A method and system for predicting oil leakage failure of an electric tricycle rear axle oil seal

Abstract

The present application relates to the technical field of electric tricycle fault detection, and particularly relates to an electric tricycle rear axle oil seal oil leakage fault prediction method and system, the method comprising: collecting oil change data, pressure data and oil level data of the electric tricycle rear axle oil seal part, and obtaining the running parameters of the electric tricycle through the vehicle-mounted controller; performing data preprocessing on the collected data and running parameters; performing feature extraction on the preprocessed data, correlating and fusing the extracted features and the electric tricycle running parameters to obtain fusion feature parameters under different driving conditions; using a machine learning algorithm to construct an electric tricycle rear axle oil seal oil leakage fault prediction model according to historical oil seal oil leakage fault and normal operation data as training samples, and performing real-time fault prediction through the model. The present application improves the accuracy of electric tricycle rear axle oil seal oil leakage fault prediction by constructing fusion feature parameters combined with a machine learning algorithm.

Description

Technical Field

[0001] This invention relates to the field of electric tricycle fault detection technology, specifically to a method and system for predicting oil leakage faults in the rear axle oil seal of an electric tricycle. Background Technology

[0002] Electric tricycles are widely used in urban and rural logistics and short-distance transportation due to their economic, environmentally friendly, and easy-to-operate characteristics. As a key component for power transmission and load-bearing in electric tricycles, the sealing performance of the oil seal on the rear axle is crucial. Oil seal leakage can occur due to aging or wear from long-term use, installation errors, abnormal pressure increases inside the rear axle, or excessive gear oil. Once oil seal leakage occurs, it not only wastes gear oil but also accelerates the wear of internal rear axle components due to insufficient lubrication, and in severe cases, can even cause vehicle malfunctions, endangering driving safety.

[0003] Currently, most methods for addressing oil leakage issues in the rear axle oil seals of electric tricycles rely on reactive repairs or periodic inspections, lacking effective prediction of potential malfunctions. Periodic inspections struggle to detect early, subtle changes in the malfunction, while reactive repairs may increase costs and vehicle downtime due to component damage already caused by the malfunction. Therefore, developing a method to accurately predict oil leakage issues in the rear axle oil seals of electric tricycles is crucial for ensuring safe vehicle operation and reducing maintenance costs. Summary of the Invention

[0004] To address the aforementioned technical shortcomings, this invention provides a method and system for predicting oil leakage faults in the rear axle oil seals of electric tricycles, thereby achieving comprehensive and accurate prediction of such faults.

[0005] This invention is achieved through the following technical solution: A method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle is provided, the method comprising the following steps: Step S10: Collect oil change data, pressure data and oil level data at the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the on-board controller; Step S20: Perform data preprocessing on the collected data and operating parameters, including filtering, noise reduction, and normalization; Step S30: Extract features from the preprocessed data to obtain the corresponding feature parameters. Perform correlation analysis and fusion analysis between the extracted feature parameters and the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions. Step S40: Using machine learning algorithms, a prediction model for oil seal leakage faults in the rear axle of an electric tricycle is constructed based on historical oil seal leakage fault data and normal operation data as training samples. The fused feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurrence. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the electric tricycle's display screen or voice prompts, indicating that the rear axle has an oil seal leakage fault.

[0006] Preferably, step S10 includes: Oil change data acquisition: An oil sensor is installed at the oil seal of the rear axle of the electric tricycle to monitor the oil changes in the oil seal area in real time and acquire oil change data. The oil sensor is a high-sensitivity oil leakage detection sensor that can detect extremely small oil leakage signals. Rear axle internal pressure data acquisition: A pressure sensor is installed inside the rear axle of the electric tricycle to collect real-time internal pressure data. The pressure sensor has high precision and fast response characteristics, and can accurately capture minute fluctuations in the internal pressure of the rear axle. Oil level data acquisition: An oil level sensor is installed near the gear oil filler port on the rear axle of the electric tricycle to monitor the gear oil level in real time and acquire oil level data; Electric tricycle operating parameter acquisition: The on-board controller acquires operating parameters such as the electric tricycle's speed, mileage, and running time.

[0007] Preferably, the step of preprocessing the collected data and operating parameters in step S20 includes: Filtering and denoising: Using the Kalman filter algorithm, state variables and observation variables are determined based on the collected data and operating parameters. State equations, observation equations and system state-space models are constructed and the state and covariance are initialized. Then, through prediction and update steps, the noise interference in the data is removed. Normalization: Determine the normalization interval, normalize the oil change data and oil level data to the interval [-1,1], and normalize the rear axle internal pressure data and the electric tricycle operating parameters to the interval [0,1]. All normalization methods are based on the Z-score standard deviation normalization method.

[0008] Preferably, the step S30, which involves extracting features from the preprocessed data to obtain the corresponding feature parameters, includes: Oil change data feature extraction: Fourier transform is used to analyze oil change data and extract the frequency characteristics of abnormal oil signals. The frequency changes of abnormal signals can reflect the type and degree of oil seal leakage. The oil signal strength of the oil sensor is calculated. The oil signal strength is reflected by calculating the root mean square value or peak value of the oil signal. The change in oil signal strength represents the change in the amount or rate of oil leakage. Rear axle internal pressure data feature extraction: Trend analysis is performed on the rear axle internal pressure data. Methods such as linear regression or multinomial fitting are used to obtain the changing trend of the rear axle internal pressure. The rising or falling trend of pressure is related to oil seal leakage. Oil level data feature extraction: Calculate the change in oil level at the gear oil filler port of the electric tricycle's rear axle between adjacent time points or within a specific time period, and then divide by the corresponding time interval to obtain the oil level change rate. An excessively rapid rate of oil level drop is likely due to oil seal leakage. Analyze the stability of the oil level change rate by calculating the variance or standard deviation. An unstable oil level change rate indicates that the oil seal leakage situation in the rear axle is relatively complex.

[0009] Preferably, the step S30, which involves correlating and fusing the extracted feature parameters with the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions, includes: Electric tricycle operating parameters classification: Electric tricycles are classified according to their operating parameters such as speed, mileage, and running time to obtain corresponding classification datasets; Feature association calculation: In each classification dataset, the correlation index between the oil change data feature, the rear axle internal pressure data feature, and the oil level data feature and the driving speed, driving mileage, and running time is calculated. The correlation index is used to measure the degree of linear correlation between each feature and to determine the closeness of their association under different driving conditions. Feature fusion construction: Based on the correlation index obtained from feature association calculation, the features are combined to construct fusion feature parameters under different driving conditions; Feature Validation and Improvement: The constructed fusion feature parameters are validated based on historical data and actual cases. Data with and without oil seal leakage faults are compared under different driving conditions to check whether the fusion feature parameters can effectively distinguish fault states. When it is found that the discrimination of some comprehensive features is not high, the feature combination or correlation analysis method is adjusted to further improve the comprehensive feature parameters.

[0010] Preferably, the step of constructing the oil leakage failure prediction model for the rear axle oil seal of the electric tricycle in step S40 includes: Training sample collection, labeling, and segmentation: A large amount of historical operating data of the rear axle of electric tricycles was collected, including normal operating data and data when oil seal leakage failure occurred. This data covers multi-source information, such as data collected by oil sensors, pressure sensors, and oil level sensors, as well as parameters such as vehicle speed, mileage, and operating time. The collected data was labeled to clearly distinguish between normal data and fault data, providing clear labels for subsequent model training. The labeled data was divided into training set, validation set, and test set according to a certain ratio. The training set was used for training the oil seal leakage failure model of the rear axle of electric tricycles, the validation set was used to adjust the model hyperparameters and prevent overfitting, and the test set was used to evaluate the model's final generalization ability and prediction accuracy. Training of a prediction model for oil leakage faults in the rear axle of electric tricycles: A machine learning algorithm is used to build a model. The fusion features obtained in step S30 are used as input, and the probability of oil leakage faults in the rear axle of electric tricycles is used as output. A prediction model for oil leakage faults in the rear axle of electric tricycles is established. The training set, validation set, and test set obtained in the steps of training sample collection, labeling, and partitioning are used to train and optimize the model, so that the model learns the mapping relationship between the fusion features and the oil leakage faults in the rear axle of electric tricycles. Prediction of oil leakage fault in the rear axle of electric tricycle: The fused features obtained in step S30 are input into the trained prediction model of oil leakage fault in the rear axle of electric tricycle. The model outputs the corresponding probability of oil leakage fault in the rear axle of electric tricycle. A probability threshold is set. When the probability of oil leakage fault in the rear axle of electric tricycle output by the model is greater than or equal to the set probability threshold, a warning message is issued to the driver through the display screen and voice prompts of the electric tricycle. When the probability of oil leakage fault in the rear axle of electric tricycle output by the model is less than the set probability threshold, it indicates that there is no oil leakage fault in the rear axle.

[0011] Furthermore, to achieve the above objectives, the present invention also proposes a fault prediction system for oil leakage from the rear axle oil seal of an electric tricycle, the fault prediction system for oil leakage from the rear axle oil seal of an electric tricycle comprising: Electric tricycle multi-source data acquisition module: used to collect oil change data, pressure data and oil level data of the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the vehicle controller; Electric tricycle multi-source data preprocessing module: used to preprocess the collected data and operating parameters, including filtering, noise reduction and normalization; Feature extraction and fusion module: This module is used to extract features from the preprocessed data, obtain the corresponding feature parameters, perform correlation analysis and fusion with the operating parameters of the electric tricycle, and obtain fused feature parameters under different driving conditions. The electric tricycle rear axle oil seal leakage fault prediction module is used to construct an electric tricycle rear axle oil seal leakage fault prediction model by using machine learning algorithms based on historical oil seal leakage fault data and normal operation data as training samples. The fused feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurring. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the electric tricycle's display screen or voice prompt.

[0012] Furthermore, to achieve the above objectives, the present invention also proposes a device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle. The device includes: a memory, a processor, and programs such as an algorithm for predicting oil leakage faults in the rear axle oil seal of an electric tricycle stored in the memory and executable on the processor. The algorithm and programs are steps for implementing the method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle as described above.

[0013] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as an algorithm for predicting oil leakage faults of the rear axle oil seal of an electric tricycle. When the algorithm for predicting oil leakage faults of the rear axle oil seal of an electric tricycle is executed by a processor, it implements the method for predicting oil leakage faults of the rear axle oil seal of an electric tricycle as described above.

[0014] The advantages and effects of this invention are: This invention proposes a method and system for predicting oil leakage faults in the rear axle oil seal of an electric tricycle. By real-time monitoring and analysis of relevant data of the rear axle of the electric tricycle, it comprehensively obtains the operating status information of the rear axle oil seal and related components. Compared with traditional single data monitoring methods, it can more accurately reflect the potential factors of fault occurrence and improve the accuracy of fault prediction. In addition, by combining data preprocessing technology and machine learning algorithms to calculate the probability of oil leakage faults, the accuracy of fault prediction is improved, providing a scientific basis for vehicle maintenance and reducing vehicle downtime and repair costs caused by faults. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, in one embodiment of the present invention, a method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle includes the following steps: Step S10: Collect oil change data, pressure data, and oil level data at the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the on-board controller.

[0019] Specifically, step S10 includes: Oil change data acquisition: An oil sensor is installed at the oil seal of the rear axle of the electric tricycle to monitor the oil changes in the oil seal area in real time and acquire oil change data. The oil sensor is a high-sensitivity oil leakage detection sensor that can detect extremely small oil leakage signals. Rear axle internal pressure data acquisition: A pressure sensor is installed inside the rear axle of the electric tricycle to collect real-time internal pressure data. The pressure sensor has high precision and fast response characteristics, and can accurately capture minute fluctuations in the internal pressure of the rear axle. Oil level data acquisition: An oil level sensor is installed near the gear oil filler port on the rear axle of the electric tricycle to monitor the gear oil level in real time and acquire oil level data; Electric tricycle operating parameter acquisition: The on-board controller acquires operating parameters such as the electric tricycle's speed, mileage, and running time.

[0020] Step S20: Perform data preprocessing on the collected data and operating parameters, including filtering, noise reduction, and normalization.

[0021] Specifically, step S20, which involves preprocessing the collected data and operating parameters, includes: Filtering and denoising: Using the Kalman filter algorithm, state variables and observation variables are determined based on the collected data and operating parameters. State equations, observation equations and system state-space models are constructed and the state and covariance are initialized. Then, through prediction and update steps, the noise interference in the data is removed. Normalization: Determine the normalization interval, normalize the oil change data and oil level data to the interval [-1,1], and normalize the rear axle internal pressure data and the electric tricycle operating parameters to the interval [0,1]. All normalization methods are based on the Z-score standard deviation normalization method.

[0022] Step S30: Extract features from the preprocessed data to obtain the corresponding feature parameters. Perform correlation analysis and fusion analysis on the extracted feature parameters and the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions.

[0023] Specifically, step S30, which involves extracting features from the preprocessed data to obtain the corresponding feature parameters, includes: Oil change data feature extraction: Fourier transform is used to analyze oil change data and extract the frequency characteristics of abnormal oil signals. The frequency changes of abnormal signals can reflect the type and degree of oil seal leakage. The oil signal strength of the oil sensor is calculated. The oil signal strength is reflected by calculating the root mean square value or peak value of the oil signal. The change in oil signal strength represents the change in the amount or rate of oil leakage. Rear axle internal pressure data feature extraction: Trend analysis is performed on the rear axle internal pressure data. Methods such as linear regression or multinomial fitting are used to obtain the changing trend of the rear axle internal pressure. The rising or falling trend of pressure is related to oil seal leakage. For example, abnormal pressure rise is due to the combined effect of vent blockage and oil seal leakage. The fluctuation range of the rear axle internal pressure data within a certain time window is calculated, for example, by measuring it through standard deviation or range. An increase in pressure fluctuation range indicates a decrease in oil seal sealing performance. Oil level data feature extraction: Calculate the change in oil level at the gear oil filler port of the electric tricycle's rear axle between adjacent time points or within a specific time period, and then divide by the corresponding time interval to obtain the oil level change rate. An excessively rapid rate of oil level drop is likely due to oil seal leakage. Analyze the stability of the oil level change rate by calculating the variance or standard deviation. An unstable oil level change rate indicates that the oil seal leakage situation in the rear axle is relatively complex.

[0024] Specifically, step S30 involves correlating and fusing the extracted feature parameters with the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions. Electric tricycle operating parameters classification: Electric tricycles are classified according to their operating parameters such as speed, mileage, and operating time to obtain corresponding classification datasets. For example, the speed range is divided into low speed (0-15km / h), medium speed (15-30km / h), and high speed (above 30km / h). Data is also classified according to different mileage ranges, such as 0-100km and 100-500km. The data is organized based on operating time (such as morning peak, off-peak, and evening peak). Feature association calculation: In each classification dataset, calculate the correlation index between the oil change data feature, the rear axle internal pressure data feature, and the oil level data feature and the driving speed, driving mileage, and running time, such as the Pearson correlation coefficient. The correlation index measures the degree of linear correlation between each feature and judges the closeness of their association under different driving conditions. Feature Fusion Construction: Based on the correlation indices obtained from feature association calculations, features are combined to construct fusion feature parameters for different driving conditions. For example, under high-speed driving conditions, high driving speed, high pressure fluctuation amplitude, and abnormal oil signals within a specific frequency range are combined into a fusion feature; under long-mileage driving conditions, fusion features are constructed by combining mileage, the gradually decreasing rate of oil level change, and pressure change trends. Feature Validation and Improvement: The constructed fusion feature parameters are validated based on historical data and actual cases. Data with and without oil seal leakage faults are compared under different driving conditions to check whether the fusion feature parameters can effectively distinguish fault states. When it is found that the discrimination of some comprehensive features is not high, the feature combination or correlation analysis method is adjusted to further improve the comprehensive feature parameters.

[0025] Step S40: Using machine learning algorithms, a prediction model for oil seal leakage faults in the rear axle of an electric tricycle is constructed based on historical oil seal leakage fault data and normal operation data as training samples. The fused feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurrence. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the electric tricycle's display screen or voice prompts, indicating that the rear axle has an oil seal leakage fault.

[0026] Specifically, step S40, which involves constructing a fault prediction model for the oil seal leakage of the rear axle of an electric tricycle, includes the following steps: Training sample collection, labeling, and segmentation: A large amount of historical operating data of the rear axle of electric tricycles was collected, including normal operating data and data when oil seal leakage failure occurred. This data covers multi-source information, such as data collected by oil sensors, pressure sensors, and oil level sensors, as well as parameters such as vehicle speed, mileage, and operating time. The collected data was labeled to clearly distinguish between normal data and fault data, providing clear labels for subsequent model training. The labeled data was divided into training set, validation set, and test set according to a certain ratio. The training set was used for training the oil seal leakage failure model of the rear axle of electric tricycles, the validation set was used to adjust the model hyperparameters and prevent overfitting, and the test set was used to evaluate the model's final generalization ability and prediction accuracy. Training of a prediction model for oil leakage faults in the rear axle oil seal of an electric tricycle: A model is built using machine learning algorithms, such as Support Vector Machine (SVM) and Random Forest. The fused features obtained in step S30 are used as input, and the probability of oil leakage faults in the rear axle oil seal of an electric tricycle is used as output to establish a prediction model for oil leakage faults in the rear axle oil seal of an electric tricycle. The training set, validation set, and test set obtained in the steps of training sample collection, labeling, and partitioning are used to train and optimize the model. For example, the model parameters are optimized through methods such as cross-validation to improve the prediction accuracy and generalization ability of the model, so that the model can learn the mapping relationship between the fused features and the oil leakage faults in the rear axle oil seal of an electric tricycle. Prediction of oil seal leakage fault in the rear axle of an electric tricycle: The fused features obtained in step S30 are input into the trained prediction model for oil seal leakage fault in the rear axle of an electric tricycle. The model outputs the corresponding probability of oil seal leakage fault in the rear axle of the electric tricycle. A probability threshold is set. When the probability of oil seal leakage fault in the rear axle of the electric tricycle output by the model is greater than or equal to the set probability threshold, a warning message is issued to the driver through the display screen and voice prompts of the electric tricycle, indicating that the probability of oil seal leakage fault in the rear axle is high and it is recommended to check and maintain it in time. When the probability of oil seal leakage fault in the rear axle of the electric tricycle output by the model is less than the set probability threshold, it means that there is no oil seal leakage fault in the rear axle. For example, if the probability threshold is set to 0.7, when the predicted probability exceeds 0.7, the vehicle's display screen shows a red warning icon and the driver is prompted by voice that "the rear axle may have an oil seal leakage fault, please check it as soon as possible."

[0027] Furthermore, in one embodiment of the present invention, a fault prediction system for oil leakage of the rear axle oil seal of an electric tricycle is proposed. The system includes: Electric tricycle multi-source data acquisition module: used to collect oil change data, pressure data and oil level data of the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the vehicle controller; Electric tricycle multi-source data preprocessing module: used to preprocess the collected data and operating parameters, including filtering, noise reduction and normalization; Feature extraction and fusion module: This module is used to extract features from the preprocessed data, obtain the corresponding feature parameters, perform correlation analysis and fusion with the operating parameters of the electric tricycle, and obtain fused feature parameters under different driving conditions. The electric tricycle rear axle oil seal leakage fault prediction module is used to construct an electric tricycle rear axle oil seal leakage fault prediction model by using machine learning algorithms based on historical oil seal leakage fault data and normal operation data as training samples. The fused feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurrence. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the electric tricycle's display screen or voice prompt, indicating that the rear axle oil seal leakage fault has occurred.

[0028] This application provides a system for predicting oil leakage faults in the rear axle oil seals of electric tricycles. It employs a method for predicting oil leakage faults in the rear axle oil seals of electric tricycles as described in the above embodiments, thus solving the technical problem that traditional methods cannot effectively predict oil leakage faults in the rear axle oil seals of electric tricycles. Compared with the prior art, the beneficial effects of the system for predicting oil leakage faults in the rear axle oil seals of electric tricycles provided in this application are the same as those of the method provided in the above embodiments. Furthermore, other technical features of the system for predicting oil leakage faults in the rear axle oil seals of electric tricycles are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0029] This application provides a device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle as described in Embodiment 1 above.

[0030] In one embodiment of the present invention, a device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The aforementioned device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments in this application.

[0031] The aforementioned electric tricycle rear axle oil seal leakage fault prediction device may include a processing system (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) or a program loaded from a storage system into random access memory (RAM). The RAM also stores various programs and data required for the operation of the electric tricycle rear axle oil seal leakage fault prediction device. The processing system, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus. Typically, the following systems can be connected to the I / O interface: input systems including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output systems including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage systems including, for example, magnetic tapes, hard disks, etc.; and communication systems. The communication system allows the electric tricycle rear axle oil seal leakage fault prediction device to communicate wirelessly or wiredly with other devices to exchange data.

[0032] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication system, or installed from a storage system, or installed from a ROM. When the computer program is executed by a processing system, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0033] This application provides a device for predicting oil leakage faults in the rear axle oil seals of electric tricycles. It employs a method for predicting oil leakage faults in the rear axle oil seals of electric tricycles as described in the above embodiments, thus solving the technical problem that traditional methods cannot effectively predict oil leakage faults in the rear axle oil seals of electric tricycles. Compared with the prior art, the beneficial effects of the device for predicting oil leakage faults in the rear axle oil seals of electric tricycles provided in this application are the same as those of the method provided in the above embodiments. Furthermore, other technical features of this device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0034] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0035] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle.

[0036] The computer program product provided in this application can solve the technical problem that traditional electric tricycle rear axle oil seal leakage failure cannot be effectively predicted. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the electric tricycle rear axle oil seal leakage failure prediction method provided in the above embodiments, and will not be repeated here.

[0037] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle, characterized in that, The method includes the following steps: Step S10: Collect oil change data, pressure data and oil level data at the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the on-board controller; Step S20: Perform data preprocessing on the collected data and operating parameters, including filtering, noise reduction, and normalization; Step S30: Extract features from the preprocessed data to obtain the corresponding feature parameters. Perform correlation analysis and fusion analysis on the extracted feature parameters and the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions. Step S40: Using machine learning algorithms, a prediction model for oil leakage faults of the rear axle of the electric tricycle is constructed based on historical oil seal leakage fault data and normal operation data as training samples. The fusion feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurring. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the display screen or voice prompt of the electric tricycle.

2. The method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to claim 1, characterized in that, Step S10 includes: Oil change data acquisition: An oil sensor is installed at the oil seal of the rear axle of the electric tricycle to monitor the oil changes in the oil seal area in real time and acquire oil change data; Rear axle internal pressure data acquisition: A pressure sensor is installed inside the rear axle of the electric tricycle to collect real-time internal pressure data. Oil level data acquisition: An oil level sensor is installed at the gear oil filler port on the rear axle of the electric tricycle to monitor the gear oil level in real time and acquire oil level data; Electric tricycle operating parameter acquisition: The vehicle controller acquires the electric tricycle's speed, mileage, and operating time.

3. The method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to claim 1, characterized in that, The data preprocessing steps for the collected data and operating parameters in step S20 include: Filtering and denoising: Using the Kalman filter algorithm, state variables and observation variables are determined based on the collected data and operating parameters. State equations, observation equations and system state-space models are constructed and the state and covariance are initialized. Then, through prediction and update steps, the noise interference in the data is removed. Normalization: Determine the normalization interval, normalize the oil change data and oil level data to the interval [-1,1], and normalize the rear axle internal pressure data and the electric tricycle operating parameters to the interval [0,1]. All normalization methods are based on the Z-score standard deviation normalization method.

4. The method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to claim 1, characterized in that, The step S30, which involves extracting features from the preprocessed data to obtain the corresponding feature parameters, includes: Oil change data feature extraction: Fourier transform is used to analyze oil change data, extract frequency features of abnormal oil signals, calculate oil signal strength from oil sensors, and reflect oil signal strength by calculating the root mean square value or peak value of the oil signal. Rear axle internal pressure data feature extraction: Perform trend analysis on the rear axle internal pressure data, use linear regression or multinomial fitting methods to obtain the changing trend of the rear axle internal pressure, and calculate the fluctuation range of the rear axle internal pressure data within a certain time window. Oil level data feature extraction: Calculate the change in oil level at the gear oil filler port of the electric tricycle's rear axle at adjacent time points or within a specific time period, and then divide by the corresponding time interval to obtain the oil level change rate. Analyze the stability of the oil level change rate by calculating its variance or standard deviation.

5. The method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to claim 1, characterized in that, The step S30, which involves correlating and fusing the extracted feature parameters with the operating parameters of the electric tricycle to obtain fused feature parameters under different driving conditions, includes: Electric tricycle operating parameters classification: Electric tricycles are classified according to their driving speed, driving distance, and operating time to obtain corresponding classification datasets; Feature association calculation: In each classification dataset, the correlation index between the oil change data feature, the rear axle internal pressure data feature, and the oil level data feature and the driving speed, driving mileage, and running time is calculated. The correlation index is used to measure the degree of linear correlation between each feature and to determine the closeness of their association under different driving conditions. Feature fusion construction: Based on the correlation index obtained by feature association calculation, the features are combined to construct fusion feature parameters under different driving conditions; Feature verification and improvement: The constructed fusion feature parameters are verified based on historical data and actual cases. Data with oil seal leakage faults and no faults are compared under different driving conditions to check whether the fusion feature parameters can effectively distinguish fault states.

6. The method for predicting oil leakage faults in the rear axle oil seal of an electric tricycle according to claim 1, characterized in that, The steps in step S40 of constructing the oil leakage failure prediction model for the rear axle oil seal of the electric tricycle include: Training sample collection, labeling and division: Collect historical operating data of the rear axle of electric tricycles, including normal operating data and data when oil seal leakage failure occurs. Label the collected data to clearly distinguish between normal data and failure data. Divide the labeled data into training set, validation set and test set according to a certain ratio. Training of a prediction model for oil leakage faults in the rear axle of electric tricycles: A machine learning algorithm is used to build a model. The fusion features obtained in step S30 are used as input, and the probability of oil leakage faults in the rear axle of electric tricycles is used as output. A prediction model for oil leakage faults in the rear axle of electric tricycles is established. The training set, validation set, and test set obtained in the steps of training sample collection, labeling, and partitioning are used to train and optimize the model, so that the model learns the mapping relationship between the fusion features and the oil leakage faults in the rear axle of electric tricycles. Prediction of oil leakage fault in the rear axle of electric tricycle: The fused features obtained in step S30 are input into the trained prediction model of oil leakage fault in the rear axle of electric tricycle. The model outputs the corresponding probability of oil leakage fault in the rear axle of electric tricycle. A probability threshold is set. When the probability of oil leakage fault in the rear axle of electric tricycle output by the model is greater than or equal to the set probability threshold, a warning message is issued to the driver through the display screen and voice prompt of the electric tricycle. When the probability of oil leakage fault in the rear axle of electric tricycle output by the model is less than the set probability threshold, it indicates that there is no oil leakage fault in the rear axle.

7. A fault prediction system for oil leakage from the rear axle oil seal of an electric tricycle, characterized in that, The electric tricycle rear axle oil seal leakage fault prediction system includes: Electric tricycle multi-source data acquisition module: used to collect oil change data, pressure data and oil level data of the oil seal of the rear axle of the electric tricycle, and obtain the operating parameters of the electric tricycle through the vehicle controller; Electric tricycle multi-source data preprocessing module: used to preprocess the collected data and operating parameters, including filtering, noise reduction and normalization; Feature extraction and fusion module: This module is used to extract features from the preprocessed data, obtain the corresponding feature parameters, perform correlation analysis and fusion with the operating parameters of the electric tricycle, and obtain fused feature parameters under different driving conditions. The electric tricycle rear axle oil seal leakage fault prediction module is used to construct an electric tricycle rear axle oil seal leakage fault prediction model by using machine learning algorithms based on historical oil seal leakage fault data and normal operation data as training samples. The fused feature parameters obtained in step S30 are input into the constructed model to output the probability of the fault occurring. A reasonable probability threshold is set. When the output probability exceeds the threshold, a warning message is issued to the driver through the electric tricycle's display screen or voice prompt.

8. A device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle, characterized in that, The aforementioned device for predicting oil leakage faults in the rear axle oil seal of an electric tricycle includes: The present invention includes a memory, a processor, and a fault prediction program for an electric tricycle rear axle oil seal leakage, which is stored in the memory and can run on the processor. When the electric tricycle rear axle oil seal leakage fault prediction program is executed by the processor, it implements a fault prediction method for an electric tricycle rear axle oil seal leakage as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes a fault prediction program for oil leakage from the rear axle oil seal of an electric tricycle. When the fault prediction program for oil leakage from the rear axle oil seal of an electric tricycle is executed by a processor, it implements a fault prediction method for oil leakage from the rear axle oil seal of an electric tricycle as described in any one of claims 1 to 6.

Images