New energy light truck energy distribution method and system

Abstract

The invention provides a new energy light truck energy distribution method and system, and the method comprises the steps: obtaining the position and track of a vehicle to obtain the road section data of a current driving road section, carrying out the data preprocessing of the road section data, and carrying out the fusion of the preprocessed data, so as to obtain the current load and driving state of the vehicle; inputting the preprocessed data into an initial energy consumption model, introducing a deep learning algorithm to dynamically adjust model parameters of the initial energy consumption model to obtain an iterated target energy consumption model, and obtaining energy consumption coefficient data according to the target energy consumption model; and a motor torque demand curve is generated in real time according to the current load, the road slope and the predicted endurance mileage, torque distribution data are adjusted in combination with an adaptive algorithm, the adjusted torque distribution data are transmitted into a vehicle power control system to obtain real-time operation data of the vehicle, and then energy distribution is conducted on the new energy light truck. According to the invention, the endurance prediction precision is improved, and the real-time adaptive optimization of torque distribution control is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy distribution for new energy light trucks, and in particular to a method and system for energy distribution for new energy light trucks. Background Art

[0002] In recent years, with the promotion and application of new energy vehicles in the field of logistics and transportation, light trucks have attracted widespread attention due to their environmental protection and high efficiency.

[0003] In existing technologies, dynamic models are mainly established to predict the vehicle's remaining range through multi-sensor data collection (such as cargo box pressure sensors, vehicle acceleration sensors, GPS positioning, etc.) and high-precision digital map data. At the same time, torque distribution control is performed based on real-time road surface, slope, load and other information. However, how to improve the accuracy of dynamic range prediction of new energy light trucks under complex working conditions, and how to achieve real-time adaptive optimization of torque distribution control to overcome the limitations of control strategies under fixed thresholds have become technical problems that urgently need to be solved. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a new energy light truck energy distribution method and system, which is used to improve the dynamic endurance prediction accuracy of new energy light trucks under complex working conditions and realize real-time adaptive optimization of torque distribution control, thereby overcoming the limitations of the control strategy under fixed thresholds.

[0005] In one aspect, the present invention provides a method for distributing energy to a new energy light truck, the method comprising: Obtaining the vehicle's position and trajectory, obtaining segment data of the current travel segment based on the vehicle's position and trajectory, the segment data including road slope, road curvature, and road material, performing data preprocessing on the segment data, and fusing the preprocessed data using a weight coefficient to obtain the vehicle's current load and travel status; The preprocessed data is input into the initial energy consumption model, and a deep learning algorithm is introduced to dynamically adjust the model parameters of the initial energy consumption model to obtain an iterative target energy consumption model to minimize the prediction error under variable operating conditions. The vehicle's current predicted cruising range and energy consumption coefficient data are obtained based on the target energy consumption model. A motor torque demand curve is generated in real time based on the current load, the road slope, and the predicted cruising range, and the torque distribution data is adjusted in combination with an adaptive algorithm to automatically adjust the switching parameters between the efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction, and torque distribution status. Energy is distributed for new energy light trucks based on the real-time operating data.

[0006] The above-mentioned energy distribution method for new energy light trucks improves the accuracy of endurance prediction through multi-sensor data fusion and high-precision digital map information, and dynamically iterates the energy consumption model through machine learning. At the same time, it introduces an adaptive adjustment mechanism in torque distribution control to achieve smooth switching between efficiency and power modes, effectively reducing energy consumption and improving safety and driving stability.

[0007] In addition, the energy distribution method for new energy light trucks according to the present invention may also have the following additional technical features: Furthermore, the step of distributing energy to the new energy light truck according to the real-time operating data includes: Upload real-time operating data to the cloud platform, which then uses big data analysis to generate fleet-level charging heat maps and energy consumption optimization strategies. Feedback information is obtained based on the charging heat map and the energy consumption optimization strategy and fed back to the scheduling platform so that the scheduling platform generates data instructions based on the feedback information and feeds them back to each vehicle to collaboratively optimize the overall energy consumption of the fleet and perform energy distribution. The feedback information includes charging pile site selection and energy consumption management suggestions.

[0008] Furthermore, the preprocessed data is input into the initial energy consumption model, and a deep learning algorithm is introduced to dynamically adjust the model parameters of the initial energy consumption model to obtain an iterative target energy consumption model to minimize the prediction error under variable working conditions. The steps include: Dynamic weight adjustment is performed based on current operating condition changes and historical deviations to minimize prediction errors under variable operating conditions.

[0009] Furthermore, the data preprocessing method includes: The collected road section data is filtered and denoised.

[0010] Furthermore, in the step of inputting the preprocessed data into the initial energy consumption model, the initial energy consumption model is constructed based on the high-precision map data, historical energy consumption records and vehicle operating status.

[0011] Another aspect of the present invention provides an energy distribution system for a new energy light truck, the system comprising: an acquisition module, configured to acquire the vehicle's position and trajectory, obtain the road section data of the current driving section based on the vehicle's position and trajectory, the road section data including the road slope, road curvature, and road material, perform data preprocessing on the road section data, and fuse the preprocessed data using a weight coefficient to obtain the vehicle's current load and driving status; An adjustment module, configured to input the preprocessed data into an initial energy consumption model and dynamically adjust the model parameters of the initial energy consumption model using a deep learning algorithm to obtain an iterative target energy consumption model to minimize prediction errors under variable operating conditions. The target energy consumption model is then used to obtain the vehicle's current predicted cruising range and energy consumption coefficient data. A distribution module is used to generate a motor torque demand curve in real time based on the current load, the road slope and the predicted cruising range, and adjust the torque distribution data in combination with an adaptive algorithm to automatically adjust the switching parameters between efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction and torque distribution status, and energy is distributed to the new energy light truck based on the real-time operating data.

[0012] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned new energy light truck energy distribution method.

[0013] On the other hand, the present invention also provides a data processing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the energy distribution method for new energy light trucks as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flow chart of the energy distribution method for a new energy light truck in the first embodiment of the present invention; Figure 2 This is a system block diagram of the energy distribution system for a new energy light truck in the second embodiment of the present invention; The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0015] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0017] To facilitate understanding of the present invention, several embodiments of the present invention are provided below. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive disclosure of the present invention.

[0018] Example 1 See also Figure 1 , which shows the energy distribution method for a new energy light truck in the first embodiment of the present invention, and includes steps S101 to S103: S101. Obtain the vehicle position and trajectory, and obtain the section data of the current driving section based on the vehicle position and trajectory. The section data includes road slope, road curvature, and road material. Preprocess the section data and fuse the preprocessed data using a weight coefficient to obtain the vehicle's current load and driving status.

[0019] In this embodiment, a high-precision pressure sensor array is installed inside the vehicle's cargo box, along with an IMU (Inertial Measurement Unit) to acquire vehicle acceleration data. The vehicle's position and trajectory are collected in real time using an onboard GPS module, which then connects to a high-precision digital map server to obtain information such as the slope, road curvature, and road material of the current road section. Furthermore, a data preprocessing module filters and denoises the collected raw data, and fuses the multi-source data using a weighting coefficient (e.g., α = 0.7 for pressure sensor data) to provide a preliminary estimate of the vehicle's current load and driving status. Kalman filtering is used to eliminate GPS positioning jitter, while wavelet transforms are used to remove high-frequency noise from the pressure sensor for denoising.

[0020] Specifically, the pressure sensor array at the bottom of the cargo box (model: Bosch BMP581) directly measures the pressure on the cargo box floor and converts it into a load value using the following formula: P load =K calib ×Pressure; Where, P load Indicates the basic load measurement value (load estimate directly converted by the pressure sensor); K calbi is the calibration coefficient (the conversion ratio between pressure value and actual load); Pressure is the original pressure value, that is, the pressure measured by the cargo box pressure sensor array.

[0021] As a specific example, first, considering the influence of road slope, the pressure sensor reading is too high when going uphill, requiring negative compensation; the pressure sensor reading is too low when going downhill, requiring positive compensation. Second, considering the influence of road surface material, wet and slippery roads cause tire slippage, requiring compensation by obtaining the road friction coefficient μ through the road recognition camera. The above is integrated into the calculation formula: W final =α⋅P load +β⋅(Slope×0.12)+γ⋅(1−μ); Where W final Indicates the final load value; P load represents the basic load measurement value; Slope represents the road slope, that is, the inclination angle of the current driving road, where uphill is "+" and downhill is "-"; α is the pressure sensor data weight, α=0.7; β is the slope compensation weight, β=0.3; γ is the road friction compensation coefficient, γ=0.15; μ is the road friction coefficient.

[0022] As shown in Table 1, this is the actual vehicle test data table for load fusion verification.

[0023] Table 1:

[0024] In this embodiment, based on the original use of the cargo box pressure sensor array and acceleration data, GPS positioning, vehicle trajectory and real-time acquisition of digital map information are added to obtain multi-dimensional parameters such as road slope, road curvature and road material; then a multi-index weighted algorithm is used to fuse the sensor data in real time to achieve accurate perception of the vehicle load and driving environment.

[0025] In this embodiment, the fusion of multi-dimensional parameters and real-time deep learning iteration make the prediction model more in line with actual driving conditions. Compared with traditional methods, the endurance prediction error is significantly reduced, which facilitates more refined energy management.

[0026] S102. Input the preprocessed data into the initial energy consumption model, and introduce a deep learning algorithm to dynamically adjust the model parameters of the initial energy consumption model to obtain an iterative target energy consumption model to minimize the prediction error under variable working conditions, and obtain the vehicle's current predicted cruising range and energy consumption coefficient data based on the target energy consumption model.

[0027] In this embodiment, an initial energy consumption model is constructed based on high-precision map data, historical energy consumption records, and vehicle operating status. Based on the initial energy consumption model framework, combined with high-precision map data and historical energy consumption records, by introducing machine learning algorithms such as convolutional neural networks or recurrent neural networks, the model parameters are dynamically adjusted every 3 minutes to 5 minutes to improve the timeliness and accuracy of the endurance prediction. Specifically, based on the convolutional neural network CNN as the basic architecture, a six-dimensional vector is input, and the energy consumption coefficient is obtained through the output layer, where the six-dimensional vector includes slope, load, vehicle speed, ambient temperature, wind speed, and battery SOC.

[0028] Using real-time data feedback, the model is constantly corrected to ensure that the prediction error is minimized under variable working conditions. Specifically, dynamic weight adjustment is performed based on current working condition changes and historical deviations to minimize the prediction error under variable working conditions. The dynamic adjustment mechanism is to dynamically adjust the LSTM hidden layer weights based on historical prediction errors. η , the specific formula is: ; in, η ∈[0.2, 0.8].

[0029] S103. Generate a motor torque demand curve in real time based on the current load, road slope, and predicted cruising range, and adjust the torque distribution data in combination with an adaptive algorithm to automatically adjust the switching parameters between efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction, and torque distribution status. Energy is distributed to new energy light trucks based on the real-time operating data.

[0030] Specifically, real-time operating data is uploaded to the cloud platform, which combines big data analysis to generate fleet-level charging heat maps and energy consumption optimization strategies. Feedback information is obtained based on the charging heat maps and energy consumption optimization strategies and fed back to the scheduling platform, so that the scheduling platform generates data instructions based on the feedback information and feeds them back to each vehicle to collaboratively optimize the overall energy consumption of the fleet and perform energy distribution. The feedback information includes charging pile site selection and energy consumption management suggestions.

[0031] In this embodiment, the traditional fixed threshold control is abandoned and an adaptive weight adjustment algorithm based on load, slope, road condition and weather factors is designed. According to the real-time generated motor torque demand curve, smooth and gradual switching is performed between efficiency priority and power priority modes to ensure that the vehicle achieves optimal energy consumption and driving stability under different operating conditions. When a sudden change in operating conditions (such as a steep slope or a slippery road surface) is detected, the system automatically adjusts the power output to ensure safe driving of the vehicle.

[0032] The cloud platform realizes real-time uploading and central dispatching of vehicle data. This application performs collaborative optimization through the cloud platform to achieve high-speed uploading of real-time vehicle data. Through edge computing and cloud big data analysis, it builds a fleet energy consumption optimization model and generates a charging heat map to provide decision support for charging station planning and vehicle dispatching. Furthermore, the cloud platform has fast data response and feedback functions to realize fleet-level energy consumption management and multi-vehicle collaborative optimization, thereby improving the dispatching and energy consumption management level of the entire fleet, and bringing long-term economic benefits to logistics companies.

[0033] In summary, the energy distribution method for new energy light trucks in the above-mentioned embodiments of the present invention improves the accuracy of endurance prediction through multi-sensor data fusion and high-precision digital map information, and dynamically iterates the energy consumption model through machine learning. At the same time, an adaptive adjustment mechanism is introduced in the torque distribution control to achieve smooth switching between efficiency and power modes, effectively reducing energy consumption and improving safety and driving stability. Example 2 like Figure 2 FIG. 1 shows an energy distribution system for a new energy light truck according to a second embodiment of the present invention, comprising: an acquisition module, configured to acquire the vehicle's position and trajectory, obtain the road section data of the current driving section based on the vehicle's position and trajectory, the road section data including the road slope, road curvature, and road material, perform data preprocessing on the road section data, and fuse the preprocessed data using a weight coefficient to obtain the vehicle's current load and driving status; An adjustment module, configured to input the preprocessed data into an initial energy consumption model and dynamically adjust the model parameters of the initial energy consumption model using a deep learning algorithm to obtain an iterative target energy consumption model to minimize prediction errors under variable operating conditions. The target energy consumption model is then used to obtain the vehicle's current predicted cruising range and energy consumption coefficient data. A distribution module is used to generate a motor torque demand curve in real time based on the current load, the road slope and the predicted cruising range, and adjust the torque distribution data in combination with an adaptive algorithm to automatically adjust the switching parameters between efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction and torque distribution status, and energy is distributed to the new energy light truck based on the real-time operating data.

[0034] In summary, the energy distribution system for new energy light trucks in the above-mentioned embodiments of the present invention improves the accuracy of endurance prediction through multi-sensor data fusion and high-precision digital map information, and dynamically iterates the energy consumption model through machine learning. At the same time, an adaptive adjustment mechanism is introduced in the torque distribution control to achieve smooth switching between efficiency and power modes, effectively reducing energy consumption and improving safety and driving stability.

[0035] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method in the above embodiment when the program is executed by a processor.

[0036] In addition, an embodiment of the present invention further provides a data processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method in the above embodiment when executing the program.

[0037] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as 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" can be 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.

[0038] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable compact disk 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 may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0039] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0040] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0041] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A new energy light truck energy distribution method, characterized in that: The method comprises: Obtaining the vehicle's position and trajectory, obtaining segment data of the current travel segment based on the vehicle's position and trajectory, the segment data including road slope, road curvature, and road material, performing data preprocessing on the segment data, and fusing the preprocessed data using a weight coefficient to obtain the vehicle's current load and travel status; The preprocessed data is input into the initial energy consumption model, and a deep learning algorithm is introduced to dynamically adjust the model parameters of the initial energy consumption model to obtain an iterative target energy consumption model to minimize the prediction error under variable operating conditions. The vehicle's current predicted cruising range and energy consumption coefficient data are obtained based on the target energy consumption model. A motor torque demand curve is generated in real time based on the current load, the road slope, and the predicted cruising range, and the torque distribution data is adjusted in combination with an adaptive algorithm to automatically adjust the switching parameters between the efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction, and torque distribution status. Energy is distributed for new energy light trucks based on the real-time operating data.

2. The energy distribution method for new energy light trucks according to claim 1, characterized in that: The step of distributing energy to the new energy light truck according to the real-time operating data includes: Upload real-time operating data to the cloud platform, which then uses big data analysis to generate fleet-level charging heat maps and energy consumption optimization strategies. Feedback information is obtained based on the charging heat map and the energy consumption optimization strategy and fed back to the scheduling platform so that the scheduling platform generates data instructions based on the feedback information and feeds them back to each vehicle to collaboratively optimize the overall energy consumption of the fleet and perform energy distribution. The feedback information includes charging pile site selection and energy consumption management suggestions.

3. The energy distribution method for new energy light trucks according to claim 1, characterized in that: The steps of inputting the preprocessed data into the initial energy consumption model and introducing a deep learning algorithm to dynamically adjust the model parameters of the initial energy consumption model to obtain an iterative target energy consumption model to minimize the prediction error under variable working conditions include: Dynamic weight adjustment is performed based on current operating condition changes and historical deviations to minimize prediction errors under variable operating conditions.

4. The energy distribution method for new energy light trucks according to claim 1, characterized in that: Data preprocessing methods include: The collected road section data is filtered and denoised.

5. The energy distribution method for new energy light trucks according to claim 1, characterized in that: In the step of inputting the preprocessed data into the initial energy consumption model, the initial energy consumption model is constructed based on the high-precision map data, historical energy consumption records and vehicle operating status.

6. A new energy light truck energy distribution system, characterized in that: The system comprises: an acquisition module, configured to acquire the vehicle's position and trajectory, obtain the road section data of the current driving section based on the vehicle's position and trajectory, the road section data including the road slope, road curvature, and road material, perform data preprocessing on the road section data, and fuse the preprocessed data using a weight coefficient to obtain the vehicle's current load and driving status; An adjustment module, configured to input the preprocessed data into an initial energy consumption model and dynamically adjust the model parameters of the initial energy consumption model using a deep learning algorithm to obtain an iterative target energy consumption model to minimize prediction errors under variable operating conditions. The target energy consumption model is then used to obtain the vehicle's current predicted cruising range and energy consumption coefficient data. A distribution module is used to generate a motor torque demand curve in real time based on the current load, the road slope and the predicted cruising range, and adjust the torque distribution data in combination with an adaptive algorithm to automatically adjust the switching parameters between efficiency priority and power priority modes. The adjusted torque distribution data is transmitted to the vehicle power control system to distribute the front and rear axle torque in real time to obtain the vehicle's real-time operating data. The real-time operating data includes energy consumption, cruising range prediction and torque distribution status, and energy is distributed to the new energy light truck based on the real-time operating data.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the energy distribution method for a new energy light truck as described in any one of claims 1 to 5 is implemented.

8. A data processing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the energy distribution method for a new energy light truck as described in any one of claims 1 to 5 is implemented.

Images