Methods, devices, and vehicles for predicting the lifespan of vehicle transmission components.

Abstract

This invention discloses a method, apparatus, and vehicle for predicting the lifespan of vehicle transmission components. The method includes: acquiring raw load spectrum data of the transmission components in the vehicle, wherein the raw load spectrum data represents the collected load spectrum data of the transmission components within a preset time period; classifying the raw load spectrum data to obtain classification results, wherein the classification results represent at least one road condition of the road on which the vehicle travels within the preset time period; and predicting the lifespan of the transmission components based on the classification results and a preset correspondence to obtain the remaining lifespan of the transmission components, wherein the preset correspondence records the lifespan of the transmission components within a temperature range corresponding to at least one road condition. This invention solves the technical problem of low accuracy in predicting the lifespan of vehicle transmission components in related technologies.

Description

Technical Field

[0001] This invention relates to the field of vehicle prediction, and more specifically, to a method, apparatus, and vehicle for predicting the lifespan of vehicle transmission components. Background Technology

[0002] Accurate prediction of vehicle transmission component lifespan allows users to know the remaining service life of these components in advance, facilitating timely replacement and preventing safety accidents. Current technologies primarily utilize sensors to monitor gear status in real time and predict remaining lifespan based on this information. The point of inflection plays a crucial role in this prediction; deviations or difficulty in identifying these points can negatively impact the accuracy of the prediction.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and vehicle for predicting the lifespan of vehicle transmission components, thereby at least addressing the technical problem of low accuracy in predicting the lifespan of vehicle transmission components in related technologies.

[0005] According to one aspect of the present invention, a method for predicting the lifespan of a vehicle transmission component is provided, comprising: acquiring raw load spectrum data of the transmission component in the vehicle, wherein the raw load spectrum data is used to represent the load spectrum data of the transmission component collected within a preset time period; classifying the raw load spectrum data to obtain a classification result, wherein the classification result is used to represent at least one road condition of the road on which the vehicle travels within the preset time period; predicting the lifespan of the transmission component based on the classification result and a preset correspondence to obtain the remaining lifespan of the transmission component, wherein the preset correspondence is used to record the lifespan of the transmission component in a temperature range corresponding to at least one road condition.

[0006] Optionally, the remaining life of the transmission component is predicted based on the classification results and a preset correspondence, including: determining the target damage rate of the transmission component based on the classification results and the preset correspondence, wherein the target damage rate is used to represent the wear state of the transmission component; and predicting the remaining life of the transmission component based on a first preset value and the target damage rate.

[0007] Optionally, the target damage rate of the transmission component is determined based on the classification results and a preset correspondence, including: determining the number of times the transmission component is used and the target temperature in at least one road condition based on the classification results; determining the target life of the transmission component at the target temperature corresponding to at least one road condition based on the preset correspondence; and determining the target damage rate based on the number of times the transmission component is used and the target life in at least one road condition.

[0008] Optionally, the original load spectrum data can be classified to obtain classification results, including: classifying the original load spectrum data using the target model to obtain classification results.

[0009] Optionally, the above method further includes: collecting sample load spectrum data of the vehicle under different road conditions and the corresponding annotation information of the sample load spectrum data, wherein the sample load spectrum data is used to represent the load spectrum data of the transmission components in the vehicle under different road conditions, and the annotation information is used to represent the road conditions of the vehicle when the sample load spectrum data is collected; and using the sample load spectrum data and the corresponding annotation information to train the initial model to obtain the target model.

[0010] Optionally, the above method further includes: displaying the original load spectrum data and classification results on the interactive interface; receiving target feedback information corresponding to the classification results, wherein the target feedback information is used to modify the classification results; and adjusting the model parameters of the target model based on the target feedback information.

[0011] Optionally, the original load spectrum data is classified to obtain classification results, including: filtering the original load spectrum data using the rainflow counting method to obtain first load spectrum data, wherein the first load spectrum data is the same data that appears more than a preset number of times in the original load spectrum data; converting the first load spectrum data using the equal damage conversion method to obtain second load spectrum data, wherein the data volume of the second load spectrum data is less than the data volume of the first load spectrum data; and classifying the second load spectrum data to obtain classification results.

[0012] According to another aspect of the present invention, a device for predicting the lifespan of a vehicle transmission component is also provided, comprising: an acquisition module for acquiring raw load spectrum data of the transmission component in a vehicle, wherein the raw load spectrum data represents the collected load spectrum data of the transmission component within a preset time period; a classification module for classifying the raw load spectrum data to obtain a classification result, wherein the classification result represents at least one road condition of the road on which the vehicle travels within the preset time period; and a prediction module for predicting the lifespan of the transmission component based on the classification result and a preset correspondence to obtain the remaining lifespan of the transmission component, wherein the preset correspondence records the lifespan of the transmission component in a temperature range corresponding to at least one road condition.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, characterized in that the non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the execution of the vehicle transmission component life prediction method described above in the processor of the device.

[0014] According to another aspect of the present invention, a vehicle is also provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the method for predicting the lifespan of a vehicle transmission component according to any one of claims 1 to 7.

[0015] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the above-described vehicle control method when it runs.

[0016] In this embodiment of the invention, the original load spectrum data of the transmission components in the vehicle is obtained; the original load spectrum data is classified to obtain a classification result, wherein the classification result is used to represent at least one road condition of the road on which the vehicle travels within a preset time period; the lifespan of the transmission components is predicted based on the classification result and a preset correspondence to obtain the remaining lifespan of the transmission components. It should be noted that the preset correspondence is used to record the lifespan of the transmission components in the temperature range corresponding to at least one road condition. In the process of predicting the lifespan of the vehicle transmission components, by classifying the original load spectrum data, load spectrum data under different road conditions can be obtained. At the same time, combined with the temperature corresponding to different road conditions, the lifespan of the transmission components is predicted, achieving the goal of considering both road condition factors and temperature factors when predicting the lifespan of the transmission components. This achieves the technical effect of improving the accuracy of vehicle transmission component lifespan prediction, and thus solves the technical problem of low prediction accuracy of vehicle transmission component lifespan in related technologies. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of an optional transmission component life prediction method based on existing technology;

[0019] Figure 2 This is a flowchart of an optional transmission component life prediction method based on existing technology;

[0020] Figure 3 This is a flowchart of an optional method for predicting the lifespan of a vehicle transmission component according to an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of a self-learning network model according to an embodiment of the present invention;

[0022] Figure 5 This is a flowchart of an optional method for predicting the lifespan of a vehicle transmission component according to an embodiment of the present invention;

[0023] Figure 6 This is a device for predicting the lifespan of a vehicle transmission component according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Currently, the main methods for predicting the lifespan of transmission components in related technologies include:

[0027] The gear's status information is monitored in real time using sensors (accelerometers, temperature sensors, noise sensors, etc.), the fatigue state of the gear is characterized, the wear degradation performance of the gear is evaluated, a degradation state space model with variable parameters is established, and the remaining life of the gear is estimated based on the gear's status. Figure 1 This is a flowchart of an optional transmission component life prediction method based on existing technology, such as... Figure 1As shown, the specific process of this method is as follows: real-time data characterizing gear degradation is obtained through gear fatigue testing; feature values ​​are extracted from the gear fatigue state; spatial modeling of the gear degradation state is performed; abrupt changes in the degradation state are detected; the prediction model is corrected; the degradation state is estimated; and finally, the real-time remaining life of the gear is predicted. This existing technology posits that during gear degradation, the wear process often evolves from gradual and quantitative changes to abrupt and qualitative changes, leading to changes in the system's materials and structure, resulting in degradation abrupt points. The degradation rate increases after the abrupt point, thus significantly altering the remaining life. The abrupt point is the starting point of the degradation state change, and the large amount of remaining life information it contains can provide useful information for remaining life prediction and the formulation of preventative maintenance strategies. By establishing a state space and combining it with the abrupt points, the remaining life can be predicted. As a critical point of state change, the abrupt point plays a crucial role in the life prediction process; therefore, the accuracy of the abrupt point becomes key to remaining life prediction. If the abrupt points are biased or complex and difficult to identify, the accuracy of the results will be challenged.

[0028] Using the structural characteristic parameters (number of teeth, roughness, etc.) and material parameters (material) of the gear as inputs, and the gear contact fatigue life as output, a neural network is constructed and trained. Figure 2 This is a flowchart of an optional transmission component life prediction method based on existing technology, such as... Figure 2 As shown, the specific process of this method is as follows: Gear contact fatigue test data is collected and normalized, serving as input and output parameters and learning parameters for a back-propagation (BP) neural network. A BP neural network structure is constructed, and a genetic algorithm is used to optimize the weights and thresholds of the BP neural network. The network is then trained, and the determination coefficient of the prediction accuracy evaluation parameters is calculated to determine if the specified requirements are met. The training weights and thresholds are then obtained, and the established BP neural network optimized using the genetic algorithm is tested using a test sample set to evaluate the network performance and prediction accuracy. It is understandable that structural and material parameters, which are inherent parameters of the gear itself, are related to the gear's lifespan, but they are not decisive factors. Different gear heat treatment processes and complex actual working conditions further complicate the issue. Therefore, relying solely on the gear's inherent parameters without considering the boundary conditions imposed on the gear by the user's actual usage is biased.

[0029] Example 1

[0030] According to an embodiment of the present invention, an embodiment of a method for predicting the lifespan of a vehicle transmission component is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] Figure 3 This is a flowchart of an optional method for predicting the lifespan of a vehicle transmission component according to an embodiment of the present invention, such as... Figure 3 As shown, the method includes the following steps:

[0032] Step S 302: Obtain the original load spectrum data of the transmission components in the vehicle, wherein the original load spectrum data is used to represent the load spectrum data of the transmission components collected within a preset time period.

[0033] The transmission component can be a power transmission device located between the engine and the drive wheels of the vehicle, used to receive the power from the engine and transmit it to the drive wheels. It mainly includes gears, bearings, couplings, and clutches. The load spectrum can be a description of the load value change of a load-bearing body within a specified range of parameters. The load spectrum represents the entire load change process. In this embodiment of the invention, the load spectrum data can be used to characterize the user's driving habits. The preset time period can be a pre-set time period for collecting the load spectrum data of the transmission component.

[0034] In one alternative embodiment, the raw load spectrum data of the transmission components in a vehicle can be obtained using a road load spectrum acquisition system.

[0035] It should be noted that, in order to ensure the accuracy of the collected data, 0.5-10,000 kilometers of data can be collected for each road condition during the acquisition of the original load spectrum data.

[0036] Step S304: Classify the original load spectrum data to obtain classification results, wherein the classification results are used to represent at least one road condition of the road on which the vehicle travels within a preset time period.

[0037] In one optional embodiment, the raw load spectrum data can be classified according to road condition information, which may include, but is not limited to, urban areas, suburbs, mountainous areas, highways, off-road areas, etc. The raw load spectrum data can be classified by a self-learning network model, which may include, but is not limited to, various machine learning methods such as logistic regression, support vector machine (SVM), clustering, etc., or a neural network self-learning mode can be used for classification.

[0038] Understandably, since self-learning network models have self-learning and associative storage functions, and have the ability to find optimal solutions at high speed, they can be used to classify the original load spectrum data. This allows for a better understanding of the road conditions a user is in within a short period of time, preparing for the subsequent prediction strategies used to predict the lifespan of transmission components.

[0039] Specifically, the process of classifying raw load spectrum data can include data annotation and algorithm model training. Data annotation can be understood as marking the corresponding road condition information on the collected raw load spectrum data, so that artificial intelligence devices can accurately obtain the road condition information corresponding to the raw load spectrum data. Through data annotation, artificial intelligence devices or systems can be taught to recognize people and objects, enabling them to continuously learn and grow. Training the algorithm model allows the artificial neural network model to learn statistical laws from a large number of training samples, thereby making predictions about unknown events and achieving the goal of accurately predicting the lifespan of vehicle transmission components.

[0040] In one alternative embodiment, the raw load spectrum data can be labeled using various methods such as text, images, and voice, and the algorithm model can be trained using Matrix Laboratory (MATLAB).

[0041] Step S306: Based on the classification results and the preset correspondence, the lifespan of the transmission component is predicted to obtain the remaining lifespan of the transmission component. The preset correspondence is used to record the lifespan of the transmission component in at least one temperature range corresponding to a road condition.

[0042] The remaining lifespan of the transmission component can be the remaining service life of the transmission component predicted based on the classification results and the preset correspondence. The preset correspondence can be pre-set and used to characterize the correspondence between the temperature range and the number of times the transmission component is used.

[0043] In one alternative embodiment, the preset correspondence can be displayed in tabular form.

[0044] Specifically, predicting the lifespan of transmission components based on classification results and preset correspondences can be achieved by obtaining road condition information corresponding to the road where the vehicle is traveling based on the classification results, finding the preset correspondence corresponding to the road condition, finding the number of times the transmission component is used corresponding to the current road condition and current temperature through parameter lookup table, and using mathematical formulas to calculate the damage rate of the transmission component under different temperatures on the same road condition in a short period of time based on the number of times it is used, thereby obtaining the remaining lifespan of the transmission component.

[0045] Through the above steps, the original load spectrum data of the transmission components in the vehicle is obtained. The original load spectrum data is classified to obtain the classification result. The classification result is used to represent at least one road condition of the road on which the vehicle travels within a preset time period. Based on the classification result and the preset correspondence, the lifespan of the transmission components is predicted to obtain the remaining lifespan of the transmission components. It should be noted that the preset correspondence is used to record the lifespan of the transmission components in the temperature range corresponding to at least one road condition. In the process of predicting the lifespan of the vehicle transmission components, by classifying the original load spectrum data, load spectrum data under different road conditions can be obtained. At the same time, combined with the temperature corresponding to different road conditions, the lifespan of the transmission components is predicted. This achieves the goal of considering both road condition factors and temperature factors when predicting the lifespan of the transmission components, thereby improving the technical effect of predicting the lifespan of vehicle transmission components and solving the technical problem of low prediction accuracy of related technologies for the lifespan of vehicle transmission components.

[0046] Optionally, the remaining life of the transmission component is predicted based on the classification results and a preset correspondence, including: determining the target damage rate of the transmission component based on the classification results and the preset correspondence, wherein the target damage rate is used to represent the wear state of the transmission component; and predicting the remaining life of the transmission component based on a first preset value and the target damage rate.

[0047] The first preset value can be a value that is preset in advance and used to calculate the remaining life of the transmission component. For example, it can be set to 1.

[0048] In one alternative embodiment, the target damage rate can be calculated using a mathematical formula, and the lifespan of the transmission component can be predicted by the difference between a first preset value and the target damage rate, thus obtaining the remaining lifespan.

[0049] It is understandable that since the calculated target damage rate is a percentage, that is, a value less than or equal to 1, the remaining life of the transmission component can be obtained by subtracting the target damage rate from 1. Therefore, the first preset value can be set to 1.

[0050] Optionally, the target damage rate of the transmission component is determined based on the classification results and a preset correspondence, including: determining the number of times the transmission component is used and the target temperature in at least one road condition based on the classification results; determining the target life of the transmission component at the target temperature corresponding to at least one road condition based on the preset correspondence; and determining the target damage rate based on the number of times the transmission component is used and the target life in at least one road condition.

[0051] Among them, the number of uses can be the number of times the transmission component is used in at least one road condition when the vehicle is in motion, the target temperature can be the temperature of the transmission component in its working state, and the target life can be a preset life of the transmission component at the target temperature corresponding to at least one road condition.

[0052] In an optional embodiment, the number of times the transmission component is used in at least one road condition can be determined based on the classification results using a transmission component control device; the target temperature of the transmission component in at least one road condition can be determined based on the classification results using a temperature sensor; the target lifespan of the transmission component at the target temperature corresponding to at least one road condition can be determined by a parameter lookup table; and the target damage rate can be determined based on the number of times the transmission component is used in at least one road condition and the target lifespan using the following formula:

[0053]

[0054] Therefore, it can be done To determine the remaining lifespan of the transmission components.

[0055] Where φ represents the target damage rate, G 01 G 02 G 03 G 04 G 05 These represent the number of times the transmission component has been used under different temperature ranges and road conditions, respectively. G 11 G 32 G 23 G 54 G 45 These represent the target lifespan of the transmission components under different temperature ranges and road conditions, for example, G. 01 G represents the number of times the transmission components of a vehicle are used when the temperature is below 90℃ in urban areas. 02 The number of times the transmission components of a vehicle are used when the temperature is between 90℃ and 110℃ in mountainous areas, G 03 G represents the number of times the transmission components of a vehicle are used when driving in suburban areas at temperatures ranging from 110℃ to 130℃. 04 The number of times the transmission components of a vehicle are used during off-road driving at a temperature of 130℃-150℃, G 05 The number of times the transmission components of a vehicle are used at high speeds when the temperature is above 150℃, corresponding to G. 11 G represents the target lifespan of transmission components in a vehicle operating in urban areas at temperatures below 90°C. 32 The target life of transmission components for vehicles operating in mountainous areas at temperatures ranging from 90℃ to 110℃, represented by G. 23 The target life of transmission components in a vehicle operating in suburban areas, represented by the temperature range of 110℃-130℃, is G. 54 The target lifespan of the transmission components of a vehicle under off-road driving conditions, represented by the temperature range of 130℃-150℃. 45The target lifespan of the transmission components in a vehicle at high speeds is represented by a temperature above 150℃. The target lifespan of the vehicle under different temperatures and road conditions can be obtained from Table 1.

[0056] Table 1 Target lifespan of transmission components under different temperature ranges and road conditions.

[0057]

[0058] Optionally, the original load spectrum data can be classified to obtain classification results, including: classifying the original load spectrum data using the target model to obtain classification results.

[0059] The target model can be any trained algorithm model that can be used to classify the raw load spectrum data. Using the target model can better distinguish what kind of road conditions the user is in for a short period of time, and prepare for what prediction strategy to use to predict lifespan.

[0060] In one alternative embodiment, the raw load spectrum data can be classified using a self-learning network model. The self-learning network model can include, but is not limited to, various machine learning methods such as logistic regression, SVM, and clustering, or it can use the self-learning mode of a neural network for classification.

[0061] Optionally, the above method further includes: collecting sample load spectrum data of the vehicle under different road conditions and the corresponding annotation information of the sample load spectrum data, wherein the sample load spectrum data is used to represent the load spectrum data of the transmission components in the vehicle under different road conditions, and the annotation information is used to represent the road conditions of the vehicle when the sample load spectrum data is collected; and using the sample load spectrum data and the corresponding annotation information to train the initial model to obtain the target model.

[0062] The initial model can be an untrained algorithm model.

[0063] In one optional embodiment, information acquisition devices can be used to collect sample load spectrum data of vehicles under different road conditions and the corresponding annotation information of the sample load spectrum data.

[0064] Figure 4 This is a schematic diagram of a self-learning network model according to an embodiment of the present invention, such as... Figure 4 As shown, the network model includes an input layer, a hidden layer, and an output layer. The input layer includes torque and speed, and the output layer includes road condition classification information, specifically: urban area, suburbs, mountainous area, highway, and off-road.

[0065] Specifically, the initial model can be trained through the following steps: First, initialize the neural network, that is, initialize the weights and biases. Then, perform forward propagation, using the given input, weights, and biases, calculate the linear combination value of the input and weights for each layer, apply the activation function to the linear combination value, then calculate the loss function, which includes the actual label and the predicted label in its expression, representing the difference between the output value and the target value. Finally, backpropagate the gradient to the parameters of the neural network to obtain the trained target model.

[0066] Optionally, the above method further includes: displaying the original load spectrum data and classification results on the interactive interface; receiving target feedback information corresponding to the classification results, wherein the target feedback information is used to modify the classification results; and adjusting the model parameters of the target model based on the target feedback information.

[0067] The interactive interface serves as a channel for information exchange between humans and computers. Users input information and perform operations through the interactive interface, while the computer provides information to users for reading, analysis, and judgment. The target feedback information can be the feedback information output by the self-learning network model corresponding to the classification result. The model parameters can be the parameters in the model that need to be adjusted when the target feedback information is incorrect.

[0068] In one alternative embodiment, various interactive interfaces such as graphical user interface, direct operation user interface, multimedia user interface, and multi-channel user interface can be used to display the original load spectrum data and classification results. The target feedback information corresponding to the classification results can be received through a data receiving device, and the model parameters of the target model can be adjusted based on the target feedback information through a parameter adjustment device.

[0069] Understandably, if false alarms are found in the target feedback information after receiving it, the false alarm data can be reloaded into the model for training. The model parameters related to the false alarm data can be adjusted to correct the results, thereby improving the robustness and accuracy of the system.

[0070] Optionally, the original load spectrum data is classified to obtain classification results, including: filtering the original load spectrum data using the rainflow counting method to obtain first load spectrum data, wherein the first load spectrum data is the same data that appears more than a preset number of times in the original load spectrum data; converting the first load spectrum data using the equal damage conversion method to obtain second load spectrum data, wherein the data volume of the second load spectrum data is less than the data volume of the first load spectrum data; and classifying the second load spectrum data to obtain classification results.

[0071] The main function of the rainflow counting method is to simplify the measured load history into several load cycles. The preset number of cycles can be pre-set and can represent the minimum number of times a certain data point occurs with a high frequency. The main function of the equal damage conversion method is to use the linear fatigue cumulative damage theory to integrate discrete load data into pre-defined torque levels while ensuring equal damage. The second load spectrum data can be understood as the strengthened first load spectrum data. The main purpose of processing the load spectrum data using the rainflow counting method and the equal damage conversion method is to generate a strengthened bench test load spectrum.

[0072] Specifically, the counting rules for the rainflow counting method are as follows: rainflows sequentially flow down the slope from the inside of the peak position of the load time history; the rainflow starts flowing from a certain peak point and stops flowing when it encounters a peak larger than its initial peak; the rainflow must stop flowing when it encounters rainflow flowing down from above; all full cycles are extracted, and the amplitude of each cycle is recorded; the remaining divergent-convergent load time history after the first stage of counting is equivalent to a convergent-divergent load time history, and the second stage of rainflow counting is performed. The total number of counting cycles is equal to the sum of the counting cycles in the two counting stages.

[0073] In one alternative embodiment, the second load spectrum data can be classified based on road condition information to obtain a classification result.

[0074] Figure 5 This is a flowchart of an optional method for predicting the lifespan of vehicle transmission components according to an embodiment of the present invention. The specific process is as follows: Load spectrum acquisition, i.e., collecting load spectrum data of user driving habits under multiple road conditions, not limited to urban areas, suburbs, highways, and off-road conditions; Data annotation and algorithm model training, performing load spectrum learning to distinguish what kind of road conditions the user is in within a short period of time; Extracting whole vehicle monitoring data, importing it into the model to obtain output, real-time monitoring of torque and speed data of the drive axle, and putting the measured data into the neural network model to obtain the sample classification and feeding it back to the controller; Rainflow counting and damage conversion to generate bench load spectrum; Bench verification at different temperatures to obtain the total number of tests (lifespan) at different temperatures; Actual working condition verification; Determining whether there are false alarms; If there are false alarms, performing secondary training on the erroneous samples.

[0075] Example 2

[0076] According to another aspect of the present invention, a vehicle transmission component life prediction device is also provided. This device can execute the vehicle transmission component life prediction method in Embodiment 1 above. The specific implementation scheme and application scenario in this embodiment are the same as those in Embodiment 1 above, and will not be repeated here.

[0077] Figure 6 This is a schematic diagram of a vehicle transmission component life prediction device according to an embodiment of the present invention, as shown below. Figure 6 As shown, the device includes: an acquisition module 602, used to acquire raw load spectrum data of transmission components in a vehicle, wherein the raw load spectrum data represents the load spectrum data of the acquired transmission components within a preset time period; a classification module 604, used to classify the raw load spectrum data to obtain a classification result, wherein the classification result represents at least one road condition of the road on which the vehicle travels within the preset time period; and a prediction module 606, used to predict the lifespan of the transmission components based on the classification result and a preset correspondence to obtain the remaining lifespan of the transmission components, wherein the preset correspondence records the lifespan of the transmission components in the temperature range corresponding to at least one road condition.

[0078] The classification module 604 includes: a first classification unit, used to classify the original load spectrum data using the target model to obtain a classification result; a data filtering unit, used to filter the original load spectrum data using the rainflow counting method to obtain first load spectrum data, wherein the first load spectrum data is the same data that appears more than a preset number of times in the original load spectrum data; a data transformation unit, used to transform the first load spectrum data using the equal damage transformation method to obtain second load spectrum data, wherein the data volume of the second load spectrum data is less than the data volume of the first load spectrum data; and a second classification unit, used to classify the second load spectrum data to obtain a classification result.

[0079] The prediction module 606 includes: a damage rate determination unit, used to determine the target damage rate of the transmission component based on the classification results and a preset correspondence, wherein the target damage rate is used to represent the wear state of the transmission component; and a life prediction unit, used to predict the life of the transmission component based on a first preset value and the target damage rate, to obtain the remaining life.

[0080] The damage rate determination unit includes: a first determination subunit, used to determine the number of times the transmission component is used and the target temperature in at least one road condition based on the classification results; a second determination subunit, used to determine the target life of the transmission component at the target temperature corresponding to at least one road condition based on a preset correspondence; and a third determination subunit, used to determine the target damage rate based on the number of times the transmission component is used and the target life in at least one road condition.

[0081] The aforementioned device further includes: an information acquisition module for acquiring sample load spectrum data of the vehicle under different road conditions and corresponding annotation information, wherein the sample load spectrum data represents the load spectrum data of the transmission components in the vehicle under different road conditions, and the annotation information represents the road conditions of the vehicle when the sample load spectrum data was acquired; a model training module for training an initial model using the sample load spectrum data and the corresponding annotation information to obtain a target model; a result display module for displaying the original load spectrum data and classification results on an interactive interface; an information receiving module for receiving target feedback information corresponding to the classification results, wherein the target feedback information is used to modify the classification results; and a parameter adjustment module for adjusting the model parameters of the target model based on the target feedback information.

[0082] Example 3

[0083] According to another aspect of the present invention, a vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the vehicle transmission component life prediction method described in any of the preceding embodiments.

[0084] Example 4

[0085] According to another aspect of the present invention, a non-volatile storage medium is also provided, characterized in that the non-volatile storage medium includes a stored program, wherein the program, when running, controls the execution of the vehicle transmission component life prediction method described in any one of the above embodiments in the processor of the device.

[0086] Example 5

[0087] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the above-described method for predicting the lifespan of vehicle transmission components.

[0088] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0089] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0091] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0093] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0094] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method of predicting the life of a vehicle driveline component, characterised by, The method comprises: acquiring original load spectrum data of a transmission member in a vehicle, wherein the original load spectrum data is used to represent collected load spectrum data of the transmission member in a preset time period; classifying the original load spectrum data to obtain a classification result, wherein the classification result is used to represent at least one road condition of a road on which the vehicle travels in the preset time period; predicting a life of the transmission member based on the classification result and a preset correspondence relationship to obtain a remaining life of the transmission member, wherein the preset correspondence relationship is used to record the life of the transmission member in a temperature interval corresponding to the at least one road condition.

2. The method of claim 1, wherein The method further comprises: determining a target damage rate of the transmission member based on the classification result and the preset correspondence relationship, wherein the target damage rate is used to represent a wear state of the transmission member; predicting the life of the transmission member based on a first preset value and the target damage rate to obtain the remaining life.

3. The method of claim 2, wherein The method further comprises: determining a use frequency and a target temperature of the transmission member in the at least one road condition based on the classification result; determining a target life of the transmission member at the target temperature corresponding to the at least one road condition based on the preset correspondence relationship; determining the target damage rate based on the use frequency and the target life of the transmission member in the at least one road condition.

4. The method of claim 1, wherein The method further comprises: classifying the original load spectrum data by using a target model to obtain the classification result.

5. The method of claim 4, wherein The method further comprises: collecting sample load spectrum data of the transmission member in the vehicle under different road conditions and labeled information corresponding to the sample load spectrum data, wherein the sample load spectrum data is used to represent load spectrum data of the transmission member in the vehicle under different road conditions, and the labeled information is used to represent a road condition of the vehicle when the sample load spectrum data is collected; training an initial model by using the sample load spectrum data and the labeled information corresponding to the sample load spectrum data to obtain the target model.

6. The method of claim 4, wherein The method further comprises: displaying the original load spectrum data and the classification result on an interactive interface; receiving target feedback information corresponding to the classification result, wherein the target feedback information is used to modify the classification result; adjusting model parameters of the target model based on the target feedback information.

7. The method of claim 1, wherein The method further comprises: screening the original load spectrum data by using a rainflow counting method to obtain first load spectrum data, wherein the first load spectrum data is the same data in the original load spectrum data that appears more than a preset number of times; transforming the first load spectrum data by using an equal-damage transformation method to obtain second load spectrum data, wherein a data amount of the second load spectrum data is less than a data amount of the first load spectrum data; classifying the second load spectrum data to obtain the classification result.

8. A device for predicting the life of a vehicle transmission member, characterized by The method further comprises: An acquisition module is configured to acquire original load spectrum data of a transmission component in a vehicle, wherein the original load spectrum data is used to represent collected load spectrum data of the transmission component in a preset time period; A classification module is configured to classify the original load spectrum data to obtain a classification result, wherein the classification result is used to represent at least one road condition of a road on which the vehicle travels in the preset time period; A prediction module is configured to predict a remaining life of the transmission component based on the classification result and a preset corresponding relationship, wherein the preset corresponding relationship is used to record a life of the transmission component in a temperature interval corresponding to the at least one road condition.

9. A non-volatile storage medium, comprising: The non-volatile storage medium includes a stored program, wherein when the program is running, the processor of the device is controlled to execute the vehicle transmission component life prediction method in any one of claims 1 to 7.

10. A vehicle characterized by comprising: Comprise: One or more processors; Storage device, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors execute the vehicle transmission component life prediction method in any one of claims 1 to 7.

Images