Vehicle control method and vehicle with same

Abstract

The invention provides a vehicle control method and a vehicle with the same. The method includes: acquiring working condition information of a target vehicle; on the basis of the working condition information, data information of the target vehicle is obtained under the condition that it is determined that the target vehicle meets the target state, information of the external environment where the current target vehicle is located is obtained, and the data information of the target vehicle comprises the charging time preference, the driving route preference and the driving mode preference of the target object; the external environment information comprises road condition information of target vehicle driving and current electricity price information; performing noise reduction and completion processing on the data information of the target vehicle and the external environment information to obtain noise-reduced and completed cleaning data; predicting energy demand information in a preset time period based on the cleaning data; a control strategy set is generated based on the energy demand information, and the control strategy set is used for controlling the target vehicle to execute the target driving mode. The problem that the flexibility of a control strategy is low due to the fact that the obtained vehicle data dimension is single in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to a vehicle control method and a vehicle having the same. BACKGROUND

[0002] Plug-in Hybrid Electric Vehicle (PHEV) as an important type of new energy vehicles, its energy management strategy is of great significance to improve energy efficiency, reduce cost and reduce emissions. At present, the energy management technology of plug-in hybrid electric vehicle has made certain development, especially in the use of cloud data for intelligent control. In the prior art, the vehicle running information and historical data of the vehicle are obtained through the vehicle controller, and the data associated with the vehicle is monitored and adjusted in real time to optimize the overall performance and energy consumption.

[0003] However, these technologies still have the following shortcomings:

[0004] 1. Single data dimension: the existing technology mainly relies on vehicle running information and historical traffic data, and fails to fully combine key parameters such as battery SOC (state of charge), charging pile distribution, and user charging habits, resulting in insufficient targeting of energy management strategies and inability to maximize the use of plug-in hybrid electric vehicle characteristics.

[0005] 2. Lack of predictability: although the existing technology uses historical data for prediction, the response to real-time sudden traffic conditions (such as temporary traffic control and sudden congestion) and dynamic energy prices (such as time-of-use electricity prices) is limited, and the energy flow cannot be accurately planned in advance, affecting energy saving effect and user driving experience.

[0006] 3. Lack of control strategy flexibility: existing control strategies are often designed to be more general and fail to provide fine control for plug-in hybrid electric vehicle's pure electric drive, hybrid drive, and brake energy recovery mode switching, which limits efficient energy management in different working conditions.

[0007] No effective solution has been proposed to address the above problems. SUMMARY

[0008] The main purpose of the present application is to provide a vehicle control method and a vehicle having the same to solve the problem of single data dimension in obtaining vehicle data in the prior art, resulting in low flexibility of control strategy.

[0009] In order to achieve the above object, according to one aspect of the present application, a control method of a vehicle is provided, comprising: obtaining working condition information of a target vehicle, wherein the working condition information at least comprises one of the following: power battery power information of the target vehicle, engine state, speed, brake signal; obtaining data information of the target vehicle and obtaining external environment information in which the target vehicle is currently located, based on the working condition information, in the case that the target vehicle meets a target state, wherein the data information of the target vehicle comprises charging time preference, driving route preference and driving mode preference of a target object, and the external environment information comprises road condition information of the target vehicle and current electricity price information; performing noise reduction and completion processing on the data information of the target vehicle and the external environment information to obtain cleaned data after noise reduction and completion, wherein the cleaned data comprises driving route congestion information, battery power information and engine working condition information; predicting energy demand information in a preset time period based on the cleaned data; and generating a control strategy set based on the energy demand information, wherein the control strategy set is used to control the target vehicle to execute a target driving mode, and the target driving mode at least comprises a pure electric driving mode, a hybrid driving mode and a brake electric energy recovery mode.

[0010] Further, the noise reduction and completion processing on the data information and the external environment information to obtain the cleaned data after noise reduction and completion comprises: identifying a type of the external environment information, converting unstructured type external environment information into a target data type, and obtaining external environment information of a pre-set structured type in the cleaned data.

[0011] Further, the noise reduction and completion processing on the data information and the external environment information to obtain the cleaned data after noise reduction and completion comprises: in the case that the external environment information comprises road condition description type information, converting the road condition description type information into congestion coefficient data of a structured type.

[0012] Further, the prediction of the energy demand information in the preset time period based on the cleaned data comprises: obtaining distance information of the driving route; determining a time length for passing through the driving route and a passing speed of the target vehicle through the driving route based on the distance information and the congestion information; and determining the energy demand information based on the time length and the passing speed, wherein the energy demand information comprises power information required for passing through the driving route.

[0013] Further, the generation of the control strategy set based on the energy demand information comprises: in the case that the power information required for passing through the driving route is determined, obtaining power information of the current power battery; and in the case that the power information of the current power battery meets the passing through the driving route, generating a first control strategy in the control strategy set, wherein the first control strategy is used to control the target vehicle to execute the pure electric driving mode in the target driving mode.

[0014] Further, based on the cleaning data, in a case where it is determined that the current power battery power information meets the passing route, a first control strategy in the control strategy set is generated, including: in response to executing the first control strategy, obtaining the target vehicle's predicted acceleration time and the current electricity price information; in a case where it is determined that the predicted acceleration time and the current electricity price information meet the preset condition, a second control strategy in the control strategy set is generated after a preset time, and the second control strategy is used to control the engine to work and charge the power battery.

[0015] Further, in a case where it is determined that the predicted acceleration time and the current electricity price information meet the preset condition, the second control strategy in the control strategy set is generated after a preset time, including: in a case where it is determined that the predicted acceleration time is less than or equal to a first preset value, and the current electricity price information is less than or equal to a second preset value, the second control strategy in the control strategy set is generated after a time of the first preset value.

[0016] Further, the control strategy set is generated based on the energy demand information, including: recording the state information of the power battery after the target vehicle executes the target driving mode each time, wherein the state information of the power battery includes the actual energy consumption of the power battery, the battery temperature information, and the power battery power increment information.

[0017] Further, in a case where it is determined that the target vehicle meets the target state based on the working condition information, the data information of the target vehicle is obtained, including: judging whether the target vehicle is in a starting state based on the engine state and the power battery power supply state in the working condition information; in a case where it is confirmed that the target vehicle is in the starting state, the data information of the target vehicle is obtained.

[0018] According to one aspect of the present application, a vehicle is provided, which is controlled by the above-mentioned control method.

[0019] By applying the technical scheme of the present application, the multi-source data fusion and processing mode is adopted, the working condition information of the target vehicle, the user preference data and the real-time external environment information are comprehensively analyzed, the purpose of accurately predicting the energy demand of the vehicle is achieved, and the dynamic optimization control strategy is realized to adapt to the technical effects of pure electric driving, hybrid driving and brake energy recovery and other driving modes, thereby solving the technical problems of poor energy management pertinence, response lag and inability to effectively cope with multi-mode switching scenarios caused by single data dimension, insufficient predictability and lack of control strategy flexibility. BRIEF DESCRIPTION OF DRAWINGS

[0020] The drawings constituting a part of the specification of the present application are used to provide a further understanding of the present application, the illustrative embodiments of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1A flowchart illustrating an embodiment of a control method of a vehicle according to the present application is shown. DETAILED DESCRIPTION

[0022] It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0023] It should be noted that the terms used herein are only intended to describe specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprise" and / or "include" when used in this specification, specify the presence of stated features, steps, operations, devices, components and / or combinations thereof.

[0024] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged as appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Now, exemplary embodiments according to the present application will be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in various different forms, and should not be interpreted as being limited only to the embodiments set forth herein. It should be understood that these embodiments are provided in order to make the present disclosure complete and comprehensive, and to adequately convey the ideas of these exemplary embodiments to those of ordinary skill in the art. In the drawings, the thickness of layers and regions can be exaggerated for clarity, and the same reference numerals are used to denote the same elements, so that a description thereof will be omitted.

[0026] As shown in FIG. 1, according to one specific embodiment, a control method of a vehicle is provided, and the specific steps include: Figure 1

[0027] S102, obtaining working condition information of the target vehicle, wherein the working condition information at least includes one of the following: power battery power information of the target vehicle, engine state, speed, brake signal;

[0028] ​Power battery power information: refers to the current SOC (state of charge) value of the target vehicle's power battery, i.e. the ratio of the remaining battery capacity to the total capacity, which is an important parameter for determining the vehicle energy management strategy. For example, an SOC of 80% means that the remaining battery capacity is 80% of the total capacity.

[0029] Engine state: including whether the engine is started, the speed, the working temperature, etc. These information is crucial for determining when to start or stop the engine to optimize energy consumption.

[0030] Speed: the real-time driving speed of the vehicle, which affects energy consumption and the selection of driving mode, for example, pure electric mode may be preferred when driving at low speed.

[0031] Brake signal: refers to the use of the vehicle's braking system, related to the activation of the brake energy recovery mode, which can convert the vehicle's kinetic energy into electrical energy and store it in the battery when the vehicle is decelerating or stopping.

[0032] S104, based on the working condition information, determine the target vehicle meets the target state, obtain the data information of the target vehicle, and obtain the external environment information of the current target vehicle, wherein the data information of the target vehicle includes the charging time preference, the driving route preference and the driving mode preference of the target object, and the external environment information includes the road condition information of the target vehicle driving, the current electricity price information;

[0033] Charging time preference: user's choice of charging time, which helps to plan the charging strategy and avoid charging during peak hours.

[0034] Driving route preference: user's preferred route or route selection, which is helpful for estimating energy demand and planning charging pile usage.

[0035] Driving mode preference: user's preferred driving mode, such as economy mode, sport mode, etc., with different modes of energy consumption.

[0036] Road condition information: including real-time traffic conditions, road congestion degree, etc.

[0037] Current electricity price information: used for planning charging time and selecting the lowest cost charging strategy.

[0038] When the target vehicle is in a specific target state, collect data information including charging time preference, driving route preference, driving mode preference, and external environment information including real-time road condition information and dynamic electricity price information, which enables the energy management strategy to be adjusted according to the user's individual needs and external environmental changes.

[0039] S106, denoising and completing the data information of the target vehicle and the external environment information to obtain cleaned data after denoising and completion, wherein the cleaned data includes congestion information of a driving route, battery power information, and engine working condition information;

[0040] Denoising: Remove abnormal values or interference information in the data to ensure the accuracy of data analysis. Specific operations include: Abnormal value identification: Through statistical analysis (such as 3σ principle), identify battery power information, engine working condition information, etc. that are out of the normal range. These abnormal values may be caused by sensor failure, data transmission error, etc. Smoothing processing: Smooth the continuous data (such as vehicle speed, battery temperature) using time series analysis method (such as moving average method), to reduce the fluctuations caused by measurement error or external interference. Data consistency check: Check the consistency between vehicle data information and external environment information. For example, if the battery power information shows that the vehicle is close to full power, but the charging time preference data shows that the user has recently charged frequently, it may mean that there is inconsistency in data collection or processing, which needs to be further verified.

[0041] Completion processing: Reasonably estimate or supplement missing data to ensure data integrity and avoid errors caused by missing data during model training or prediction. Completion methods include: Historical data-based completion: For missing battery power information or engine working condition information, historical data of the vehicle can be analyzed to complete the data under similar working conditions. Default value-based completion: For some parameters, such as engine speed when not started, a default value can be set for completion. External information-based inference completion: For example, it is currently 6 am, and according to the user preference data (the user likes to charge in the morning), it is inferred that the battery SOC may be at a high level, and the completion is made accordingly.

[0042] By denoising and completing a large amount of collected data to form cleaned data, the quality and integrity of the input data are ensured, and the control decision deviation caused by data abnormalities is avoided.

[0043] S108, based on the cleaned data, predict the energy demand information in a preset time period;

[0044] The present application utilizes the cleaned dataset to predict the energy demand of the target vehicle in the next predetermined time period through advanced prediction algorithms such as machine learning models, long short-term memory networks (LSTM) or convolutional neural networks (CNN). This step aims to provide a foundation for the generation of predictive control strategies, ensuring that the energy management of the vehicle can achieve optimal state under different driving conditions in the future. Through step S108, we can obtain high-precision energy demand prediction, which helps the vehicle to plan power use in advance, avoid energy waste, and ensure effective use of existing power resources in any situation while reducing dependence on fuel. In addition, the prediction can also take into account external environmental changes such as real-time traffic conditions and dynamic electricity prices, thereby better optimizing the energy management of the vehicle under complex driving conditions.

[0045] S110, generating a control strategy set based on the energy demand information, wherein the control strategy set is used to control the target vehicle to execute the target driving mode, and the target driving mode at least includes a pure electric driving mode, a hybrid driving mode and a brake electric energy recovery mode.

[0046] After obtaining the energy demand information, step S110 is to generate a series of control strategies to form a control strategy set, which aims to guide the vehicle to execute the target driving mode under different driving conditions to meet the predicted energy demand while achieving energy saving and emission reduction and improving driving experience.

[0047] Through the above steps S102 to S110, the present application adopts a multi-source data fusion and processing method, which comprehensively analyzes the working condition information of the target vehicle, user preference data and real-time external environment information, achieves the purpose of accurately predicting the energy demand of the vehicle, and realizes dynamic optimization of the control strategy to adapt to the technical effects of pure electric driving, hybrid driving and brake energy recovery and other driving modes, thereby solving the technical problems of poor energy management targeting, response lag and inability to effectively respond to multi-mode switching scenarios caused by single data dimension, insufficient predictability and lack of control strategy flexibility.

[0048] Specifically, step S106, the noise reduction and completion processing is performed on the data information and the external environment information to obtain cleaned data after noise reduction and completion, including: identifying the type of external environment information, converting unstructured type external environment information into target data type, and obtaining external environment information in the cleaning data that conforms to the pre-set structured type. This process aims to improve the quality and applicability of the data, and ensure the accuracy and impartiality of the data input into the predictive energy saving model. By converting unstructured information such as road condition description and charging pile layout text into structured data such as congestion coefficient and charging pile distance, the model can more effectively understand and utilize these information, and perform accurate energy demand prediction and multi-mode control strategy optimization. The application of cleaned data makes the control strategy more robust, reduces the decision bias caused by data noise, and enhances the prediction ability and control accuracy of the model.

[0049] Optionally, the collected unstructured data is converted into structured data to meet the input requirements of the model. For example: text information is converted into numerical value: the road condition description in the external environment information (such as "there is traffic control ahead") is converted into congestion coefficient (such as 0.7), reflecting the severity of traffic conditions. The extracted electricity price information is standardized in format, i.e. ensuring that all time periods and prices are presented in a uniform format. For example: electricity price information is often received in an unstructured form, such as through email, text message or web announcement, containing information such as "today's peak electricity price period is 10am-12pm, with a price of 1.2 yuan / kWh; the valley electricity price period is 10pm-6am, with a price of 0.3 yuan / kWh." "10am-12pm" and "10pm-6am" are converted into "10:00-12:00" and "22:00-06:00" in 24-hour format, and the prices "1.2 yuan / kWh" and "0.3 yuan / kWh" are converted into numerical data.

[0050] Specifically, step S106, the noise reduction and completion processing is performed on the data information and the external environment information to obtain cleaned data after noise reduction and completion, including: in the case where it is determined that the external environment information includes road condition description type information, the road condition description type information is converted into congestion coefficient data in the structured type. Through algorithm analysis and mapping, the vague road condition description is quantified into clear congestion coefficient, so as to better reflect the actual traffic conditions. This standardized processing of data enables the predictive energy saving model to more accurately understand and predict the influence of external environment on vehicle energy demand, and further optimize the control strategy, so that the vehicle can realize optimal control of energy consumption and cost in the face of variable traffic environment.

[0051] The congestion coefficient is a quantitative indicator for evaluating the degree of road congestion, usually ranging from 0 to 1, where 0 represents a smooth road without obstruction, and 1 represents complete congestion and inability to travel.

[0052] In one embodiment, a model is pre-trained in the system, which maps the "expected travel time increase" to the congestion coefficient based on the description of the road condition in the historical data and the actual observed travel time. For example, for the description of "there is a long-time congestion 3 kilometers ahead, the expected travel time increases by 10 minutes", the model may convert it into a higher congestion coefficient, such as 0.8.

[0053] Specifically, step S108, based on the cleaning data, predicts the energy demand information in a preset time period, including: obtaining distance information of the driving route;

[0054] Step S1081, based on the distance information and the congestion information, determines the time length of passing through the driving route and the passing speed of the target vehicle passing through the driving route;

[0055] Step S1082, based on the time length and the passing speed, determines the energy demand information, wherein the energy demand information includes the electric quantity information required for passing through the driving route.

[0056] Steps S1081 to S1082 make full use of the vehicle operating state, external environment and user behavior data, and through comprehensive consideration, the best energy management and distribution strategy can be planned in advance to ensure that the energy consumption of the vehicle within the expectation reaches the optimal state, thereby significantly improving the energy utilization efficiency and economy of the plug-in hybrid electric vehicle.

[0057] In one embodiment, a plug-in hybrid electric vehicle travels from home to the downtown work site, about 15 kilometers away. All relevant data, including vehicle operating conditions, user preferences, real-time traffic conditions, and dynamic energy price information, have been obtained and processed. It is known that the distance from home to the city center is 15 kilometers (driving route distance information). Real-time data obtained through Internet of Vehicles technology shows that the first half of the journey (about 8 kilometers) is smooth, the second half (about 7 kilometers) has a 3-kilometer light congestion (congestion coefficient 0.3), and the last 2 kilometers is a serious congestion (congestion coefficient 0.9). The user tends to use pure electric mode for driving, especially during peak traffic hours. The driving time of the smooth section is predicted: the current battery SOC is 85%, the vehicle is in pure electric mode, and the vehicle speed is 50 km / h. Assuming that the vehicle travels at an average speed of 50 km / h on the smooth section, the 8-kilometer expected travel time is: [8 / 50 60=9.6 minutes]. The speed and time prediction of the light congestion section: according to the congestion coefficient 0.3, the average speed is reduced to 40 km / h, then the 3-kilometer expected travel time is: [3 / 40 60=4.5 minutes]. Considering the instability of traffic flow, an additional 10% of the estimated time is added: [4.5 1.1=4.95 minutes]. Speed and time prediction of severe congestion section: according to the congestion coefficient 0.9, the average speed is reduced to 15 km / h, and the estimated driving time of 2 kilometers is: [2 / 15 60=8 minutes]. Similarly, considering the potential stagnation, an additional 20% of the estimated time is added: [8 1.2=9.6 minutes]. Based on the energy consumption rate of the vehicle at different speeds (this information can be found in the vehicle manual or database). It is assumed that the energy consumption rate of the pure electric mode under smooth road conditions is 0.15 kWh / km, the energy consumption rate under light congestion is 0.2 kWh / km, and the energy consumption rate under severe congestion is 0.3 kWh / km. Energy demand calculation: smooth section: [8km 0.15 kWh / km=1.2 kWh]; Mild congestion section: [3km 0.2 kWh / km=0.6 kWh]; Severe congestion section: [2km 0.3 kWh / km=0.6 kWh]; Total amount calculation: [1.2 kWh+0.6 kWh+0.6 kWh=2.4 kWh]. By combining the distance information of the driving route and the congestion information of the specific road conditions, the system can accurately predict the energy required for a specific driving route within a predetermined time period, i.e. 2.4 kWh. Assuming the total capacity of the battery is 20 kWh, and the current battery SOC is 85%, i.e. the battery still has 17 kWh of power, which meets the above demand.

[0058] Optionally, based on the energy demand information, a control strategy set is generated, such as when approaching a congestion area, if the battery SOC is below a certain threshold, it will prompt to switch to hybrid mode, with the engine as the main power supply, while charging the battery, to ensure the endurance of the pure electric mode. Information about the estimated energy consumption and suggestions for optimizing the driving mode can be provided to the driver, such as suggesting charging during off-peak hours, or planning to charge in advance to avoid running out of power during congestion.

[0059] Specifically, step S110, based on the energy demand information, generating a control strategy set, comprising:

[0060] Step S1101, in the case of determining the energy required for the driving route, obtaining the current power battery power information;

[0061] Step S1102, in the case of determining that the current power battery power information meets the driving route, generating a first control strategy in the control strategy set, wherein the first control strategy is used to control the target vehicle to execute the pure electric driving mode in the target driving mode.

[0062] This process ensures the priority use of battery energy under sufficient power conditions, realizes effective allocation of resources, and responds to user demands for environmentally friendly travel, reducing carbon emissions.

[0063] In a specific embodiment, assuming we are dealing with the energy management of a plug-in hybrid vehicle, the goal is to ensure that the vehicle can efficiently use energy in future travel. In this embodiment, it has been predicted that the vehicle will need to consume 2.4 kWh of electricity through a specific driving route in the next 30 minutes of travel. Currently, the power battery's power information shows that the SOC is 85%, i.e. the remaining power is 17 kWh (assuming the total capacity of the battery is 20 kWh). Since the remaining power is significantly higher than the required power, it is determined that the current power battery power information can meet the needs of future travel, and a pure electric driving mode is used during travel. At the same time, feedback information such as "current battery power is sufficient, pure electric driving mode will be used in the next step, estimated driving range covers the entire journey" can be provided to the driver through the vehicle infotainment system.

[0064] Specifically, step S1102, based on the cleaning data, in the case where it is determined that the current power battery power information meets the driving route, a first control strategy in the control strategy set is generated, including:

[0065] Step S11021, in response to executing the first control strategy, obtaining the predicted acceleration time and the current electricity price information of the target vehicle;

[0066] Step S11022, in the case where it is determined that the predicted acceleration time and the current electricity price information meet the preset conditions, a second control strategy in the control strategy set is generated after a preset time, and the second control strategy is used to control the engine to work and charge the power battery.

[0067] The predicted acceleration time indicates that the road ahead is in good condition and there is no congestion.

[0068] By steps S11021 to S11022, the fluctuation of electricity price and the predicted road conditions are fully utilized to ensure pre-charging before the power demand increases, avoiding high-cost charging triggered by insufficient power, thereby significantly reducing operating costs while ensuring normal operation of the vehicle.

[0069] In a specific embodiment, a typical morning and evening commuting scenario, on the section of urban expressway to highway, the vehicle is about to enter a long and smooth highway. At this time, based on the cleaning data prediction, the target vehicle will mainly drive at high speed in the next half hour, and it is expected to drive on the highway for about 20 minutes. In addition, the current electricity price information is checked, and it is found that it is currently in the electricity price trough period, and the electricity price is 0.3 yuan per degree. The SOC of the target vehicle's current power battery is 75%, that is, 24kWh (assuming the total capacity of the battery is 32kWh). According to the historical data analysis and current energy demand prediction, the system determines that the vehicle's power before entering the highway is sufficient to support the driving demand in pure electric driving mode. After determining that the current power battery power information can meet the driving demand, the system activates the first control strategy in the control strategy set, that is, the vehicle drives in pure electric driving mode until the highway entrance. In this mode, the vehicle can fully utilize the battery power and reduce fuel consumption. Since the predicted acceleration time is 20 minutes, and it is currently in the electricity price trough period, it is judged that both conditions are met. After 5 minutes (in order to avoid the influence of highway entrance congestion, ensure that it is executed immediately after entering the highway, the current SOC is 75%, and it is expected that the driving before entering the highway will not consume a lot of battery power.), the engine is automatically started, and the hybrid mode is entered, and the excess energy of the engine is used to charge the power battery. The second control strategy ensures that the energy demand is low during high-speed driving, and the charging is carried out in advance at a lower cost, which not only guarantees the subsequent driving power demand, but also avoids the high cost of charging in the peak period. After 15 minutes of engine auxiliary charging (assuming the charging efficiency), the battery SOC is restored to 85%, that is, 27.2kWh. Compared with charging in the peak period, this strategy saves at least 50% of the charging cost.

[0070] Specifically, in the case where the predicted acceleration time length and the current electricity price information satisfy the preset condition, the second control strategy in the control strategy set is generated after a preset time length in step S11022. The second control strategy in the control strategy set is generated after a time length of the first preset value in the case where the predicted acceleration time length is less than or equal to the first preset value and the current electricity price information is less than or equal to the second preset value. In this embodiment, when the predicted acceleration time length and the current electricity price information satisfy a specific preset condition, that is, in the case where the predicted acceleration time length is less than or equal to the first preset value T1 and the current electricity price information is less than or equal to the second preset value P2, the second control strategy in the control strategy set is automatically generated and executed after a time length of the first preset value T1. The core of this design is to make decisions based on real-time information to optimize the use of low-cost electricity to charge the battery or maintain a high SOC state, thereby maximizing the use of low-cost electricity to charge the battery or maintaining a high SOC state. In this way, not only can the energy consumption during the high electricity price period be effectively avoided, but also the battery can have enough energy reserves when it needs to accelerate quickly or cope with sudden working conditions, thereby ensuring driving safety while improving energy use efficiency and vehicle operation efficiency.

[0071] In a specific embodiment, it is assumed that the vehicle is starting from an urban area to a suburban area, and will enter a relatively smooth expressway section in the middle of the journey, with an estimated duration of 15 minutes (predicted acceleration time length). Currently, the SOC of the vehicle's power battery is 80%, that is, the remaining capacity is 16 kWh (assuming the total capacity of the battery is 20 kWh). The real-time monitored electricity price is 0.4 yuan / kWh, which is in the trough electricity price interval. The first preset value: the threshold of the predicted acceleration time length is set to 15 minutes, which means that only when the predicted smooth driving time is less than or equal to 15 minutes, the subsequent control strategy adjustment will be considered. The second preset value: the threshold of the current electricity price information is set to 0.5 yuan / kWh, that is, only when the current electricity price is less than or equal to 0.5 yuan / kWh, the second control strategy of charging with the engine will be considered. At the moment when the target vehicle is about to enter the expressway section, the system evaluates the current situation based on the preset conditions: it is confirmed that the predicted acceleration time length is 15 minutes, which is equal to the first preset value, indicating that the smooth driving time of the expressway section meets the condition. The current electricity price is 0.4 yuan / kWh, which is less than the second preset value 0.5 yuan / kWh, indicating that the current charging cost is at an acceptable low level. Based on the above evaluation, the system decides to generate and execute the second control strategy after a time length of the first preset value (i.e., 15 minutes) after entering the expressway section, that is, to start the engine and charge the power battery with the engine's excess energy in hybrid mode. This avoids unnecessary engine operation during congestion or high electricity price periods, reducing energy waste and emissions. According to the dynamically changing road conditions and electricity price information, the energy management strategy is automatically adjusted without manual intervention by the driver, improving the convenience of driving and the intelligence level of energy management.

[0072] Specifically, step S110, generating a control strategy set based on energy demand information, includes:

[0073] Step S1103, recording the state information of the power battery after the target vehicle executes the target driving mode each time, wherein the state information of the power battery includes the actual energy consumption of the power battery, battery temperature information, and power battery power increment information.

[0074] The recording of the actual energy consumption helps to understand the energy consumption of the vehicle under a specific working condition, the collection of the battery temperature information helps to monitor the thermal management state of the battery under different environmental conditions, and the power increment information of the power battery is directly related to the charging efficiency, that is, how much power is charged to the power battery under the charging mode. This process aims to collect and analyze the energy consumption and battery state changes of the vehicle under different driving modes. Through the recording and analysis of these data, a more accurate energy demand model can be established, laying a foundation for subsequent generation of targeted control strategy sets.

[0075] In a specific embodiment, it is assumed that the battery SOC of the target vehicle decreases to 60% after a day of use. In the return trip, it is predicted that: congested section: 3 kilometers are expected to be driven, the vehicle enters the hybrid driving mode 10 minutes in advance, the engine is mainly used to maintain the SOC, 0.5 liters of fuel are consumed during this period, the actual energy consumption of the battery is 0.5 kWh, and the battery temperature increases from 20°C to 25°C. Smooth section: 12 kilometers are expected to be driven, return to pure electric driving mode, the vehicle consumes 2.0 kWh of battery power, and the battery temperature stabilizes at 24°C without significant change. In the last 5 kilometers approaching the charging station, real-time electricity price information is obtained, it is judged that the current is in the electricity price trough period, the engine is started 5 minutes in advance, the brake electric energy recovery mode is entered, the battery power increases from 60% to 75%, that is, the battery power increases by 3 kWh, and the battery temperature increases to 26°C. After each target driving mode is executed (such as the hybrid mode in the congested section and the pure electric mode in the smooth section), the actual energy consumption of the power battery is recorded, that is, the power consumed by the vehicle under a specific mode. At the same time, the battery temperature information is continuously monitored, especially the battery temperature change caused by the engine start and the temperature performance of the battery during discharging in the pure electric mode. After entering the brake electric energy recovery mode, the power increment information of the power battery is recorded, that is, the power increment of the battery in a specific time period, so as to evaluate the charging efficiency and the effectiveness of the energy management strategy.

[0076] Specifically, step S104, based on the working condition information, the data information of the target vehicle is obtained under the condition that the target vehicle meets the target state, including:

[0077] Step S1041, determine whether the target vehicle is in the starting state based on the engine state and the power supply state of the power battery in the working condition information;

[0078] S1041, in the case of confirming that the target vehicle is in the starting state, acquire the data information of the target vehicle.

[0079] This step ensures the timeliness and accuracy of data collection, avoiding invalid data processing on vehicles that have not started. After confirming that the target vehicle has started, the system immediately acquires and fuses the multi-source data information of the target vehicle, including but not limited to battery SOC, vehicle speed, engine working state, etc., as well as real-time road conditions, charging pile distribution, and dynamic energy prices, etc. Through this design, the system can more accurately identify the actual running state and environmental conditions of the target vehicle, providing high-quality input data for subsequent prediction models.

[0080] In a specific embodiment, assume that the user starts the vehicle at 7 am, preparing to leave home for work, at this time the engine starts to warm up and the power battery supplies power to the vehicle electronic system. Detecting that both the engine state and the power battery supply state are active, immediately confirming that the vehicle has been in the starting state. Then start to acquire engine state information (such as speed of 1200 RPM, fuel consumption rate of 0.1 L / h) and power battery state information (such as SOC of 90%, battery temperature of 22°C), as well as other running parameters. Analyzing these information, found that the current battery power is sufficient, the predicted driving distance is suitable for pure electric mode, thus generating and executing the control strategy, instructing the vehicle to switch to pure electric drive mode, to reduce fuel consumption and emissions.

[0081] In another specific embodiment, a target vehicle is traveling during the morning and evening peak hours, and the current battery power is 80%, i.e. 16 kWh (assuming the total capacity of the battery is 20 kWh, the current speed is 50 km / h, and the vehicle is running in pure electric mode, at which time the engine is in the off state. The system receives and analyzes real-time traffic data, which shows that the vehicle will encounter a long congestion within the next 3 kilometers, with a congestion coefficient of 0.8, meaning that the traffic flow rate will be greatly reduced. Through the charging time preference and driving mode preference of the vehicle owner, it is learned that the user tends to travel in pure electric mode and prefers to charge during the valley period of electricity price to save cost. The vehicle remains in pure electric mode according to the first control strategy, passes through the congestion section, and continuously monitors the decrease of the battery SOC. When the vehicle passes through the congestion section, the system detects that the battery SOC decreases to 20% (assuming 4 kWh), and immediately activates the second control strategy to automatically switch to hybrid mode, starts the engine, and charges the battery to meet the energy demand for subsequent travel. After returning home from work in the evening, it is found that there is a available charging pile within 2 kilometers, and it is checked that the current electricity price is in the valley period, i.e. 0.3 yuan / kWh, which is the economic period for charging, and the vehicle can be charged through the charging pile.

[0082] According to another embodiment of the present application, a vehicle is provided, which is controlled by the above-mentioned control method.

[0083] According to another embodiment of the present application, a control device of a vehicle is provided, which comprises:

[0084] The data acquisition module is configured to acquire working condition information of the target vehicle, wherein the working condition information at least includes one of the following: power battery power information of the target vehicle, engine state, speed, and brake signal; based on the working condition information, the data information of the target vehicle is acquired when the target vehicle meets the target state, and the external environment information in which the target vehicle is currently located is acquired, wherein the data information of the target vehicle includes charging time preference, driving route preference and driving mode preference of the target object, and the external environment information includes road condition information and current electricity price information of the target vehicle;

[0085] The data processing and fusion module is configured to perform noise reduction and completion processing on the data information of the target vehicle and the external environment information to obtain cleaned data after noise reduction and completion, wherein the cleaned data includes driving route congestion information, battery power information and engine working condition information.

[0086] The predictive energy-saving model module is configured to predict energy demand information within a preset time period based on the cleaned data, construct an energy demand prediction model based on a machine learning algorithm (such as a long short-term memory network LSTM), input multi-source fusion data, and output an energy demand curve within a future period of time.

[0087] The control execution module generates a control strategy set based on the energy demand information, wherein the control strategy set is used to control the target vehicle to execute a target driving mode, and the target driving mode at least includes a pure electric driving mode, a hybrid driving mode and a brake electric energy recovery mode.

[0088] By using the multi-source data fusion and processing mode, the technical scheme of the application achieves the purpose of accurately predicting the energy demand of the vehicle by comprehensively analyzing the working condition information of the target vehicle, the user preference data and the real-time external environment information, thereby realizing dynamic optimization of the control strategy to adapt to the pure electric driving, hybrid driving and brake energy recovery and other driving modes, and further solving the technical problems of poor energy management pertinence, response lag and inability to effectively respond to multi-mode switching scenarios caused by single data dimension, insufficient predictability and lack of control strategy flexibility.

[0089] Optionally, specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, and the embodiment will not be described here.

[0090] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0091] In the above-mentioned embodiments of the application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0092] In several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit described as the division is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, and can be electrical or other forms.

[0093] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0094] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0095] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0096] The above is only the preferred embodiment of the present application, it should be noted that for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A control method of a vehicle, characterized by, The method comprises the following steps: acquiring working condition information of a target vehicle, wherein the working condition information at least comprises one of the following: state of charge information of a power battery of the target vehicle, engine state, speed, brake signal; in a case where it is determined that the target vehicle meets a target state based on the working condition information, acquiring data information of the target vehicle and acquiring external environment information in which the target vehicle is currently located, wherein the data information of the target vehicle comprises charging time preference, driving route preference and driving mode preference of a target object, and the external environment information comprises road condition information of a driving route of the target vehicle and current electricity price information; performing noise reduction and completion processing on the data information of the target vehicle and the external environment information to obtain cleaned data after noise reduction and completion, wherein the cleaned data comprises driving route congestion information, battery state of charge information and engine working condition information; predicting energy demand information in a preset time period based on the cleaned data; generating a control strategy set based on the energy demand information, wherein the control strategy set is used to control the target vehicle to execute a target driving mode, and the target driving mode at least comprises a pure electric driving mode, a hybrid driving mode and a brake electric energy recovery mode.

2. The control method according to claim 1, characterized by, The noise reduction and completion processing on the data information and the external environment information to obtain the cleaned data after noise reduction and completion comprises: identifying a type of the external environment information, converting unstructured type external environment information into a target data type, and obtaining the external environment information of the cleaned data in a pre-set structured type.

3. The control method according to claim 1 or 2, characterized by, The noise reduction and completion processing on the data information and the external environment information to obtain the cleaned data after noise reduction and completion comprises: in a case where it is determined that the external environment information comprises information of a road condition description type, converting the information of the road condition description type into congestion coefficient data in a structured type.

4. The control method according to claim 1, characterized by, The prediction of the energy demand information in the preset time period based on the cleaned data comprises: acquiring distance information of the driving route; determining a time length for passing through the driving route and a passing speed of the target vehicle through the driving route based on the distance information and the congestion information; determining the energy demand information based on the time length and the passing speed, wherein the energy demand information comprises electric quantity information required for passing through the driving route.

5. The control method according to claim 4, characterized by The generation of the control strategy set based on the energy demand information comprises: in a case where the electric quantity information required for passing through the driving route is determined, acquiring current state of charge information of the power battery; in a case where it is determined that the current state of charge information of the power battery meets the passing through the driving route, generating a first control strategy in the control strategy set, wherein the first control strategy is used to control the target vehicle to execute a pure electric driving mode in the target driving mode.

6. The control method according to claim 5, characterized by The generation of the first control strategy in the control strategy set based on the cleaned data in a case where it is determined that the current state of charge information of the power battery meets the passing through the driving route comprises: acquiring predicted acceleration time length of the target vehicle and current electricity price information in response to executing the first control strategy; In a case where the predicted acceleration time length and the current electricity price information satisfy a preset condition, a second control strategy in the control strategy set is generated after a preset time length, and the second control strategy is used to control the engine to work and charge the power battery.

7. The control method according to claim 6, characterized by In a case where the predicted acceleration time length and the current electricity price information satisfy a preset condition, the second control strategy in the control strategy set is generated after the preset time length, including: In a case where the predicted acceleration time length is less than or equal to a first preset value, and the current electricity price information is less than or equal to a second preset value, the second control strategy in the control strategy set is generated after a time length of the first preset value.

8. The control method according to claim 1, characterized by, The control strategy set is generated based on the energy demand information, including: State information of the power battery after the target vehicle executes the target driving mode each time is recorded, and the state information of the power battery includes actual energy consumption of the power battery, battery temperature information, and power amount increment information of the power battery.

9. The control method according to claim 5, characterized by, In a case where the target vehicle satisfies a target state based on the working condition information, the data information of the target vehicle is acquired, including: Whether the target vehicle is in a starting state is judged based on the engine state and the power supply state of the power battery in the working condition information. In a case where it is confirmed that the target vehicle is in the starting state, the data information of the target vehicle is acquired.

10. A vehicle characterized by comprising: The vehicle is controlled by the control method in any one of claims 1 to 9.

Images