the real-time geometric integrity status of the transmission shaft to ensure that any abnormality or damage can be discovered in time.

[0092] Next, in step S502, the fault prediction algorithm estimates the probability and preliminary time of potential drive shaft failure by combining historical data and machine learning models. This process involves time series analysis, which is used to identify the changing trend of drive shaft performance indicators over time, and probability models, which are used to predict the possibility of failure. Then, through iterative training and verification of the machine learning model, the accuracy and reliability of fault prediction are improved.

[0093] Finally, in step S503, based on the potential fault occurrence probability and preliminary time estimation obtained in step S502, the adaptive adjustment mechanism further optimizes these predictions, including dynamic threshold adjustment to adapt to the performance changes of the transmission shaft under different working conditions; and model parameter optimization to improve the generalization ability of the fault prediction model. Through this adaptive adjustment, a more accurate prediction time of the transmission shaft fault is obtained, and at the same time, the health status monitoring database of the transmission shaft is updated in real time to ensure that the monitoring system always reflects the latest status of the transmission shaft.

[0094] Through the coordinated work of these three steps, the patented method can not only monitor the geometric integrity status of the drive shaft in real time, but also predict and prevent potential failures in advance, thereby significantly improving the safety and reliability of the automobile transmission system; in addition, the implementation in this embodiment also helps to reduce maintenance costs, optimize maintenance plans, and reduce the risks and losses caused by unexpected failures. Embodiment 2:

[0095] like Figure 2 As shown, this embodiment provides a system for detecting the geometric integrity of a vehicle transmission shaft, see Figure 2 The system comprises:

[0096] Acquisition module 701: used to acquire magnetic field change data of the transmission shaft. According to the principle of electromagnetic induction, an alternating magnetic field is excited by an electromagnetic coil array evenly arranged around the transmission shaft, and the induced electromotive force is measured using Faraday's law of electromagnetic induction, so as to obtain magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase change of the induced electromotive force;

[0097] The first processing module 702 is used to adjust the damping ratio and natural frequency to match the resonance characteristics of the transmission shaft according to the magnetic field change information through adaptive resonance analysis and processing, so as to obtain the resonance frequency and mode data reflecting the slight changes of the torsion and shaft diameter of the transmission shaft;

[0098] The second processing module 703 is used to extract and process the features of the resonance frequency and mode data using a quantum machine learning algorithm to obtain the extracted quantum features, and to perform feature mapping and classification on the extracted quantum features using a quantum convolutional neural network model to obtain key features that characterize the geometric integrity of the transmission shaft, wherein the extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space;

[0099] The third processing module 704 is used to evaluate the key features based on the quantum approximate optimization algorithm, and find the configuration corresponding to the minimum energy state through the evolution of the quantum state, so as to obtain the health status evaluation result of the geometric integrity of the transmission shaft;

[0100] Adjustment detection module 705: It is used to obtain the current geometric integrity status and potential fault occurrence time of the drive shaft based on the health status assessment result, through real-time updating and fault prediction model processing, and adaptively adjust the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm according to the feedback of the machine learning model, so as to achieve the final integrity detection of the drive shaft torsion and shaft diameter change.

[0101] Specifically, the second processing module 703 includes:

[0102] Preprocessing unit: used to preprocess the resonance frequency and mode data obtained by adaptive resonance analysis, wherein the preprocessing includes normalization, denoising and feature scaling to obtain a set of key data features after preprocessing;

[0103] Extraction unit: used to use quantum machine learning algorithms to identify patterns and correlations between data in a key data feature set, and extract features that reflect the geometric integrity of the drive shaft, including the offset of the resonant frequency, the frequency distribution width, and the shape parameters of the mode;

[0104] The first processing unit is used to map the characteristic situation into a superposition state of quantum bits to obtain quantized input data, and use the feature mapping and classification processing of the quantum convolutional neural network model to obtain a quantum feature set that can characterize the geometric integrity of the transmission shaft;

[0105] The second processing unit is used to optimize the quantum feature set through a quantum algorithm to obtain key features of the geometric integrity of the transmission shaft, wherein the key features include the frequency shift and amplitude change of the resonance peak.

[0106] Specifically, the third processing module 704 includes constructing a calculation formula of the Hamiltonian as follows: In the formula, represents the ground state Hamiltonian or the unperturbed Hamiltonian of the system, Hi Indicates the i The Hamiltonian of the perturbation term, γi represents the penalty weight, H is the Hamiltonian, p represents the total number of disturbance terms.

[0107] Specifically, the adjustment detection module 705 includes:

[0108] The third processing unit is used to obtain the real-time geometric integrity status of the transmission shaft according to the health status index obtained by the quantum approximate optimization algorithm through data fusion and real-time monitoring system processing;

[0109] The fourth processing unit is used to combine historical data with the machine learning model, and obtain the probability of occurrence and preliminary time estimation of potential failure of the transmission shaft through processing by the fault prediction algorithm, wherein the processing process includes time series analysis and probability model;

[0110] Adjustment and optimization unit: It is used to obtain the predicted time of the failure of the transmission shaft based on the probability of occurrence and preliminary time estimation of the potential failure of the transmission shaft through an adaptive adjustment mechanism, and to update the health status monitoring database of the transmission shaft in real time. The adaptive adjustment mechanism includes dynamic threshold adjustment and model parameter optimization.

[0111] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here. Embodiment 3:

[0112] Corresponding to the above method embodiment, this embodiment also provides a device for detecting the geometric integrity of an automobile drive shaft. The device for detecting the geometric integrity of an automobile drive shaft described below and the method for detecting the geometric integrity of an automobile drive shaft described above can be referenced to each other.

[0113] Figure 3 FIG. 8 is a block diagram of a device 800 for detecting the geometric integrity of a vehicle transmission shaft according to an exemplary embodiment. Figure 3 As shown, the device 800 for detecting the geometric integrity of a vehicle transmission shaft includes: a processor 801 and a memory 802. The device 800 for detecting the geometric integrity of a vehicle transmission shaft also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0114] The processor 801 is used to control the overall operation of the device 800 for detecting the geometric integrity of an automobile transmission shaft to complete all or part of the steps in the above-mentioned method for detecting the geometric integrity of an automobile transmission shaft. The memory 802 is used to store various types of data to support the operation of the device 800 for detecting the geometric integrity of an automobile transmission shaft, and these data may include, for example, instructions for any application or method operating on the device 800 for detecting the geometric integrity of an automobile transmission shaft, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse or buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the device 800 for detecting the geometric integrity of the automobile transmission shaft and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: a Wi-Fi module, a Bluetooth module or an NFC module.

[0115] In an exemplary embodiment, the device 800 for detecting the geometric integrity of an automobile drive shaft can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned method for detecting the geometric integrity of an automobile drive shaft.

[0116] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned method for detecting the geometric integrity of an automobile transmission shaft are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the device 800 for detecting the geometric integrity of an automobile transmission shaft to complete the above-mentioned method for detecting the geometric integrity of an automobile transmission shaft. Embodiment 4:

[0117] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the method for detecting the geometric integrity of a vehicle transmission shaft described above can refer to each other.

[0118] A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the steps of the method for detecting the geometric integrity of the automobile transmission shaft in the above method embodiment are implemented.

[0119] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0120] In summary, the present invention realizes non-contact data collection by adopting the principle of electromagnetic induction, combined with adaptive resonance analysis and quantum machine learning algorithms, to achieve real-time monitoring and high-precision analysis of the geometric integrity of the automobile transmission shaft; wherein the method can fully integrate multi-source data, use the acceleration capability of quantum computing, quickly extract key features and predict potential faults, and dynamically optimize monitoring parameters through an adaptive adjustment mechanism, significantly improving the accuracy of fault prediction and the responsiveness of the system. In addition, the intelligent and automated features of the present invention reduce the reliance on manual experience, provide consistent and objective detection results, reduce maintenance costs, and maintain stability and accuracy under various environmental conditions, thereby improving the safety and reliability of the automobile transmission system.

[0121] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0122] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for detecting the geometric integrity of an automobile transmission shaft, characterized in that: include: Obtain the magnetic field change data of the transmission shaft. According to the principle of electromagnetic induction, an alternating magnetic field is excited by an array of electromagnetic coils evenly arranged around the transmission shaft. The induced electromotive force is measured using Faraday's law of electromagnetic induction, thereby obtaining the magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase changes of the induced electromotive force. According to the magnetic field change information, after adaptive resonance analysis, the damping ratio and natural frequency are adjusted to match the resonance characteristics of the transmission shaft, and the resonance frequency and mode data reflecting the slight changes in the transmission shaft torsion and shaft diameter are obtained; The quantum machine learning algorithm is used to extract and process the features of the resonance frequency and mode data to obtain the extracted quantum features, and the quantum convolutional neural network model is used to perform feature mapping and classification on the extracted quantum features to obtain the key features that characterize the geometric integrity of the transmission shaft. The extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space. The key features are evaluated based on the quantum approximate optimization algorithm, and the configuration corresponding to the minimum energy state is found through the evolution of the quantum state, thereby obtaining the health status evaluation result of the geometric integrity of the transmission shaft; Based on the health status assessment results, the current geometric integrity status of the drive shaft and the time of potential fault occurrence are obtained through real-time updating and processing of the fault prediction model. Based on the feedback from the machine learning model, the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm are adaptively adjusted to achieve the ultimate integrity detection of the drive shaft torsion and shaft diameter change.

2. The method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: The calculation formula for measuring the induced electromotive force using Faraday's law of electromagnetic induction is as follows: In the formula, ε represents the induced electromotive force, Φ represents the magnetic flux, t represents time, and dt represents a small change in time.

3. The method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: The adaptive resonance analysis process includes using nonlinear dynamic equations to simulate the vibration response of the transmission shaft, and the calculation formula is as follows: In the formula, Indicates displacement x About Time t The second derivative of , which is the acceleration, x represents displacement, ζ represents the damping ratio, represents the natural frequency, F ( t ) represents the external excitation force, Indicates displacement x About Time t The first derivative of , i.e., velocity, F ( t ) indicates time t function.

4. The method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: The method uses a quantum machine learning algorithm to extract and process the features of the resonance frequency and mode data to obtain the extracted quantum features, and uses a quantum convolutional neural network model to perform feature mapping and classification on the extracted quantum features to obtain key features that characterize the geometric integrity of the transmission shaft, including: preprocessing the resonance frequency and mode data obtained by the adaptive resonance analysis, wherein the preprocessing includes normalization, denoising and feature scaling to obtain a preprocessed key data feature set; Use quantum machine learning algorithms to identify patterns and correlations between data in a key data feature set, extracting features that reflect the geometric integrity of the drive shaft, including the offset of the resonant frequency, the frequency distribution width, and the shape parameters of the mode; The characteristic conditions are mapped into the superposition state of quantum bits to obtain quantized input data. The quantum feature set that can characterize the geometric integrity of the transmission shaft is obtained by using the feature mapping and classification processing of the quantum convolutional neural network model. The quantum feature set is optimized by quantum algorithm to obtain the key features of the geometric integrity of the transmission shaft, including the frequency shift and amplitude change of the resonance peak.

5. The method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: The evaluation of key features by quantum approximate optimization algorithm includes constructing Hamiltonian to simulate the health status evaluation problem of the transmission shaft, where the calculation formula for constructing Hamiltonian is as follows: In the formula, represents the ground state Hamiltonian or the unperturbed Hamiltonian of the system, Hi Indicates the i The Hamiltonian of the perturbation term, γi represents the penalty weight, H is the Hamiltonian, p represents the total number of disturbance terms.

6. The method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: According to the health status assessment results, the current geometric integrity status of the transmission shaft and the potential failure occurrence time are obtained through real-time updating and processing of the fault prediction model, including: The health status indicators obtained by the quantum approximate optimization algorithm are processed by data fusion and real-time monitoring system to obtain the real-time geometric integrity status of the transmission shaft; Combining historical data with machine learning models, the probability and preliminary time estimate of potential drive shaft failures are obtained through processing with a fault prediction algorithm, which includes time series analysis and probability models. Based on the probability of occurrence and preliminary time estimation of potential failures of the drive shaft, the predicted time of failure of the drive shaft is obtained through an adaptive adjustment mechanism, and the health status monitoring database of the drive shaft is updated in real time. The adaptive adjustment mechanism includes dynamic threshold adjustment and model parameter optimization.

7. A system for detecting the geometric integrity of an automobile transmission shaft, based on the method for detecting the geometric integrity of an automobile transmission shaft according to claim 1, characterized in that: include: Acquisition module: used to obtain the magnetic field change data of the transmission shaft. According to the principle of electromagnetic induction, an alternating magnetic field is excited by an array of electromagnetic coils evenly arranged around the transmission shaft, and the induced electromotive force is measured using Faraday's law of electromagnetic induction, thereby obtaining the magnetic field change information related to the torsion and shaft diameter change of the transmission shaft, including the amplitude and phase change of the induced electromotive force; The first processing module is used to adjust the damping ratio and natural frequency to match the resonance characteristics of the transmission shaft according to the magnetic field change information through adaptive resonance analysis and processing, so as to obtain the resonance frequency and mode data reflecting the slight changes in the torsion and shaft diameter of the transmission shaft; The second processing module is used to extract and process the features of the resonance frequency and mode data using a quantum machine learning algorithm to obtain the extracted quantum features, and use a quantum convolutional neural network model to perform feature mapping and classification on the extracted quantum features to obtain key features that characterize the geometric integrity of the transmission shaft, wherein the extraction process includes using the principles of quantum state superposition and quantum entanglement to accelerate the search of the feature space; The third processing module is used to evaluate and process the key features based on the quantum approximate optimization algorithm, and find the configuration corresponding to the minimum energy state through the evolution of the quantum state, so as to obtain the health status evaluation result of the geometric integrity of the transmission shaft; Adjustment detection module: It is used to obtain the current geometric integrity status and potential fault occurrence time of the drive shaft based on the health status assessment results, through real-time updating and processing of the fault prediction model, and adaptively adjust the layout of the electromagnetic induction coil and the parameters of the adaptive resonance algorithm according to the feedback of the machine learning model, so as to achieve the final integrity detection of the drive shaft torsion and shaft diameter change.

8. The system for detecting the geometric integrity of an automobile transmission shaft according to claim 7, characterized in that: The second processing module comprises: Preprocessing unit: used to preprocess the resonance frequency and mode data obtained by adaptive resonance analysis, wherein the preprocessing includes normalization, denoising and feature scaling to obtain a set of key data features after preprocessing; Extraction unit: used to use quantum machine learning algorithms to identify patterns and correlations between data in a key data feature set, and extract features that reflect the geometric integrity of the drive shaft, including the offset of the resonant frequency, the frequency distribution width, and the shape parameters of the mode; The first processing unit is used to map the characteristic situation into a superposition state of quantum bits to obtain quantized input data, and use the feature mapping and classification processing of the quantum convolutional neural network model to obtain a quantum feature set that can characterize the geometric integrity of the transmission shaft; The second processing unit is used to optimize the quantum feature set through a quantum algorithm to obtain key features of the geometric integrity of the transmission shaft, wherein the key features include the frequency shift and amplitude change of the resonance peak.

9. The system for detecting the geometric integrity of an automobile transmission shaft according to claim 7, characterized in that: The third processing module includes constructing a calculation formula for the Hamiltonian as follows: In the formula, represents the ground state Hamiltonian or the unperturbed Hamiltonian of the system, Hi Indicates the i The Hamiltonian of the perturbation term, γi represents the penalty weight, H is the Hamiltonian, p represents the total number of disturbance terms.

10. The system for detecting the geometric integrity of a vehicle transmission shaft according to claim 7, characterized in that: The adjustment detection module includes: The third processing unit is used to obtain the real-time geometric integrity status of the transmission shaft according to the health status index obtained by the quantum approximate optimization algorithm through data fusion and real-time monitoring system processing; The fourth processing unit is used to combine historical data with the machine learning model, and obtain the probability of occurrence and preliminary time estimation of potential failure of the transmission shaft through processing by the fault prediction algorithm, wherein the processing process includes time series analysis and probability model; Adjustment and optimization unit: It is used to obtain the predicted time of the failure of the transmission shaft based on the probability of occurrence and preliminary time estimation of the potential failure of the transmission shaft through an adaptive adjustment mechanism, and to update the health status monitoring database of the transmission shaft in real time. The adaptive adjustment mechanism includes dynamic threshold adjustment and model parameter optimization.

Images