End-to-end energy management control method fusing laser radar and LSTM-transformer speed prediction

Abstract

The invention relates to an end-to-end energy management control method fusing laser radar and LSTM-transformer speed prediction, and belongs to the field of hybrid electric vehicle energy management. According to the method, front obstacles are recognized through a laser radar, speed prediction is carried out in combination with an end-to-end LSTM-transformer model, and the future vehicle speed and the required power are obtained. An equivalent consumption minimization strategy (ECMS) is utilized to optimize power distribution of fuel cells and cells, and a fuel cell power change penalty factor is introduced to inhibit performance degradation of the fuel cells. In addition, a multi-objective optimization method is adopted, the battery energy and the service life of the fuel battery are taken into consideration, and comprehensive optimization of an energy management strategy is achieved. According to the method, through end-to-end modeling and optimization, the efficiency of the fuel cell system is effectively improved, the service life of the system is prolonged, the total cost of the fuel cell and the battery is further reduced, and meanwhile, the energy conservation and emission reduction performance of the hybrid electric vehicle is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of hybrid vehicle energy management, and specifically relates to an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction. Background Art

[0002] With the global attention to energy conservation and emission reduction, fuel cell hybrid electric vehicles (FCHEV) have received more and more attention due to their high efficiency and zero emission characteristics. FCHEV uses a combination of fuel cells and batteries to provide power while achieving efficient energy management to meet the power requirements under different working conditions. An effective energy management strategy (EMS) is crucial to improving the overall performance of FCHEV. Existing energy management strategies can generally be divided into rule-based strategies, optimization strategies, and learning-based strategies. Among them, the control method based on real-time speed prediction has received widespread attention due to its strong adaptability and good real-time performance.

[0003] Current speed prediction methods mainly focus on short-term prediction and can be divided into model-based methods and data-driven methods. Model-based methods usually rely on the vehicle's historical motion state for prediction, while data-driven methods use big data analysis to improve prediction accuracy. However, these methods usually face several challenges. First, existing speed prediction algorithms mostly rely on the motion state of the ego vehicle, and the prediction accuracy will be significantly reduced when the external environment changes significantly. In addition, traditional methods often fail to effectively integrate surrounding environmental information, such as the status of the preceding vehicle, pedestrian dynamics, etc., resulting in limited accuracy in speed prediction.

[0004] As an emerging sensing technology, LiDAR can provide high-precision environmental perception information. By integrating LiDAR data with the LSTM-transformer model, changes in the surrounding environment can be captured more accurately, thereby improving the accuracy of speed prediction. At the same time, the LSTM-transformer-based model has the advantage of processing time series data and can respond quickly to dynamically changing traffic scenes.

[0005] Although previous studies have attempted to combine different information sources for speed prediction, existing methods are still insufficient in terms of real-time performance and accuracy in dynamic traffic environments. In addition, current energy management strategies are often based on static power allocation models and lack the ability to flexibly respond to transient environmental factors. Therefore, how to use lidar data to improve the accuracy of speed prediction and effectively apply it to the energy management control of FCHEV has become an urgent problem to be solved. Summary of the invention

[0006] The purpose of the present invention is to provide an end-to-end energy management control method that integrates laser radar and LSTM-transformer speed prediction to improve the collaborative working efficiency of fuel cells and batteries by acquiring and analyzing surrounding environmental information in real time. The method of the present invention can not only improve the overall energy efficiency of FCHEV, but also provide an important theoretical basis and technical support for the realization of future intelligent transportation systems.

[0007] To achieve the above object, the technical solution of the present invention is: an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction, comprising:

[0008] The laser radar is used to obtain point cloud data of the vehicle's surrounding environment online, and after three-dimensional target detection and identification of the vehicle's surrounding environment information, target tracking is performed;

[0009] The vehicle's surrounding environment information after target tracking is input into the LSTM-transformer speed prediction model as real-time state quantity and constraint quantity, and the current predicted speed sequence of the vehicle is generated through feature extraction and time series prediction;

[0010] Through the current predicted speed sequence, the current power is obtained as input, and the objective function of the equivalent consumption minimization strategy ECMS is constructed through equivalent hydrogen consumption, fuel cell degradation and power battery degradation for multi-objective optimization, so as to realize the transformation of the predicted speed sequence into the optimal power distribution of fuel cells and lithium-ion batteries.

[0011] In one embodiment of the present invention, multi-objective optimization refers to taking into account battery degradation and minimizing equivalent hydrogen consumption, adjusting the equivalent factor, and obtaining the optimal power sequence.

[0012] In one embodiment of the present invention, point cloud data of the vehicle's surroundings are obtained online through a laser radar, and target tracking is performed after three-dimensional target detection and identification of the vehicle's surroundings information. The specific implementation is as follows:

[0013] Calibration: Use a laser rangefinder and a level to measure the external parameter matrix of the laser radar relative to the vehicle coordinate system;

[0014] Target vehicle data processing: Kalman filter denoising is performed on the point cloud data of the vehicle's surrounding environment obtained online by the lidar, and then the denoised point cloud data is processed by the PointPillar model to perform three-dimensional target detection. The obtained target information is used for environmental understanding and real-time tracking is performed through a multi-target tracking algorithm;

[0015] Driving vehicle data acquisition: The vehicle's current driving speed and acceleration are obtained through the CAN bus.

[0016] In one embodiment of the present invention, the laser radar is installed at the center of the front of the vehicle.

[0017] In one embodiment of the present invention, the target information is the target vehicle position P in front of the traveling vehicle. f , Size D f , yaw angle and vehicle speed V p , and the pedestrian position P p , obstacles are blocked.

[0018] In one embodiment of the present invention, the prediction method of the LSTM-transformer speed prediction model is: the sequence data is processed by LSTM, and the input data X = [x1, x2, ..., x T ], LSTM generates hidden state H = [h1,h2,...,h T ], LSTM updates and maintains the hidden state and memory unit state in sequence through the gating mechanism of input gate i, forget gate f, candidate memory C and output gate o. Its core formula is:

[0019]

[0020] In the formula, 1≤t≤T, x t is the input of the current time step, h t-1 is the hidden state of the previous time step, C t-1 The cell state at the previous time step, is the cell state at the current moment, σ is the activation function Sigmoid, tanh is the activation function, i t 、f t and t are the outputs of the corresponding gates, W i , W f and W o are the weights of the corresponding gates, b i , b f and b o are the bias of the corresponding gate, C t , W C and b C are memory cell outputs, weights and biases, h t is the hidden state at the current time step;

[0021] The hidden state H generated by LSTM is used as the input of the transformer to obtain the current predicted speed sequence v pre =Transformer(H).

[0022] In one embodiment of the present invention, the LSTM-transformer speed prediction model is composed of three layers of LSTM and transformer. First, the target vehicle position P in front of the traveling vehicle is f , Size D f , yaw angle and vehicle speed V p The input of lstm1 is used as the input of lstm2, the input of lstm1 and the speed and acceleration of the target vehicle are used as the input of lstm2, the output of lstm1, the output of lstm2, and the static obstacle are used as the input of lstm3, and the output of lstm1, lstm2 and lstm3 are used as the input of transformer, and finally the current predicted speed V is obtained. pre .

[0023] In one embodiment of the present invention, the functional relationship between the current predicted speed sequence and the power at the current moment is:

[0024]

[0025] Where P pre is the power at the current moment, v pre is the current predicted speed; m is the mass of the vehicle; F f is the rolling resistance; g = 9.81 m·s -2 is the acceleration of gravity; f=0.009 is the rolling resistance coefficient; α is the road slope angle (°); F a is air resistance; C d =0.312 is the air resistance coefficient; A = 2.06m 2 is the frontal area; ρ a =1.2N·s 2 ·m -4 is the air density; F i is the slope resistance; F j is the acceleration resistance; δ=1.05 is the rotation mass conversion factor; dv pre / dt is the driving acceleration (m·s -2 ).

[0026] In one embodiment of the present invention, the objective function of the constructed equivalent consumption minimization strategy ECMS is:

[0027]

[0028] In the formula, J ECMS Indicates the instantaneous hydrogen consumption of the fuel cell power system; is the instantaneous hydrogen consumption of the fuel cell; P B (t) is the power of lithium battery; P FC (t) is the fuel cell power; KEF is the equivalent factor, δ is the penalty factor for fuel cell power variation, is the lower calorific value of hydrogen (kJ·g -1 );

[0029] The constraints are

[0030]

[0031] Where P B (t) is the power on the DC bus, and the subscripts max and min are the maximum and minimum values ​​of the corresponding variables, respectively.

[0032] In one embodiment of the present invention, the SOC change rate is solved by SQP, and the objective function is at the current iteration point u=[P B ,P FC ] T The form is:

[0033]

[0034] In the formula, is the gradient of the objective function at the current point, Δu is the update step size, and Hk is the approximate value of the second-order derivative of the objective function (usually obtained by fitting the Hessian matrix).

[0035] In one embodiment of the present invention, based on the generated optimal SOC change rate curve The target vehicle predicts the speed and adjusts the vehicle speed reference trajectory V ref (t), get the optimal P B (t) and P FC (t) power distribution.

[0036] The present invention also provides a computer-readable storage medium, on which computer program instructions that can be executed by a processor are stored. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0037] Compared with the prior art, the present invention has the following beneficial effects: the end-to-end energy management control method proposed in the present invention integrates laser radar and LSTM-transformer speed prediction, which uses laser radar to online identify surrounding environment information, outputs speed prediction sequence, and combines equivalent fuel minimization strategy to achieve optimal power allocation of fuel cells and lithium-ion batteries, significantly improves the fuel economy, hydrogen consumption and battery degradation rate of the vehicle, extends the service life of fuel cells and batteries, and further improves the economy and environmental performance of hybrid vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1The present invention is a flowchart of an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction. DETAILED DESCRIPTION

[0039] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0040] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] The present invention provides an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction, comprising:

[0043] The laser radar is used to obtain point cloud data of the vehicle's surrounding environment online, and after three-dimensional target detection and identification of the vehicle's surrounding environment information, target tracking is performed;

[0044] The vehicle's surrounding environment information after target tracking is input into the LSTM-transformer speed prediction model as real-time state quantity and constraint quantity, and the current predicted speed sequence of the vehicle is generated through feature extraction and time series prediction;

[0045] Through the current predicted speed sequence, the current power is obtained as input, and the objective function of the equivalent consumption minimization strategy ECMS is constructed through equivalent hydrogen consumption, fuel cell degradation and power battery degradation for multi-objective optimization, so as to realize the transformation of the predicted speed sequence into the optimal power distribution of fuel cells and lithium-ion batteries.

[0046] The following is the specific implementation process of the present invention.

[0047] like Figure 1 As shown, an example of the present invention provides an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction, comprising the following steps:

[0048] Step S1: Obtain point cloud data of the vehicle's surroundings online through a laser radar, perform three-dimensional target detection, identify vehicle environment information, and then perform target tracking.

[0049] Step S2: Input the environmental information after target tracking into the Transform+LSTM model as the real-time state quantity and constraint quantity, and generate the current predicted speed sequence of the vehicle through feature extraction and time series prediction.

[0050] Step S3, using the current predicted speed sequence to obtain the current power as input, and constructing the objective function of ECMS through equivalent factors to distribute power;

[0051] Step S4: converting the vehicle speed prediction sequence into the optimal power distribution of the fuel cell and the lithium-ion battery.

[0052] Step S1 specifically includes the following:

[0053] Calibration: Use a laser rangefinder and a level to measure the external parameter matrix of the laser radar relative to the vehicle coordinate system. The laser radar is installed at the center of the front of the vehicle to obtain point cloud data.

[0054] Target vehicle data processing: The acquired point cloud data is subjected to Kalman filtering for noise reduction, and then the noise-reduced point cloud data is processed through the PointPillar model for three-dimensional target detection. The obtained target information is used for environmental understanding and real-time tracking is performed through a multi-target tracking algorithm.

[0055] Vehicle data acquisition: The vehicle's current speed and acceleration are acquired through the CAN bus

[0056] The target information is the target vehicle position P in front of the moving vehicle f , Size D f , yaw angle and vehicle speed V p , and the pedestrian position P p , obstacles are blocked.

[0057] In step S2, the LSTM-transformer speed prediction model is calculated. First, LSTM processes the sequence data. The input data X = [x1, x2, ..., x T ], LSTM generates hidden state H = [h1,h2,...,h T ], LSTM updates and maintains the hidden state and memory unit state in sequence through the gating mechanism of input gate i, forget gate f, candidate memory C and output gate o. Its core formula is:

[0058]

[0059] In the formula, 1≤t≤T, x t is the input of the current time step, h t-1 is the hidden state of the previous time step, C t-1 The cell state at the previous time step, is the cell state at the current moment, σ is the activation function Sigmoid, tanh is the activation function, i t 、f t and t are the outputs of the corresponding gates, W i , W f and W o are the weights of the corresponding gates, b i , b f and b o are the bias of the corresponding gate, C t , W C and b C are memory cell outputs, weights and biases, h t is the hidden state at the current time step;

[0060] The hidden state H generated by LSTM is used as the input of the transformer to obtain the current predicted speed sequence v pre =Transformer(H).

[0061] In step S2, the LSTM-transformer model is specifically composed of three layers of LSTM and transformer. First, the target vehicle position P in front of the moving vehicle is f , Size D f , yaw angle and vehicle speed V p The input of lstm1 is used as the input of lstm2, the output of lstm1, lstm2 and the static obstacle are used as the input of lstm3, and the output of lstm1, lstm2 and lstm3 are used as the input of transformer. Finally, the current predicted speed V is obtained. pre .

[0062] In step S3, the functional relationship between the current predicted speed sequence and the power at the current moment is:

[0063]

[0064] Where P pre is the power at the current moment, v pre is the current predicted speed (km·h-1), m is the mass of the vehicle; F f is the rolling resistance; g = 9.81 m·s -2is the acceleration of gravity; f=0.009 is the rolling resistance coefficient; α is the road slope angle (°); F a is air resistance; C d =0.312 is the air resistance coefficient; A = 2.06m 2 is the frontal area; ρ a =1.2N·s 2 ·m -4 is the air density; F i is the slope resistance; F j is the acceleration resistance; δ=1.05 is the rotation mass conversion factor; dv pre / dt is the driving acceleration (m·s -2 ).

[0065] In step S3, the objective function of the constructed equivalent consumption minimization strategy ECMS is:

[0066]

[0067] In the formula, J ECMS Indicates the instantaneous hydrogen consumption of the fuel cell power system; is the instantaneous hydrogen consumption of the fuel cell; P B (t) is the power of lithium battery; P FC (t) is the fuel cell power; K EF is the equivalent factor, δ is the penalty factor for fuel cell power variation, is the lower calorific value of hydrogen (kJ·g -1 ).

[0068] The constraints are

[0069]

[0070] Where P B (t) is the power on the DC bus, and the subscripts max and min are the maximum and minimum values ​​of the corresponding variables, respectively.

[0071] In step S3, the SOC change rate is solved by SQP, and the objective function is at the current iteration point u = [P B ,P FC ] T The form is:

[0072]

[0073] In the formula, is the gradient of the objective function at the current point, Δu is the update step size, and Hk is the approximate value of the second-order derivative of the objective function (usually obtained by fitting the Hessian matrix).

[0074] In step S4, based on the optimal SOC change rate curve generated in step S3 The target vehicle predicts the speed and adjusts the vehicle speed reference trajectory V ref (t), get the optimal P B (t) and P FC (t) power distribution.

[0075] The present invention also provides a computer-readable storage medium, on which computer program instructions that can be executed by a processor are stored. When the processor executes the computer program instructions, the method steps described above can be implemented.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0080] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. An end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction, characterized in that: include: The laser radar is used to obtain point cloud data of the vehicle's surrounding environment online, and after three-dimensional target detection and identification of the vehicle's surrounding environment information, target tracking is performed; The vehicle's surrounding environment information after target tracking is input into the LSTM-transformer speed prediction model as real-time state quantity and constraint quantity, and the current predicted speed sequence of the vehicle is generated through feature extraction and time series prediction; Through the current predicted speed sequence, the current power is obtained as input, and the objective function of the equivalent consumption minimization strategy ECMS is constructed through equivalent hydrogen consumption, fuel cell degradation and power battery degradation for multi-objective optimization, so as to realize the transformation of the predicted speed sequence into the optimal power distribution of fuel cells and lithium-ion batteries.

2. According to claim 1, an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction is characterized in that: Multi-objective optimization refers to taking into account battery degradation and minimizing equivalent hydrogen consumption, adjusting the equivalent factors, and obtaining the optimal power sequence.

3. According to claim 1, an end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction is characterized in that: The point cloud data of the vehicle's surroundings is obtained online through the laser radar, and after three-dimensional target detection and identification of the vehicle's surrounding environment information, target tracking is performed. The specific implementation is as follows: Calibration: Use a laser rangefinder and a level to measure the external parameter matrix of the laser radar relative to the vehicle coordinate system; Target vehicle data processing: Kalman filter denoising is performed on the point cloud data of the vehicle's surrounding environment obtained online by the lidar, and then the denoised point cloud data is processed by the PointPillar model to perform three-dimensional target detection. The obtained target information is used for environmental understanding and real-time tracking is performed through a multi-target tracking algorithm; Driving vehicle data acquisition: The vehicle's current driving speed and acceleration are obtained through the CAN bus.

4. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 1 or 3, characterized in that: The laser radar is installed in the center of the front of the vehicle.

5. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 3 is characterized in that: The target information is the target vehicle position P in front of the moving vehicle f , Size D f , yaw angle and vehicle speed V p , and the pedestrian position P p , obstacles are blocked.

6. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 1 is characterized in that: The prediction method of the LSTM-transformer speed prediction model is as follows: the sequence data is processed by LSTM, the input data X = [x1, x2, ..., xT], and the LSTM generates the hidden state H = [h1, h2, ..., h T ], LSTM updates and maintains the hidden state and memory unit state in sequence through the gating mechanism of input gate i, forget gate f, candidate memory C and output gate o. Its core formula is: In the formula, 1≤t≤T, x t is the input of the current time step, h t-1 is the hidden state of the previous time step, C t-1 The cell state at the previous time step, is the cell state at the current moment, σ is the activation function Sigmoid, tanh is the activation function, i t 、f t and t are the outputs of the corresponding gates, W i , W f and Wo are the weights of the corresponding gates, b i , b f and b o are the bias of the corresponding gate, C t , W C and b C are memory cell outputs, weights and biases, h t is the hidden state at the current time step; The hidden state H generated by LSTM is used as the input of the transformer to obtain the current predicted speed sequence v pre =Transformer(H).

7. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 1 or 7, characterized in that: The LSTM-transformer speed prediction model consists of three layers of LSTM and transformer. First, the target vehicle position P in front of the moving vehicle is f , Size D f , yaw angle and vehicle speed V p The input of lstm1 is used as the input of lstm2, the input of lstm1 and the speed and acceleration of the target vehicle are used as the input of lstm2, the output of lstm1, the output of lstm2, and the static obstacle are used as the input of lstm3, and the output of lstm1, lstm2 and lstm3 are used as the input of transformer, and finally the current predicted speed V is obtained. pre .

8. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 1 is characterized in that: The functional relationship between the current predicted speed sequence and the power at the current moment is: Where P pre is the power at the current moment, v pre is the current predicted speed; m is the mass of the vehicle; F f is the rolling resistance; g is the acceleration of gravity; f is the rolling resistance coefficient; α is the road slope angle; F a is air resistance; C d is the air resistance coefficient; A is the windward area; ρ a is the air density; F i is the slope resistance; F j is the acceleration resistance; δ is the rotation mass conversion factor; dv pre / dt is the driving acceleration.

9. The end-to-end energy management control method integrating laser radar and LSTM-transformer speed prediction according to claim 1 is characterized in that: The objective function of the constructed equivalent consumption minimization strategy ECMS is: In the formula, J ECMS Indicates the instantaneous hydrogen consumption of the fuel cell power system; is the instantaneous hydrogen consumption of the fuel cell; P B (t) is the power of lithium battery; P FC (t) is the fuel cell power; K EF is the equivalent factor, δ is the penalty factor for fuel cell power variation; It is the low calorific value of hydrogen; The constraints are Where P B (t) is the power on the DC bus, and the subscripts max and min are the maximum and minimum values ​​of the corresponding variables, respectively.

10. A computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor, and when the processor executes the computer program instructions, the method steps according to any one of claims 1 to 9 can be implemented.

Images