Energy consumption optimal control method and device for automatic driving electric mine card

Abstract

The invention provides an energy consumption optimal control method and device for an automatic driving electric mine truck, and relates to the technical field of electric mine trucks. According to the method, vehicle running state data are obtained in real time by integrating an advanced sensor technology and complex simulation modeling, and a multi-dimensional data set is constructed in combination with environmental factors. The optimized neural network model is utilized to accurately predict the energy consumption, and according to the comparison between the prediction result and the actual energy consumption, the control strategy is intelligently switched to ensure that the energy consumption of the vehicle is always kept optimal under the complex working condition. According to the system, the precision and adaptability of energy consumption control are improved, the reliability and stability of the system are enhanced through an interactive feedback mechanism, and powerful support is provided for efficient operation of an automatic driving electric mine card. The problems that in the prior art, energy consumption control precision is insufficient, and adaptability is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric mining trucks, and in particular to an energy consumption optimal control method and device for an autonomous driving electric mining truck. Background Art

[0002] In modern mining transportation, electric mining trucks have gradually become one of the mainstream transportation tools due to their environmental protection and high efficiency. However, with the rise of autonomous driving technology, the energy consumption optimization of autonomous electric mining trucks has become a key technical bottleneck. How to achieve optimal energy consumption control of autonomous electric mining trucks under complex mining conditions is the focus of current research.

[0003] Traditional energy consumption optimization methods mainly rely on simple data-driven or rule-based control strategies. Although these methods can provide ideas for energy consumption optimization to a certain extent, their limitations gradually become apparent when facing self-driving electric mining trucks. For example, rule-based control methods can often only adapt to specific working conditions and have poor adaptability to complex and changeable mining environments; while data-driven methods have extremely high requirements on data quality and quantity, and it is difficult to guarantee prediction accuracy and control accuracy in practical applications.

[0004] In addition, existing technologies also have deficiencies in data collection and model building. Traditional energy consumption optimization methods usually only focus on some operating parameters of the vehicle, such as vehicle speed, load, etc., while ignoring the significant impact of environmental factors (such as temperature, humidity, slope, etc.) on energy consumption. This one-sided data collection method results in an incomplete data set that cannot accurately reflect the energy consumption characteristics of electric mining trucks in actual operation.

[0005] In terms of model construction, most existing technologies use a single mathematical model or a simple machine learning algorithm, which makes it difficult to capture the complex time series characteristics of electric mining trucks' energy consumption. For example, the energy consumption of electric mining trucks varies in different terrains (uphill, downhill, flat), different loads (full load, no load), and different environmental conditions (high temperature, low temperature, high humidity, etc.), making it difficult for traditional models to accurately predict and optimize their control.

[0006] Therefore, the existing technology has obvious deficiencies in the field of energy consumption optimization of autonomous driving electric mining trucks, and cannot meet the needs of optimal energy consumption control under complex mining conditions. This not only affects the operating efficiency and economy of electric mining trucks, but also limits the further promotion and application of autonomous driving technology in mining transportation. Therefore, there is an urgent need for a new energy consumption optimization method that can comprehensively consider multiple factors and realize accurate prediction and real-time optimization control of the energy consumption of autonomous driving electric mining trucks, thereby promoting technological progress and sustainable development in the mining transportation industry.

[0007] In view of this, this application is filed. Summary of the invention

[0008] The present invention provides a method and device for optimal energy consumption control of an autonomous driving electric mining truck, which can at least partially improve the above-mentioned problems.

[0009] To achieve the above object, the present invention adopts the following technical solutions: An optimal energy consumption control method for an autonomous driving electric mining truck, comprising: Acquire a physical data set collected by a sensor component configured on the electric mining truck to be tested, and establish a virtual entity corresponding to the electric mining truck based on the physical data set; Acquire a virtual data set of a virtual entity, and fuse the virtual data set with a physical data set to obtain a driving data set based on multiple working conditions; Call the pre-trained PSO-BiLSTM-Attention neural network model to predict energy consumption and obtain the predicted energy consumption value; The predicted energy consumption value is compared with the actual energy consumption to obtain an energy consumption deviation, and the state parameters of the electric mining truck are adjusted according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

[0010] The present invention also provides an energy consumption optimal control device for an autonomous driving electric mining truck, which comprises: A simulation unit, used for acquiring a physical data set collected by a sensor assembly configured on the electric mining truck to be tested, and establishing a virtual entity corresponding to the electric mining truck based on the physical data set; A fusion unit, used for acquiring a virtual data set of a virtual entity, and fusing the virtual data set with a physical data set to obtain a driving data set based on multiple working conditions; The prediction unit is used to call the pre-trained PSO-BiLSTM-Attention neural network model to predict energy consumption and obtain the predicted energy consumption value; The adjustment unit is used to compare the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and adjust the state parameters of the electric mining truck according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

[0011] In summary, the energy consumption optimal control method for autonomous driving electric mining trucks aims to solve the shortcomings of existing technologies in energy consumption control, and to achieve accurate prediction and real-time optimization control of energy consumption of autonomous driving electric mining trucks through innovative methods. This method constructs a comprehensive mapping of physical entities and virtual entities, uses a variety of sensors to collect vehicle operation status data, and combines virtual data generated by simulation models to construct a driving data set based on multiple working conditions. The simulation data is calculated using the MPC control algorithm, and the HIL hardware-in-the-loop test verification is performed to improve the accuracy and reliability of the data set. The PSO-BiLSTM-Attention neural network model is used to train and learn the data set to predict the vehicle state with optimal energy consumption, and based on the comparison of the predicted energy consumption and the actual energy consumption, the control mode is intelligently switched to keep the energy consumption of the electric mining truck in the optimal range.

[0012] The innovation of the optimal energy consumption control method for autonomous driving electric mining trucks lies in that it comprehensively considers the impact of multiple factors on energy consumption, improves the accuracy of energy consumption prediction by combining simulation with actual data, and provides two sets of main and auxiliary control modes to achieve real-time adjustment of energy consumption, which effectively improves the operating efficiency and economy of autonomous driving electric mining trucks, and has important application value and broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flow chart of an energy consumption optimal control method for an autonomous driving electric mining truck provided by the first embodiment of the present invention; Figure 2 It is a flowchart of an energy consumption optimal control method for an autonomous driving electric mining truck provided by the first embodiment of the present invention; Figure 3 is a flow chart of constructing a driving data set based on multiple working conditions provided by an embodiment of the present invention; Figure 4 It is a training flow chart of the PSO-BiLSTM-Attention neural network model provided by an embodiment of the present invention; Figure 5 is a vehicle state control flow chart for optimal energy consumption provided by an embodiment of the present invention; Figure 6 It is a module schematic diagram of an energy consumption optimal control device for an autonomous driving electric mining truck provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0015] refer to Figure 1, Figure 2 As shown, the first embodiment of the present invention discloses an energy consumption optimal control method for an autonomous driving electric mining truck, which can be executed by an energy consumption optimal control device for an autonomous driving electric mining truck (hereinafter referred to as a control device), and in particular, executed by one or more processors in the control device to implement the following method: S1, obtaining a physical data set collected by a sensor component configured on the electric mining truck to be tested, and establishing a virtual entity corresponding to the electric mining truck based on the physical data set; Specifically, step S1 includes: obtaining a physical data set collected by a sensor component configured on the electric mining truck to be tested, and constructing and processing the physical data set using AVL Cruise software to obtain a whole vehicle model of the electric mining truck; Based on the physical data set, the dynamic equations and control system of the electric mining truck are established using Simulink software, and the dynamic equations and control system are combined with the electric mining truck whole vehicle model to obtain the electric mining truck whole vehicle simulation model.

[0016] Preferably, the sensor assembly includes: a speed sensor, a SOC sensor, a tilt sensor, a mass sensor, a humidity sensor, a temperature sensor and a pedal sensor.

[0017] In this embodiment, the electric mining truck is equipped with a variety of sensor components, which can collect the running status data of the vehicle in real time to form a physical data set. These sensor components include speed sensors, SOC sensors, inclination sensors, mass sensors, humidity sensors, temperature sensors and pedal sensors, as shown in Table 1; they are used to measure the key parameters of the electric mining truck, such as the driving speed, remaining battery power, inclination angle, load mass, ambient humidity, working temperature and pedal opening.

[0018] Table 1 Sensor categories and their functions

[0019] The physical data sets collected by these sensors are processed by AVL Cruise software. AVLCruise is a professional vehicle modeling and simulation software that can build a vehicle model corresponding to the electric mining truck based on the input physical data set. In this process, the software will build a virtual model containing various key components of the vehicle, such as the vehicle chassis, power system, transmission system, etc., based on the actual parameters of the vehicle, such as vehicle size, power system configuration, etc., thereby forming a virtual entity that is highly similar to the actual electric mining truck.

[0020] Among them, the whole vehicle model of the electric mining truck includes modules such as the vehicle, cab, monitor, motor, clutch, brake, etc., and these modules need to be mechanically connected. In the vehicle structure, there are many sensors that can detect the implementation and operation status of the vehicle, and the signals of each module of the whole vehicle need to be electrically connected. Taking torque as an example, in order to evaluate the impact of different torques on the energy consumption of electric mining trucks, the typical driving conditions of electric mining trucks are used as Cruise cycle test conditions to simulate the energy consumption of different torques. Set the torque to different values, import the different torque values ​​into Cruise for simulation analysis, set the load to no-load state and full-load state, and simulate the energy consumption of electric mining trucks under different torques through Cruise.

[0021] At the same time, based on the same physical data set, the dynamic equations and control system of the electric mining truck are established using Simulink software. Simulink is a powerful dynamic system modeling and simulation tool that can establish corresponding dynamic equations based on the dynamic characteristics of the vehicle. These equations can describe the motion state of the vehicle under different working conditions, such as acceleration, deceleration, torque output, etc. In addition, Simulink can also design the vehicle's control system, including motor control, brake control, etc., to ensure that the vehicle can operate according to the predetermined motion equation. Specifically, select appropriate modules to establish the motion equations, sensor simulation modules, and corresponding control logic of the mining truck. Use the mathematical operation module to establish the dynamic equations related to the driving motion of the mining truck; use the sensor simulation module (Sensor Simulation) in Simulink to simulate the output of the internal sensor of the hub motor, including motor speed, power, etc.; use the transfer function module (TransferFunction) in Simulink to establish the control system of the hub motor of the mining truck to ensure that the motor can be controlled according to the predetermined motion equation; use the "Scope" module to monitor the output of the motor model in real time to ensure the effectiveness of the model's motion equation and control logic.

[0022] The dynamic equations and control systems established in Simulink are combined with the vehicle model built by AVL Cruise to finally obtain the electric mining truck vehicle simulation model. This vehicle simulation model not only contains the static structural information of the vehicle, but also can simulate the dynamic behavior of the vehicle in actual operation, providing an accurate virtual platform for subsequent energy consumption optimization control.

[0023] See also Figure 3 , S2, obtaining a virtual data set of a virtual entity, fusing the virtual data set with the physical data set to obtain a driving data set based on multiple working conditions; Specifically, step S2 includes: using an MPC control algorithm to calculate the virtual data set, and using HIL hardware to perform an in-loop test on the calculated data set to obtain an output result; Performing verification and comparison processing on the output result to determine whether the output result is greater than a preset value; If not, the output is fed back to the virtual entity for improvement; If so, combine the output results with the physical data set to construct a driving data set based on multiple working conditions.

[0024] Preferably, the physical data set includes speed, temperature, mass, humidity, slope, pedal opening, and SOC, and the virtual data set includes torque, motor speed, power, gear, and energy consumption.

[0025] In this embodiment, after obtaining the physical data set and establishing the virtual entity, the key step is to process the virtual data set generated by the virtual entity and fuse it with the physical data set to construct a driving data set based on multiple working conditions. First, the types and functions of sensors, various characteristic parameters related to the energy consumption of mining trucks, and different driving conditions of mining trucks are introduced in turn. Then the data measured by the sensor is input into the simulation model, and the virtual data is output and compared with the actual data of the mining truck. Under various driving conditions of electric mining trucks, the physical data and virtual data are fused to construct a driving data set based on multiple working conditions. This process not only involves complex data processing, but also ensures the accuracy and reliability of the data through specific algorithms and testing methods, providing a solid data foundation for subsequent energy consumption optimization control.

[0026] Specifically, first obtain a virtual data set from a virtual entity. These virtual data sets are generated by a simulation model, including parameters such as torque, motor speed, power, gear, and energy consumption. Although these parameters are derived from the simulation model, they can reflect the theoretical operating state of the vehicle under different working conditions and are an important reference for energy consumption optimization control. The physical data and virtual data obtained by the energy consumption optimal control method for autonomous driving electric mining trucks have a total of 12 characteristic parameters, including speed, temperature, mass, humidity, slope, pedal opening, SOC, torque, motor speed, power, gear, energy consumption and other information. These parameters can reflect the driving characteristics and performance of electric mining trucks, and are all related factors that can affect the energy consumption of mining trucks, which can provide reliable data support for the energy consumption prediction of electric mining trucks. The specific data information is shown in Table 2.

[0027] Table 2 Related characteristic data information

[0028] In order to improve the accuracy and practicality of these virtual data, the model predictive control (MPC) algorithm is used to calculate the virtual data set. The MPC algorithm is an advanced control algorithm that can predict the future state based on the dynamic characteristics of the system and optimize the control strategy. By processing the virtual data set with the MPC algorithm, optimized data that is more in line with the actual operating conditions can be obtained, thereby improving the quality of the data set. The processed data set is then verified through hardware-in-the-loop (HIL) testing. HIL testing is a testing method that combines actual hardware with simulation models, which can verify the accuracy and reliability of simulation models under conditions close to the actual operating environment. Through HIL testing, the data generated by the simulation model can be compared with the operating results of the actual hardware to verify the validity of the simulation data.

[0029] Next, the output results obtained from the HIL test are verified and compared. The key to this process is to determine whether the output results meet the preset accuracy requirements. Specifically, it is necessary to determine whether the similarity between the output results and the actual operating data is greater than the preset value, where the preset value is 90%. If the similarity of the output results is lower than the preset value, it means that the current simulation model or data processing method is insufficient, and the output results need to be fed back to the virtual entity for improvement. This feedback mechanism can ensure that the simulation model is continuously optimized and the accuracy of the data is gradually improved. On the contrary, if the similarity of the output results is greater than the preset value, it means that the current data processing and simulation model can better reflect the actual operation. At this time, these verified output results are combined with the physical data set to construct a driving data set based on multiple working conditions. The physical data set includes parameters such as speed, temperature, mass, humidity, slope, pedal opening and SOC, which directly reflect the actual operating status of the vehicle. By fusing the virtual data set with the physical data set, the driving data set obtained can fully reflect the operating characteristics of the electric mining truck under different working conditions, providing comprehensive and accurate data support for subsequent energy consumption optimization control.

[0030] As electric mining trucks are affected by the working environment and road conditions during driving, the driving conditions are constantly changing. In order to explore the impact of different working conditions on the energy consumption of mining trucks, it is necessary to classify the driving conditions of mining trucks. By using various sensors installed on mining trucks to obtain data in real time, the data collected under different working conditions are then associated with the operating status. The specific working conditions are shown in Table 3.

[0031] Table 3 Driving conditions of electric mining trucks

[0032] Simply put, the fusion steps of the driving data set based on multiple working conditions can be understood as: the data measured by various sensors installed on the actual vehicle, including speed, temperature, mass, humidity, slope, pedal opening, SOC, a total of 7 characteristic parameters, are used as constraints, and input into the Cruise simulation model and Simlink simulation model for joint simulation, and the torque, motor speed, power, gear, and energy consumption are used as outputs. The simulation data set is calculated using the MPC control algorithm, and the calculated data is subjected to HIL hardware-in-the-loop testing, and the test results are verified and compared. If the similarity of the output result is greater than 90%, it meets the conditions and is used as the basis for constructing the data set. If it does not meet the conditions, it returns to the joint simulation model for improvement. Under the various working conditions in Table 3, various characteristic parameters of different working conditions are fused to map the operating status of the electric mining truck. , and construct a driving data set based on multiple working conditions.

[0033] See also Figure 4 ,S3, calls the pre-trained PSO-BiLSTM-Attention neural network model to predict energy consumption and obtain the predicted energy consumption value; Specifically, before calling the pre-trained PSO-BiLSTM-Attention neural network model for energy consumption prediction, it also includes: acquiring energy consumption sample data, dividing the energy consumption sample data into a training set and a test set, normalizing the training set and the test set, and converting the normalized data into a cell array; Create the function to be optimized, set the number of particles, maximum number of iterations and particle dimension of the PSO algorithm, and optimize the cell array based on the function to be optimized and the PSO algorithm; Initialize the position and velocity of the particle, use the training set for training, and use the mean square error between the predicted value and the true value as the fitness function to calculate the fitness value of each particle; Calculate the corresponding individual optimal position and global optimal position according to the fitness value, and update the position and speed of the particle according to the current position, speed, individual optimal position and global optimal position; When it is determined that the fitness of the selected optimal solution is not less than the preset fitness error, continue to optimize according to the PSO optimization algorithm; When it is determined that the fitness of the selected optimal solution is less than the preset fitness error, the optimal parameter combination is output, and the test set is predicted based on the optimal parameter combination to obtain the prediction result; When the prediction result reaches a preset value, the training is terminated to obtain a trained PSO-BiLSTM-Attention neural network model.

[0034] In this embodiment, according to the time-series characteristics of the energy consumption of electric mining trucks, it is proposed to use the PSO-BiLSTM-Attention neural network model to predict energy consumption. This model can improve the prediction accuracy, optimize the model parameters through the PSO algorithm, use BiLSTM to capture the potential information of time series data, and highlight the key features in combination with the self-attention mechanism. After obtaining the driving data set optimized by the joint simulation model under multiple working conditions, 7 characteristic parameters including speed, temperature, mass, humidity, slope, pedal opening, and SOC are used as the input of the prediction model, and 5 characteristic parameters including torque, motor speed, power, gear, and energy consumption are used as output.

[0035] Specifically, before calling the PSO-BiLSTM-Attention neural network model for energy consumption prediction, it is necessary to first obtain energy consumption sample data. These sample data include the operating parameters of electric mining trucks under different working conditions, such as speed, temperature, mass, humidity, slope, pedal opening, SOC and other physical data, as well as torque, motor speed, power, gear, energy consumption and other virtual data. These data are divided into training sets and test sets for model training and verification.

[0036] In order to improve the training efficiency and prediction accuracy of the model, the training set and test set are normalized. Normalization can convert data of different dimensions and ranges to the same scale, avoid certain features dominating the model training process, and thus improve the stability and accuracy of the model. The normalized data is converted into a cell array for the processing of the neural network model. Next, the function to be optimized is created, and the relevant parameters of the PSO (particle swarm optimization) algorithm are set, including the number of particles, the maximum number of iterations, and the particle dimension. The PSO algorithm is an optimization algorithm based on swarm intelligence, which simulates the foraging behavior of bird flocks to find the optimal solution. In this recipe, the PSO algorithm is used to optimize the parameters of the neural network model to improve the prediction performance of the model.

[0037] After initializing the position and velocity of the particle, the training set is used to train the neural network model. During the training process, the mean square error between the predicted value and the true value is selected as the fitness function to calculate the fitness value of each particle. The fitness function reflects the difference between the model prediction result and the actual data. The smaller the fitness value, the higher the prediction accuracy of the model. According to the calculated fitness value, the individual optimal position and global optimal position of each particle are determined. The individual optimal position refers to the optimal solution found by the particle during the search process, while the global optimal position refers to the optimal solution found by all particles in the entire particle swarm. The position and velocity of the particle are updated according to the current position, velocity, individual optimal position and global optimal position. This process is iterated continuously until the optimal solution that meets the conditions is found.

[0038] When the fitness of the selected optimal solution is not less than the preset fitness error, continue to optimize according to the PSO optimization algorithm. This process ensures that the model parameters are continuously optimized and the prediction accuracy of the model is gradually improved. When the fitness of the optimal solution is less than the preset fitness error, the optimal parameter combination is output, and the test set is predicted based on these optimal parameter combinations to obtain the prediction results. If the prediction result reaches the preset value, it means that the model has a high prediction accuracy. At this time, the training is terminated and the trained PSO-BiLSTM-Attention neural network model is obtained. This model can accurately predict the vehicle state with the best energy consumption based on the input vehicle operation state parameters, providing accurate data support for subsequent energy consumption optimization control.

[0039] Optimizing the parameters of the neural network model through the PSO algorithm can significantly improve the prediction accuracy of the model. BiLSTM (bidirectional long short-term memory network) can capture the potential information in time series data, while the attention mechanism can highlight key features and further improve the performance of the model. This optimization and prediction method can not only accurately predict the energy consumption of electric mining trucks, but also adjust the prediction results in real time according to the actual operating conditions, providing strong technical support for energy consumption optimization control. In addition, through normalization processing and cell array conversion, the efficiency of data processing and the stability of model training are improved, ensuring the efficient operation of the entire system.

[0040] See also Figure 5 , S4, comparing the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and adjusting the state parameters of the electric mining truck according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

[0041] Specifically, step S4 includes: comparing the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and determining whether the energy consumption deviation is less than a preset deviation value; If so, adjusting the vehicle state parameters in an end-to-end manner according to the predicted energy consumption value; If not, a voice reminder will be given and the system will switch to auxiliary control mode based on dynamic programming to adjust the gear position, transmission ratio and motor speed.

[0042] In this embodiment, after completing the energy consumption prediction through the PSO-BiLSTM-Attention neural network model, the key step is to compare the predicted energy consumption value with the actual energy consumption of the electric mining truck, and adjust the vehicle state parameters according to the comparison results to ensure that the energy consumption of the electric mining truck is always kept within the preset optimal range. This process is not an important part of the entire method. It not only involves accurate energy consumption comparison and judgment, but also realizes real-time optimization and adjustment of energy consumption through intelligent control mode switching. The energy consumption value predicted by the neural network model is compared with the energy consumption data of the electric mining truck during actual operation. This comparison process can intuitively reflect the difference between the model prediction and the actual operation, thereby obtaining the energy consumption deviation. The energy consumption deviation is an important indicator to measure the degree of match between the prediction accuracy and the actual operating state. By setting a preset deviation value (for example: 10%), it can be judged whether the current energy consumption control is in an ideal state. When the energy consumption deviation is less than the preset deviation value, it means that the predicted energy consumption value is close to the actual energy consumption. At this time, it can be considered that the energy consumption control of the vehicle is in a relatively ideal state. In this case, according to the predicted energy consumption value, the vehicle state parameters are adjusted in an end-to-end manner. The end-to-end adjustment method is a direct and efficient control strategy that can quickly adjust the key operating parameters of the vehicle, such as vehicle speed, torque, motor speed, etc., based on the prediction results, so that the vehicle's energy consumption remains within the optimal range. This adjustment method not only has a fast response speed, but also can make full use of the high-precision advantages of the prediction model to achieve refined control of energy consumption.

[0043] On the contrary, when the energy consumption deviation is greater than or equal to the preset deviation value, it means that there is a large difference between the predicted energy consumption value and the actual energy consumption, and additional control measures need to be taken. In this case, the system will issue a voice reminder to inform the operator or the autonomous driving system that there is a deviation in the current energy consumption control, and automatically switch to the auxiliary control mode based on the dynamic programming method. The dynamic programming method is a classic optimization algorithm that can dynamically adjust parameters such as gear position, transmission ratio, and motor speed according to the current vehicle status and operating conditions to achieve optimal control of energy consumption. This auxiliary control mode can provide a reliable backup plan when there is a large deviation in the prediction model to ensure that the vehicle's energy consumption does not deviate too far from the optimal range.

[0044] In simple terms, step S4 is to input the driving characteristic parameters of the mining truck, including speed, temperature, mass, humidity, slope, pedal opening, and SOC, into the neural network prediction model to predict the vehicle state parameters with the best energy consumption, including torque, motor speed, power, gear and energy consumption, and then verify and compare the predicted energy consumption with the actual energy consumption of the real vehicle. If the energy consumption deviation is within 10%, the main control method is used to return the energy consumption of the mining truck to the optimal state. Otherwise, it means that the gap between the actual energy consumption and the ideal energy consumption is too large, and the auxiliary control method is switched to, and voice prompts are given to adjust the gear, transmission ratio, motor speed and other parameters to keep the motor in a high-efficiency operating range, thereby keeping the energy consumption in the optimal range.

[0045] In summary, the energy consumption optimal control method for autonomous electric mining trucks collects real-time operating status data of the vehicle through a variety of sensors, including physical data such as speed, temperature, mass, humidity, slope, pedal opening, and SOC, and combines the virtual data generated by the Cruise simulation model of the whole vehicle and the Simulink simulation model to build a driving data set based on multiple working conditions. This process not only covers the actual operating parameters of the vehicle, but also supplements the theoretical operating status through the simulation model, providing comprehensive data support for energy consumption optimization.

[0046] In the data processing stage, the MPC control algorithm is used to calculate the virtual data set, and the accuracy of the data is verified through HIL hardware-in-the-loop testing. This verification process ensures the reliability and practicality of the data set, providing a high-quality data foundation for subsequent energy consumption prediction. By comparing the verification results with the preset values, the system can automatically feedback and improve the simulation model to further optimize the construction of the data set.

[0047] In the energy consumption prediction stage, the pre-trained PSO-BiLSTM-Attention neural network model is called. The model optimizes the model parameters through the particle swarm optimization (PSO) algorithm, uses the bidirectional long short-term memory network (BiLSTM) to capture the potential information of time series data, and combines the attention mechanism to highlight key features, thereby achieving high-precision energy consumption prediction. This process not only improves the accuracy of the prediction, but also ensures the stability and adaptability of the model through the optimization algorithm.

[0048] In the energy consumption control stage, the predicted energy consumption value is compared with the actual energy consumption, and the vehicle state parameters are adjusted according to the energy consumption deviation. When the energy consumption deviation is less than the preset value, the vehicle state parameters are quickly adjusted in an end-to-end manner to ensure that the energy consumption remains in the optimal range. When the deviation is large, the system will issue a voice reminder and switch to the auxiliary control mode based on the dynamic programming method to dynamically adjust parameters such as gear position, transmission ratio and motor speed to further optimize energy consumption control. This dual control strategy not only improves the accuracy of energy consumption control, but also enhances the robustness and reliability of the system.

[0049] Compared with the existing technology, the energy consumption optimal control method for autonomous driving electric mining trucks constructs a comprehensive and accurate driving data set through the integration of physical data and virtual data, providing a solid data foundation for energy consumption optimization. At the same time, advanced neural network models and optimization algorithms are used to achieve high-precision energy consumption prediction and real-time control. In addition, through intelligent control mode switching, the optimal state of energy consumption can be maintained under different working conditions, which significantly improves the operating efficiency and economy of electric mining trucks. This innovative energy consumption control method is not only applicable to autonomous driving electric mining trucks, but can also be extended to other autonomous driving electric vehicle fields, and has broad application prospects and important practical significance.

[0050] See also Figure 6 The second embodiment of the present invention provides an energy consumption optimal control device for an autonomous driving electric mining truck, which includes: The simulation unit 201 is used to obtain a physical data set collected by a sensor component configured on the electric mining truck to be tested, and to establish a virtual entity corresponding to the electric mining truck based on the physical data set; A fusion unit 202 is used to obtain a virtual data set of a virtual entity, and fuse the virtual data set with a physical data set to obtain a driving data set based on multiple working conditions; The prediction unit 203 is used to call the pre-trained PSO-BiLSTM-Attention neural network model to perform energy consumption prediction and obtain a predicted energy consumption value; The adjustment unit 204 is used to compare the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and adjust the state parameters of the electric mining truck according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

[0051] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An optimal energy consumption control method for an autonomous driving electric mining truck, characterized in that: include: Acquire a physical data set collected by a sensor component configured on the electric mining truck to be tested, and establish a virtual entity corresponding to the electric mining truck based on the physical data set; Acquire a virtual data set of a virtual entity, and fuse the virtual data set with a physical data set to obtain a driving data set based on multiple working conditions; Call the pre-trained PSO-BiLSTM-Attention neural network model to predict energy consumption and obtain the predicted energy consumption value; The predicted energy consumption value is compared with the actual energy consumption to obtain an energy consumption deviation, and the state parameters of the electric mining truck are adjusted according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

2. The method for optimal energy consumption control of an autonomous driving electric mining truck according to claim 1 is characterized in that: A physical data set collected by a sensor assembly configured on the electric mining truck to be tested is obtained, and a virtual entity corresponding to the electric mining truck is established based on the physical data set, specifically: Obtain a physical data set collected by a sensor component configured on the electric mining truck to be tested, and use AVL Cruise software to construct and process the physical data set to obtain a complete vehicle model of the electric mining truck; Based on the physical data set, the dynamic equations and control system of the electric mining truck are established using Simulink software, and the dynamic equations and control system are combined with the electric mining truck whole vehicle model to obtain the electric mining truck whole vehicle simulation model.

3. The energy consumption optimal control method for an autonomous driving electric mining truck according to claim 1 is characterized in that: The sensor assembly includes: a speed sensor, a SOC sensor, a tilt sensor, a mass sensor, a humidity sensor, a temperature sensor and a pedal sensor.

4. The method for optimal energy consumption control of an autonomous driving electric mining truck according to claim 1 is characterized in that: The physical data set includes speed, temperature, mass, humidity, slope, pedal opening, and SOC, and the virtual data set includes torque, motor speed, power, gear, and energy consumption.

5. The method for optimal energy consumption control of an autonomous driving electric mining truck according to claim 1 is characterized in that: A virtual data set of a virtual entity is obtained, and the virtual data set is fused with the physical data set to obtain a driving data set based on multiple working conditions, specifically: The virtual data set is calculated by using an MPC control algorithm, and the calculated data set is tested in the loop by using HIL hardware to obtain an output result; Performing verification and comparison processing on the output result to determine whether the output result is greater than a preset value; If not, the output is fed back to the virtual entity for improvement; If so, combine the output results with the physical data set to construct a driving data set based on multiple working conditions.

6. The energy consumption optimal control method for an autonomous driving electric mining truck according to claim 1 is characterized in that: Before calling the pre-trained PSO-BiLSTM-Attention neural network model for energy consumption prediction, it also includes: Acquire energy consumption sample data, divide the energy consumption sample data into a training set and a test set, perform normalization processing on the training set and the test set, and convert the normalized data into a cell array; Create the function to be optimized, set the number of particles, maximum number of iterations and particle dimension of the PSO algorithm, and optimize the cell array based on the function to be optimized and the PSO algorithm; Initialize the position and velocity of the particle, use the training set for training, and use the mean square error between the predicted value and the true value as the fitness function to calculate the fitness value of each particle; Calculate the corresponding individual optimal position and global optimal position according to the fitness value, and update the position and speed of the particle according to the current position, speed, individual optimal position and global optimal position; When it is determined that the fitness of the selected optimal solution is not less than the preset fitness error, continue to optimize according to the PSO optimization algorithm; When it is determined that the fitness of the selected optimal solution is less than the preset fitness error, the optimal parameter combination is output, and the test set is predicted based on the optimal parameter combination to obtain the prediction result; When the prediction result reaches a preset value, the training is terminated to obtain a trained PSO-BiLSTM-Attention neural network model.

7. The method for optimal energy consumption control of an autonomous driving electric mining truck according to claim 1 is characterized in that: The predicted energy consumption value is compared with the actual energy consumption to obtain the energy consumption deviation, and the state parameters of the electric mining truck are adjusted according to the energy consumption deviation, specifically: Compare the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and determine whether the energy consumption deviation is less than a preset deviation value; If so, adjusting the vehicle state parameters in an end-to-end manner according to the predicted energy consumption value; If not, a voice reminder will be given and the system will switch to auxiliary control mode based on dynamic programming to adjust the gear position, transmission ratio and motor speed.

8. An energy consumption optimal control device for an autonomous driving electric mining truck, characterized in that: include: A simulation unit, used for acquiring a physical data set collected by a sensor assembly configured on the electric mining truck to be tested, and establishing a virtual entity corresponding to the electric mining truck based on the physical data set; A fusion unit, used for acquiring a virtual data set of a virtual entity, and fusing the virtual data set with a physical data set to obtain a driving data set based on multiple working conditions; The prediction unit is used to call the pre-trained PSO-BiLSTM-Attention neural network model to predict energy consumption and obtain the predicted energy consumption value; The adjustment unit is used to compare the predicted energy consumption value with the actual energy consumption to obtain an energy consumption deviation, and adjust the state parameters of the electric mining truck according to the energy consumption deviation to ensure that the energy consumption of the electric mining truck remains within a preset optimal range.

Images