Commercial vehicle lubricating oil replacement period prediction method, system, equipment and medium
The prediction model of lubricant quality parameters is established through deep learning algorithms, which solves the problems of high manufacturing cost and inaccurate readings of lubricant sensors in the prior art, and realizes efficient prediction of lubricant replacement cycles, reducing resource consumption.
Patent Information
- Application Number
- CN202510210194.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-25
- Publication Date
- 2025-06-27
AI Technical Summary
In the prior art, the solution by installing a lubricant sensor has the risk of high manufacturing costs and inaccurate readings, while the solution by passing the lubricant circuit test requires a lot of time and resources.
A commercial vehicle lubricant replacement cycle prediction method is adopted. By obtaining engine type and vehicle working condition information, a deep learning algorithm is used to establish a prediction model of lubricant quality parameters, and the vehicle's mileage and working condition information are obtained in real time, thereby predicting the lubricant replacement cycle.
No need to install lubricant sensors, which reduces manufacturing costs and avoids the risk of inaccurate readings. At the same time, data simulation is implemented through algorithms, reducing the time and resources required to pass road tests.
Smart Images
Figure CN120218302A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of cycle prediction, and particularly to a method, system, device and medium for predicting the replacement cycle of lubricating oil for commercial vehicles. Background Art
[0002] Engine lubricating oil (abbreviation: engine oil) plays important roles such as reducing friction between engine components, preventing wear, taking away heat and cleaning the engine, and is a prerequisite for the normal operation of the vehicle. Heavy trucks often operate continuously at high speeds under heavy loads for a long time. Therefore, the lubricating oil will inevitably oxidize and its performance will degrade, and the protection effect on the engine will gradually decline, so the lubricating oil needs to be replaced in time.
[0003] Currently, vehicle manufacturers attach increasing importance to the intelligent maintenance of vehicles. As a part of intelligent maintenance, lubricating oil maintenance has also been widely studied. Since there are many factors affecting the decay of lubricating oil and its decay is non-linear, current research is mainly in the exploratory stage. The mainstream research directions for engine oil life mainly fall into two categories: one is to install a lubricating oil sensor and judge whether the oil needs to be changed by detecting key lubricating oil quality parameters (engine oil viscosity, dielectric constant); the other is to conduct a lubricating oil road test, take samples regularly, and summarize the relationship between engine oil decay and driving mileage.
[0004] However, the above scheme of installing a lubricating oil sensor may increase the manufacturing cost of the vehicle. For economy vehicles, this may not be a feasible option. In addition, the long-term stability and accuracy of the sensor may be a problem. The sensor may be affected by factors such as impurities in the lubricating oil and temperature changes, resulting in inaccurate readings. The above scheme of conducting a lubricating oil road test requires a large amount of time and resources, including vehicles, fuel, manpower, etc. This makes the research cycle long and the cost high. Summary of the Invention
[0005] In view of the above deficiencies of the prior art, this application provides a method, system, device and medium for predicting the replacement cycle of lubricating oil for commercial vehicles to solve the problems that the existing scheme of installing a lubricating oil sensor has a manufacturing cost and a risk of inaccurate subsequent readings, and the scheme of conducting a lubricating oil road test requires a large amount of time and resources.
[0006] In a first aspect, this application provides a method for predicting the replacement cycle of lubricating oil for commercial vehicles, the method comprising: Obtain the road test data of vehicle operating conditions corresponding to each engine type and several types of lubricant oil quality parameters within a preset time period, and store them in a preset sample database; wherein, several types of lubricant oil quality parameters at least include: kinematic viscosity at 100°C, total acid number, total base number, oxidation value, soot content, iron content; use the data in the preset sample database to train a preset deep learning algorithm to obtain a trained preset deep learning algorithm for each engine type corresponding to various lubricant oil quality parameters; obtain the driving mileage of each associated vehicle in real time, and determine whether prediction is required according to the driving mileage; obtain the vehicle operating conditions information uploaded by the vehicle to be predicted, and determine the corresponding several trained preset deep learning algorithms according to the engine type of the vehicle to be predicted, and then obtain the predicted lubricant oil data of various lubricant oil quality parameters; determine the predicted lubricant oil life according to the preset corresponding relationship between the lubricant oil data corresponding to various lubricant oil quality parameters and the lubricant oil life.
[0007] The commercial vehicle lubricant oil replacement cycle prediction method provided by the embodiments of this application collects engine type, vehicle operating conditions information and lubricant oil quality parameters (road test data of several types of lubricant oil quality parameters), and uses a preset deep learning algorithm (for example, the long short-term memory network algorithm of deep learning) to establish a prediction model of lubricant oil quality parameters. Then, input the real-time vehicle operating conditions information of the vehicle into this model, and the predicted values of lubricant oil quality parameters can be obtained. Compare them with the preset corresponding relationship between the lubricant oil data and the lubricant oil life, so as to judge whether to replace the lubricant oil and the predicted lubricant oil life. This application does not require the manufacturing cost of the solution of installing a lubricant oil sensor, solves the risks existing in installing a lubricant oil sensor, and in addition, directly realizes data simulation through the algorithm, solving the problem that a large amount of time and resources are required for the lubricant oil road test, regular sampling, and summarizing the relationship between oil decay and driving mileage.
[0008] In an implementation manner of this application, the vehicle operating conditions information at least includes: total mileage after oil change, total fuel consumption, total engine running time, working time at different torques / speeds.
[0009] In an implementation manner of this application, using the data in the preset sample database to train a preset deep learning algorithm to obtain a trained preset deep learning algorithm for each engine type corresponding to various lubricant oil quality parameters specifically includes: Classify the road test data of vehicle operating conditions and several types of lubricant oil quality parameters according to the engine type to obtain the data corresponding to each engine type; Under the data corresponding to the current engine type, train a preset deep learning algorithm according to the vehicle operating conditions information and the road test data of various lubricant oil quality parameters to obtain a trained preset deep learning algorithm for various lubricant oil quality parameters under the current engine type; Among them, one type of lubricating oil quality parameter corresponds to a trained preset deep learning algorithm.
[0010] In an implementation manner of the present application, before obtaining the driving mileage of each associated vehicle in real time, the method further includes: establishing a communication connection with the vehicle's vehicle control unit to complete the association of the vehicle; wherein, the association process includes uploading the vehicle identification number or equipment number file of the vehicle.
[0011] In an implementation manner of the present application, obtaining the driving mileage of each vehicle in real time and determining whether prediction is required according to the driving mileage specifically includes: When the total mileage after the vehicle changes the lubricating oil is less than a preset first number of kilometers, determine that the current vehicle needs to predict the replacement time once every preset first kilometer interval; When the total mileage after the vehicle changes the lubricating oil is greater than or equal to the preset first number of kilometers and less than the preset second number of kilometers, determine that the current vehicle needs to predict the replacement time once every preset second kilometer interval; When the total mileage after the vehicle changes the lubricating oil is greater than or equal to the preset second number of kilometers, determine that the current vehicle needs to predict the replacement time once every preset third kilometer interval; Among them, the preset first kilometer interval > the preset second kilometer interval > the preset third kilometer interval.
[0012] In an implementation manner of the present application, determining the predicted lubricating oil life according to the preset corresponding relationship between the lubricating oil data corresponding to various types of lubricating oil quality parameters and the lubricating oil life specifically includes: According to the preset corresponding relationship between the lubricating oil data corresponding to various types of lubricating oil quality parameters and the lubricating oil life; Determine the lubricating oil life of the lubricating oil data corresponding to various types of lubricating oil quality parameters; Determine that the minimum lubricating oil life corresponding to all types of lubricating oil parameters is the predicted lubricating oil life.
[0013] In an implementation manner of the present application, the method further includes: Log in the user through a preset login interface; When the login is successful, display a preset retrieval interface; Obtain retrieval information through the preset retrieval interface; According to the retrieval information, display the vehicle condition information, predicted lubricating oil data, and predicted lubricating oil life that meet the retrieval information.
[0014] In a second aspect, the present application provides a commercial vehicle lubricating oil replacement cycle prediction system, and the system includes: A database data acquisition module, which is used to acquire the vehicle operating condition information corresponding to each engine type and the road test data of several types of lubricating oil quality parameters within a preset time period, and store them in a preset sample database; wherein, several types of lubricating oil quality parameters at least include: kinematic viscosity at 100°C, total acid value, total base number, oxidation value, soot content, iron content; a prediction model acquisition module, which is used to train a preset deep learning algorithm using the data in the preset sample database to obtain a trained preset deep learning algorithm for each type of lubricating oil quality parameter corresponding to each engine type; a life prediction module, which is used to acquire the driving mileage of each associated vehicle in real time, determine whether prediction is required according to the driving mileage; acquire the vehicle operating condition information uploaded by the vehicle to be predicted, determine the corresponding several trained preset deep learning algorithms according to the engine type of the vehicle to be predicted, and further obtain the predicted lubricating oil data of various types of lubricating oil quality parameters; determine the predicted lubricating oil life according to the preset corresponding relationship between the lubricating oil data corresponding to various types of lubricating oil quality parameters and the lubricating oil life.
[0015] Thirdly, the present application provides a commercial vehicle lubricating oil replacement cycle prediction device, and the device includes: A processor; and a memory, on which executable code is stored, and when the executable code is executed, it causes the processor to execute a commercial vehicle lubricating oil replacement cycle prediction method as described in any one of the above.
[0016] Fourthly, the present application provides a non-volatile computer storage medium, on which computer instructions are stored, and when the computer instructions are executed, they implement a commercial vehicle lubricating oil replacement cycle prediction method as described in any one of the above.
[0017] Those skilled in the art can understand that the present application has at least the following beneficial effects: The present application proposes a commercial vehicle lubricating oil replacement cycle prediction method, system, device and medium. By collecting the engine type, vehicle operating condition information and lubricating oil quality parameters (road test data of several types of lubricating oil quality parameters), a prediction model of lubricating oil quality parameters is established using a preset deep learning algorithm (for example, the long short-term memory network algorithm of deep learning). Then, the real-time vehicle operating condition information of the vehicle is input into this model, and the predicted value of the lubricating oil quality parameters can be obtained. Compare it with the preset corresponding relationship between the lubricating oil life to determine whether to replace the lubricating oil and the predicted lubricating oil life. The present application eliminates the manufacturing cost of the solution of installing a lubricating oil sensor, solves the risks existing in installing a lubricating oil sensor, and in addition, directly realizes data simulation through an algorithm, solving the problem that a large amount of time and resources are required for the lubricating oil road test, regular sampling, and summarizing the relationship between oil decay and driving mileage. Description of the Drawings
[0018] The following describes some embodiments of the present disclosure with reference to the accompanying drawings, in which: Figure 1 is a flowchart of a method for predicting the lubricating oil replacement cycle of a commercial vehicle provided by an embodiment of the present application.
[0019] Figure 2 is a schematic diagram of the internal structure of a system for predicting the lubricating oil replacement cycle of a commercial vehicle provided by an embodiment of the present application.
[0020] Figure 3 is a schematic diagram of the internal structure of a device for predicting the lubricating oil replacement cycle of a commercial vehicle provided by an embodiment of the present application. Detailed implementation manners
[0021] Those skilled in the art should understand that the embodiments described below are only the preferred embodiments of the present disclosure, and do not mean that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are only used to explain the technical principles of the present disclosure, and are not used to limit the protection scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should still fall within the protection scope of the present disclosure.
[0022] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or elements inherent to such process, method, commodity or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.
[0023] The following details the technical solutions proposed by the embodiments of the present application with reference to the accompanying drawings.
[0024] An embodiment provides a method for predicting the lubricating oil replacement cycle of a commercial vehicle. As Figure 1 shown, the method provided by the embodiment of the present application mainly includes the following steps: Step 110: Obtain the vehicle condition information corresponding to each engine type and the road test data of several types of lubricating oil quality parameters within a preset time period, and store them in a preset sample database.
[0025] It should be noted that the vehicle condition information at least includes: the total mileage after oil change, the total fuel consumption, the total engine operation duration, and the working duration at different torques / speeds.
[0026] As an example, when several types of lubricating oil quality parameters are: kinematic viscosity at 100°C, total acid number, total base number, oxidation value, soot content, iron content (6 types). For engine type classification, the model is divided into MC11, MC11(H), MC13, MC13(H) (4 types). The total number of required models is 24 (4 engine models, 6 parameters).
[0027] Step 120: Use the data in the preset sample database to train the preset deep learning algorithm to obtain the trained preset deep learning algorithm for each engine type corresponding to various lubricating oil quality parameters.
[0028] This step can be specifically as follows: Classify the vehicle condition information and the road test data of several types of lubricating oil quality parameters according to the engine type to obtain the data corresponding to each engine type; under the data corresponding to the current engine type, train the preset deep learning algorithm according to the vehicle condition information and the road test data of various lubricating oil quality parameters to obtain the trained preset deep learning algorithm for various lubricating oil quality parameters under the current engine type; among them, one type of lubricating oil quality parameter corresponds to one trained preset deep learning algorithm.
[0029] More specifically, taking the MC13(H) engine as an example, first arrange the vehicle condition information of the vehicle in chronological order, then select one type of lubricating oil quality parameter (for example, select the kinematic viscosity at 100°C), convert the data set into the shape required by the time series model (number of samples, time step, number of features). Assuming the time step is set to 30 days, that is, using 30 days of data, that is, 30 rows and n columns (feature columns), predict the target column (kinematic viscosity at 100°C) on the 31st day and later to obtain the trained preset deep learning algorithm, establish a fitting model, and perform the prediction of the kinematic viscosity at 100°C for the MC13(H) engine.
[0030] Step 130: Real-time obtain the driving mileage of each associated vehicle, determine whether prediction is required according to the driving mileage; obtain the vehicle condition information uploaded by the vehicle that needs to be predicted, and determine the corresponding several trained preset deep learning algorithms according to the engine type of the vehicle that needs to be predicted, so as to obtain the predicted lubricating oil data of various lubricating oil quality parameters.
[0031] In addition, in order to realize the management of the vehicle and the server involved in this method, before the server real-time obtains the driving mileage of each associated vehicle, a communication connection is established between the server and the vehicle's vehicle control unit to complete the association of the vehicle; among them, the association process includes uploading the vehicle's vehicle identification number or device number file to facilitate the distinction of different vehicles.
[0032] In the step, real-time obtain the driving mileage of each vehicle, and determine whether prediction is required according to the driving mileage. Specifically, it can be as follows: When the total mileage of the vehicle after oil change is less than the preset first number of kilometers, determine the time when the current vehicle needs to predict the replacement once every preset first kilometer interval; when the total mileage of the vehicle after oil change is greater than or equal to the preset first number of kilometers and less than the preset second number of kilometers, determine the time when the current vehicle needs to predict the replacement once every preset second kilometer interval; when the total mileage of the vehicle after oil change is greater than or equal to the preset second number of kilometers, determine the time when the current vehicle needs to predict the replacement once every preset third kilometer interval; wherein, the preset first kilometer interval > the preset second kilometer interval > the preset third kilometer interval.
[0033] As an example, the method involved in the present application can calculate the predicted value of the lubricating oil quality parameter (determine the time when the current vehicle needs to predict the replacement once) every 5000 kilometers within a total mileage of 100,000 kilometers, calculate once every 2000 kilometers when the total mileage is 100,000 - 120,000 kilometers, and calculate once every 1000 kilometers when it exceeds 120,000 kilometers.
[0034] Step 140: Determine the predicted lubricating oil life according to the preset corresponding relationship between the lubricating oil data corresponding to various lubricating oil quality parameters and the lubricating oil life.
[0035] It should be noted that there is a preset corresponding relationship between the lubricating oil data corresponding to each type of lubricating oil quality parameter and the lubricating oil life. This corresponding relationship can be obtained by those skilled in the art through experiments.
[0036] This step can be specifically: According to the preset corresponding relationship between the lubricating oil data corresponding to various lubricating oil quality parameters and the lubricating oil life; determine the lubricating oil life of the lubricating oil data corresponding to various lubricating oil quality parameters; determine the minimum lubricating oil life corresponding to all types of lubricating oil parameters as the predicted lubricating oil life.
[0037] In addition, the present application can also provide user login to facilitate viewing data.
[0038] The specific process can be: Perform user login through a preset login interface.
[0039] It should be added that during the user login process, the present application can provide a function for checking the user login account / password and adopt information encryption means to ensure the security of the user account.
[0040] When the login is successful, display a preset retrieval interface; obtain retrieval information through the preset retrieval interface; display the vehicle condition information, predicted lubricating oil data, and predicted lubricating oil life that meet the retrieval information according to the retrieval information.
[0041] It should be noted that the preset retrieval interface can provide single-vehicle retrieval and grouped retrieval. Among them, single-vehicle retrieval queries the lubricating oil quality parameter information of the vehicle by the user inputting the vehicle frame number or equipment number; grouped retrieval requires the user to upload a file containing the vehicle frame number / equipment number, which is convenient for tracking and analyzing the lubricating oil of multiple vehicles. Conditional retrieval includes vehicle configuration, working conditions, lubricating oil information, etc. Vehicle configuration includes engine model, transmission model, rear axle ratio, product line, vehicle model, engine type, etc. Working condition information includes: total mileage, total fuel consumption, engine running time, average fuel consumption, average speed, predicted remaining mileage, predicted total mileage, etc. Lubricating oil information includes: lubricating oil model, kinematic viscosity at 100°C, total acid value, total base number, oxidation value, soot content, iron content, etc. Conditional retrieval is mainly used to query and analyze the health status of lubricating oil under specific conditions.
[0042] In addition, this application Figure 2 provides a commercial vehicle lubricating oil replacement cycle prediction system according to an embodiment of this application. As Figure 2 shown, the system provided by the embodiment of this application mainly includes: A database data acquisition module 210, configured to acquire the vehicle working condition information corresponding to each engine type and the road test data of several types of lubricating oil quality parameters within a preset time period, and store them in a preset sample database; among them, several types of lubricating oil quality parameters at least include: kinematic viscosity at 100°C, total acid value, total base number, oxidation value, soot content, iron content.
[0043] A prediction model acquisition module 220, configured to use the data in the preset sample database to train a preset deep learning algorithm, and obtain a trained preset deep learning algorithm for each type of lubricating oil quality parameter corresponding to each engine type.
[0044] A life prediction module 230, configured to obtain the driving mileage of each associated vehicle in real time, determine whether prediction is required according to the driving mileage; obtain the vehicle working condition information uploaded by the vehicle to be predicted, determine the corresponding several trained preset deep learning algorithms according to the engine type of the vehicle to be predicted, and then obtain the predicted lubricating oil data of various types of lubricating oil quality parameters; determine the predicted lubricating oil life according to the preset corresponding relationship between the lubricating oil data corresponding to various types of lubricating oil quality parameters and the lubricating oil life.
[0045] The above is the method embodiment in this application. Based on the same inventive concept, the embodiment of this application also provides a commercial vehicle lubricating oil replacement cycle prediction device. As Figure 3 shown, the device includes: a processor; and a memory, on which executable code is stored, and when the executable code is executed, the processor is caused to execute a commercial vehicle lubricating oil replacement cycle prediction method as in the above embodiment.
[0046] Specifically, the server obtains the vehicle operating condition information corresponding to each engine type and the road test data of several types of lubricating oil quality parameters within a preset time period, and stores them in a preset sample database; wherein, several types of lubricating oil quality parameters at least include: kinematic viscosity at 100°C, total acid value, total base value, oxidation value, soot content, iron content; use the data in the preset sample database to train a preset deep learning algorithm to obtain a trained preset deep learning algorithm for each type of lubricating oil quality parameter corresponding to each engine type; obtain the driving mileage of each associated vehicle in real time, and determine whether prediction is required according to the driving mileage; obtain the vehicle operating condition information uploaded by the vehicle to be predicted, and determine the corresponding several trained preset deep learning algorithms according to the engine type of the vehicle to be predicted, and then obtain the predicted lubricating oil data of various types of lubricating oil quality parameters; determine the predicted lubricating oil life according to the preset corresponding relationship between the lubricating oil data corresponding to various types of lubricating oil quality parameters and the lubricating oil life.
[0047] In addition, the embodiment of the present application also provides a non-volatile computer storage medium, on which executable instructions are stored, and when the executable instructions are executed, the above-mentioned method for predicting the lubricating oil replacement cycle of a commercial vehicle is implemented.
[0048] So far, the technical solutions of the present disclosure have been described in combination with multiple foregoing embodiments. However, it is easy for those skilled in the art to understand that the protection scope of the present disclosure is not limited to these specific embodiments. Without departing from the technical principle of the present disclosure, those skilled in the art can split and combine the technical solutions in the above-mentioned various embodiments, and can also make equivalent changes or replacements to the relevant technical features. Any changes, equivalent replacements, improvements, etc. made within the technical concept and / or technical principle of the present disclosure will fall within the protection scope of the present disclosure.
Claims
1. A commercial vehicle lubricant replacement cycle prediction method, characterized in that: The method comprises: Obtaining vehicle operating condition information and road test data of several types of lubricant quality parameters corresponding to each engine type within a preset time period, and storing them in a preset sample database; wherein the several types of lubricant quality parameters at least include: 100°C kinematic viscosity, total acid number, total base number, oxidation number, soot content, and iron content; Using the data in the preset sample database to train the preset deep learning algorithm, a trained preset deep learning algorithm corresponding to various lubricant quality parameters for each engine type is obtained; Obtain the mileage of each associated vehicle in real time, and determine whether prediction is needed based on the mileage; obtain the vehicle operating condition information uploaded by the vehicle that needs to be predicted, predict the engine type of the vehicle as needed, determine the corresponding trained preset deep learning algorithms, and then obtain the predicted lubricant data of various lubricant quality parameters; The predicted life of the lubricant is determined based on the preset correspondence between the lubricant data corresponding to various lubricant quality parameters and the lubricant life.
2. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: The vehicle operating condition information includes at least: total mileage after oil change, total fuel consumption, total engine operating time, and operating time at different torques / speeds.
3. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: The preset deep learning algorithm is trained using the data in the preset sample database to obtain the trained preset deep learning algorithm for each type of lubricant quality parameters corresponding to each engine type, including: Classify vehicle operating condition information and road test data of several types of lubricant quality parameters according to engine type to obtain data corresponding to each engine type; Under the data corresponding to the current engine type, according to the vehicle operating condition information and the road test data of various lubricant quality parameters, the preset deep learning algorithm is trained to obtain the trained preset deep learning algorithm of various lubricant quality parameters under the current engine type; Among them, one type of lubricant quality parameter corresponds to a trained preset deep learning algorithm.
4. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: Before obtaining the mileage of each associated vehicle in real time, the method further includes: Establish a communication connection with the vehicle controller to complete the vehicle association; wherein the association process includes uploading the vehicle frame number or device number file.
5. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: Obtain the mileage of each vehicle in real time and determine whether a prediction is needed based on the mileage, including: When the total mileage of the vehicle after the oil change is less than the preset first kilometer, the predicted replacement time of the current vehicle is determined once every preset first kilometer interval; When the total mileage of the vehicle after the oil change is greater than or equal to the preset first kilometer and less than the preset second kilometer, the predicted replacement time of the current vehicle is determined once every preset second kilometer interval; When the total mileage of the vehicle after the oil change is greater than or equal to the preset second kilometer, the predicted replacement time of the current vehicle is determined once every preset third kilometer interval; Among them, the preset first kilometer interval>the preset second kilometer interval>the preset third kilometer interval.
6. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: According to the preset correspondence between the lubricant data corresponding to various lubricant quality parameters and the lubricant life, the predicted lubricant life is determined, including: According to the preset correspondence between the lubricating oil data corresponding to various lubricating oil quality parameters and the lubricating oil life; Determine the lubricant life of the lubricant data corresponding to various lubricant quality parameters; The minimum lubricant life corresponding to all lubricant parameters is determined as the predicted lubricant life.
7. The commercial vehicle lubricant replacement cycle prediction method according to claim 1, characterized in that: The method further comprises: Log in through the preset login interface; When the login is successful, the preset search interface is displayed; Obtain search information through the preset search interface; According to the search information, the vehicle operating condition information, predicted lubricant data and predicted lubricant life that match the search information are displayed.
8. A commercial vehicle lubricant replacement cycle prediction system, characterized in that: The system comprises: A database data acquisition module is used to acquire vehicle operating condition information corresponding to each engine type within a preset time period and road test data of several types of lubricant quality parameters, and store them in a preset sample database; wherein the several types of lubricant quality parameters at least include: 100°C kinematic viscosity, total acid number, total base number, oxidation number, soot content, and iron content; A prediction model acquisition module, used to train a preset deep learning algorithm using data in a preset sample database to obtain a trained preset deep learning algorithm corresponding to various lubricant quality parameters for each engine type; The life prediction module is used to obtain the mileage of each associated vehicle in real time, and determine whether prediction is needed based on the mileage; obtain the vehicle operating condition information uploaded by the vehicle that needs to be predicted, predict the engine type of the vehicle as needed, determine the corresponding trained preset deep learning algorithms, and then obtain the predicted lubricant data of various lubricant quality parameters; determine the predicted life of the lubricant based on the preset correspondence between the lubricant data corresponding to various lubricant quality parameters and the lubricant life.
9. A commercial vehicle lubricant replacement cycle prediction device, characterized in that: The device comprises: processor; and a memory having executable codes stored thereon, which, when executed, causes the processor to execute a commercial vehicle lubricant replacement cycle prediction method as described in any one of claims 1 to 7.
10. A non-volatile computer storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, a commercial vehicle lubricant replacement cycle prediction method as described in any one of claims 1-7 is implemented.