Processing method for engine oil dilution, vehicle control device, vehicle and electronic equipment

Abstract

The invention provides an engine oil dilution treatment method, a vehicle control device, a vehicle and electronic equipment, and belongs to the technical field of vehicle control. The method comprises the steps that real-time state parameters related to a vehicle are obtained, and the engine oil dilution change rate is predicted based on the real-time state parameters related to the vehicle; performing integral operation on the engine oil dilution change rate according to the time sequence to obtain a real-time engine oil dilution rate; acquiring real-time path planning data based on a navigation system, and inputting the real-time path planning data into the LSTM neural network to obtain a predicted single travel mileage; and based on the real-time engine oil dilution rate, the predicted single stroke mileage, the current vehicle speed and the current battery remaining capacity, a strategy for maintaining engine oil dilution is determined. According to the method, the contradiction between engine oil protection and energy consumption is balanced by comprehensively considering the real-time engine oil dilution rate, the predicted single stroke mileage, the current vehicle speed and the current battery remaining capacity, and the optimal strategy for maintaining engine oil dilution is obtained.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method for processing oil dilution, a vehicle control device, a vehicle, and an electronic device. Background Art

[0002] Oil dilution refers to the phenomenon in which, during cold operation of a direct-injection engine, the cylinder wall temperature is low, resulting in poor fuel atomization and wetted walls. During the compression stroke, the fuel adhering to the cylinder wall enters the crankcase through the piston oil return hole and flows into the oil pan, mixing with the engine oil. When the engine oil reaches the fuel volatilization temperature, the mixed fuel evaporates and enters the engine through the crankcase ventilation system, continuing to burn.

[0003] Oil dilution has long been a persistent problem for major automakers, and it's particularly acute in hybrid vehicles. This problem is exacerbated by the frequent starts and stops of the electric motors that occur in hybrid vehicles, depending on driving scenarios, user journeys, engine operating conditions, and battery power consumption. These frequent starts and stops further exacerbate the oil dilution problem.

[0004] Therefore, providing a method for diluting engine oil suitable for hybrid vehicles has become a technical problem that technicians in this field urgently need to solve. Summary of the Invention

[0005] In view of the above problems, the present application provides an oil dilution treatment method, a vehicle control device, a vehicle, and an electronic device that overcome the above problems or at least partially solve the above problems. The technical solutions are as follows: A method for treating engine oil dilution, applied to a vehicle control device, comprising: Acquiring real-time state parameters related to the vehicle, and predicting a rate of change of oil dilution based on the real-time state parameters related to the vehicle; Performing an integration operation on the oil dilution change rate according to a time series to obtain a real-time oil dilution rate; Obtain real-time path planning data based on the navigation system and input it into a pre-trained long short-term memory (LSTM) neural network to predict the mileage of a single trip. A strategy for maintaining oil dilution is determined based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery power.

[0006] By means of the above technical solution, the present application provides a method for processing oil dilution, which embeds the real-time path planning data (such as remaining mileage and slope) based on the navigation system into the start-stop engine maintenance oil dilution strategy, thereby realizing the coordinated optimization of "road-oil-engine". Through a comprehensive analysis of the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed and the current remaining battery power, while ensuring the optimal battery life and vehicle energy consumption, the risk of oil dilution is reduced, the engine is protected, and the optimal maintenance oil dilution strategy is obtained, which balances the contradiction between oil protection and energy consumption and achieves the effect of improving both oil life and power utilization.

[0007] Optionally, the predicting of the oil dilution change rate based on the vehicle-related real-time state parameters includes: inputting the vehicle-related real-time state parameters into a pre-built gradient boosting tree (GBDT) prediction model, and outputting the oil dilution change rate, wherein the vehicle-related real-time state parameters include at least one of the following: vehicle engine speed, vehicle torque, vehicle water temperature, and vehicle oil temperature.

[0008] Compared with the existing technology in which oil dilution rate prediction mostly relies on single-dimensional data such as engine water temperature, this application fully considers the relationship between key parameters such as engine speed, vehicle torque, vehicle water temperature and vehicle oil temperature, and conducts a comprehensive analysis, thereby more accurately predicting the oil dilution change rate and improving the prediction accuracy.

[0009] Optionally, before obtaining the real-time route planning data based on the navigation system and inputting it into a pre-trained long short-term memory (LSTM) neural network to obtain the predicted single trip mileage, the method further includes: Acquiring historical driving data of the vehicle, wherein the historical driving data of the vehicle includes at least one of the following: average daily driving distance, high-frequency destinations, and driving style; Building a user's usual route feature library based on the historical driving data of the vehicle; The LSTM neural network is trained using the user's usual route feature library.

[0010] In this application, an LSTM neural network is obtained by learning and training the user's usual route feature library. The LSTM neural network can output prediction results with a confidence level ≥ 85%, which can provide accurate prediction of single-trip mileage information for subsequent determination of maintenance oil dilution strategies.

[0011] Optionally, determining a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge includes: Initiating engine maintenance oil dilution when the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current battery remaining power meet a first preset condition; When the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet a second preset condition, the engine is shut down and the oil dilution maintenance is stopped.

[0012] Optionally, the first preset condition includes: the real-time dilution rate > a first preset value; the predicted single trip mileage > a maintenance mileage value; the current vehicle speed ≥ a first preset vehicle speed; the current remaining battery power < a first preset remaining power; The second preset condition includes at least one of the following: the real-time dilution rate < the second preset value; the current vehicle speed < the second preset vehicle speed; the current remaining battery power > the second preset remaining power; Among them, the second preset value is less than the first preset value, the second preset vehicle speed is less than the first preset vehicle speed, and the second preset remaining power is greater than the first preset remaining power.

[0013] In this embodiment, a dual-condition collaborative trigger mechanism is adopted to determine the strategy for maintaining oil dilution and find a balance point, which can effectively reduce oil dilution and protect the engine, while optimizing energy consumption and improving the overall energy efficiency of the vehicle.

[0014] Optionally, before determining the strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge, the method further includes: Obtaining different driving scenarios and driving conditions based on the real-time path planning data and historical driving data of the navigation system; According to the different driving scenarios and driving conditions, the first preset value, the first preset remaining power, the second preset value and the second preset remaining power are adjusted.

[0015] In this application, a fixed strategic threshold for determining maintenance oil dilution is no longer used. Instead, the strategic threshold for determining maintenance oil dilution is dynamically adjusted based on different driving scenarios and driving conditions according to the real-time path planning data and historical driving data of the navigation system. This can deal with the oil dilution problem more flexibly and effectively, and improve the adaptability and reliability of the system.

[0016] Optionally, the maintenance mileage value is obtained by querying an oil dilution maintenance mileage data table based on the current ambient temperature and the current water temperature; Before determining the strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge, the method further includes: The oil dilution maintenance mileage data table is constructed, wherein the oil dilution maintenance mileage data table includes: maintenance mileage values ​​corresponding to different ambient temperatures and water temperatures.

[0017] In this application, the corresponding maintenance mileage value is dynamically obtained based on the current starting water temperature, ambient temperature and other information, so as to more accurately determine when measures need to be taken to maintain the oil dilution state and ensure that the engine is always in a good working environment.

[0018] A vehicle control device, applied to a vehicle, comprising: An oil dilution rate prediction module is configured to obtain real-time vehicle-related state parameters, predict an oil dilution change rate based on the real-time vehicle-related state parameters, and integrate the oil dilution change rate over a time series to obtain a real-time oil dilution rate. The single trip prediction module is used to obtain real-time path planning data based on the navigation system and input it into the pre-trained long short-term memory network (LSTM) neural network to obtain the predicted single trip mileage; The control module is configured to determine a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge.

[0019] A vehicle comprises at least one processor, wherein the at least one processor implements the steps of the oil dilution processing method as described above when executed.

[0020] An electronic device is characterized in that the electronic device includes a processor and a memory, the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the oil dilution processing method described above are implemented.

[0021] By means of the above technical solution, the present application provides a vehicle control device, a vehicle, and an electronic device, which embeds the real-time path planning data (such as remaining mileage and slope) based on the navigation system into the start-stop engine maintenance oil dilution strategy, thereby realizing the coordinated optimization of "road-oil-engine". Through a comprehensive analysis of the real-time oil dilution rate, the predicted single-trip mileage, the current vehicle speed, and the current remaining battery power, while ensuring the optimal battery life and vehicle energy consumption, the risk of oil dilution is reduced, the engine is protected, and the optimal maintenance oil dilution strategy is obtained, thereby balancing the contradiction between oil protection and energy consumption, and achieving the effect of improving both oil life and power utilization.

[0022] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: FIG1 shows a flow chart of a method for processing engine oil dilution provided in an embodiment of the present application; FIG2 shows a schematic structural diagram of a vehicle control device provided in an embodiment of the present application; FIG3 shows a schematic structural diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following describes exemplary embodiments of the present application in more detail with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0025] With the continuous development of hybrid vehicles, more and more users are choosing hybrid vehicles for travel. Due to various driving scenarios, such as long-distance driving, short-distance urban driving, and mountain driving, as well as various factors such as different user journeys, engine operating conditions, and battery energy consumption, hybrid vehicles may frequently start and stop the electric motor. Under these frequent start-stop conditions, the oil dilution problem is even more serious.

[0026] At present, the following problems exist in related technologies: (1) Limited prediction accuracy: Most existing oil dilution rate prediction models rely only on single-dimensional data such as engine water temperature and operating conditions, and do not fully consider the relationship between key parameters such as torque and oil temperature for comprehensive analysis. Therefore, it is impossible to accurately predict the oil dilution rate, resulting in low prediction accuracy. (2) Lack of dynamic control strategy: Traditional methods do not combine vehicle driving scenarios, such as user route mileage, navigation data and other information. Under the condition of frequent start-stop of hybrid vehicles, the oil dilution problem is more serious because the control strategy cannot be adjusted according to the actual driving conditions. (3) Fixed dilution rate threshold: The dilution rate threshold currently used is a fixed value and cannot be adjusted according to the differences in different driving scenarios, such as long-distance driving, short-distance urban driving, mountain driving, etc., and cannot meet diverse needs.

[0027] To this end, an embodiment of the present application provides a method for diluting engine oil. Figure 1 A schematic flow chart of the oil dilution treatment method is shown in FIG1 . As shown in FIG1 , the method can be applied to a vehicle controller and includes the following steps ( S101 - S104 ): S101, obtaining vehicle-related real-time state parameters, and predicting an oil dilution change rate based on the vehicle-related real-time state parameters; In this embodiment, real-time vehicle status parameters related to oil dilution are collected. As an optional implementation in this embodiment, the vehicle-related real-time status parameters include at least one of the following: vehicle engine speed, vehicle torque, vehicle water temperature, and vehicle oil temperature. Optionally, the vehicle controller can obtain these real-time vehicle status parameters from various onboard sensors. The rate of change of vehicle torque over time facilitates identifying the risk of wall wetting caused by a sudden increase in fuel injection during rapid acceleration, while the rate of change of vehicle oil temperature facilitates quantifying the effect of rising oil temperature on fuel volatilization.

[0028] In this embodiment, a Gradient Boosting Decision Tree (GBDT) prediction model can be pre-built. Specifically, a quantitative relationship between fuel crossover into the crankcase under different operating conditions can be calibrated through extensive bench testing. This relationship is then used as a training model, and the trained GBDT prediction model is finally deployed to the vehicle controller. As an optional implementation in this embodiment, the oil dilution rate of change is predicted based on real-time vehicle-related state parameters. This includes inputting the real-time vehicle-related state parameters into the GBDT prediction model and outputting the oil dilution rate of change. In this embodiment, the GBDT prediction model is effectively used to predict the oil dilution rate, providing data support for oil dilution prevention and protection measures for vehicles.

[0029] Those skilled in the art will appreciate that the present embodiment describes step S101 using the GBDT prediction model to predict the oil dilution change rate as an example. This is merely an illustrative example and does not limit the scope of protection of the claims corresponding to this solution. This application does not limit other methods for predicting the oil dilution change rate.

[0030] Compared with traditional methods that only rely on single parameters such as engine water temperature or operating time, in this embodiment, multiple real-time vehicle status parameters related to oil dilution are integrated and input into the GBDT prediction model, fully considering the relationship between key parameters such as engine speed, vehicle torque, vehicle water temperature and vehicle oil temperature, and performing a comprehensive analysis. This can more accurately predict the oil dilution change rate and improve the prediction accuracy.

[0031] In an application example, compared with the traditional single water temperature model, the prediction accuracy of the GBDT prediction model was improved by 32%, greatly improving the prediction accuracy of the oil dilution rate.

[0032] S102, integrating the oil dilution change rate according to the time series to obtain a real-time oil dilution rate; In an application example, suppose r( ) represents the oil dilution change rate at time t (unit: % / min).

[0033] The time series-based integral operation is calculated using the following formula:

[0034] The real-time oil dilution rate D(t) is the integral of r(t) over time.

[0035] After discretization (for example, sampling once per minute), it is calculated using the following formula:

[0036] Where Δt is the sampling interval and t0 is the initial time (such as the engine start time).

[0037] In one application scenario, hybrid vehicles frequently cold-start during short winter trips, which can easily lead to fuel mixing with the engine oil. The engine control unit (ECU) records the oil dilution rate r(t) output by the GBDT prediction model every minute. For example, r(t) = [0.5%, 0.4%, 0.3%, 0.2%, 0.1%, 0%, 0%] The dilution rate is high during the initial cold start and gradually decreases to a stable level as the engine warms up.

[0038] Assume that the sampling interval Δt = 1 minute and the initial dilution rate =0%. Using the above formula for integral calculation, the cumulative dilution rate at the 5th minute is: D( )=(0.5+0.4+0.3+0.2+0.1)×1=1.5%.

[0039] This integration calculation yields the real-time oil dilution rate at each moment, comprehensively reflecting the cumulative change in oil dilution over time. This real-time oil dilution rate subsequently serves as a basis for determining oil dilution maintenance strategies, enabling dynamic engine start-stop control strategies to be implemented based on the real-time oil dilution rate.

[0040] S103, obtaining real-time path planning data based on the navigation system, and inputting it into a pre-trained long short-term memory (LSTM) neural network to obtain a predicted single trip mileage; In this embodiment, before obtaining real-time path planning data based on the navigation system and inputting it into a pre-trained long short-term memory network (LSTM) neural network to obtain a predicted single trip mileage, the method provided in the embodiment of the present application further includes: obtaining historical driving data of the vehicle, wherein the historical driving data of the vehicle includes at least one of the following: average daily driving distance, high-frequency destinations, and driving style (frequency of sudden acceleration / deceleration), which can reflect the user's driving habits and daily travel patterns; constructing a user's usual route feature library based on the vehicle's historical driving data, and using the user's usual route feature library to train a long short-term memory network (LSTM) neural network.

[0041] In this embodiment, the navigation system can acquire a variety of real-time route planning data, including at least one of the following: the vehicle's remaining range, road slope, and congestion index. This real-time route planning data is input into a pre-trained LSTM neural network to obtain a predicted single-trip mileage. LSTM neural networks are capable of processing sequential data and memorizing long-term information, making them ideal for analyzing and predicting user mileage. By learning and analyzing historical driving data and real-time route planning data from the navigation system, the LSTM neural network can output predictions with a confidence level of ≥85%, providing accurate trip information for subsequent determination of maintenance oil dilution strategies.

[0042] For example, on a certain day, the navigation shows that the remaining mileage is 60 kilometers (including congested roads), and the LSTM neural network predicts that the journey will be 55 kilometers (with a confidence level of 90%). The vehicle controller can use this information to determine the maintenance oil dilution strategy.

[0043] S104 : Determine a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery power.

[0044] In hybrid vehicles, the contradiction between oil dilution and energy consumption optimization under start-stop conditions lies in: Oil dilution problem: When the engine is started and stopped frequently, the cold engine runs for a long time, and the fuel atomization is poor, which can easily cause oil dilution and affect the engine life and performance.

[0045] Energy consumption optimization needs: In order to reduce fuel consumption and improve electricity utilization, it is necessary to minimize unnecessary engine starts and increase pure electric driving mileage.

[0046] In this embodiment, a hybrid-powered vehicle control strategy is employed to address the conflict between start-stop engine maintenance oil dilution and energy efficiency optimization. As an optional implementation in this embodiment, a maintenance oil dilution strategy is determined based on the real-time oil dilution rate, predicted single-trip mileage, current vehicle speed, and current battery remaining charge, including: (1) When the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery power meet a first preset condition, the engine is started to maintain oil dilution; (2) When the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet the second preset condition, the engine is shut down and the oil dilution maintenance is stopped.

[0047] In this embodiment, a dual-condition collaborative trigger mechanism is adopted to determine the strategy for maintaining oil dilution and find a balance point, which can effectively reduce oil dilution and protect the engine, while optimizing energy consumption and improving the overall energy efficiency of the vehicle.

[0048] In case (1), when the real-time oil dilution rate, predicted single trip mileage, current vehicle speed and current remaining battery power meet the first preset condition, it indicates that the oil dilution may be aggravated and the oil dilution needs to be maintained. If the vehicle driving conditions permit, start the engine in time and maintain the oil dilution state through normal operation of the engine to avoid damage to the engine caused by excessive oil dilution.

[0049] In the second case, when the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet the second preset condition, it means that the oil dilution is in good condition and maintenance is temporarily unnecessary. When the oil dilution is in good condition, the vehicle driving state does not require the engine to work, or the battery power is sufficient, it is reasonable to shut down the engine to optimize the vehicle's energy consumption and reduce unnecessary fuel consumption.

[0050] In this embodiment, real-time route planning data (such as remaining mileage and slope) is embedded in the start-stop engine maintenance oil dilution strategy, achieving coordinated optimization of "route, oil, and engine." By comprehensively analyzing the real-time oil dilution rate, predicted single-trip mileage, current vehicle speed, and the current battery remaining charge, the optimal oil dilution maintenance strategy is developed, minimizing the risk of oil dilution and protecting the engine while ensuring optimal battery life and vehicle energy consumption. This balances oil conservation with energy consumption, ultimately improving both oil life and energy efficiency.

[0051] As an optional implementation in the embodiment of the present application, the first preset condition includes: real-time dilution rate > first preset value; predicted single trip mileage > maintenance mileage value; current vehicle speed ≥ first preset speed; current battery remaining power < first preset remaining power; the second preset condition includes at least one of the following: real-time dilution rate < second preset value; current vehicle speed < second preset speed; current battery remaining power > second preset remaining power; wherein, the second preset value < first preset value, the second preset speed < first preset speed, and the second preset remaining power > first preset remaining power.

[0052] In one application example, the first preset value can be set to 10%, the second preset value can be set to 5%, the maintenance mileage value can be set to 30 kilometers, the first preset vehicle speed can be set to 15 km / h (to ensure efficient engine operation), the second preset vehicle speed can be set to 10 km / h (to prioritize electric propulsion at low speeds), the first preset remaining battery charge can be set to 60% (requiring engine start charging), and the second preset remaining battery charge can be set to 80%. If the real-time dilution rate is greater than 10%, the predicted single-trip range is greater than 30 kilometers, the current vehicle speed is ≥15 km / h, and the current remaining battery charge is less than 60% (battery charge is sufficient), the system will force the engine to start to maintain oil dilution and prevent damage to the engine caused by excessive oil dilution. If any of the three conditions, the real-time dilution rate is less than 5%, the current vehicle speed is less than 10 km / h, or the current remaining battery charge is less than 80%, the system will allow the engine to shut down to effectively control engine operation and save energy.

[0053] In one application example, when a vehicle is traveling at high speed, the real-time dilution rate rises to 12%, the predicted remaining mileage is 40 kilometers, and the SOC is 50%. At this time, the system forcibly starts the engine to maintain oil dilution and continues to run until the oil dilution rate drops below 5% or reaches the destination.

[0054] In this embodiment, a further optimization is that the parameter thresholds in the first and second preset conditions can be dynamically adjusted based on actual driving scenarios and conditions to timely adjust the oil dilution maintenance strategy. As an optional implementation of this embodiment, before determining the oil dilution maintenance strategy based on the real-time oil dilution rate, predicted single trip mileage, current vehicle speed, and current battery remaining charge, the oil dilution processing method provided in this embodiment also includes: a1. Obtain different driving scenarios and conditions based on the navigation system's real-time path planning data and historical driving data; a2. Adjust the first preset value, the first preset remaining power, the second preset value, and the second preset remaining power according to different driving scenarios and driving conditions.

[0055] In this embodiment, instead of using a fixed threshold for determining the strategy for maintaining oil dilution, the first preset value, the first preset remaining battery charge, the second preset value, and the second preset remaining battery charge are dynamically adjusted based on the navigation system's real-time route planning data and historical driving data, taking into account different driving scenarios and conditions, such as driving habits (aggressive users tend to accelerate quickly, while gentle users prefer a steady speed), driving routes (e.g., commuting from home to work, from home to parents' home), and environmental conditions (e.g., long-distance driving, short-distance urban driving, mountainous driving, etc.). For example, in high-speed driving scenarios, where the engine speed is high and relatively stable, a higher first preset value may be required to avoid unnecessary control actions, as a small amount of fuel entering the crankcase would have a lesser impact on overall engine performance. In contrast, in urban congestion scenarios, where the engine frequently starts and stops and operates at low speeds, a lower first preset value may be more conducive to timely detection and resolution of oil dilution issues.

[0056] In specific implementations, real-time route planning data and historical driving data can be used to classify driving scenarios and conditions, assigning scenario labels (e.g., urban congestion, highway driving, mountain road driving, etc.), and setting the most appropriate threshold for each scenario. Driving scenarios and conditions are then associated with thresholds to create a scenario condition threshold mapping table. While the vehicle is driving, sensors continuously collect data. The trained scenario classification model is used to identify the current driving scenario and conditions in real time. Based on the identified driving scenario and conditions, the corresponding condition values ​​are retrieved from the scenario condition threshold mapping table, and the relevant preset values ​​in the system are adjusted to the current values. For example, if historical driving data indicates that the user is an aggressive driver, the first preset value can be lowered from 10% to 8% to provide early intervention. For moderate drivers, the first preset value remains at 10% to reduce unnecessary engine starts. For another example, if real-time route planning data indicates that the vehicle is in urban congestion, the first preset value can be lowered from 10% to 8% to more promptly detect potential oil dilution issues.

[0057] Therefore, based on the real-time path planning data and historical driving data of the navigation system, different driving scenarios and driving conditions are obtained, and the strategic threshold for maintaining oil dilution is determined by dynamic adjustment. This can deal with the oil dilution problem more flexibly and effectively, improving the adaptability and reliability of the system.

[0058] In some embodiments, the maintenance mileage value is obtained by querying the oil dilution maintenance mileage data table based on the current ambient temperature and the current water temperature; as an optional implementation in the embodiments of the present application, before determining the maintenance oil dilution strategy based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed and the current remaining battery power, the oil dilution processing method provided in the embodiments of the present application also includes: constructing an oil dilution maintenance mileage data table, wherein the oil dilution maintenance mileage data table includes: maintenance mileage values ​​corresponding to different ambient temperatures and water temperatures.

[0059] Specifically, based on bench test data, a two-dimensional oil dilution maintenance mileage data table is constructed, with water temperature on the horizontal axis and ambient temperature on the vertical axis. The table corresponds to maintenance mileage values ​​under different operating conditions. This embodiment fully considers the impact of different water and ambient temperatures on oil dilution. By analyzing and organizing test data under various operating conditions, appropriate maintenance mileage values ​​are determined for different conditions. For example, for an ambient temperature of -10°C and a cold start (water temperature of 20°C), the maintenance mileage is set to 20 kilometers. If the predicted range is 30 kilometers, the system will start and stop the engine during the initial driving period to maintain oil dilution, preventing excessive oil dilution during long-distance driving. For another example, for an ambient temperature of 5°C and a hot engine (water temperature of 90°C), the maintenance mileage is set to 50 kilometers. This allows dynamic acquisition of corresponding maintenance mileage values ​​based on current starting water temperature, ambient temperature, and other information, enabling more accurate determination of when to take action to maintain oil dilution, ensuring the engine is always in a good operating environment.

[0060] Below, in an application example, the oil dilution processing method provided by the embodiment of the present application is explained in application. The driving conditions of the vehicle on a certain day and the control work of the vehicle controller are as follows: (1) Oil dilution rate prediction: When the car starts in the morning, the engine speed is 1000 rpm, the torque is 150 N·m, the water temperature is 30°C, and the oil temperature is 25°C. The sensor inputs this data into the GBDT prediction model in real time. Based on the previously calibrated quantitative relationship and the GBDT algorithm, the GBDT prediction model calculates a dynamic dilution rate of 0.5% / hour. As the car drives for two hours, the real-time dilution rate reaches 1% through integration.

[0061] (2) Single trip prediction: Before departure, the navigation system predicted a remaining distance of 150 kilometers, with a relatively gentle road gradient and good traffic conditions. Furthermore, analysis of the user's historical driving data revealed an average daily distance of approximately 120 kilometers, with frequent visits to locations within 100-180 kilometers of the current location. Using an LSTM neural network, the system predicted a mileage of 160 kilometers, with a 90% confidence level.

[0062] (3) Oil dilution maintenance mileage setting: With the ambient temperature at 20°C and the water temperature at vehicle startup at 25°C, the oil dilution maintenance mileage table was consulted and the maintenance mileage value was set to 100 kilometers. This setting provided an important basis for determining the maintenance oil dilution strategy.

[0063] (3) Determine the strategy for maintaining oil dilution: After driving for a while, the real-time dilution rate rises to 12%. The predicted mileage is 160 kilometers, the maintenance mileage is set at 100 kilometers, the vehicle speed is stable at 60 km / h, and the battery SOC drops to 55%. At this point, all four conditions for forced engine start are met, and the system automatically starts the engine to perform maintenance on the oil dilution.

[0064] As the vehicle nears its destination, the oil dilution rate drops to 4% as the engine runs and fuel is consumed. The vehicle's speed gradually decreases to 8 km / h as it enters a residential area, and the battery SOC rises to 85% after charging. At this point, the system allows the engine to shut down, saving energy, as the shutdown conditions are met.

[0065] In summary, the oil dilution processing method provided in the embodiments of the present application, compared to the prior art in which oil dilution rate prediction mainly relies on single-dimensional data such as engine water temperature, fully considers the interrelationships between key parameters such as engine speed, vehicle torque, vehicle water temperature, and vehicle oil temperature, and performs a comprehensive analysis. This allows for more accurate prediction of the oil dilution change rate, thereby improving prediction accuracy. Furthermore, in the present application, real-time path planning data (such as remaining mileage and slope) based on the navigation system is embedded in the start-stop engine maintenance oil dilution strategy to achieve "road-oil-engine" coordinated optimization. Through a comprehensive analysis of the real-time oil dilution rate, predicted single-trip mileage, current vehicle speed, and current battery remaining charge, the risk of oil dilution is reduced, the engine is protected, and an optimal oil dilution maintenance strategy is obtained while ensuring optimal battery life and vehicle energy consumption. This balances the contradiction between oil protection and energy consumption, achieving the dual effect of improving oil life and power utilization. Furthermore, this application eliminates the need for a fixed threshold for determining oil dilution maintenance. Instead, it dynamically adjusts the threshold based on different driving scenarios and conditions, based on the navigation system's real-time route planning data and historical driving data. This allows for a more flexible and effective response to oil dilution issues, improving the system's adaptability and reliability. Furthermore, based on information such as the current starting water temperature and ambient temperature, the corresponding maintenance mileage value is dynamically acquired, allowing for a more accurate determination of when to take action to maintain oil dilution, ensuring the engine always maintains a healthy operating environment.

[0066] Furthermore, an exemplary embodiment of the present application provides a vehicle control device 10 . Figure 2 FIG1 shows a structural block diagram of a vehicle control device 10 provided by an exemplary embodiment of the present application. The vehicle control device 10 is applied to a vehicle controller, and can be implemented as follows: Figure 1The following is a brief description of the structure and functions of the vehicle control device 10. For other matters not covered, please refer to the relevant description of the oil dilution treatment method described above. The embodiment of the vehicle control device 10 corresponds to the embodiment of the oil dilution treatment method described above. The various implementation processes and methods of the aforementioned method embodiments are applicable to the embodiment of the vehicle control device 10 and can achieve the same technical effects.

[0067] like Figure 2 As shown, the vehicle control device 10 includes: an oil dilution rate prediction module 100, a single trip prediction module 200 and a control module 300, wherein: The oil dilution rate prediction module 100 is configured to obtain real-time vehicle-related state parameters, predict an oil dilution change rate based on the real-time vehicle-related state parameters, and integrate the oil dilution change rate over a time series to obtain a real-time oil dilution rate. A single trip prediction module 200 is used to obtain real-time route planning data based on the navigation system and input it into a pre-trained LSTM neural network to obtain a predicted single trip mileage; The control module 300 is configured to determine a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge.

[0068] In this embodiment, real-time vehicle state parameters related to oil dilution are collected. As an optional implementation in this embodiment, these real-time vehicle state parameters include at least one of the following: engine speed, torque, water temperature, and oil temperature. Alternatively, the oil dilution rate prediction module 100 can obtain these real-time vehicle state parameters from various onboard sensors. The rate of change of vehicle torque over time facilitates identifying the risk of wall wetting caused by a sudden increase in fuel injection during rapid acceleration, while the rate of change of oil temperature facilitates quantifying the effect of rising oil temperature on fuel volatilization.

[0069] In this embodiment, a GBDT prediction model can be pre-built. During implementation, a quantitative relationship between fuel leakage into the crankcase under various operating conditions can be calibrated through extensive bench testing. This relationship is then used as a training model, and the trained GBDT prediction model is then deployed to the vehicle controller. As an optional implementation in this embodiment, the oil dilution rate prediction module 100 predicts the oil dilution rate based on real-time vehicle-related state parameters by inputting these real-time vehicle-related state parameters into the GBDT prediction model, which then outputs the oil dilution rate. In this embodiment, the GBDT prediction model is effectively used to predict the oil dilution rate, providing data support for oil dilution prevention and protection measures for vehicles.

[0070] Those skilled in the art will appreciate that the present embodiment describes the implementation of the oil dilution rate prediction module 100 using the GBDT prediction model to predict the oil dilution change rate as an example. This is merely an example and does not limit the scope of protection of the claims corresponding to this solution. This application does not limit other methods of predicting the oil dilution change rate.

[0071] Compared with traditional methods that only rely on single parameters such as engine water temperature or operating time, in this embodiment, multiple real-time vehicle status parameters related to oil dilution are integrated and input into the GBDT prediction model, fully considering the relationship between key parameters such as engine speed, vehicle torque, vehicle water temperature and vehicle oil temperature, and performing a comprehensive analysis. This can more accurately predict the oil dilution change rate and improve the prediction accuracy.

[0072] In an application example, compared with the traditional single water temperature model, the prediction accuracy of the GBDT prediction model was improved by 32%, greatly improving the prediction accuracy of the oil dilution rate.

[0073] In this embodiment, the oil dilution rate prediction module 100 integrates the oil dilution change rate according to a time series to obtain a real-time oil dilution rate. The specific method and corresponding application examples have been described in detail in the embodiments of the method and will not be elaborated on here.

[0074] In this embodiment, the single trip prediction module 200 combines the vehicle's historical driving data, such as average daily driving distance, high-frequency destinations, and driving style (frequency of sudden acceleration / deceleration). These data can reflect the user's driving habits and daily travel patterns to construct a user's usual route feature library, and uses the user's usual route feature library to train the LSTM neural network.

[0075] In this embodiment, the navigation system can acquire a variety of real-time route planning data, including at least one of the following: the vehicle's remaining range, road slope, and congestion index. The single-trip prediction module 200 inputs this real-time route planning data into a pre-trained LSTM neural network to obtain a predicted single-trip mileage. LSTM neural networks are capable of processing sequential data and memorizing long-term information, making them ideal for analyzing and predicting user mileage. By learning and analyzing historical driving data and real-time route planning data from the navigation system, the LSTM neural network can output predictions with a confidence level of ≥85%, providing accurate trip information for subsequent determination of maintenance oil dilution strategies.

[0076] For example, on a certain day, the navigation shows that the remaining mileage is 60 kilometers (including congested roads), and the LSTM neural network predicts that the journey will be 55 kilometers (with a confidence level of 90%). The vehicle controller can use this information to determine the maintenance oil dilution strategy.

[0077] In this embodiment, the control module 300 employs a hybrid-specific control strategy to address the conflict between oil dilution and energy efficiency optimization during start-stop operation. As an optional implementation in this embodiment, the control module 300 determines a strategy for maintaining oil dilution based on the real-time oil dilution rate, predicted single-trip mileage, current vehicle speed, and current remaining battery charge in the following manner: (1) When the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery power meet a first preset condition, the engine is started to maintain oil dilution; (2) When the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet the second preset condition, the engine is shut down and the oil dilution maintenance is stopped.

[0078] In this embodiment, the control module 300 adopts a dual-condition collaborative trigger mechanism to determine the strategy for maintaining oil dilution and find a balance point that can effectively reduce oil dilution and protect the engine while optimizing energy consumption and improving the overall energy efficiency of the vehicle.

[0079] In case (1), when the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed and the current remaining battery power meet the first preset condition, it indicates that the oil dilution may be aggravated and the oil dilution needs to be maintained. If the vehicle driving conditions permit, the control module 300 starts the engine in time and maintains the oil dilution state through the normal operation of the engine to avoid damage to the engine caused by excessive oil dilution.

[0080] In the second case, when the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet the second preset condition, it indicates that the oil dilution is in good condition and maintenance is temporarily unnecessary. When the oil dilution is in good condition, the vehicle driving state does not require the engine to operate, or the battery power is sufficient, the control module 300 reasonably shuts down the engine to optimize the vehicle's energy consumption and reduce unnecessary fuel consumption.

[0081] In this embodiment, real-time route planning data (such as remaining mileage and slope) is embedded in the start-stop engine maintenance oil dilution strategy, achieving coordinated optimization of "route, oil, and engine." By comprehensively analyzing the real-time oil dilution rate, predicted single-trip mileage, current vehicle speed, and the current battery remaining charge, the optimal oil dilution maintenance strategy is developed, minimizing the risk of oil dilution and protecting the engine while ensuring optimal battery life and vehicle energy consumption. This balances oil conservation with energy consumption, ultimately improving both oil life and energy efficiency.

[0082] As an optional implementation in the embodiment of the present application, the first preset condition includes: real-time dilution rate > first preset value; predicted single trip mileage > maintenance mileage value; current vehicle speed ≥ first preset speed; current battery remaining power < first preset remaining power; the second preset condition includes at least one of the following: real-time dilution rate < second preset value; current vehicle speed < second preset speed; current battery remaining power > second preset remaining power; wherein, the second preset value < first preset value, the second preset speed < first preset speed, and the second preset remaining power > first preset remaining power.

[0083] In one application example, the first preset value can be set to 10%, the second preset value can be set to 5%, the maintenance mileage value can be set to 30 kilometers, the first preset vehicle speed can be set to 15 km / h (to ensure efficient engine operation), the second preset vehicle speed can be set to 10 km / h (to prioritize electric propulsion at low speeds), the first preset remaining battery charge can be set to 60% (requiring engine start charging), and the second preset remaining battery charge can be set to 80%. If the real-time dilution rate is greater than 10%, the predicted single-trip range is greater than 30 kilometers, the current vehicle speed is ≥15 km / h, and the current remaining battery charge is less than 60% (battery charge is sufficient), the system will force the engine to start to maintain oil dilution and prevent damage to the engine caused by excessive oil dilution. If any of the three conditions, the real-time dilution rate is less than 5%, the current vehicle speed is less than 10 km / h, or the current remaining battery charge is less than 80%, the system will allow the engine to shut down to effectively control engine operation and save energy.

[0084] In one application example, when a vehicle is traveling at high speed, the real-time dilution rate rises to 12%, the predicted remaining mileage is 40 kilometers, and the SOC is 50%. At this time, the system forcibly starts the engine to maintain oil dilution and continues to run until the oil dilution rate drops below 5% or reaches the destination.

[0085] In this embodiment, the parameter thresholds in the first and second preset conditions can be dynamically adjusted based on actual driving scenarios and conditions to timely adjust the oil dilution maintenance strategy. As an optional implementation in this embodiment, the control module 300 is further configured to perform the following operations before determining the oil dilution maintenance strategy based on the real-time oil dilution rate, predicted single trip mileage, current vehicle speed, and current battery remaining charge: a1. Obtain different driving scenarios and conditions based on the navigation system's real-time path planning data and historical driving data; a2. Adjust the first preset value, the first preset remaining power, the second preset value, and the second preset remaining power according to different driving scenarios and driving conditions.

[0086] In this embodiment, the control module 300 no longer uses a fixed threshold for determining the strategic threshold for maintaining oil dilution. Instead, the control module 300 dynamically adjusts the first preset value, the first preset remaining battery charge, the second preset value, and the second preset remaining battery charge based on real-time route planning data from the navigation system and historical driving data, taking into account different driving scenarios and conditions, such as driving habits (aggressive users tend to accelerate quickly, moderate users tend to maintain a constant speed), driving routes (e.g., commuting from home to work, from home to parents' home), and environmental conditions (e.g., long-distance driving, short-distance urban driving, mountainous driving, etc.). For example, in high-speed driving scenarios, where the engine speed is high and relatively stable, a higher first preset value may be required to avoid unnecessary control actions, as a small amount of fuel entering the crankcase would have a lesser impact on overall engine performance. In contrast, in urban congestion scenarios, where the engine frequently starts and stops and operates at low speeds, a lower first preset value may be more conducive to timely detection and resolution of oil dilution issues.

[0087] In specific implementations, the control module 300 classifies driving scenarios and conditions by learning from real-time route planning data and historical driving data, assigning scenario labels (e.g., urban congestion, highway driving, mountain road driving, etc.), setting the most appropriate threshold for each scenario, and associating driving scenarios and conditions with the thresholds to establish a scenario condition threshold mapping table. As the vehicle drives, sensors continuously collect data. The control module 300 uses the trained scenario classification model to identify the current driving scenario and conditions in real time. Based on the identified driving scenario and conditions, the control module 300 retrieves the corresponding condition value from the scenario condition threshold mapping table and adjusts the relevant preset values ​​in the system to the current values. For example, if historical driving data indicates that the user is an aggressive driver, the first preset value can be lowered from 10% to 8% to provide early intervention. For moderate drivers, the first preset value remains at 10% to reduce unnecessary engine starts. For another example, if real-time route planning data indicates that the vehicle is in urban congestion, the first preset value can be lowered from 10% to 8% to more promptly detect potential oil dilution issues.

[0088] Therefore, based on the real-time path planning data and historical driving data of the navigation system, different driving scenarios and driving conditions are obtained, and the strategic threshold for maintaining oil dilution is determined by dynamic adjustment. This can deal with the oil dilution problem more flexibly and effectively, improving the adaptability and reliability of the system.

[0089] In some embodiments, the maintenance mileage value is obtained by querying the oil dilution maintenance mileage data table based on the current ambient temperature and the current water temperature; as an optional implementation in the embodiments of the present application, the control module 300 is also used to construct the oil dilution maintenance mileage data table before determining the maintenance oil dilution strategy based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed and the current remaining battery power, wherein the oil dilution maintenance mileage data table includes: maintenance mileage values ​​corresponding to different ambient temperatures and water temperatures.

[0090] Specifically, the control module 300 constructs a two-dimensional oil dilution maintenance mileage data table based on bench test data. The horizontal axis represents water temperature, and the vertical axis represents ambient temperature. The table corresponds to maintenance mileage values ​​under different operating conditions. This embodiment fully considers the impact of varying water and ambient temperatures on oil dilution. By analyzing and organizing test data under various operating conditions, appropriate maintenance mileage values ​​are determined for each condition. For example, for an ambient temperature of -10°C and a cold start (water temperature of 20°C), the maintenance mileage is set to 20 kilometers. If the predicted range is 30 kilometers, the system will start and stop the engine during the initial driving phase to maintain oil dilution and avoid excessive oil dilution during long-distance driving. For another example, for an ambient temperature of 5°C and a hot engine (water temperature of 90°C), the maintenance mileage is set to 50 kilometers. This allows dynamic acquisition of corresponding maintenance mileage values ​​based on current starting water temperature, ambient temperature, and other information, enabling more accurate determination of when to take action to maintain oil dilution, ensuring the engine is always in a good operating environment.

[0091] Below, in an application example, the operation of the vehicle control device 10 provided in the embodiment of the present application is explained based on the driving conditions of the vehicle on a certain day.

[0092] Oil dilution rate prediction module 100: When the car starts in the morning, the engine speed is 1000 rpm, the torque is 150 N·m, the water temperature is 30°C, and the oil temperature is 25°C. The sensor inputs this data into the GBDT prediction model of the oil dilution rate prediction module 100 in real time. Based on the previously calibrated quantitative relationship and the GBDT algorithm, the GBDT prediction model calculates a dynamic dilution rate of 0.5% / hour. As the car drives for two hours, the real-time dilution rate reaches 1% through integration.

[0093] (2) Single trip prediction module 200: Before departure, the single-trip prediction module 200 obtains the remaining mileage of the trip projected by the navigation system as 150 kilometers, the road slope is relatively gentle, and the congestion index indicates good road conditions. Furthermore, by analyzing the user's historical driving data, the single-trip prediction module 200 discovers that the user's average daily driving distance is approximately 120 kilometers, and that they frequently visit locations within 100-180 kilometers of their current location. Using an LSTM neural network, the module predicts the current trip distance to be 160 kilometers, with a 90% confidence level.

[0094] (3) The control module 300 sets the oil dilution maintenance mileage: Given that the ambient temperature on that day is 20°C and the water temperature at vehicle startup is 25°C, control module 300 queries the oil dilution maintenance mileage data table and determines that the maintenance mileage value is set to 100 kilometers. This setting provides an important basis for determining the maintenance oil dilution strategy.

[0095] (3) Control module 300: After driving for a while, the real-time dilution rate rises to 12%. The predicted mileage is 160 kilometers, the maintenance mileage is set at 100 kilometers, the vehicle speed is stable at 60 km / h, and the battery SOC drops to 55%. At this point, all four conditions for forced engine start are met, and control module 300 automatically starts the engine to maintain the oil dilution.

[0096] As the vehicle approaches its destination, the oil dilution rate drops to 4% as the engine runs and fuel is consumed. The vehicle's speed gradually decreases to 8 km / h as it enters a residential area, and the battery SOC rises to 85% after charging. At this point, the shutdown conditions are met, and control module 300 allows the engine to shut down to save energy.

[0097] Regarding the apparatus in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0098] In summary, the vehicle control device 10 provided in the embodiment of the present application fully considers the relationship between key parameters such as engine speed, vehicle torque, vehicle water temperature, and vehicle oil temperature, and performs a comprehensive analysis, compared to the prior art in which the prediction of oil dilution rate mostly relies on single-dimensional data such as engine water temperature. This application can more accurately predict the oil dilution change rate, thereby improving the prediction accuracy. In addition, in the present application, real-time path planning data based on the navigation system (such as remaining mileage and slope) is embedded in the start-stop engine maintenance oil dilution strategy to achieve "road-oil-engine" collaborative optimization. Through comprehensive analysis of the real-time oil dilution rate, predicted single trip mileage, current vehicle speed, and current battery remaining power, while ensuring optimal battery life and vehicle energy consumption, the risk of oil dilution is reduced, the engine is protected, and the optimal maintenance oil dilution strategy is obtained, which balances the contradiction between oil protection and energy consumption, and achieves the effect of improving both oil life and power utilization. Furthermore, this application eliminates the need for a fixed threshold for determining oil dilution maintenance. Instead, it dynamically adjusts the threshold based on different driving scenarios and conditions, based on the navigation system's real-time route planning data and historical driving data. This allows for a more flexible and effective response to oil dilution issues, improving the system's adaptability and reliability. Furthermore, based on information such as the current starting water temperature and ambient temperature, the corresponding maintenance mileage value is dynamically acquired, allowing for a more accurate determination of when to take action to maintain oil dilution, ensuring the engine always maintains a healthy operating environment.

[0099] FIG3 is a schematic structural diagram of a vehicle provided in an embodiment of the present application.

[0100] Exemplarily, as shown in FIG3 , the vehicle includes: a memory 501 and a processor 502 , wherein the memory 501 stores an executable program code 5011 , and the processor 502 is configured to call and execute the executable program code 5011 to perform an oil dilution processing method.

[0101] This embodiment can divide the vehicle into functional modules based on the above-described method example. For example, each functional module can be mapped to a specific function, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used.

[0102] When functional modules are divided according to their functions, the vehicle may include an oil dilution rate prediction module, a single trip prediction module, and a control module. It should be noted that all relevant details of the steps involved in the above method embodiment can be referenced in the functional descriptions of the corresponding functional modules and will not be repeated here.

[0103] The vehicle provided in this embodiment is used to execute the above-mentioned oil dilution treatment method, and thus can achieve the same effect as the above-mentioned implementation method.

[0104] In the case of an integrated unit, the vehicle may include a processing module and a storage module. The processing module may be used to control and manage the vehicle's movements, while the storage module may be used to support the vehicle's execution of program codes and data.

[0105] The processing module may be a processor or a controller that can implement or execute various exemplary logic blocks, modules, and circuits disclosed in conjunction with the present application. The processor may also be a combination that implements computing functions. For example, it may include a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0106] This embodiment further provides a computer-readable storage medium (including but not limited to a magnetic disk storage, a CD-ROM, an optical storage device, etc.), which stores computer program code. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the oil dilution processing method provided in the above embodiment.

[0107] This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement the oil dilution processing method provided in the above embodiment.

[0108] Among them, the beneficial effects of the above embodiments can refer to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0109] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0110] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0111] In the description of this application, it should be understood that if the terms "up", "down", "front", "back", "left" and "right" are used to indicate directions or positional relationships, they are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the positions or elements referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limitations of this application.

[0112] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. It should also be noted that the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, commodity, or device comprising the element.

[0113] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for treating oil dilution, applied to a vehicle control device, characterized in that: include: Acquiring real-time state parameters related to the vehicle, and predicting a rate of change of oil dilution based on the real-time state parameters related to the vehicle; Performing an integration operation on the oil dilution change rate according to a time series to obtain a real-time oil dilution rate; Obtain real-time path planning data based on the navigation system and input it into a pre-trained long short-term memory (LSTM) neural network to predict the mileage of a single trip. A strategy for maintaining oil dilution is determined based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery power.

2. The method according to claim 1, characterized in that The predicting of the oil dilution change rate based on the real-time state parameters related to the vehicle includes: The vehicle-related real-time state parameters are input into a pre-built gradient boosting tree (GBDT) prediction model, and the oil dilution change rate is obtained as an output, wherein the vehicle-related real-time state parameters include at least one of the following: vehicle engine speed, vehicle torque, vehicle water temperature, and vehicle oil temperature.

3. The method according to claim 1, characterized in that Before obtaining the real-time route planning data based on the navigation system and inputting it into a pre-trained long short-term memory (LSTM) neural network to obtain the predicted single trip mileage, the method further includes: Acquiring historical driving data of the vehicle, wherein the historical driving data of the vehicle includes at least one of the following: average daily driving distance, high-frequency destinations, and driving style; Building a user's usual route feature library based on the historical driving data of the vehicle; The LSTM neural network is trained using the user's usual route feature library.

4. The method according to claim 1, wherein The determining of a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge includes: Initiating engine maintenance oil dilution when the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current battery remaining power meet a first preset condition; When the real-time dilution rate, the current vehicle speed, and the current remaining battery power meet a second preset condition, the engine is shut down and the oil dilution maintenance is stopped.

5. The method according to claim 4, characterized in that The first preset condition includes: the real-time dilution rate > the first preset value; the predicted single trip mileage > the maintenance mileage value; the current vehicle speed ≥ the first preset vehicle speed; the current battery remaining power < the first preset remaining power; The second preset condition includes at least one of the following: the real-time dilution rate < the second preset value; the current vehicle speed < the second preset vehicle speed; the current remaining battery power > the second preset remaining power; Among them, the second preset value is less than the first preset value, the second preset vehicle speed is less than the first preset vehicle speed, and the second preset remaining power is greater than the first preset remaining power.

6. The method according to claim 5, characterized in that Before determining the strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge, the method further includes: Obtaining different driving scenarios and driving conditions based on the real-time path planning data and historical driving data of the navigation system; According to the different driving scenarios and driving conditions, the first preset value, the first preset remaining power, the second preset value and the second preset remaining power are adjusted.

7. The method according to claim 5, characterized in that The maintenance mileage value is obtained by querying the oil dilution maintenance mileage data table according to the current ambient temperature and the current water temperature; Before determining the strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge, the method further includes: The oil dilution maintenance mileage data table is constructed, wherein the oil dilution maintenance mileage data table includes: maintenance mileage values ​​corresponding to different ambient temperatures and water temperatures.

8. A vehicle control device, applied to a vehicle, characterized in that: The vehicle control device comprises: An oil dilution rate prediction module is configured to obtain real-time vehicle-related state parameters, predict an oil dilution change rate based on the real-time vehicle-related state parameters, and integrate the oil dilution change rate over a time series to obtain a real-time oil dilution rate. The single trip prediction module is used to obtain real-time path planning data based on the navigation system and input it into the pre-trained long short-term memory network (LSTM) neural network to obtain the predicted single trip mileage; The control module is configured to determine a strategy for maintaining oil dilution based on the real-time oil dilution rate, the predicted single trip mileage, the current vehicle speed, and the current remaining battery charge.

9. A vehicle, characterized in that: The vehicle includes at least one processor, and when executed, the at least one processor implements the oil dilution processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the oil dilution processing method according to any one of claims 1 to 7 are implemented.

Images