Energy management method for vehicles

Abstract

The present application relates to the field of new energy vehicle detection technology, and in particular to a vehicle energy management method, wherein the method comprises: obtaining operating condition data corresponding to at least one vehicle under different operating conditions; segmenting the road during which the vehicle is traveling to obtain section operating condition data corresponding to different road sections; calculating the SOC value of at least one vehicle that meets preset optimal conditions under the corresponding operating conditions; using the SOC value and operating condition data that meet the preset optimal conditions to train a pre-built CNN-LSTM global SOC planning model to obtain a trained CNN-LSTM global SOC planning model, and predicting the SOC value of the vehicle based on the trained CNN-LSTM global SOC planning model to achieve vehicle energy management. Thus, the method solves the problems in the related technology such as the inability to adapt to complex traffic environments and operating conditions, the low degree of intelligence, the low energy utilization rate, and the inability to effectively improve fuel economy.

Description

Technical Field

[0001] The present application relates to the technical field of new energy vehicle detection, and in particular to a vehicle energy management method. Background Art

[0002] This vehicle combines the advantages of traditional internal combustion engines and electric drive systems, providing a long driving range while effectively reducing environmental pollution. With technological advancements, the automotive industry is gradually entering an era of intelligence and connectivity. This allows the control strategies of automotive components and systems to be effectively integrated with ITS (Intelligent Transport System). Integrating real-time vehicle status information, operating data, and traffic information into the energy management strategy of extended-range hybrid vehicles can significantly enhance operating adaptability and thus improve fuel economy.

[0003] In related technologies, an LSTM (Long Short-Term Memory) vehicle speed prediction model can be constructed based on traffic information obtained from an intelligent transportation system, and the global on-chip system SOC (State of Charge) can be planned through a target model, thereby establishing a relationship between the adaptive equivalent factor and the on-chip system SOC, and obtaining the optimal control quantity by solving the ECMS (Equivalent Consumption Minimization Strategy). Alternatively, the optimal equivalent factors of different categories can be derived based on the DP algorithm and the ECMS strategy, and a numerical library of torque, SOC, and equivalent factors under different road section categories and different battery SOCs can be constructed. The optimal equivalent factor for adaptive working conditions can be obtained by combining vehicle speed information with the equivalent factor expression, thereby performing energy management of hybrid vehicles with variable equivalent factors.

[0004] However, related technologies are unable to adapt to complex traffic environments and working conditions, the vehicle energy scheduling is not highly intelligent, and the energy utilization rate is low, which leads to the inability to effectively improve fuel economy and urgently needs improvement. Summary of the Invention

[0005] The present application provides a vehicle energy management method to solve the problems in related technologies, such as the inability to adapt to complex traffic environments and working conditions, low intelligence level, low energy utilization rate, and inability to effectively improve fuel economy.

[0006] A first aspect embodiment of the present application provides a vehicle energy management method, which is applied to a model offline training stage, wherein the method includes the following steps: obtaining operating condition data corresponding to at least one vehicle under different operating conditions; based on the operating condition data, segmenting the road on which the vehicle is traveling to obtain section operating condition data corresponding to different road sections; based on the section operating condition data, calculating the SOC value of the at least one vehicle that meets preset optimal conditions under the corresponding operating conditions; using the SOC value that meets the preset optimal conditions and the operating condition data to train a pre-constructed CNN (Convolutional Neural Network)-LSTM global SOC planning model to obtain a trained CNN-LSTM global SOC planning model, and predicting the SOC value of the vehicle based on the trained CNN-LSTM global SOC planning model to achieve energy management of the vehicle.

[0007] Through the above technical solution, the road can be segmented according to the corresponding operating condition data under different operating conditions obtained by the vehicle, and then the section operating condition data corresponding to different road sections can be obtained, and then the SOC value of the vehicle that meets certain optimal conditions under the corresponding operating conditions can be calculated, and then the pre-built CNN-LSTM global SOC planning model can be trained, so that the trained CNN-LSTM global SOC planning model can be used to predict the SOC value of the vehicle to realize vehicle energy management, so that the vehicle can dynamically optimize the energy use strategy according to different operating conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the range extender power output. It can not only optimize the energy management of a single vehicle, but also may provide real-time scheduling support for a wider range of fleets or transportation systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions.

[0008] Optionally, in one embodiment of the present application, segmenting the road during the vehicle's driving process based on the operating condition data includes: determining at least one of the average vehicle speed, road section length and road section congestion level of the vehicle during the driving process based on the operating condition data; judging whether the vehicle speed change rate at different positions is greater than a preset value based on the average vehicle speed and the road section length, and / or judging whether the road section congestion level meets a preset condition based on the road section congestion level and the road section length; if the vehicle speed change rate is greater than the preset value, segmenting the corresponding road according to the average vehicle speed and the road section length, and / or, if the road section congestion level meets the preset condition, segmenting the corresponding road according to the road section congestion level and the road section length; if the vehicle speed change rate is less than or equal to the preset value, the corresponding road is not segmented, and / or, if the road section congestion level does not meet the preset condition, the corresponding road is not segmented.

[0009] Through the above technical solution, it is possible to judge whether the speed change rate of the vehicle at different positions is greater than a preset value based on at least one of the average speed of the vehicle, the length of the road section and the congestion level of the road section during driving, and when the speed change rate is greater than a certain value, the corresponding road is segmented according to the average speed and the length of the road section, otherwise, it is not segmented; and / or whether the congestion level of the road section meets certain conditions, and when the congestion level of the road section meets certain conditions, the corresponding road is segmented according to the congestion level and the length of the road section, otherwise, it is not segmented. By calculating the average speed and congestion level of different road sections, the actual traffic conditions of the road can be reflected more accurately, the accuracy and refinement of the data can be improved, and then dynamic adjustment strategies can be formulated to achieve reasonable resource allocation, optimize traffic management and control, and promote the development of intelligent transportation systems.

[0010] Optionally, in one embodiment of the present application, obtaining the corresponding operating condition data of at least one vehicle under different operating conditions includes: obtaining the initial driving data of the at least one vehicle under the corresponding operating conditions; obtaining the initial road data of the at least one vehicle under the corresponding operating conditions; processing the initial driving data and the initial road data respectively to obtain corresponding driving data and road data; and obtaining the operating condition data based on the driving data and the road data.

[0011] Through the above technical solution, the initial driving data and initial road data of the vehicle under the corresponding working conditions can be processed to obtain the corresponding driving data and road data, thereby obtaining the working condition data. By fine-tuning the data, the data dimension can be reduced, the computational complexity can be reduced, and key information can be retained, thereby improving the model training efficiency and the model training quality. In addition, the working condition data combines driving data and road data, and the data dimensions are fully covered, which can better adapt to different driving scenarios, avoid overfitting problems caused by single data, and improve the generalization ability in practical applications.

[0012] Optionally, in one embodiment of the present application, before using the SOC value that meets the preset optimal conditions and the operating condition data to train the pre-constructed CNN-LSTM global SOC planning model, it also includes: using the SOC value that meets the preset optimal conditions and the operating condition data to construct the input feature matrix of the CNN-LSTM global SOC planning model; based on the input feature matrix, determining the CNN feature extraction layer of the CNN-LSTM global SOC planning model; using the CNN feature extraction layer to obtain the output one-dimensional vector corresponding to the input feature matrix; based on the output one-dimensional vector, determining the LSTM network of the CNN-LSTM global SOC planning model; using the CNN feature extraction layer and the LSTM network to construct the CNN-LSTM global SOC planning model.

[0013] Through the above technical solution, the SOC values ​​and operating condition data that meet certain optimal conditions can be used to construct the input feature matrix of the CNN-LSTM global SOC planning model, and then the CNN feature extraction layer can be determined. The CNN feature extraction layer is used to generate an output one-dimensional vector, thereby determining the LSTM network, and then constructing the CNN-LSTM global SOC planning model. Through multi-source data fusion, the vehicle's operating status and external environment can be more comprehensively reflected, providing the model with richer information. The CNN feature extraction layer is used to automatically extract spatial and temporal features in the input feature matrix, capture the change pattern of the SOC value under different operating conditions, improve the expressive ability of the model, and use the LSTM network to capture long-term dependencies in the time series, improve the prediction accuracy, and then combine CNN and LSTM to achieve globally optimal SOC planning.

[0014] Optionally, in one embodiment of the present application, determining the LSTM network of the CNN-LSTM global SOC planning model based on the output one-dimensional vector includes: determining the input gate of the LSTM network based on the output one-dimensional vector; obtaining the cell state and hidden state of the LSTM network; determining the forget gate of the LSTM network based on the input gate and the hidden state; determining the output gate of the LSTM network based on the input gate, the cell state, the hidden state and the forget gate; and obtaining the LSTM network using the input gate, the cell state, the hidden state, the forget gate and the output gate.

[0015] Through the above technical solution, the input gate of the LSTM network can be determined based on the output one-dimensional vector, and the cell state and hidden state of the LSTM network can be obtained, and the forget gate and output gate can be determined to construct the LSTM network. Through the gating mechanism of the LSTM network, the operating condition data and the SOC value that meets certain optimal conditions are deeply integrated into the LSTM network design, which significantly improves the LSTM network's modeling ability for the dynamic characteristics of SOC, adaptability to complex working conditions, and interpretability, thereby realizing accurate prediction of SOC and efficient management of vehicle energy.

[0016] Optionally, in one embodiment of the present application, the SOC value that meets the preset optimal conditions and the operating condition data are used to train the pre-constructed CNN-LSTM global SOC planning model to obtain a trained CNN-LSTM global SOC planning model, including: obtaining the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate of the Adam (Adaptive Moment Estimation) optimizer corresponding to the training of the pre-constructed CNN-LSTM global SOC planning model; based on the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate, training the pre-constructed CNN-LSTM global SOC planning model until the pre-constructed CNN-LSTM global SOC planning model meets the preset training conditions to obtain the trained CNN-LSTM global SOC planning model.

[0017] Through the above technical solution, the Adam optimizer can be used to train the pre-built CNN-LSTM global SOC planning model until certain training conditions are met, thereby obtaining a trained CNN-LSTM global SOC planning model. The Adam optimizer can automatically adjust the learning rate according to different parameters and training stages, avoiding the tedious process of manually adjusting the learning rate, improving training efficiency and model performance, and when training the pre-built CNN-LSTM global SOC planning model, it can find the optimal solution more quickly, reduce training time, effectively deal with the problems of gradient vanishing and gradient exploding, and improve the stability and robustness of the model.

[0018] Optionally, in one embodiment of the present application, the SOC value of the vehicle is predicted based on the trained CNN-LSTM global SOC planning model to achieve energy management of the vehicle, including: determining the energy consumption per unit distance of the vehicle on the corresponding road section based on the SOC value; constructing an energy management database corresponding to the vehicle using the road section operating condition data, the SOC value and the energy consumption per unit distance; and generating an energy management strategy for the vehicle using the energy management database to achieve energy management of the vehicle.

[0019] Through the above technical solution, the energy consumption per unit distance of the vehicle on the corresponding road section can be determined based on the SOC value, and then the road section operating condition data, SOC value and unit distance energy consumption can be used to build an energy management database, and the energy management database can be used to generate the vehicle's energy management strategy to achieve vehicle energy management. The energy management database can store energy consumption information on different sections and different operating conditions, realize refined monitoring and management of vehicle energy consumption, avoid energy waste, improve decision-making scientificity, optimize energy utilization efficiency, and enhance strategy adaptability and robustness.

[0020] The second aspect of the present application provides a vehicle energy management method, which is applied to the online application stage of the model, wherein the method includes the following steps: obtaining actual operating condition data of the vehicle under different operating conditions; based on the actual operating condition data, segmenting the road on which the vehicle is traveling to obtain actual section operating condition data corresponding to different road sections; inputting the starting SOC value corresponding to the actual section operating condition data into a trained CNN-LSTM global SOC planning model to obtain the ending SOC value of the vehicle on the corresponding road section, wherein the trained CNN-LSTM global SOC planning model is trained by the starting SOC value and the actual section operating condition data; controlling the power output of the vehicle according to the starting SOC value or the ending SOC value to achieve energy management of the vehicle.

[0021] Through the above technical solution, the road where the vehicle is traveling can be segmented based on the actual operating condition data obtained, and then the actual road section operating condition data corresponding to different road sections can be obtained. The output of the trained CNN-LSTM global SOC planning model can be used to obtain the vehicle's terminal SOC value on the corresponding road section, and then the vehicle's power output can be controlled according to the starting SOC value or the ending SOC value to achieve vehicle energy management. Through segmented prediction, error accumulation can be suppressed and the SOC prediction error can be reduced. According to the actual operating condition data received in real time, the SOC prediction value can be dynamically adjusted to reduce the prediction delay and meet real-time requirements. Energy management can be adaptively managed according to different operating conditions to improve driving comfort, extend battery life, and enhance safety.

[0022] The third aspect of the present application provides an energy management device for a vehicle, which is applied to the offline training stage of a model, wherein the device includes: a first acquisition module, used to obtain operating condition data corresponding to at least one vehicle under different operating conditions; a first segmentation module, used to segment the road on which the vehicle is traveling based on the operating condition data, so as to obtain section operating condition data corresponding to different road sections; a first calculation module, used to calculate the SOC value of the at least one vehicle that meets preset optimal conditions under the corresponding operating conditions based on the section operating condition data; a prediction module, used to use the SOC value that meets the preset optimal conditions and the operating condition data to train a pre-constructed CNN-LSTM global SOC planning model to obtain a trained CNN-LSTM global SOC planning model, and predict the SOC value of the vehicle based on the trained CNN-LSTM global SOC planning model to achieve energy management of the vehicle.

[0023] Through the above technical solution, the road can be segmented according to the corresponding operating condition data under different operating conditions obtained by the vehicle, and then the section operating condition data corresponding to different road sections can be obtained, and then the SOC value of the vehicle that meets certain optimal conditions under the corresponding operating conditions can be calculated, and then the pre-built CNN-LSTM global SOC planning model can be trained, so that the trained CNN-LSTM global SOC planning model can be used to predict the SOC value of the vehicle to realize vehicle energy management, so that the vehicle can dynamically optimize the energy use strategy according to different operating conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the range extender power output. It can not only optimize the energy management of a single vehicle, but also may provide real-time scheduling support for a wider range of fleets or transportation systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions.

[0024] Optionally, in one embodiment of the present application, the first segmentation module includes: a first determination unit, used to determine at least one of the average vehicle speed, road section length and road section congestion level of the vehicle during driving based on the operating condition data; a judgment unit, used to judge whether the vehicle speed change rate at different positions is greater than a preset value based on the average vehicle speed and the road section length, and / or, based on the road section congestion level and the road section length, judge whether the road section congestion level meets a preset condition; the first segmentation unit is used to segment the corresponding road according to the average vehicle speed and the road section length when the vehicle speed change rate is greater than the preset value, and / or, if the road section congestion level meets the preset condition, segment the corresponding road according to the road section congestion level and the road section length; the second segmentation unit is used to not segment the corresponding road when the vehicle speed change rate is less than or equal to the preset value, and / or, if the road section congestion level does not meet the preset condition, not segment the corresponding road.

[0025] Through the above technical solution, it is possible to judge whether the speed change rate of the vehicle at different positions is greater than a preset value based on at least one of the average speed of the vehicle, the length of the road section and the congestion level of the road section during driving, and when the speed change rate is greater than a certain value, the corresponding road is segmented according to the average speed and the length of the road section, otherwise, it is not segmented; and / or whether the congestion level of the road section meets certain conditions, and when the congestion level of the road section meets certain conditions, the corresponding road is segmented according to the congestion level and the length of the road section, otherwise, it is not segmented. By calculating the average speed and congestion level of different road sections, the actual traffic conditions of the road can be reflected more accurately, the accuracy and refinement of the data can be improved, and then dynamic adjustment strategies can be formulated to achieve reasonable resource allocation, optimize traffic management and control, and promote the development of intelligent transportation systems.

[0026] Optionally, in one embodiment of the present application, the first acquisition module includes: a first acquisition unit, used to obtain the initial driving data of the at least one vehicle under the corresponding working conditions; a second acquisition unit, used to obtain the initial road data of the at least one vehicle under the corresponding working conditions; a processing unit, used to process the initial driving data and the initial road data respectively to obtain corresponding driving data and road data; and a generation unit, used to obtain the working condition data based on the driving data and the road data.

[0027] Through the above technical solution, the initial driving data and initial road data of the vehicle under the corresponding working conditions can be processed to obtain the corresponding driving data and road data, thereby obtaining the working condition data. By fine-tuning the data, the data dimension can be reduced, the computational complexity can be reduced, and key information can be retained, thereby improving the model training efficiency and the model training quality. In addition, the working condition data combines driving data and road data, and the data dimensions are fully covered, which can better adapt to different driving scenarios, avoid overfitting problems caused by single data, and improve the generalization ability in practical applications.

[0028] Optionally, in one embodiment of the present application, it also includes: a first construction module, used to construct the input feature matrix of the CNN-LSTM global SOC planning model using the SOC value that meets the preset optimal conditions and the operating condition data before training the pre-constructed CNN-LSTM global SOC planning model using the SOC value that meets the preset optimal conditions and the operating condition data; a first determination module, used to determine the CNN feature extraction layer of the CNN-LSTM global SOC planning model based on the input feature matrix; a first generation module, used to use the CNN feature extraction layer to obtain the output one-dimensional vector corresponding to the input feature matrix; a second determination module, used to determine the LSTM network of the CNN-LSTM global SOC planning model based on the output one-dimensional vector; a second construction module, used to construct the CNN-LSTM global SOC planning model using the CNN feature extraction layer and the LSTM network.

[0029] Through the above technical solution, the SOC values ​​and operating condition data that meet certain optimal conditions can be used to construct the input feature matrix of the CNN-LSTM global SOC planning model, and then the CNN feature extraction layer can be determined. The CNN feature extraction layer is used to generate an output one-dimensional vector, thereby determining the LSTM network, and then constructing the CNN-LSTM global SOC planning model. Through multi-source data fusion, the vehicle's operating status and external environment can be more comprehensively reflected, providing the model with richer information. The CNN feature extraction layer is used to automatically extract spatial and temporal features in the input feature matrix, capture the change pattern of the SOC value under different operating conditions, improve the expressive ability of the model, and use the LSTM network to capture long-term dependencies in the time series, improve the prediction accuracy, and then combine CNN and LSTM to achieve globally optimal SOC planning.

[0030] Optionally, in one embodiment of the present application, the second determination module includes: a second determination unit, used to determine the input gate of the LSTM network based on the output one-dimensional vector; a third acquisition unit, used to acquire the cell state and hidden state of the LSTM network; a third determination unit, used to determine the forget gate of the LSTM network based on the input gate and the hidden state; a fourth determination unit, used to determine the output gate of the LSTM network based on the input gate, the cell state, the hidden state and the forget gate; a second generation unit, used to obtain the LSTM network using the input gate, the cell state, the hidden state, the forget gate and the output gate.

[0031] Through the above technical solution, the input gate of the LSTM network can be determined based on the output one-dimensional vector, and the cell state and hidden state of the LSTM network can be obtained, and the forget gate and output gate can be determined to construct the LSTM network. Through the gating mechanism of the LSTM network, the operating condition data and the SOC value that meets certain optimal conditions are deeply integrated into the LSTM network design, which significantly improves the LSTM network's modeling ability for the dynamic characteristics of SOC, adaptability to complex working conditions, and interpretability, thereby realizing accurate prediction of SOC and efficient management of vehicle energy.

[0032] Optionally, in one embodiment of the present application, the prediction module includes: a fourth acquisition unit, used to obtain the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate of the Adam optimizer corresponding to the training of the pre-constructed CNN-LSTM global SOC planning model; a training unit, used to train the pre-constructed CNN-LSTM global SOC planning model based on the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate until the pre-constructed CNN-LSTM global SOC planning model meets the preset training conditions to obtain the trained CNN-LSTM global SOC planning model.

[0033] Through the above technical solution, the Adam optimizer can be used to train the pre-built CNN-LSTM global SOC planning model until certain training conditions are met, thereby obtaining a trained CNN-LSTM global SOC planning model. The Adam optimizer can automatically adjust the learning rate according to different parameters and training stages, avoiding the tedious process of manually adjusting the learning rate, improving training efficiency and model performance, and when training the pre-built CNN-LSTM global SOC planning model, it can find the optimal solution more quickly, reduce training time, effectively deal with the problems of gradient vanishing and gradient exploding, and improve the stability and robustness of the model.

[0034] Optionally, in one embodiment of the present application, the prediction module includes: a fifth determination unit, used to determine the energy consumption per unit distance of the vehicle on the corresponding road section based on the SOC value; a third construction unit, used to construct an energy management database corresponding to the vehicle using the road section operating condition data, the SOC value and the energy consumption per unit distance; and a third generation unit, used to generate an energy management strategy for the vehicle using the energy management database to achieve energy management of the vehicle.

[0035] Through the above technical solution, the energy consumption per unit distance of the vehicle on the corresponding road section can be determined based on the SOC value, and then the road section operating condition data, SOC value and unit distance energy consumption can be used to build an energy management database, and the energy management database can be used to generate the vehicle's energy management strategy to achieve vehicle energy management. The energy management database can store energy consumption information on different sections and different operating conditions, realize refined monitoring and management of vehicle energy consumption, avoid energy waste, improve decision-making scientificity, optimize energy utilization efficiency, and enhance strategy adaptability and robustness.

[0036] The fourth aspect of the present application provides an energy management device for a vehicle, which is applied to the online application stage of a model, wherein the device includes: a second acquisition module, used to obtain actual operating condition data of the vehicle under different operating conditions; a second segmentation module, used to segment the road on which the vehicle is traveling based on the actual operating condition data, so as to obtain actual section operating condition data corresponding to different road sections; a second generation module, used to input the starting SOC value corresponding to the actual section operating condition data into a trained CNN-LSTM global SOC planning model, so as to obtain the ending SOC value of the vehicle on the corresponding road section, wherein the trained CNN-LSTM global SOC planning model is trained by the starting SOC value and the actual section operating condition data; a control module, used to control the power output of the vehicle according to the starting SOC value or the ending SOC value, so as to realize energy management of the vehicle.

[0037] Through the above technical solution, the road where the vehicle is traveling can be segmented based on the actual operating condition data obtained, and then the actual road section operating condition data corresponding to different road sections can be obtained. The output of the trained CNN-LSTM global SOC planning model can be used to obtain the vehicle's terminal SOC value on the corresponding road section, and then the vehicle's power output can be controlled according to the starting SOC value or the ending SOC value to achieve vehicle energy management. Through segmented prediction, error accumulation can be suppressed and the SOC prediction error can be reduced. According to the actual operating condition data received in real time, the SOC prediction value can be dynamically adjusted to reduce the prediction delay and meet real-time requirements. Energy management can be adaptively managed according to different operating conditions to improve driving comfort, extend battery life, and enhance safety.

[0038] The fifth aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle energy management method as described in the above embodiment.

[0039] The sixth aspect of the present application provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-mentioned vehicle energy management method.

[0040] The seventh aspect embodiment of the present application provides a computer program product, including a computer program, which implements the above vehicle energy management method when executed.

[0041] The embodiment of the present application can segment the road according to the corresponding working condition data under different working conditions obtained by the vehicle, and then obtain the section working condition data corresponding to different road sections, and then calculate the SOC value of the vehicle that meets certain optimal conditions under the corresponding working conditions, and then train the pre-built CNN-LSTM global SOC planning model, so as to use the trained CNN-LSTM global SOC planning model to predict the SOC value of the vehicle, realize the energy management of the vehicle, so that the vehicle can dynamically optimize the energy use strategy according to different working conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the power output of the range extender. It can not only optimize the energy management of a single vehicle, but also provide real-time scheduling support for a wider range of fleets or traffic systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions. Therefore, it solves the problems in the related art that it cannot adapt to complex traffic environments and working conditions, has a low degree of intelligence, has low energy utilization, and cannot effectively improve fuel economy.

[0042] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0044] Figure 1 This is a flow chart of a vehicle energy management method provided according to an embodiment of the present application;

[0045] Figure 2 A flowchart of obtaining operating condition data according to one embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of a CNN-LSTM network provided according to one embodiment of the present application;

[0047] Figure 4 A schematic diagram of the structure of a pre-trained CNN-LSTM global SOC planning model provided according to one embodiment of the present application;

[0048] Figure 5 A block diagram of an energy management device for a vehicle according to an embodiment of the present application;

[0049] Figure 6 This is a flowchart of a vehicle energy management method provided according to another embodiment of the present application;

[0050] Figure 7 A flowchart of the working principle of a vehicle energy management method provided according to another embodiment of the present application;

[0051] Figure 8 This is a block diagram of an energy management device for a vehicle according to another embodiment of the present application;

[0052] Figure 9 A schematic structural diagram of a vehicle provided according to an embodiment of the present application.

[0053] Reference numerals:

[0054] Among them, 50 is the vehicle's energy management device; 501 is the first acquisition module, 502 is the first segmentation module, 503 is the first calculation module, 504 is the prediction module; 80 is the vehicle's energy management device; 801 is the second acquisition module, 802 is the second segmentation module, 803 is the second generation module, 804 is the control module; 901 is the memory, 902 is the processor, 903 is the communication interface. DETAILED DESCRIPTION

[0055] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0056] The energy management method for a vehicle according to an embodiment of the present application will be described below with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, such as the inability to adapt to complex traffic environments and operating conditions, low intelligence, low energy utilization, and inability to effectively improve fuel economy, the present application provides a vehicle energy management method. In this method, the road can be segmented based on the operating condition data corresponding to different operating conditions obtained by the vehicle, and then the section operating condition data corresponding to different road sections can be obtained. The SOC value of the vehicle that meets certain optimal conditions under the corresponding operating conditions is calculated, and a pre-built CNN-LSTM global SOC planning model is then trained. The trained CNN-LSTM global SOC planning model is then used to predict the vehicle's SOC value to achieve vehicle energy management, so that the vehicle can dynamically optimize the energy usage strategy according to different operating conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the range extender power output. This method can not only optimize the energy management of a single vehicle, but may also provide real-time scheduling support for a wider range of fleets or transportation systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions. This solves the problems in related technologies, such as the inability to adapt to complex traffic environments and working conditions, low intelligence level, low energy utilization rate, and inability to effectively improve fuel economy.

[0057] Specifically, Figure 1 This is a flowchart of a vehicle energy management method provided according to an embodiment of the present application.

[0058] like Figure 1 As shown, the vehicle energy management method is applied to the model offline training stage, wherein the method includes the following steps:

[0059] In step S101, operating condition data corresponding to at least one vehicle under different operating conditions is obtained.

[0060] It can be understood that in the embodiments of the present application, the operating condition data may include, but is not limited to, driving data of the driver's travel conditions collected using a GPS (Global Positioning System) receiver, road data provided by a map API (Application Programming Interface), etc., and this application does not impose specific restrictions.

[0061] Furthermore, in the embodiments of the present application, different operating conditions may include but are not limited to urban operating conditions, high-speed operating conditions and mountainous operating conditions, and the present application does not impose specific restrictions; among them, under urban operating conditions, the roads are relatively congested, the traffic lights are relatively dense, the vehicle travels at a low speed, and starts and stops frequently; under high-speed operating conditions, the roads are relatively flat, the traffic lights are relatively sparse, and the vehicle travels stably at a high speed; under mountainous operating conditions, there are a large number of climbing and downhill roads, and the vehicle ensures safe driving.

[0062] As a possible implementation method, the embodiment of the present application can obtain corresponding operating condition data of at least one vehicle under different operating conditions.

[0063] Illustratively, the embodiment of the present application can obtain operating condition data through driving data collected by a GPS receiver and road data provided by a map API.

[0064] Optionally, in one embodiment of the present application, obtaining corresponding operating condition data of at least one vehicle under different operating conditions includes: obtaining initial driving data of at least one vehicle under corresponding operating conditions; obtaining initial road data of at least one vehicle under corresponding operating conditions; processing the initial driving data and the initial road data respectively to obtain corresponding driving data and road data; and obtaining operating condition data based on the driving data and road data.

[0065] It can be understood that in the embodiments of the present application, the initial driving data may include but is not limited to the vehicle speed, acceleration, battery SOC, rotation speed, etc., and the present application does not impose specific restrictions; the initial road data may include but is not limited to congestion conditions, road length, remaining mileage, traffic light position, etc., and the present application does not impose specific restrictions.

[0066] During the actual implementation process, the embodiment of the present application can use a GPS receiver to collect initial driving data, process it, and extract operating condition curves, such as the changing trends of vehicle speed, acceleration, battery SOC, etc. over time or mileage, to obtain corresponding driving data, and use the map API to obtain initial road data, wherein the initial road data may include but is not limited to road congestion conditions (smooth, awakening, congested, severe congestion), road length, etc., and this application does not make specific restrictions, and process it to obtain corresponding road data. Furthermore, the embodiment of the present application generates operating condition data based on driving data and road data.

[0067] For example, combined Figure 2As shown, embodiments of the present application can utilize a GPS receiver to collect initial driving data, including average vehicle speed and battery SOC, which are not specifically limited in this application. Initial road data provided by a map API can also be collected, including road congestion conditions (smooth, slow, congested, severely congested), road length, and other information, which are not specifically limited in this application. Furthermore, embodiments of the present application process the initial driving data and initial road data, and combine them with historical data to construct operating condition data comprising 30 sets of operating conditions, which largely cover daily usage scenarios.

[0068] In step S102 , based on the operating condition data, the road on which the vehicle is traveling is divided into sections to obtain section operating condition data corresponding to different road sections.

[0069] It can be understood that the embodiments of the present application can segment the road according to the vehicle speed change rate, road section length and road section congestion level. The specific settings can be made by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0070] During actual implementation, the embodiment of the present application can segment the road during vehicle driving, and then obtain road condition data corresponding to different road sections.

[0071] Optionally, in one embodiment of the present application, the road on which the vehicle is traveling is segmented based on the operating condition data, including: determining at least one of the average vehicle speed, section length and section congestion level of the vehicle during the driving process based on the operating condition data; judging whether the vehicle speed change rate at different positions is greater than a preset value based on the average vehicle speed and section length, and / or judging whether the section congestion level meets preset conditions based on the section congestion level and section length; if the vehicle speed change rate is greater than the preset value, the corresponding road is segmented according to the average vehicle speed and section length, and / or, if the section congestion level meets the preset conditions, the corresponding road is segmented according to the section congestion level and section length; if the vehicle speed change rate is less than or equal to the preset value, the corresponding road is not segmented, and / or, if the section congestion level does not meet the preset conditions, the corresponding road is not segmented.

[0072] In some embodiments, the present application can segment roads according to the average speed of vehicles during travel, the length of road sections, and the congestion level of road sections. The content can be:

[0073] In some embodiments, the present application can determine whether the rate of change of vehicle speed at different locations is greater than a certain value based on average vehicle speed and road segment length. If the rate of change is greater than the certain value, the corresponding road is segmented based on the average vehicle speed and road segment length. If the rate of change is less than or equal to a preset value, the corresponding road is not segmented. The certain value can be set by those skilled in the art based on actual conditions and is not specifically limited by this application.

[0074] For example, the embodiment of the present application can improve the road segmentation method of the static API map by introducing a dynamic adaptive segmentation mechanism to further segment the road, the content of which is as follows:

[0075] In this embodiment of the present application, road segment features may be extracted based on operating condition data. The information contained in each API road segment may include, but is not limited to:

[0076] ,

[0077] in, express The average speed of the road section, express The length of the road segment, express The segment congestion level of the road segment.

[0078] Furthermore, the embodiment of the present application can segment the road during which the vehicle is traveling into multiple sub-segments, and the judgment conditions are as follows:

[0079] If the speed change rate of two adjacent sampling points is greater than a certain value, such as 0.2, segmentation is performed. The expression can be, but is not limited to, expressed as:

[0080] ,

[0081] in, represents the average vehicle speed at the previous sampling point, Indicates the average vehicle speed at the current sampling point.

[0082] Each adaptive road segment The input features are reconstructed as:

[0083] ,

[0084] It is then used to input the pre-built CNN-LSTM global SOC planning model to predict the SOC value.

[0085] In some embodiments, embodiments of the present application can determine whether a road segment's congestion level meets certain conditions based on the road segment's congestion level and length. If the road segment's congestion level meets certain conditions, the corresponding road is segmented based on the road segment's congestion level and length. If the road segment's congestion level does not meet certain conditions, the corresponding road is not segmented. The certain conditions can be set by those skilled in the art based on actual circumstances and are not specifically limited in this application.

[0086] For example, the embodiment of the present application can improve the road segmentation method of the static API map by introducing a dynamic adaptive segmentation mechanism to further segment the road, the content of which is as follows:

[0087] In this embodiment of the present application, road segment features may be extracted based on operating condition data. The information contained in each API road segment may include, but is not limited to:

[0088] ,

[0089] in, express The average speed of the road section, express The length of the road segment, express The segment congestion level of the road segment.

[0090] Furthermore, the embodiment of the present application can segment the road during which the vehicle is traveling into multiple sub-segments, and the judgment conditions are as follows:

[0091] If the congestion level of a road section meets certain conditions, such as .

[0092] Each adaptive road segment The input features are reconstructed as:

[0093] ,

[0094] It is then used to input the pre-built CNN-LSTM global SOC planning model to predict the SOC value.

[0095] In step S103, based on the road section operating condition data, the SOC value of at least one vehicle that meets the preset optimal conditions under the corresponding operating condition is calculated.

[0096] It can be understood that in the embodiments of the present application, the certain optimal condition can be understood as the SOC value corresponding to when the vehicle energy consumption is minimized. The specific setting can be made by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0097] As a possible implementation method, the embodiment of the present application can use the PMP (Pontryagin's Minimum Principle) algorithm to calculate the SOC value that meets certain optimal conditions under the corresponding working conditions based on the working condition data obtained by the vehicle, and use the SOC value that meets certain optimal conditions as a training sample for training a pre-built CNN-LSTM global SOC planning model.

[0098] Optionally, in one embodiment of the present application, before using the SOC value and operating condition data that meet the preset optimal conditions to train the pre-constructed CNN-LSTM global SOC planning model, it also includes: using the SOC value and operating condition data that meet the preset optimal conditions to construct the input feature matrix of the CNN-LSTM global SOC planning model; based on the input feature matrix, determining the CNN feature extraction layer of the CNN-LSTM global SOC planning model; using the CNN feature extraction layer to obtain the output one-dimensional vector corresponding to the input feature matrix; based on the output one-dimensional vector, determining the LSTM network of the CNN-LSTM global SOC planning model; and using the CNN feature extraction layer and the LSTM network to construct the CNN-LSTM global SOC planning model.

[0099] It is understood that in the embodiment of the present application, the CNN-LSTM global SOC planning model may include, but is not limited to, a CNN feature extraction layer, an LSTM network, and a fully connected layer, and the present application does not impose any specific restrictions. In the embodiment of the present application, a Dropout layer is set between the LSTM network output and the fully connected layer, and a regularization operation is introduced to effectively prevent the LSTM network from learning too fast and overfitting the training set, which is particularly important when the samples are limited. For example, in the embodiment of the present application, a Dropout (0.3) is introduced between the LSTM network output and the fully connected layer in the CNN-LSTM global SOC planning model to suppress the risk of overfitting, and the position is as follows: LSTM (64) → Dropout (0.3) → fully connected layer (1). In this case, the Dropout layer is not specific to a certain network (such as an LSTM network or a CNN-LSTM global SOC planning model), but is a general regularization method that can be inserted between any two layers.

[0100] In some embodiments, the process of constructing a CNN-LSTM global SOC planning model in an embodiment of the present application is as follows: First, the embodiment of the present application uses SOC values ​​and operating condition data that meet certain optimal conditions to construct the input feature matrix of the CNN-LSTM global SOC planning model, and then determines the CNN feature extraction layer to output a one-dimensional vector, and uses the output one-dimensional vector to determine the LSTM network, and then constructs the CNN-LSTM global SOC planning model.

[0101] For example, the embodiment of the present application can construct a length of The input time series is The input feature matrix can be expressed as but not limited to:

[0102] ,

[0103] in, Indicates the average speed of the current road section. Indicates the length of the current road section. Indicates the starting SOC, Indicates the remaining mileage. Indicates the congestion level, Indicates the global starting SOC.

[0104] Furthermore, the embodiment of the present application uses the CNN feature extraction layer to determine the output one-dimensional vector corresponding to the input feature matrix. It can be understood that the embodiment of the present application can use the CNN feature extraction layer to convert the input feature matrix into a one-dimensional vector of size The two-dimensional tensor is subjected to a one-dimensional convolution operation to extract the local pattern, and its expression can be but is not limited to:

[0105] ,

[0106] in, Indicates input, represents the convolution kernel, Represents a filter.

[0107] Then the local pattern output dimension is , and then flattened by the flattening layer to output a one-dimensional vector The output one-dimensional vector is input into the LSTM network for time dimension modeling, thereby obtaining the final time series encoding vector. The expression of the LSTM network output can be, but is not limited to:

[0108] ,

[0109] Furthermore, in the embodiment of the present application, the SOC value at the end of the next road segment can be predicted by fully connected layer regression, and its expression can be, but is not limited to,:

[0110] .

[0111] Optionally, in one embodiment of the present application, the input gate of the LSTM network is determined based on the output one-dimensional vector; the cell state and hidden state of the LSTM network are obtained; the forget gate of the LSTM network is determined based on the input gate and the hidden state; the output gate of the LSTM network is determined based on the input gate, cell state, hidden state and forget gate; and the LSTM network is obtained using the input gate, cell state, hidden state, forget gate and output gate.

[0112] It should be noted that the embodiments of the present application can be combined with Figure 3 The structure of the LSTM network is introduced as shown below. The LSTM network can remember information over a long time interval when processing sequence data. It can memorize historical information and apply it to the calculation of the current output.

[0113] Furthermore, the embodiments of the present application are Figure 3 middle, 、 They are Time and Next moment The input of the LSTM network at this moment, 、 、 Divided into time, Time and The cell state of the LSTM network at this moment, 、 、 They are time, Time and The output of the LSTM network at this moment, 、 They are Time and The state of controlling data transmission in the LSTM network at all times. These four variables become the input gate, cell state, output gate, and forget gate of the LSTM neural network respectively. for function.

[0114] Among them, the formula of the working mechanism of the LSTM network input gate of the embodiment of the present application is as follows, including the current sequence and the previous moment series , its expression can be but not limited to:

[0115] ,

[0116] The expression of the forget gate working mechanism can be, but is not limited to:

[0117] ,

[0118] The expression of the output gate working mechanism can be, but is not limited to:

[0119] ,

[0120] in, express The input of the LSTM network at this moment, express The output of the LSTM network at this moment, express function, 、 、 、 Represent different weight coefficients of LSTM network, 、 、 、 Respectively represent the corresponding bias of the LSTM network, express The cell state of the LSTM network at this moment.

[0121] Furthermore, in an embodiment of the present application, the LSTM global SOC planning model can predict and optimize the SOC reference trajectory, and introduce the input, cell state, output, and forgetting state in combination with the structure and working mechanism of the LSTM network.

[0122] Input variables express Time input, which may include but is not limited to road congestion , average speed of the road section , section length , SOC value at the beginning of the section , total remaining mileage and the starting SOC value of the working condition ; Input variables and Similar, indicating The input at the moment corresponds to the feature vector of the next road segment.

[0123] Cell state express The cell state at a certain moment is the state of the memory unit in the LSTM network, which is used to store historical information; express The cell state at a moment is the cell state after the current input and the previous state are updated; express The cell state at this moment is the cell state after the next input update.

[0124] Hidden State express The hidden state at the moment is the output of the LSTM network and is used to pass to the next time step; Indicates The hidden state at the moment is the output state of the current time step, reflecting the comprehensive result of the current input and historical information; express The hidden state at the moment is the output state of the next time step.

[0125] Forget Gate Indicates The moment-by-moment forget gate is used to decide which information in the cell state needs to be forgotten; express The forget gate at the moment is used to decide which information needs to be forgotten in the next time step.

[0126] Optionally, in one embodiment of the present application, a pre-constructed CNN-LSTM global SOC planning model is trained using SOC values ​​and operating condition data that meet preset optimal conditions to obtain a trained CNN-LSTM global SOC planning model, including: obtaining the first-order moment estimated exponential decay rate, second-order moment estimated exponential decay rate and learning rate of the Adam optimizer corresponding to the pre-constructed CNN-LSTM global SOC planning model for training; based on the first-order moment estimated exponential decay rate, second-order moment estimated exponential decay rate and learning rate, training the pre-constructed CNN-LSTM global SOC planning model until the pre-constructed CNN-LSTM global SOC planning model meets the preset training conditions to obtain a trained CNN-LSTM global SOC planning model.

[0127] It is understood that in the embodiment of the present application, the Adam optimizer can optimize all trainable parameters in the CNN-LSTM global SOC planning model, including the convolution kernel weights and biases of the convolution layer, the weight matrix and bias terms of each gate unit in the LSTM network structure, and the output weights and biases of the fully connected layer. By gradually minimizing the loss function, the model's fitting ability and convergence efficiency in the SOC prediction task are effectively improved.

[0128] Among them, the Adam optimizer used in the embodiment of the present application combines the advantages of the momentum method and RMSProp, and can realize adaptive gradient adjustment. The core parameters set can include but are not limited to the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate, etc. This application does not impose specific restrictions.

[0129] Among them, the first-order moment estimates the exponential decay rate The momentum used to control the gradient can be ; Second-order moment estimate exponential decay rate Reflects the weighted average of the squared gradient, which can be ; A small constant to prevent the denominator from being zero, used for numerical stability; the initial learning rate Set to , and dynamically adjust the learning rate using an exponential decay strategy: ,in, , for Among them, the embodiment of the present application uses a larger learning rate to accelerate convergence in the early stage of training, and reduces the stride to refine the weights in the later stage.

[0130] It should be noted that the embodiment of this application sets a dropout layer between the LSTM network output and the fully connected layer, with a dropout ratio of 0.3. During the training phase, 30% of the neuron outputs are randomly discarded to enhance the robustness of the model. After each round of training, the validation set loss is monitored. If the validation error does not decrease for 10 consecutive rounds, the training process is terminated early to avoid overfitting.

[0131] In addition, in order to prevent the gradient explosion problem, the embodiment of the present application performs truncation when the gradient norm of the back propagation is greater than 5.0. The expression thereof can be, but is not limited to,:

[0132] ,

[0133] This ensures the stability and numerical convergence of model parameter updates.

[0134] Through the above optimization strategy, the model training time is shortened by about 15%, and the mean square error loss of SOC prediction on the validation set is reduced by about 7.2% on average.

[0135] The expression of the mean square error loss function can be, but is not limited to,:

[0136] ,

[0137] in, Indicates the true value of SOC, Indicates the SOC prediction value.

[0138] Furthermore, the embodiment of the present application uses the Adam optimizer for training, with an initial learning rate of 0.001 and a self-driven momentum mechanism to improve the convergence speed.

[0139] The average SOC prediction error of the embodiment of the present application in the validation set decreased by 3.8%, and it was more sensitive to SOC trend changes under complex working conditions, thereby improving the prediction accuracy and robustness of the model.

[0140] In summary, the embodiments of the present application can use the Adam optimizer to train a pre-built CNN-LSTM global SOC planning model until the pre-built CNN-LSTM global SOC planning model meets certain training conditions, thereby obtaining a trained CNN-LSTM global SOC planning model. The certain training conditions can be set by those skilled in the art according to actual conditions and are not specifically limited in this application.

[0141] In step S104, the pre-built CNN-LSTM global SOC planning model is trained using the SOC value and operating condition data that meet the preset optimal conditions to obtain a trained CNN-LSTM global SOC planning model, and the SOC value of the vehicle is predicted based on the trained CNN-LSTM global SOC planning model to achieve vehicle energy management.

[0142] As a possible implementation method, the embodiment of the present application can train a pre-built CNN-LSTM global SOC planning model based on operating condition data using the SOC value that meets the preset optimal conditions, thereby obtaining a trained CNN-LSTM global SOC planning model, and then predicting the SOC value of the vehicle, thereby realizing vehicle energy management.

[0143] For example, the embodiments of the present application are combined with Figure 4 As shown, the predicted SOC value, its main contents are:

[0144] Step S401: construct training samples.

[0145] The embodiment of the present application can set the initial SOC values ​​based on 30 sets of working condition data. , the termination SOC is 0.3, and the PMP algorithm is used to solve the SOC value that meets certain optimal conditions under different starting SOC conditions for each group of working conditions. The 510 groups of SOC values ​​that meet certain optimal conditions are used as training samples for the pre-built CNN-LSTM global SOC planning model.

[0146] Step S402: Setting model parameters.

[0147] Among them, the embodiment of the present application divides the divided road sections into sections according to the map API for each group of SOC values ​​that meet certain optimal conditions (each working condition section is numbered as ), using a variable step size method to predict the terminal SOC at the end of each road section, setting the input of the model to 、 、 、 、 and , the output of the model is set to , set the learning rate of the model to 0.001, and the step length to the time interval between two road sections. The specific settings can be made by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0148] Step S403: training the model.

[0149] Among them, the embodiment of the present application can train a pre-built CNN-LSTM global SOC planning model based on training samples and model parameters, update the weight gradient of the pre-built CNN-LSTM global SOC planning model, and obtain a trained CNN-LSTM global SOC planning model.

[0150] Step S404: predicting the SOC value.

[0151] Among them, the embodiment of the present application can use the trained CNN-LSTM global SOC planning model to predict the terminal SOC at the end of each road section and perform interpolation to obtain the global continuous time SOC curve .

[0152] Optionally, in one embodiment of the present application, the SOC value of the vehicle is predicted based on the trained CNN-LSTM global SOC planning model to achieve vehicle energy management, including: determining the vehicle's unit distance energy consumption on the corresponding road section based on the SOC value; using section operating condition data, SOC value and unit distance energy consumption to construct an energy management database corresponding to the vehicle; using the energy management database to generate the vehicle's energy management strategy to achieve vehicle energy management.

[0153] It is understandable that the embodiment of the present application is to support model training and generalization capability expansion, build an energy management database for storing "operating condition data - SOC - energy consumption" ternary data. The sample structure of the ternary data can be, but is not limited to:

[0154] ,

[0155] in, represents the input feature vector, as constructed above; Indicates the optimal SOC value of the corresponding segment; Indicates the energy consumption per unit distance on the corresponding road section, in Wh / km); Represents the total number of road segments.

[0156] In addition, the energy management database may include, but is not limited to, 60 sets of urban road samples, 50 sets of highway samples, and 40 sets of suburban / rural samples, for a total of 150 sets of samples, with a total mileage exceeding 1000km and a sampling period of 5 seconds. This application does not impose specific restrictions.

[0157] Furthermore, the embodiment of the present application can upload the operating trajectory, actual SOC curve and energy consumption to the server after each user completes a full path operation, automatically match the tags and archive them in the energy management database, and then use the energy management database to generate the vehicle's energy management strategy, thereby realizing vehicle energy management.

[0158] According to the vehicle energy management method proposed in the embodiment of the present application, the road can be segmented according to the corresponding operating condition data obtained by the vehicle under different operating conditions, and then the road section operating condition data corresponding to different road sections can be obtained, and then the SOC value of the vehicle that meets certain optimal conditions under the corresponding operating conditions can be calculated, and then a pre-built CNN-LSTM global SOC planning model can be trained, so that the SOC value of the vehicle can be predicted using the trained CNN-LSTM global SOC planning model to achieve vehicle energy management, so that the vehicle can dynamically optimize the energy use strategy according to different operating conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the range extender power output. This can not only optimize the energy management of a single vehicle, but also provide real-time scheduling support for a wider range of fleets or traffic systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions. Therefore, the above problems in the related art are solved, such as the inability to adapt to complex traffic environments and operating conditions, the low degree of intelligence, the low energy utilization rate, and the inability to effectively improve fuel economy.

[0159] Next, the energy management device for a vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0160] Figure 5 This is a block diagram of an energy management device for a vehicle provided according to an embodiment of the present application.

[0161] like Figure 5 As shown, the vehicle energy management device 50 is applied to the offline model training stage, wherein the device 50 includes: a first acquisition module 501, a first segmentation module 502, a first calculation module 503 and a prediction module 504.

[0162] The first acquisition module 501 is used to acquire operating condition data corresponding to at least one vehicle under different operating conditions.

[0163] The first segmentation module 502 is configured to segment the road on which the vehicle is traveling based on the operating condition data, so as to obtain section operating condition data corresponding to different road sections.

[0164] The first calculation module 503 is used to calculate the SOC value of at least one vehicle that meets the preset optimal conditions under the corresponding working conditions based on the road section working condition data.

[0165] The prediction module 504 is used to train a pre-built CNN-LSTM global SOC planning model using the SOC value and operating condition data that meet the preset optimal conditions to obtain a trained CNN-LSTM global SOC planning model, and predict the vehicle's SOC value based on the trained CNN-LSTM global SOC planning model to achieve vehicle energy management.

[0166] Optionally, in one embodiment of the present application, the first segmentation module 502 includes: a first determination unit, a judgment unit, a first segmentation unit, and a second segmentation unit.

[0167] The first determination unit is configured to determine at least one of an average vehicle speed, a road section length, and a road section congestion level during driving based on the operating condition data.

[0168] The judgment unit is used to judge whether the speed change rate of the vehicle at different positions is greater than a preset value based on the average vehicle speed and the road section length, and / or, based on the road section congestion level and the road section length, whether the road section congestion level meets the preset conditions.

[0169] The first segmentation unit is used to segment the corresponding road according to the average vehicle speed and the road section length when the vehicle speed change rate is greater than a preset value, and / or, if the road section congestion level meets a preset condition, segment the corresponding road according to the road section congestion level and the road section length.

[0170] The second segmentation unit is configured to not segment the corresponding road when the vehicle speed change rate is less than or equal to a preset value, and / or not segment the corresponding road if the congestion level of the road section does not meet a preset condition.

[0171] Optionally, in one embodiment of the present application, the first acquisition module 501 includes: a first acquisition unit, a second acquisition unit, a processing unit, and a generation unit.

[0172] The first acquisition unit is used to acquire initial driving data of at least one vehicle under corresponding working conditions.

[0173] The second acquisition unit is used to acquire initial road data of at least one vehicle under corresponding working conditions.

[0174] The processing unit is used to process the initial driving data and the initial road data respectively to obtain corresponding driving data and road data.

[0175] The generating unit is used to obtain the working condition data based on the driving data and the road data.

[0176] Optionally, in one embodiment of the present application, it further includes: a first building module, a first determining module, a first generating module, a second determining module and a second building module.

[0177] Among them, the first construction module is used to construct the input feature matrix of the CNN-LSTM global SOC planning model using the SOC value and operating condition data that meet the preset optimal conditions before training the pre-constructed CNN-LSTM global SOC planning model using the SOC value and operating condition data that meet the preset optimal conditions.

[0178] The first determination module is used to determine the CNN feature extraction layer of the CNN-LSTM global SOC planning model based on the input feature matrix.

[0179] The first generation module is used to use the CNN feature extraction layer to obtain an output one-dimensional vector corresponding to the input feature matrix.

[0180] The second determination module is used to determine the LSTM network of the CNN-LSTM global SOC planning model based on the output one-dimensional vector.

[0181] The second building module is used to build a CNN-LSTM global SOC planning model using the CNN feature extraction layer and the LSTM network.

[0182] Optionally, in one embodiment of the present application, the second determination module includes: a second determination unit, a third acquisition unit, a third determination unit, a fourth determination unit and a second generation unit.

[0183] The second determining unit is used to determine the input gate of the LSTM network based on the output one-dimensional vector.

[0184] The third acquisition unit is used to obtain the cell state and hidden state of the LSTM network.

[0185] The third determining unit is used to determine the forget gate of the LSTM network based on the input gate and the hidden state.

[0186] The fourth determining unit is used to determine the output gate of the LSTM network based on the input gate, the cell state, the hidden state and the forget gate.

[0187] The second generation unit is used to obtain an LSTM network using an input gate, a cell state, a hidden state, a forget gate, and an output gate.

[0188] Optionally, in one embodiment of the present application, the prediction module 504 includes: a fourth acquisition unit and a training unit.

[0189] Among them, the fourth acquisition unit is used to obtain the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate and the learning rate of the Adam optimizer corresponding to the pre-built CNN-LSTM global SOC planning model for training.

[0190] The training unit is used to train a pre-built CNN-LSTM global SOC planning model based on the first-order moment estimated exponential decay rate, the second-order moment estimated exponential decay rate and the learning rate until the pre-built CNN-LSTM global SOC planning model meets preset training conditions to obtain a trained CNN-LSTM global SOC planning model.

[0191] Optionally, in one embodiment of the present application, the prediction module 504 includes: a fifth determination unit, a third construction unit and a third generation unit.

[0192] The fifth determination unit is configured to determine the energy consumption per unit distance of the vehicle on the corresponding road section based on the SOC value.

[0193] The third construction unit is used to construct an energy management database corresponding to the vehicle by using the road section operating condition data, SOC value and energy consumption per unit distance.

[0194] The third generating unit is configured to generate an energy management strategy for the vehicle using the energy management database to implement energy management of the vehicle.

[0195] It should be noted that the above explanation of the embodiment of the vehicle energy management method is also applicable to the vehicle energy management device of this embodiment, and will not be repeated here.

[0196] According to the vehicle energy management device proposed in the embodiment of the present application, the road can be segmented based on the corresponding operating condition data obtained by the vehicle under different operating conditions, thereby obtaining the section operating condition data corresponding to different road sections, and then calculating the SOC value of the vehicle that meets certain optimal conditions under the corresponding operating conditions, and then training a pre-built CNN-LSTM global SOC planning model. The trained CNN-LSTM global SOC planning model is then used to predict the vehicle's SOC value, realizing vehicle energy management, so that the vehicle can dynamically optimize the energy usage strategy according to different operating conditions, improve the overall energy efficiency and economy of the extended-range hybrid vehicle, and by optimizing the SOC, ensure that the actual SOC of the vehicle is as close as possible to the SOC curve that meets certain optimal conditions, optimize the battery charging and discharging process, extend the battery life and reduce energy waste, and reasonably adjust the range extender power output. This can not only optimize the energy management of a single vehicle, but also potentially provide real-time scheduling support for a wider range of fleets or transportation systems in the future, further optimize the road network and traffic flow, and reduce overall energy consumption and carbon emissions. Thus, the above-mentioned problems in the related art, such as the inability to adapt to complex traffic environments and operating conditions, low intelligence, low energy utilization, and inability to effectively improve fuel economy, are solved.

[0197] The above embodiment describes the offline model training stage. The following describes an embodiment of the online model application stage.

[0198] Figure 6 This is a flowchart of a vehicle energy management method provided according to another embodiment of the present application.

[0199] like Figure 6 As shown, the vehicle energy management method is applied in the model online application stage, wherein the method includes the following steps:

[0200] In step S601 , actual operating condition data of the vehicle under different operating conditions is obtained.

[0201] In some embodiments, the embodiments of the present application can collect actual operating data of the vehicle under different operating conditions based on API map information.

[0202] For example, in an embodiment of the present application, the starting position of vehicle A is B, the ending position is B', and its operating condition is an urban condition. Thus, the embodiment of the present application can use the API map to obtain the actual operating condition data of the vehicle in real time.

[0203] In step S602 , based on the actual working condition data, the road on which the vehicle is traveling is divided into sections to obtain actual section working condition data corresponding to different road sections.

[0204] In some embodiments, the embodiments of the present application can segment the road based on actual working condition data, and then obtain actual road section working condition data corresponding to different road sections.

[0205] For example, in an embodiment of the present application, vehicle A can segment road BB' into three road sections, and then according to the actual road section operating condition data corresponding to different road sections, where section 1 is unobstructed, section 2 is slow-moving, and section 3 is congested, the corresponding actual road section operating condition data are also different.

[0206] In step S603, the starting SOC value corresponding to the actual road section operating condition data is input into the trained CNN-LSTM global SOC planning model to obtain the ending SOC value of the vehicle on the corresponding road section, wherein the trained CNN-LSTM global SOC planning model is trained by the starting SOC value and the actual road section operating condition data.

[0207] In some embodiments, the present application embodiment can extract the congestion situation of each road section , average speed , section length , the starting SOC value at the beginning of the section , total remaining mileage and the starting SOC value of the working condition As the input of the trained CNN-LSTM global SOC planning model, the trained CNN-LSTM global SOC planning is used to obtain the starting SOC value of the next road section. .

[0208] In step S604 , the power output of the vehicle is controlled according to the starting SOC value or the ending SOC value to achieve energy management of the vehicle.

[0209] In some embodiments, the present invention can calculate the end SOC at the end of each road section and interpolate to obtain a global continuous time SOC curve. , adjust the power output of the range extender, control the actual SOC to follow the SOC reference curve, achieve optimal energy distribution, and realize vehicle energy management.

[0210] The working principle of the vehicle energy management method proposed in the embodiment of the present application is introduced below with reference to a specific embodiment.

[0211] in, Figure 7 The present invention is a flowchart illustrating the working principle of a vehicle energy management method according to another embodiment of the present application.

[0212] Offline training phase:

[0213] Step S701: Acquire operating condition data.

[0214] Among them, the embodiments of the present application can be combined with Figure 2 The method shown is used to obtain working condition data.

[0215] Step S702: Calculate the SOC value that meets certain optimal conditions based on the operating condition data.

[0216] Among them, the embodiment of the present application can use the PMP algorithm to calculate the SOC value that meets certain optimal conditions under the corresponding working conditions, and use the SOC value that meets certain optimal conditions as a training sample for training the pre-built CNN-LSTM global SOC planning model.

[0217] Step S703: Determine the SOC values ​​that meet certain optimal conditions under different operating conditions.

[0218] Step S704: training the pre-built CNN-LSTM global SOC planning model.

[0219] Among them, the embodiment of the present application can use the SOC values ​​that meet certain optimal conditions under different working conditions to train the pre-built CNN-LSTM global SOC planning model, and then obtain the trained CNN-LSTM global SOC planning model.

[0220] Online application stage:

[0221] Step S705: Acquire actual working condition data.

[0222] Among them, the embodiment of the present application can collect the actual working condition data of the vehicle under different working conditions based on API map information.

[0223] Step S706: Segmentation to obtain actual road section working condition data corresponding to different road sections.

[0224] Step S707: Using the trained CNN-LSTM global SOC planning model, the termination SOC value is obtained.

[0225] Among them, the embodiment of the present application can extract the congestion situation of each road section , average speed , section length , the starting SOC value at the beginning of the section , total remaining mileage and the starting SOC value of the working condition As the input of the trained CNN-LSTM global SOC planning model, the trained CNN-LSTM global SOC planning is used to obtain the starting SOC value of the next road section. .

[0226] Step S708: Control the power output according to the SOC value to achieve energy management of the vehicle.

[0227] Among them, the embodiment of the present application can control the power output according to the starting or ending SOC value to achieve vehicle energy management.

[0228] According to the vehicle energy management method proposed in the embodiment of the present application, the road on which the vehicle is traveling can be segmented based on the actual operating condition data obtained, thereby obtaining the actual road section operating condition data corresponding to different road sections, and using the output of the trained CNN-LSTM global SOC planning model to obtain the vehicle's final SOC value on the corresponding road section, and then controlling the vehicle's power output according to the starting SOC value or the final SOC value to achieve vehicle energy management. Through segmented prediction, error accumulation is suppressed, and SOC prediction error is reduced. Based on the actual operating condition data received in real time, the SOC prediction value is dynamically adjusted to reduce prediction latency, meet real-time requirements, and adaptively manage energy according to different operating conditions, thereby improving driving comfort, extending battery life, and enhancing safety. This solves the problems in related technologies such as the inability to adapt to complex traffic environments and operating conditions, low intelligence, low energy utilization, and inability to effectively improve fuel economy.

[0229] Next, the energy management device for a vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0230] Figure 8 This is a block diagram of an energy management device for a vehicle provided according to another embodiment of the present application.

[0231] like Figure 8 As shown, the vehicle energy management device 80 is applied in the model online application stage, wherein the device 80 includes: a second acquisition module 801, a second segmentation module 802, a second generation module 803 and a control module 804.

[0232] The second acquisition module 801 is used to acquire actual operating condition data of the vehicle under different operating conditions.

[0233] The second segmentation module 802 is used to segment the road on which the vehicle is traveling based on the actual working condition data, so as to obtain actual section working condition data corresponding to different road sections.

[0234] The second generation module 803 is used to input the starting SOC value corresponding to the actual road section operating condition data into the trained CNN-LSTM global SOC planning model to obtain the ending SOC value of the vehicle on the corresponding road section, wherein the trained CNN-LSTM global SOC planning model is trained by the starting SOC value and the actual road section operating condition data.

[0235] The control module 804 is configured to control the power output of the vehicle according to the starting SOC value or the ending SOC value to achieve energy management of the vehicle.

[0236] It should be noted that the above explanation of the embodiment of the vehicle energy management method is also applicable to the vehicle energy management device of this embodiment, and will not be repeated here.

[0237] According to the vehicle energy management device proposed in the embodiment of the present application, the road on which the vehicle is traveling can be segmented based on the actual operating condition data obtained, thereby obtaining the actual road section operating condition data corresponding to different road sections, and using the trained CNN-LSTM global SOC planning model output to obtain the vehicle's terminal SOC value on the corresponding road section, and then controlling the vehicle's power output according to the starting SOC value or the terminal SOC value, thereby achieving vehicle energy management. Through segmented prediction, error accumulation is suppressed, and SOC prediction error is reduced. Based on the actual operating condition data received in real time, the SOC prediction value is dynamically adjusted to reduce prediction latency, meet real-time requirements, and adaptively manage energy according to different operating conditions, thereby improving driving comfort, extending battery life, and enhancing safety. Thus, the problems in related technologies such as the inability to adapt to complex traffic environments and operating conditions, low intelligence, low energy utilization, and inability to effectively improve fuel economy are solved.

[0238] Figure 9 This is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. The vehicle may include:

[0239] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0240] When the processor 902 executes the program, the vehicle energy management method provided in the above embodiment is implemented.

[0241] Furthermore, the vehicle further comprises:

[0242] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0243] The memory 901 is used to store computer programs that can be run on the processor 902 .

[0244] The memory 901 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0245] If the memory 901, processor 902, and communication interface 903 are implemented independently, the communication interface 903, memory 901, and processor 902 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0246] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0247] The processor 902 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0248] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned vehicle energy management method.

[0249] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above vehicle energy management method when executed.

[0250] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0251] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0252] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0253] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable media include: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0254] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0255] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0256] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0257] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A vehicle energy management method, characterized in that: Applied to the offline model training stage, wherein the method includes the following steps: Obtaining operating condition data corresponding to at least one vehicle under different operating conditions; Based on the operating condition data, the road on which the vehicle is traveling is divided into sections to obtain section operating condition data corresponding to different road sections; Calculating, based on the road section operating condition data, a state of charge (SOC) value of the at least one vehicle that satisfies a preset optimal condition under the corresponding operating condition; Using the SOC value that meets the preset optimal conditions and the operating condition data to train a pre-built convolutional long short-term memory network (CNN-LSTM) global SOC planning model to obtain a trained CNN-LSTM global SOC planning model, and predicting the SOC value of the vehicle based on the trained CNN-LSTM global SOC planning model to achieve energy management of the vehicle; The step of segmenting the road on which the vehicle is traveling based on the operating condition data includes: determining at least one of an average vehicle speed, a road section length, and a road section congestion level during the driving process of the vehicle based on the operating condition data; Based on the average vehicle speed and the length of the road section, determining whether a rate of change of the vehicle speed at different locations is greater than a preset value, and / or, based on the congestion level of the road section and the length of the road section, determining whether the congestion level of the road section meets a preset condition; If the vehicle speed change rate is greater than the preset value, the corresponding road is segmented according to the average vehicle speed and the road section length; and / or, if the road section congestion level meets the preset condition, the corresponding road is segmented according to the road section congestion level and the road section length; If the vehicle speed change rate is less than or equal to the preset value, the corresponding road is not segmented, and / or if the congestion level of the road section does not meet the preset condition, the corresponding road is not segmented; The method of training a pre-built CNN-LSTM global SOC planning model using the SOC value that meets the preset optimal condition and the operating condition data to obtain a trained CNN-LSTM global SOC planning model includes: Obtaining the first-order moment estimation exponential decay rate, the second-order moment estimation exponential decay rate, and the learning rate of the adaptive moment estimation optimizer Adam optimizer corresponding to the training of the pre-built CNN-LSTM global SOC planning model; Based on the first-order moment estimated exponential decay rate, the second-order moment estimated exponential decay rate and the learning rate, the pre-constructed CNN-LSTM global SOC planning model is trained until the pre-constructed CNN-LSTM global SOC planning model meets the preset training conditions to obtain the trained CNN-LSTM global SOC planning model.

2. The method according to claim 1, characterized in that The obtaining of operating condition data corresponding to at least one vehicle under different operating conditions includes: Acquiring initial driving data of the at least one vehicle under corresponding operating conditions; Acquiring initial road data of the at least one vehicle under corresponding working conditions; processing the initial driving data and the initial road data respectively to obtain corresponding driving data and road data; The operating condition data is obtained based on the driving data and the road data.

3. The method according to claim 1, characterized in that Before using the SOC value that meets the preset optimal condition and the operating condition data to train the pre-built CNN-LSTM global SOC planning model, the method further includes: Constructing an input feature matrix of a CNN-LSTM global SOC planning model using the SOC value that meets the preset optimal conditions and the operating condition data; Based on the input feature matrix, determining the CNN feature extraction layer of the CNN-LSTM global SOC planning model; Using the CNN feature extraction layer to obtain an output one-dimensional vector corresponding to the input feature matrix; Based on the output one-dimensional vector, determining the LSTM network of the CNN-LSTM global SOC planning model; The CNN feature extraction layer and the LSTM network are used to construct the CNN-LSTM global SOC planning model.

4. The method according to claim 3, characterized in that The step of determining the LSTM network of the CNN-LSTM global SOC planning model based on the output one-dimensional vector includes: Determining an input gate of the LSTM network based on the output one-dimensional vector; Obtain the cell state and hidden state of the LSTM network; Determining a forget gate of the LSTM network based on the input gate and the hidden state; Determining an output gate of the LSTM network based on the input gate, the cell state, the hidden state, and the forget gate; The LSTM network is obtained by using the input gate, the cell state, the hidden state, the forget gate and the output gate.

5. The method according to claim 1, characterized in that The predicting the SOC value of the vehicle based on the trained CNN-LSTM global SOC planning model to achieve energy management of the vehicle includes: Determining the energy consumption per unit distance of the vehicle on the corresponding road section based on the SOC value; constructing an energy management database corresponding to the vehicle using the road section operating condition data, the SOC value, and the energy consumption per unit distance; The energy management database is used to generate an energy management strategy for the vehicle to implement energy management of the vehicle.

6. A vehicle energy management method, characterized in that: The vehicle energy management method according to any one of claims 1 to 5 is applied to the model online application stage, wherein the method comprises the following steps: Obtain the actual working condition data of the vehicle under different working conditions; Based on the actual working condition data, the road on which the vehicle is traveling is divided into sections to obtain actual road section working condition data corresponding to different road sections; Inputting the starting SOC value corresponding to the actual road section operating condition data into a trained CNN-LSTM global SOC planning model to obtain a terminal SOC value of the vehicle on the corresponding road section, wherein the trained CNN-LSTM global SOC planning model is trained by the starting SOC value and the actual road section operating condition data; The power output of the vehicle is controlled according to the starting SOC value or the ending SOC value to achieve energy management of the vehicle.

7. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the energy management method for a vehicle according to any one of claims 1 to 5 or the energy management method for a vehicle according to claim 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the vehicle energy management method according to any one of claims 1 to 5 or the vehicle energy management method according to claim 6.

Images