Energy management and control method for complex working conditions of mine vehicle

Abstract

The invention relates to the technical field of mine vehicle energy management and control, and particularly discloses an energy management and control method for a mine vehicle under a complex working condition, and the method comprises the steps: obtaining a mine vehicle dynamics model and mine vehicle operation related information; global planning is carried out according to the mine vehicle dynamic model and the mine vehicle operation related information in combination with a dynamic planning algorithm, and mine vehicle operation global planning control quantity is obtained; local optimization is carried out on the real-time operation information of the mine vehicle according to a model prediction control algorithm, and the local planning control quantity of mine vehicle operation is obtained; and according to the global planning control quantity of the mine vehicle and the local planning control quantity of the mine vehicle, carrying out weighted hybrid coordination processing to obtain the actual operation control quantity of the mine vehicle. According to the energy management and control method for the complex working condition of the mine vehicle, integrated consideration of real-time response and energy management of the mine vehicle under the complex working condition can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management and control for mining vehicles, and particularly to an energy management and control method for complex working conditions of mining vehicles. Background Art

[0002] With the gradual development of mining dump trucks towards hybrid and pure electric drive, the integrated technology of energy management and motion control for mining vehicles under complex working conditions (such as sharp changes in slope and heavy-load operation) faces severe challenges. In mining areas, how to optimize energy use while ensuring vehicle safety control has become an important goal for improving system energy efficiency and stability. However, in the prior art, the energy management system and the control system are usually designed separately, and this separation causes the system to be unable to quickly respond to changes in working conditions during actual application, affecting the overall energy efficiency and control performance.

[0003] The energy management and control strategies for mining vehicles in the prior art are mainly divided into the following categories: (1) Fixed-rule-based control: This control method allocates vehicle energy and controls power output through preset rules and thresholds. Although this method is simple to operate, it lacks flexibility and cannot adjust the strategy according to dynamic working conditions. For example, when the slope changes sharply or the vehicle is operating under heavy load, the fixed rules cannot adapt to complex working condition changes, resulting in decreased energy efficiency and control failure. (2) Vehicle-dynamics-model-based control: This method relies on the physical model of the vehicle and optimizes energy distribution and power control by calculating the dynamic characteristics of the vehicle. However, the working conditions in mines are complex and changeable, especially under sharp slope changes and heavy-load operation, and it is difficult for the dynamic model to quickly respond to sudden working conditions. The response speed of this method is slow, which easily leads to uneven vehicle energy distribution, increasing fuel consumption or power consumption. (3) Prediction-control-based method: Model predictive control (MPC) is a relatively advanced control method, which adjusts the control input and energy output of the vehicle by predicting short-term working conditions to adapt to the dynamic environment. However, the optimization effect of MPC depends on the prediction accuracy of short-term future working conditions and cannot achieve optimal energy management and control globally. Especially in the complex dynamic environment of mining areas, the accuracy of short-term prediction is insufficient to ensure optimal control effects.

[0004] In summary, the energy management and control of existing mining vehicles usually consider energy management and motion control separately, resulting in insufficient coordination between energy management and control during actual vehicle driving. Traditional energy management methods, such as dynamic programming (DP), focus on global energy distribution and optimize energy use by planning power output throughout the driving process. However, DP cannot respond to the dynamic changes of vehicles under complex working conditions in real time. Especially when encountering sharp slope changes, load fluctuations, or sudden deceleration of the vehicle in front, its local control ability is weak.

[0005] Therefore, how to achieve real-time response of mining vehicles under complex working conditions and integrated consideration of energy management has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0006] The present invention provides an energy management and control method for complex working conditions of mining vehicles, which solves the problem that mining vehicles in related technologies cannot achieve integrated consideration of real-time response and energy management under complex working conditions.

[0007] As an aspect of the present invention, there is provided an energy management and control method for complex working conditions of mining vehicles, which includes:

[0008] Obtain the dynamic model of the mining vehicle and information related to the operation of the mining vehicle, where the information related to the operation of the mining vehicle at least includes vehicle load, driving path, driving map data, and path node information where the load changes.

[0009] Perform global planning based on the dynamic model of the mining vehicle and the information related to the operation of the mining vehicle in combination with the dynamic programming algorithm to obtain the global planning control quantity of the mining vehicle operation.

[0010] Perform local optimization on the real-time operation information of the mining vehicle according to the model predictive control algorithm to obtain the local planning control quantity of the mining vehicle operation.

[0011] Perform weighted mixing and coordination processing based on the global planning control quantity and the local planning control quantity of the mining vehicle to obtain the actual control quantity of the mining vehicle operation.

[0012] Further, performing global planning based on the dynamic model of the mining vehicle and the information related to the operation of the mining vehicle in combination with the dynamic programming algorithm includes:

[0013] Determine the state variables and control variables of the dynamic programming algorithm according to the dynamic model of the mining vehicle and the information related to the operation of the mining vehicle, where the state variables include the battery charge state and the current speed of the mining vehicle, and the control variables include the engine output power and the motor output power.

[0014] Determine the objective function of the dynamic programming algorithm.

[0015] Form multiple groups of iterative variables by combining the state variables and the control variables, where each group of iterative variables includes a state variable factor and a control variable factor.

[0016] Iteratively optimize the objective function of the dynamic programming algorithm by polling and using multiple groups of the iterative variables to obtain the global planning control quantity of the mining vehicle operation, where one group of iterative variables is selected for each iterative optimization.

[0017] Furthermore, the real-time operation information of the mine vehicle is locally optimized according to the model predictive control algorithm to obtain the local planning control quantity of the mine vehicle operation, including:

[0018] Predict the operation state information of the mine vehicle within the next N time steps according to the current operation information of the mine vehicle, where the operation state information at least includes the operation speed, battery state information, and the distance information from the vehicle in front;

[0019] For each time step, solve the optimal control input information for the next N time steps through the model predictive control algorithm;

[0020] Perform local optimization according to the optimal control input information of the current time step, and repeat the above steps to obtain the local planning control quantity of the mine vehicle operation.

[0021] Furthermore, predict the operation state information of the mine vehicle within the next N time steps according to the current operation information of the mine vehicle, including:

[0022] Input the historical speed and historical slope information of the vehicle in front into the LSTM network to obtain the predicted vehicle speed and predicted slope information of the vehicle in front within the next N time steps;

[0023] Predict the operation state information of the mine vehicle within the next N time steps according to the predicted vehicle speed and predicted slope information within the next N time steps and the current operation information of the mine vehicle.

[0024] Furthermore, for each time step, solve the optimal control input information for the next N time steps through the model predictive control algorithm, including:

[0025] Determine the objective function of the model predictive control algorithm, and the expression of the objective function of the model predictive control algorithm is:

[0026]

[0027] where γ d represents the vehicle distance constraint weight, d front,k represents the vehicle distance from the vehicle in front of the current mine vehicle, d limit represents the safety distance limit, α v represents the speed weight of the mine vehicle, β SOC represents the deviation weight of the battery state information, δ P represents the power consumption weight;

[0028] Optimize the objective function according to the preset state variable constraint conditions, preset control variable constraint conditions, and the preset conditions of the vehicle distance from the vehicle in front of the mine vehicle to solve the optimal control input information for the next N time steps.

[0029] Further, perform weighted hybrid coordination processing based on the global planning control quantity and the local planning control quantity of the mining vehicle, including:

[0030] Perform a weighted hybrid strategy based on the global planning control quantity and the local planning control quantity of the mining vehicle;

[0031] Dynamically adjust the weighted hybrid weight factor in the weighted hybrid strategy according to the real-time working conditions, so that the global planning control quantity and the local planning control quantity of the mining vehicle reach dynamic balance.

[0032] Further, performing a weighted hybrid strategy based on the global planning control quantity and the local planning control quantity of the mining vehicle includes:

[0033] When the load of the mining vehicle is less than the preset load threshold, the expression of the weighted hybrid strategy is:

[0034] P engine,out = α·P engine,DP +(1 - α)·P engine,MPC ,

[0035] P motor,out = α·P motor,DP +(1 - α)·P motor,MPC ,

[0036] When the load of the mining vehicle is not less than the preset load threshold, the expression of the weighted hybrid strategy is:

[0037] P engine,out = α·P engine,MPC +(1 - α)·P engine,DP ,

[0038] P motor,out = α·P motor,MPC +(1 - α)·P motor,DP ,

[0039] Wherein, P engine,out represents the actual output power of the engine of the mining vehicle, P motor,out represents the actual output power of the motor of the mining vehicle, P engine,DP represents the global planning output power of the engine of the mining vehicle, P motor,DP represents the global planning output power of the motor of the mining vehicle, P engine,MPC represents the local planning output power of the engine of the mining vehicle, P motor,MPC represents the local planning output power of the motor of the mining vehicle, α represents the weighted hybrid weight factor, and 0 ≤ α ≤ 1.

[0040] Further, when the load of the mining vehicle is less than the preset load threshold, the weighted mixing weight factor in the weighted mixing strategy is dynamically adjusted according to the real-time working conditions, including:

[0041] When the distance between the mining vehicle and the vehicle in front is greater than the preset distance threshold and the fluctuation range of the real-time working conditions is within the preset range, increase the weighted mixing weight factor to increase the weight of the global planning control amount of the mining vehicle;

[0042] When the distance between the mining vehicle and the vehicle in front is less than the preset distance threshold and the fluctuation range of the real-time working conditions is not within the preset range, reduce the weighted mixing weight factor to increase the weight of the local planning control amount of the mining vehicle.

[0043] Further, when the load of the mining vehicle is not less than the preset load threshold, the weighted mixing weight factor in the weighted mixing strategy is dynamically adjusted according to the real-time working conditions, including:

[0044] Calculate the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle;

[0045] Dynamically adjust the weighted mixing weight factor according to the TTC, the warning coefficient and the distance to the vehicle in front. The dynamic adjustment expression of the weighted mixing weight factor is:

[0046]

[0047] where, K represents the warning coefficient, d front represents the distance to the vehicle in front of the mining vehicle, d limit represents the safety distance threshold, d b represents the braking distance.

[0048] Further, calculating the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle includes:

[0049] Calculate the TTC and the warning coefficient respectively according to the running speed, the distance to the vehicle in front, the relative speed and the load of the mining vehicle. The calculation formula of the warning coefficient is:

[0050]

[0051] where, K represents the warning coefficient, d front represents the distance to the vehicle in front of the mining vehicle, d b represents the braking distance, m represents the total mass of the mining vehicle, v self represents the running speed of the mining vehicle, F brake represents the braking force of the mining vehicle, d w represents the warning distance, d w =d b +dlimit , d limit represents the safety distance threshold;

[0052] The calculation formula of the TTC is as follows:

[0053]

[0054] where, v rel represents the relative speed between the mining vehicle and the vehicle in front, v rel = v self - v front and v front represents the speed of the vehicle in front of the mining vehicle.

[0055] The energy management and control method for complex working conditions of mining vehicles provided by the present invention combines global dynamic programming and model predictive control. Among them, global dynamic programming can provide a global energy management plan for mining vehicles to ensure the optimal energy efficiency during the overall journey, while model predictive control makes dynamic adjustments to the real-time changes of working conditions through rolling optimization. This energy management and control method for complex working conditions of mining vehicles can dynamically adjust the power output of the engine and the motor considering factors such as slope, load, and vehicle distance through a control strategy that combines global and local aspects, achieving the best fuel consumption and driving safety, enabling the mining vehicle to optimize energy use globally and flexibly respond to emergencies under actual working conditions, improving the response speed and flexibility of the control of mining vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification, and are used together with the following specific embodiments to explain the present invention, but do not constitute a limitation to the present invention.

[0057] Figure 1 is a flowchart of the energy management and control method for complex working conditions of mining vehicles provided by the present invention.

[0058] Figure 2 is a flowchart of the global planning provided by the present invention.

[0059] Figure 3 is a flowchart of the local planning provided by the present invention.

[0060] Figure 4 is a flowchart of the weighted mixing of global and local provided by the present invention.

[0061] Figure 5a is a schematic diagram of the simulation effect of the iterative dynamic programming IDP and the traditional dynamic programming DP of the present invention.

[0062] Figure 5bThis is a comparison diagram of the fuel consumption and battery state based on the combination of IDP and MPC in the present invention and the simulation effects of the fuel consumption and battery state when only MPC is applied alone. Detailed implementation manners

[0063] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0064] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to describe the embodiments of the present invention here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0066] In this embodiment, an energy management and control method for complex working conditions of mining vehicles is provided. Figure 1 It is a flowchart of the energy management and control method for complex working conditions of mining vehicles provided according to the embodiments of the present invention, as Figure 1 shown, and includes:

[0067] S100. Obtain the dynamic model of the mining vehicle and the information related to the operation of the mining vehicle. The information related to the operation of the mining vehicle at least includes vehicle load, driving path, driving map data, and path node information where the load changes.

[0068] In the embodiments of the present invention, the dynamic model of the mining vehicle may specifically include the engine output power MAP diagram of the mining vehicle, the motor output power MAP diagram of the mining vehicle, and the working efficiency of the motor and the engine of the mining vehicle, etc.

[0069] S200. Perform global planning based on the mine vehicle dynamics model, information related to the operation of the mine vehicle, and in combination with the dynamic programming algorithm to obtain the global planning control quantity for the operation of the mine vehicle.

[0070] In the embodiment of the present invention, global dynamic planning can be specifically performed according to the mine vehicle dynamics model and information related to the operation of the mine vehicle. This global dynamic planning can provide a global energy management plan for the mine vehicle to ensure the optimal energy efficiency during the overall journey, and based on this, the global planning control quantity for the operation of the mine vehicle is obtained.

[0071] It should be understood that the global planning control quantity for the operation of the mine vehicle can specifically include the global engine output power for the operation of the mine vehicle and the global motor output power for the operation of the mine vehicle.

[0072] S300. Perform local optimization on the real-time operation information of the mine vehicle according to the model predictive control algorithm to obtain the local planning control quantity for the operation of the mine vehicle.

[0073] In the embodiment of the present invention, performing local optimization on the real-time operation information of the mine vehicle through the model predictive control algorithm can be specifically understood as making dynamic adjustments to the real-time changes of the working conditions through rolling optimization, so as to be able to control the mine vehicle in a timely manner when encountering sharp changes in slope, load fluctuations, or sudden deceleration of the vehicle in front.

[0074] S400. Perform weighted hybrid coordination processing according to the global planning control quantity and the local planning control quantity of the mine vehicle to obtain the actual control quantity for the operation of the mine vehicle.

[0075] It should be understood that by performing weighted hybrid coordination processing on the global planning control quantity and the local planning control quantity, it is possible to optimize the energy use globally and flexibly respond to unexpected situations under actual working conditions.

[0076] In summary, the energy management and control method for mine vehicles in complex working conditions provided by the present invention combines global dynamic planning and model predictive control. Among them, global dynamic planning can provide a global energy management plan for mine vehicles to ensure the optimal energy efficiency during the overall journey, while model predictive control makes dynamic adjustments to the real-time changes of working conditions through rolling optimization. This energy management and control method for mine vehicles in complex working conditions, through a control strategy that combines global and local aspects, can dynamically adjust the power output of the engine and the motor considering factors such as slope, load, and vehicle distance, achieving the best fuel consumption and driving safety, enabling the mine vehicle to not only optimize the energy use globally but also flexibly respond to unexpected situations under actual working conditions, and improving the response speed and flexibility of the control of the mine vehicle.

[0077] In an embodiment of the present invention, global planning is performed according to the mine vehicle dynamics model, information related to the operation of the mine vehicle, and in combination with a dynamic programming algorithm, as Figure 2 shown, including:

[0078] S210. Determine the state variables and control variables of the dynamic programming algorithm according to the mine vehicle dynamics model and information related to the operation of the mine vehicle, where the state variables include the battery charge state and the current speed of the mine vehicle, and the control variables include the engine output power and the motor output power;

[0079] It should be noted that in the embodiment of the present invention, the state variables of the dynamic programming specifically for the Iterative Dynamic Programming (IDP) algorithm may specifically include:

[0080] SOC (state of charge of the battery): used to measure the remaining battery power, and the value range is SOC ∈ [0.3, 0.8];

[0081] The current speed v of the mine vehicle: used to describe the driving speed of the current mine vehicle, and the value range is v ∈ [5, 55] km / h;

[0082] Slope θ: used to describe the slope of the current road, with the unit of radian (rad), and it is a known constant in the IDP algorithm.

[0083] The control variables include:

[0084] Engine power P engine : The power output provided by the engine, and the value range is P engine ∈ [0, 1200] kW;

[0085] Motor power P motor : The power output provided by the motor, and the value range is P motor ∈ [-880, 1400] kW. Positive power indicates that the motor provides driving force, and negative power indicates that the motor recovers energy during braking.

[0086] S220. Determine the objective function of the dynamic programming algorithm;

[0087] It should be understood that the goal of the IDP algorithm is to minimize fuel consumption and battery state fluctuations on the entire driving path while maintaining the vehicle speed within a reasonable range. The objective function of the DP algorithm can be expressed as:

[0088]

[0089] Where: D represents the path distance from the starting point to the ending point; α, β, γ, δ all represent the weight coefficients of different terms; Fueld Indicates the fuel consumption of the d-th section of the path; SOC d Indicates the battery state of the d-th section of the path; v d Indicates the vehicle speed in the d-th section of the path; The objective function of this IDP algorithm aims to optimize factors such as fuel consumption, battery state, and speed smoothness simultaneously to ensure the overall optimization of the vehicle during the entire driving process.

[0090] S230. Combine the state variables and the control variables to form multiple groups of iterative variables, where each group of iterative variables includes a state variable factor and a control variable factor;

[0091] S240. Iteratively optimize the objective function of the dynamic programming algorithm by polling and using multiple groups of the iterative variables to obtain the global planning control quantity for the operation of the mining vehicle, where one group of iterative variables is selected for each iterative optimization.

[0092] It should be understood that in order to improve the operation speed, when performing iterative calculations of the objective function for the IDP algorithm, only one state variable factor and one control variable factor are involved in the iterative calculation each time. For example, in the current iteration, SOC and engine power can be selected to form iterative variables for the iteration, and in the next iteration, the current speed of the mining vehicle and motor power can be selected to form iterative variables for the iteration. This method can effectively improve the operation speed of the dynamic programming algorithm by reducing the dimensions of the state space and the control space, thereby improving the real-time performance of the dynamic programming algorithm. Specifically, by decomposing the high-dimensional optimization problem into a sequence of low-dimensional sub-problems, the dynamic programming in the embodiments of the present invention actually refers to IDP (Iterative Dynamic Programming), which can significantly reduce the computational complexity while ensuring global optimality. Compared with traditional dynamic programming methods, IDP can quickly solve problems under complex working conditions while maintaining accuracy, thus meeting the real-time requirements of the calculation of the mining area transportation system.

[0093] Due to the discretization requirement of the multi-dimensional state space in traditional dynamic programming, the computational complexity increases exponentially. The dynamic programming in the embodiments of the present invention adopts Iterative Dynamic Programming (IDP), which realizes theoretical innovation through a three-layer architecture of "decomposition - cooperation - iteration". Its core idea is to transform the high-dimensional optimization problem into an iterative solution process of multiple low-dimensional sub-problems, and gradually approach the global optimal solution through dynamic information interaction. Compared with traditional DP methods, IDP can solve the problem of excessive computational complexity and achieve a balance between real-time performance and global optimization.

[0094] The algorithm mechanism of IDP is first reflected in the dimension decoupling and step-by-step optimization strategy. In the first round of iteration, the vehicle speed reference trajectory is fixed, and the power distribution between the engine and the battery is optimized with SOC as the single state variable. Next, based on the updated SOC trajectory, the vehicle speed is used as the state variable for re-optimization to adjust the torque output of the drive motor. This step-by-step optimization reduces the computational complexity from the cubic order of traditional DP to the quadratic order, significantly improving the computational efficiency. In addition, IDP introduces a dynamic grid adjustment mechanism. In the first round of iteration, a coarse-grained discretization is used to quickly generate an approximate optimal trajectory, and then the grid is refined in key regions (such as the section with rapid SOC change) according to the curvature characteristics of the trajectory, and redundant grid points in low-sensitivity regions are removed based on historical error data. This method focuses the computational resources on high-value state space regions, thus further improving the computational efficiency and optimization accuracy.

[0095] Therefore, IDP effectively solves the core contradiction of the traditional DP method in the energy management of mining dump trucks. The iterative optimization process of IDP not only retains the forward-looking advantage of global planning but also integrates into the real-time control loop through a dynamic correction mechanism, enabling the global optimization and local real-time response to work in coordination, thus providing an effective collaborative solution for long-time domain optimization and short-time domain response. This integrated optimization method not only improves the real-time adaptability of the system but also avoids the disconnection between global planning and local control in traditional methods, achieving more efficient energy management.

[0096] The iterative solution process of IDP alternates between assumptions and optimizations to gradually determine the optimal control strategy of the system. This process is divided into four main steps, and each step is equivalent to solving a dynamic programming problem with a single state variable and a single control variable. In IDP, the computational efficiency is significantly improved because it avoids the complexity of simultaneously processing multiple state variables and control variables. Compared with the traditional dynamic programming method, IDP shows obvious advantages in computational time.

[0097] The iterative solution process of IDP alternates between assumptions and optimizations to gradually determine the optimal control strategy of the system. This process is divided into four main steps, and each step is equivalent to solving a dynamic programming problem with a single state variable and a single control variable. In IDP, the computational efficiency is significantly improved because it avoids the complexity of simultaneously processing multiple state variables and control variables. Compared with the traditional dynamic programming method, IDP shows obvious advantages in computational time.

[0098] Step 1: Assume the vehicle speed sequence of future working conditions.

[0099] In the first step of IDP, assume the vehicle speed sequence {V t} is known. This assumption provides the basis for subsequent energy management optimization. Combining the known vehicle speed information and the dynamic model, the power sequence {P edrive,t} of the drive motor can be calculated, providing a decision-making basis for subsequent energy management. The specific process is as follows:

[0100] Given the vehicle speed V t , the vehicle mass m, and the resistance F resist,t during driving, the power P edrive,t of the drive motor can be calculated through the vehicle dynamics equation:

[0101]

[0102] where represents the rate of change of vehicle speed, and F resist,t is the resistance caused by road and air resistance.

[0103] Next, based on the vehicle dynamics model and the known V t and P edrive,t the SOC (state of charge) sequence SOC t of the battery and the battery power P bat，t can be solved through the energy balance equation:

[0104]

[0105] where ΔT is the time step, Q bat is the battery capacity, and U bat is the working voltage of the battery.

[0106] Through this step, a dynamic programming problem of a single state variable (SOC) and a single control variable (battery power P bat,t ) is obtained, providing the basis for subsequent optimization.

[0107] Step 2: Calculate the vehicle speed and drive motor power based on SOC and battery power.

[0108] In the first step, the SOC sequence and the battery power sequence have been obtained. Next, the task of the second step is to recalculate the vehicle speed sequence {V t} and the drive motor power sequence {P edrive,t} based on these results.

[0109] The specific steps are as follows:

[0110] Given the SOC sequence {SOC t} and the battery power sequence {P bat,t}, the vehicle speed and the drive motor power can be recalculated through the vehicle dynamics equation by using the relationship between the battery power and the drive motor power:

[0111]

[0112] Among them, P edrive,t = P engine,t + P bat,t , indicating that the power of the drive motor consists of the sum of the engine power and the battery power.

[0113] This step is also a dynamic programming problem of a single state variable (vehicle speed V t ) and a single control variable (drive motor power Pedrive t ).

[0114] Step 3: Calculate the SOC and the battery power based on the new vehicle speed and the drive motor power.

[0115] In Step 2, the vehicle speed {V t} and the drive motor power {P edrive,t} are recalculated. The goal of Step 3 is to recalculate the SOC and the battery power according to these new data. The specific process is as follows:

[0116] Given the new vehicle speed V t and the new drive motor power P edrive,t , the new SOC state can be calculated through the state transition equation:

[0117]

[0118] This process is also a dynamic programming problem of a single state variable (SOC) and a single control variable (battery power P bat,t ).

[0119] Step 4: Calculate the vehicle speed and the drive motor power based on the SOC and the battery power.

[0120] In Step 3, a new SOC sequence {SOC t} and a battery power sequence {P bat,t} are obtained. The task of the last step is to use these new SOC and battery power to recalculate the vehicle speed V t and the drive motor power P edrive,t . The specific steps are as follows:

[0121] Given SOC SOC t and battery power P bat,t , the vehicle speed and the drive motor power of the vehicle can be recalculated by using the vehicle dynamics equation:

[0122]

[0123] This process completes a full iteration cycle and re-optimizes the control strategy for each time step.

[0124] Therefore, the dynamic programming in the embodiments of the present invention adopts the real iterative dynamic programming method. In the iterative solution process, continuous assumptions and optimizations are alternately carried out, gradually approaching the optimal control strategy. Through the iteration of these four steps, IDP solves a simplified dynamic programming problem in each round of calculation, avoiding the complexity of directly dealing with multiple states and control quantities. This gradually optimized process significantly reduces the computational complexity, making IDP an efficient method for dealing with complex multi-stage decision-making problems. Compared with the traditional dynamic programming method, IDP significantly reduces the calculation time. Assuming that the SOC and vehicle speed are discretized into 50 points respectively, and the battery power and drive motor power are also discretized into 50 points, in the traditional dynamic programming, the amount of calculation will be 50×50×50×50 = 6,250,000 calculations. While in IDP, since only a single state quantity and a control quantity are processed in each step, the amount of calculation is only 4×50×50 = 10,000 times, and the amount of calculation is significantly reduced, greatly improving the calculation efficiency.

[0125] Specifically, the iterative optimization method includes recursively and reversely solving to obtain the global planning control quantity of the mine vehicle operation according to the preset initialization end condition, or calculating the global planning control quantity of the mine vehicle operation forward according to the control quantity of each stage.

[0126] When implementing iterative optimization, first determine the state transition equation of the IDP algorithm. Among them, the speed update equation is specifically that the speed update of the mine vehicle is determined by the vehicle dynamics equation:

[0127]

[0128] where, v new represents the speed at the next time step; ΔT represents the time step; m represents the total mass of the mine vehicle (including the body mass and the load mass); F d represents the total resistance of the mine vehicle, including air resistance, rolling resistance and slope influence: where, C d represents the air resistance coefficient, A represents the frontal area of the vehicle, ρ represents the air density, g represents the acceleration due to gravity, f r represents the rolling resistance coefficient, and θ represents the slope angle.

[0129] The SOC update equation is specifically that the SOC (battery state) is updated through the following formula:

[0130]

[0131] Where: P bat represents the battery power; Q bat represents the battery capacity; U bat represents the battery voltage, which can be represented by a cubic polynomial fitting model of SOC: U bat = 269.7·SOC 3 - 512.6·SOC 2 + 339.5·SOC + 1197.

[0132] Therefore, the optimization process of the IDP algorithm can specifically obtain the optimal power distribution strategy through the way of backward solution or forward solution.

[0133] As a specific implementation manner, IDP backward solves the optimal power distribution strategy in a recursive way, and adopts the following steps:

[0134] Initialize the end condition: At the end of the vehicle's travel, set the battery SOC target value and the desired speed as boundary conditions, usually set as SOC end = 0.5, v end = 30 / 3.6 m / s.

[0135] State transition and recursion: Starting from the end point, gradually recursively backward, calculate the state (including SOC, speed) at each stage through the state transition equation, and select the optimal control input at each stage according to the objective function.

[0136] Calculate the cost function: At each time step, IDP calculates the costs corresponding to different control inputs (engine power, motor power), and retains the control strategy with the minimum cost.

[0137] As another specific implementation manner, forward solve the optimal strategy: After obtaining the optimal control input at each stage, IDP calculates forward to obtain the optimal control strategy and state sequence on the entire driving path.

[0138] Therefore, in the present invention, IDP is applied to the global energy management of mining dump trucks. Due to the complex mine working conditions (such as slope, load, and influence of the vehicle in front), the global planning of IDP ensures that the vehicle can achieve the optimal fuel consumption and maximize the energy efficiency during the entire driving process. In addition, the embodiments of the present invention can also combine LSTM to predict the information of the vehicle in front and the change of the slope, so that IDP can reasonably plan the power distribution of the entire path, and further provide a global reference for MPC (Model Predictive Control), enabling MPC to perform more accurate real-time control under local working conditions.

[0139] Specifically, the energy management of the IDP when the slope changes can be specifically reflected in that when going uphill or downhill, the IDP will reasonably plan the power output of the engine and the motor to ensure the optimal energy efficiency of the vehicle under different slopes. By considering the influence of the slope, the IDP preferentially uses the motor to assist in driving when going uphill to reduce fuel consumption, and uses the electric motor braking to recover energy when going downhill to reduce battery consumption. Control optimization during heavy-load operation: When the vehicle load increases, the IDP will adjust the power distribution of the engine and the motor to ensure the optimal fuel consumption under heavy-load conditions. At the same time, the IDP will balance the change of the battery SOC to avoid excessive consumption of the battery or fuel.

[0140] In the embodiment of the present invention, the real-time operation information of the mining vehicle is locally optimized according to the model predictive control algorithm to obtain the local planning control quantity of the mining vehicle operation, as Figure 3 shown, including:

[0141] S310. Predict the operation state information of the mining vehicle within the next N time steps according to the current operation information of the mining vehicle, where the operation state information at least includes the operation speed, the battery state information, and the distance information from the vehicle in front.

[0142] It should be noted that model predictive control (MPC) mainly optimizes the control input in real time by predicting the behavior of the system within a period of time in the future to achieve the desired system state. In the embodiment of the present invention, MPC is used to optimize the local energy distribution of the mining vehicle. Through rolling horizon prediction, MPC can adjust the power output of the engine and the motor in real time according to the current state and future prediction of the vehicle to ensure the optimal energy efficiency and driving safety.

[0143] Specifically, predicting the operation state information of the mining vehicle within the next N time steps according to the current operation information of the mining vehicle includes:

[0144] 1) Input the historical speed and historical slope information of the vehicle in front into the LSTM network to obtain the predicted vehicle speed and predicted slope information of the vehicle in front within the next N time steps;

[0145] 2) Predict the operation state information of the mining vehicle within the next N time steps according to the predicted vehicle speed and predicted slope information within the next N time steps and the current operation information of the mining vehicle.

[0146] It should be understood that MPC combines the predicted vehicle speed and distance information of the vehicle in front predicted by LSTM, and can dynamically adjust the power output according to the behavior of the vehicle in front, ensuring the safety of the vehicle distance while achieving the optimal energy efficiency. For example, when the vehicle distance shrinks, MPC will reduce the vehicle power output to decelerate while trying to maintain the energy efficiency.

[0147] It should be noted that LSTM (Long Short-Term Memory) is a recurrent neural network (RNN) specifically designed for processing time series data. It can effectively capture long-term and short-term dependencies in data and is particularly suitable for time series prediction problems. Different from traditional RNNs, LSTM overcomes the problems of gradient vanishing and gradient explosion that are prone to occur in long sequences by introducing memory cells and gate mechanisms, enabling it to handle long-term dependencies.

[0148] In the embodiments of the present invention, the application of LSTM is mainly reflected in the prediction of the future speed and slope of the vehicle ahead. By learning historical vehicle speed and slope data, LSTM can predict the state of the vehicle ahead in multiple future time steps, helping MPC (Model Predictive Control) to perform more accurate real-time optimization.

[0149] Specifically, the network structure of LSTM consists of three main parts:

[0150] Input gate: Determines the magnitude of the influence of the current input information on the state of the memory cell;

[0151] Forget gate: Determines how much information from the previous state in the memory cell needs to be forgotten;

[0152] Output gate: Determines the output at the current moment and updates the state of the memory cell simultaneously.

[0153] For the control of mining vehicles, the input of the LSTM network includes the historical vehicle speed and historical slope information of the vehicle ahead, and the output is the predicted vehicle speed and slope within multiple future time steps. The following is a detailed description of the network structure:

[0154] Input layer: The input has three dimensions, namely the historical vehicle speed of the vehicle ahead, the historical slope data, and the prediction signal at a future moment;

[0155] Hidden layer: The network contains two LSTM layers for extracting time series features from the input data;

[0156] Fully connected layer: The features extracted by the LSTM layer are input to the fully connected layer for further processing;

[0157] Output layer: Outputs the predicted values of the vehicle speed of the vehicle ahead in multiple future time steps.

[0158] In the embodiments of the present invention, the training process of LSTM is a supervised learning process based on time series data. The training data usually includes input sequences and their corresponding target outputs. The purpose of training is to continuously adjust the network weights so that LSTM can correctly predict future states based on the input sequences. The following is the detailed training process of LSTM:

[0159] (1) Data preparation. Input data: historical vehicle speed, historical and future slope data of the leading vehicle, with a time step length of t - 1. Output data: The target value for training is the vehicle speed (and possibly the slope) of the leading vehicle in the time steps from t, t + 1,..., t + N. In the present invention, the input of the LSTM is the speed and slope data of the leading vehicle in the past 20 time steps, and the output is the predicted vehicle speed value for the next 20 time steps. Construct a cell array of the input data: Since the LSTM needs to process time series data, the input data needs to be converted into the form of a cell array. For each time step t, the input data consists of the historical speed and slope sequences of the leading vehicle, and the output is the vehicle speed in the time steps from t + 1 to t + N.

[0160] (2) Network architecture design: The LSTM network architecture needs to be designed according to the complexity of the time series data. Generally, the more network layers and the larger the number of hidden units, the stronger the fitting ability of the model, but it is also prone to overfitting problems. In the embodiment of the present invention, the LSTM network includes two LSTM layers. The first layer is set with 400 hidden units, and the second layer is set with 200 hidden units. The final output layer is a fully connected layer, which outputs the predicted vehicle speed value for the next 20 time steps.

[0161] (3) Training process: The LSTM is trained through backpropagation and optimization algorithms. In the embodiment of the present invention, the Adam optimization algorithm is selected because it has strong convergence and the ability to adapt to dynamic changes. The training process gradually updates the weights and biases in the LSTM network according to the error between the input and the output to minimize the prediction error.

[0162] Therefore, in the embodiment of the present invention, the LSTM is mainly used to assist the MPC in predicting the state of the leading vehicle. The application of the LSTM is specifically reflected in the following aspects:

[0163] Prediction of the leading vehicle speed: By learning the historical vehicle speed and slope of the leading vehicle, the LSTM can predict the vehicle speed of the leading vehicle in the next several time steps. This is crucial for the control of the MPC because the MPC relies on the prediction of future states for real-time adjustment during the rolling optimization process.

[0164] Slope prediction: In addition to speed prediction, the LSTM can also predict future slope changes based on historical slope information, which enables the control to more accurately adapt to the changes in the mine working conditions, especially in scenarios where the slopes change frequently.

[0165] Combination of MPC and LSTM: The prediction results of LSTM (speed and slope in future time steps) are used as the input of MPC, helping MPC consider future vehicle speed changes during the optimization process, thus achieving more flexible and precise control. When the slope changes sharply, the early prediction of LSTM can effectively prevent control lag and improve the response speed and energy efficiency of control.

[0166] Solution to the multi-input single-output problem: LSTM processes multiple inputs (historical speed and slope) by using cell arrays and processes them through the recursive network mechanism of time series, and the output is the prediction of speed and slope for a future period of time. This structure can well solve the non-linear multi-input problem under complex working conditions.

[0167] S320. For each time step, the optimal control input information for the next N time steps is solved through the model predictive control algorithm;

[0168] It should be noted that the core of MPC is to use the vehicle's dynamic model to predict the future system state and optimize the control input so that the control can reach the target state in future time steps. At each time step, MPC predicts the system behavior for the next N steps based on the current system state and optimizes the control input (such as engine power, motor power) so that the vehicle's speed, battery SOC, etc. meet the desired goals.

[0169] In the embodiments of the present invention, the state variables of MPC include:

[0170] SOC (charge state of the battery): used to describe the remaining battery power, with the range SOC ∈ [0.3, 0.8];

[0171] The current vehicle speed v: used to describe the current driving speed of the vehicle, with the range v ∈ [5, 55] km / h;

[0172] Vehicle distance d front : The distance between the vehicle and the vehicle in front, used to ensure safe driving.

[0173] The control variables of MPC include:

[0174] Engine power P engine : The power output provided by the engine, with the range of P engine ∈ [0, 1200] kW;

[0175] Motor power P motor : The power output provided by the motor, with the range of P motor ∈ [-880, 1400] kW.

[0176] Specifically, for each time step, the optimal control input information for the next N time steps is solved through the model predictive control algorithm, including:

[0177] 1) Determine the objective function of the model predictive control algorithm. The expression of the objective function of the model predictive control algorithm is as follows:

[0178]

[0179] where γ d represents the vehicle distance constraint weight, d front,k represents the vehicle distance of the preceding vehicle of the current mine vehicle, d limit represents the safety distance limit, α v represents the vehicle speed weight of the mine vehicle, β SOC represents the deviation weight of the battery state information, δ P represents the power consumption weight;

[0180] It should be understood that the goal of MPC is to make the vehicle speed, battery SOC, and vehicle distance as close as possible to the target values within the next N steps by optimizing the control input, while minimizing the power consumption. This objective function ensures that the vehicle can maintain efficient energy management and safe driving under complex working conditions by considering the control deviations of speed, SOC, and vehicle distance, as well as power fuel consumption.

[0181] 2) Optimize the objective function according to the preset state variable constraint conditions, preset control variable constraint conditions, and the preset conditions of the vehicle distance of the preceding vehicle of the mine vehicle to solve the optimal control input information for the next N time steps.

[0182] It should be understood that in order to ensure the practical feasibility of the control, multiple physical constraints will be introduced during the optimization process of MPC to ensure that state values such as power output and SOC are within a reasonable range.

[0183] (1) The constraints on the engine and motor powers are respectively:

[0184] 0 ≤ P engine ≤ 1200 kW,

[0185] -880 ≤ P motor ≤ 1400 kW.

[0186] (2) Battery SOC constraint. The SOC of the battery needs to be maintained within a reasonable range to avoid over-discharge or over-charging:

[0187] 0.3 ≤ SOC ≤ 0.8.

[0188] (3) The constraints on the vehicle speed and vehicle distance are respectively:

[0189] v min ≤ v ≤ v max ,

[0190] dfront >d limit 。

[0191] It should be noted that MPC needs to continuously predict the future state in the rolling time domain. The state transition equation is used to describe the evolution of the state over time steps, mainly including the updates of speed and SOC.

[0192] (1) Speed update equation, the speed v of the mining vehicle k The update equation is:

[0193]

[0194] where, v represents the current speed; ΔT represents the time step; m represents the vehicle mass; F d represents the total resistance, including air resistance, rolling resistance and slope influence.

[0195] (2) The update equation of SOC is:

[0196]

[0197] where, Q bat represents the battery capacity; U bat represents the battery voltage, based on the polynomial fitting model of SOC.

[0198] S330. Perform local optimization according to the optimal control input information of the current time step, and repeat the above steps to obtain the local planning control quantity of the mining vehicle operation.

[0199] In the embodiment of the present invention, MPC uses the sequential quadratic programming (SQP) algorithm for solution. During the solution process, the minimization of the cost function and the constraints of the control input are considered simultaneously. SQP has the following advantages in solving:

[0200] a1. Ability to handle nonlinear systems: MPC is essentially an optimization problem, and the system control in many practical applications is usually nonlinear. As a method for solving nonlinear optimization problems, SQP can effectively handle the nonlinear constraints and objective functions in MPC. By approximating the nonlinear problem as a series of quadratic programming problems and solving them step by step, SQP can well adapt to the complex dynamic systems in practice.

[0201] a2. Adaptation to constraint conditions: SQP can well handle various constraints in MPC, including the upper and lower limits of input power, the limitations of battery SOC, and speed and safety distance, etc. This is very important for the actual physical constraints in the MPC optimization process, because it can ensure that the control input does not exceed the physical limits of the actual system, thus ensuring the feasibility of the solution.

[0202] a3. Fast convergence: Compared with other non-linear optimization methods, SQP has a faster convergence rate when solving constrained optimization problems. By gradually linearizing non-linear constraints and solving a quadratic programming problem in each iteration, it can find the optimal solution in fewer iterations. This is particularly important for MPC systems that require real-time control, as it can shorten the calculation time and improve the real-time response ability.

[0203] a4. High-precision solution: SQP uses quadratic programming to approximate the objective function and can converge to a relatively accurate optimal solution after multiple iterations. Since MPC usually involves predicting the states and control inputs of multiple future time steps, using SQP can ensure a high-precision optimal solution, thereby improving the control effect.

[0204] a5. Flexibility: SQP is not only applicable to objective functions with quadratic forms (such as quadratic cost functions), but can also be extended to a wider range of non-linear optimization problems. Its flexibility enables MPC to handle various complex control problems, such as non-linear cost functions in energy management and complex physical dynamics models.

[0205] a6. Effective response to uncertainties: In MPC, the prediction of future states may be affected by various uncertainties (such as changes in the behavior of the vehicle in front, sudden changes in road conditions, etc.). By iteratively solving the optimal solution at each step, SQP can quickly adjust the prediction of future states and the optimization results, making the control more robust to uncertainties.

[0206] In summary, in the embodiments of the present invention, MPC can handle complex working conditions in mines (such as slope changes, load fluctuations, and the behavior of the vehicle in front) through rolling optimization and real-time prediction. Specifically, it is manifested as follows:

[0207] b1. Energy management for slope changes:

[0208] When the vehicle is in the uphill or downhill working condition, MPC can dynamically adjust the power output of the engine and the motor according to the real-time slope information. When going uphill, MPC preferentially uses the engine to drive and reduces fuel consumption through appropriate motor-assisted driving; when going downhill, MPC uses electric braking to recover energy and improve energy efficiency.

[0209] b2. Control optimization under heavy load conditions:

[0210] When the load increases, MPC can adjust the power output of the vehicle in real time through optimization to ensure the balance between power performance and fuel consumption under high load. By predicting future load changes, MPC can make adjustments in advance to avoid power distribution imbalance.

[0211] b3. Response to dynamic changes of the vehicle in front:

[0212] The information of the speed and distance of the vehicle ahead predicted by MPC combined with LSTM can dynamically adjust the power output according to the behavior of the vehicle ahead, ensuring the safety of the vehicle distance while achieving optimal energy efficiency. For example, when the vehicle distance decreases, MPC will reduce the vehicle power output to decelerate while maintaining the energy efficiency as much as possible.

[0213] In the embodiment of the present invention, weighted hybrid coordination processing is performed according to the global planning control quantity and the local planning control quantity of the mining vehicle, as Figure 4 shown, including:

[0214] S410. Perform a weighted hybrid strategy according to the global planning control quantity and the local planning control quantity of the mining vehicle;

[0215] It should be understood that in order to better combine global optimization and local optimization, the embodiment of the present invention designs a weighted hybrid strategy, that is, dynamically adjusts the output power ratio of MPC and IDP according to the current working conditions.

[0216] Specifically, performing a weighted hybrid strategy according to the global planning control quantity and the local planning control quantity of the mining vehicle includes:

[0217] (1) When the load of the mining vehicle is less than the preset load threshold, the expression of the weighted hybrid strategy is:

[0218] P engine,out = α·P engine,DP +(1 - α)·P engine,MPC ,

[0219] P motor,out = α·P motor,DP +(1 - α)·P motor,MPC ,

[0220] (2) When the load of the mining vehicle is not less than the preset load threshold, the expression of the weighted hybrid strategy is:

[0221] P engine,out = α·P engine,MPC +(1 - α)·P engine,DP ,

[0222] P motor,out = α·P motor,MPC +(1 - α)·P motor,DP ,

[0223] Among them, P engine,out represents the actual output power of the engine of the mining vehicle, P motor,out represents the actual output power of the motor of the mining vehicle, P engine,DP represents the global planning output power of the engine of the mining vehicle, P motor,DPRepresents the global planning output power of the motor of the mining vehicle, P engine,MPC Represents the local planning output power of the engine of the mining vehicle, P motor,MPC Represents the local planning output power of the motor of the mining vehicle. α represents the weighted mixing weight factor, and 0 ≤ α ≤ 1.

[0224] S420. Dynamically adjust the weighted mixing weight factor in the weighted mixing strategy according to the real-time working conditions, so that the global planning control quantity of the mining vehicle and the local planning control quantity of the mining vehicle reach dynamic balance.

[0225] As a specific implementation manner, when the load of the mining vehicle is less than the preset load threshold, dynamically adjusting the weighted mixing weight factor in the weighted mixing strategy according to the real-time working conditions includes:

[0226] (1) When the distance between the mining vehicle and the vehicle in front is greater than the preset distance threshold and the fluctuation range of the real-time working conditions is within the preset range, increase the weighted mixing weight factor to increase the weight of the global planning control quantity of the mining vehicle;

[0227] (2) When the distance between the mining vehicle and the vehicle in front is less than the preset distance threshold and the fluctuation range of the real-time working conditions is not within the preset range, reduce the weighted mixing weight factor to increase the weight of the local planning control quantity of the mining vehicle.

[0228] It should be noted that the weighted mixing weight factor α is dynamically adjusted according to the current working conditions. When the vehicle is far from the vehicle in front and the working conditions change little, the weight of IDP is large, that is, α is close to 1; when the distance to the vehicle in front shortens and the slope changes greatly, MPC gradually takes over the control, α decreases, and the weight of MPC increases.

[0229] Specifically, long-distance driving: When the vehicle is far from the vehicle in front, it mainly relies on the global planning of DP. At this time, α ≈ 1. Short-distance driving: When the vehicle approaches the vehicle in front, in order to ensure safety, MPC gradually takes over the control, α decreases, and more relies on the local optimization of MPC. Slope change: When the road surface slope changes violently, MPC optimizes and adjusts first, and IDP provides a global reference. At this time, the dynamic adjustment of α is determined according to the change rate of the slope.

[0230] It should be understood that in the energy management and safety control of mining vehicles, the load of the vehicle not only affects the energy distribution, but also significantly affects the calculation of the time to collision (TTC) and the warning coefficient. Therefore, in the control strategy combining MPC and IDP, in order to ensure the driving safety and energy efficiency optimization under different load conditions, the dynamic influence of vehicle weight on TTC and the warning coefficient is considered for loads exceeding the preset load threshold (that is, the threshold that can be understood as affecting driving safety).

[0231] Based on this, as another specific implementation, when the load of the mining vehicle is not less than the preset load threshold, the weighted mixing weight factor in the weighted mixing strategy is dynamically adjusted according to the real-time working conditions, including:

[0232] (1) Calculate the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle;

[0233] It should be noted that the time to collision (TTC): TTC refers to the time required for the vehicle to collide with the vehicle in front at the current speed. Warning coefficient (K): The warning coefficient is used to measure the safety of the current vehicle distance and TTC, and determines the degree of intervention of the MPC in the control strategy of the IDP.

[0234] Calculating the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle includes:

[0235] Calculate the TTC and the warning coefficient respectively according to the running speed, the distance to the vehicle in front, the relative speed and the load of the mining vehicle, where the calculation formula of the warning coefficient is:

[0236]

[0237] Among them, K represents the warning coefficient, d front represents the distance to the vehicle in front of the mining vehicle, d b represents the braking distance, m represents the load of the mining vehicle, v self represents the running speed of the mining vehicle, F brake represents the braking force of the mining vehicle, d w represents the warning distance, d w =d b +d limit , d limit represents the safety distance threshold;

[0238] The calculation formula of the TTC is:

[0239]

[0240] Among them, v rel represents the relative speed between the mining vehicle and the vehicle in front, v rel =v self -v front , v front represents the speed of the vehicle in front of the mining vehicle.

[0241] In the embodiments of the present invention, K∈[0,1] represents the safety factor. When K is small, it means that the vehicle distance is too small, and the MPC will take over the control to increase safety.

[0242] (2) Dynamically adjust the weighted hybrid weight factor according to TTC, the warning coefficient, and the distance to the vehicle ahead. The dynamic adjustment expression of the weighted hybrid weight factor is as follows:

[0243]

[0244] where k represents the warning coefficient, d front represents the distance to the vehicle ahead of the mining vehicle, d limit represents the safety distance threshold, and d b represents the braking distance.

[0245] It should be noted that the load of the mining vehicle directly affects the braking distance d b and the warning distance d w , thus having a significant impact on TTC and the warning coefficient K. Specifically:

[0246] The braking distance d b : The braking distance is proportional to the vehicle weight m. The heavier the vehicle, the longer the required braking distance. The calculation formula for the braking distance is:

[0247]

[0248] where m is the total mass of the vehicle; v self is the current speed of the vehicle; F brake is the braking force of the vehicle, which is usually provided by the electric motor braking for the energy-saving control target. The maximum braking force F brake = P max / v self where P max is the maximum power of the electric motor braking.

[0249] The warning distance d w : The warning distance is the braking distance plus the safety margin, indicating the minimum distance required to maintain a safe vehicle distance under the current conditions. The calculation formula for the warning distance is:

[0250] d w = d b + d limit ,

[0251] where d limit is the safety distance threshold.

[0252] It can be seen from the above formula that an increase in vehicle weight will cause an increase in d b and d w , thus affecting the warning coefficient K and TTC. When the vehicle weight is large, the vehicle requires a longer braking distance. Therefore, MPC will adjust the power distribution and vehicle distance control according to the real-time vehicle weight and TTC calculation results.

[0253] When considering the influence of vehicle weight, the hybrid strategy of MPC and IDP not only needs to optimize the energy distribution, but also ensure the safety distance between the vehicle and the vehicle in front, especially when the vehicle weight is large. This part of the strategy dynamically adjusts the power output of the engine and the motor through TTC and the warning coefficient K. The specific steps are as follows:

[0254] Dynamic calculation of TTC and warning coefficient: According to the current state of the vehicle (speed, distance, relative speed and vehicle weight), calculate TTC and warning coefficient in real time:

[0255]

[0256] When the value of K or TTC is less than a certain set value, it means that the vehicle distance is extremely small and there is a risk of collision. MPC will completely take over the control and forcefully reduce the power output.

[0257] Weight adjustment of MPC and IDP: When the vehicle weight is large and TTC is short, the weight α of MPC will increase significantly to prioritize safety control. When the vehicle distance is too small, MPC gradually takes over the control to reduce the vehicle speed and increase the vehicle distance. The dynamic adjustment formula of the weight factor is:

[0258]

[0259] When α = 1, MPC completely takes over the control to ensure safety.

[0260] Therefore, when considering the vehicle load, the specific control output of the combination of MPC and IDP is that the final control output determined according to TTC and the warning coefficient is the weighted hybrid result of MPC and IDP:

[0261] P engine,out = α·P engine,MPC +(1 - α)·P engine,DP ,

[0262] P motor,out = α·P motor,MPC +(1 - α)·P motor,DP ,

[0263] When the vehicle distance is large enough, IDP is responsible for providing global energy distribution, and when the vehicle distance shrinks, MPC gradually takes over to ensure vehicle safety through real-time optimization.

[0264] It should be understood that in the hybrid strategy of MPC and IDP, electric braking is the main braking method of the vehicle. Especially when the vehicle weight is large, the braking power becomes a key factor. To ensure braking safety, the braking power P of the motor brake needs to be dynamically adjusted according to the vehicle load. Specifically:

[0265]

[0266] When P brake is less than the maximum braking power P max (e.g., 880 kW) of the motor, the motor braking can effectively control the vehicle speed.

[0267] When P brake exceeds the maximum braking power, the vehicle needs to take additional measures (such as brake caliper braking) to reduce the vehicle speed.

[0268] In summary, the MPC and IDP hybrid strategy combining TTC and the warning coefficient in the embodiments of the present invention can achieve the following advantages under complex working conditions:

[0269] Real-time safety guarantee: By dynamically calculating TTC and the warning coefficient, it can make safety control in a timely manner according to the real-time vehicle distance and vehicle weight, ensuring driving safety in the case of high load and short vehicle distance.

[0270] Flexible energy distribution: The weighted hybrid strategy of MPC and IDP can make corresponding adjustments according to the vehicle weight and vehicle distance under different working conditions, which can not only ensure the optimal global energy efficiency, but also perform local optimization control in case of emergency.

[0271] Dynamic response: When the vehicle distance shortens, the vehicle weight increases or the vehicle in front suddenly decelerates, the power output and vehicle speed are dynamically adjusted through TTC and the warning coefficient, ensuring that the vehicle can respond to changes in a timely manner and avoid collisions.

[0272] In summary, the control strategy combining MPC and IDP ensures the safety and energy efficiency optimization of the vehicle under complex mine working conditions by considering the influence of vehicle weight on TTC and the warning coefficient, and effectively copes with challenges such as slope changes, heavy load working conditions and vehicle distance fluctuations.

[0273] In addition, by combining MPC and IDP, the present invention can achieve the comprehensive optimization of the global and local under complex working conditions, and has the following advantages:

[0274] Combination of global planning and local optimization: IDP provides a path planning with the optimal global energy efficiency, while MPC makes local corrections to it at each time step, ensuring the real-time response ability of the vehicle under complex working conditions.

[0275] Adapt to dynamic working conditions: MPC combines the predicted vehicle speed and vehicle distance information of the vehicle in front by LSTM, and can cope with real-time changing working conditions, such as slope changes, vehicle distance shortening, etc., ensuring safety and energy efficiency.

[0276] Dynamic adjustment of weights: By dynamically adjusting the weight distribution of MPC and IDP, it can balance global planning and local optimization, and achieve the optimal control strategy under different working conditions.

[0277] Consideration of vehicle weight impact: By considering the load changes of the vehicle, the combined strategy of MPC and IDP can dynamically adjust for heavy-load and light-load conditions, ensuring optimal energy efficiency of the vehicle under different load conditions.

[0278] Through this combined strategy, stable, efficient, and safe driving control can be achieved in the complex working conditions of mines, which is applicable to heavy-duty vehicles that require complex energy management.

[0279] The following combines Figure 5a and Figure 5b the following simulation schematic diagrams to describe the effects of the embodiments of the present invention.

[0280] Figure 5a FIG. is a schematic diagram of the simulation results of the iterative dynamic programming IDP of the embodiments of the present invention and the traditional dynamic programming DP. It can be seen from Figure 5a that the simulation results of the IDP of the embodiments of the present invention and the traditional DP are very close in key indicators. The simulation data of the calculation efficiency of the embodiments of the present invention are shown in Table 1 below. It can be seen from this that the IDP of the embodiments of the present invention effectively improves the calculation efficiency on the basis of retaining the key indicator performance of DP. That is, the traditional DP needs to traverse the entire state space and calculate the global optimal solution through reverse recursion, which takes about 760 seconds. However, the iterative DP of the embodiments of the present invention decomposes the problem into sub-problems of single state quantity and single control quantity through alternating iteration of assumptions and optimizations, significantly reducing the calculation complexity and only taking about 1.8 seconds, greatly improving the real-time calculation ability.

[0281] Table 1 Comparison of calculation efficiency and simulation result data between IDP and DP

[0282]

[0283] Figure 5b FIG. is a comparison diagram of the fuel consumption and battery state based on the combination of IDP and MPC and the fuel consumption and battery state when only MPC is used in the embodiments of the present invention. In addition, the following Table 2 shows the specific fuel consumption and SOC change data tables.

[0284] Table 2 Comparison table of fuel consumption and SOC change data

[0285]

[0286] According to Figure 5bAs well as Table 2, IDP&MPC is more fuel-efficient than MPC, and at the same time has a larger SOC margin. It also shows that in terms of overall fuel consumption, the IDP&MPC fusion strategy can still maintain a low fuel consumption relying on the global optimal control quantity of IDP, demonstrating the effectiveness of cooperative optimization control in energy conservation. At the same time, the trend of SOC (remaining battery power) is similar under the two strategies, and the remaining battery power at the end of the simulation of the fused global and local control systems is more. This indicates that the cooperative optimization control strategy effectively improves the battery management and utilization efficiency while ensuring low energy consumption.

[0287] From the above analysis, it can be seen that the cooperative optimization (IDP and MPC) strategy of global and local control significantly improves the energy efficiency and safety of hybrid mining dump trucks, especially under complex mine working conditions. Through simulation and experimental verification, the fused control system not only performs excellently in optimizing fuel consumption, SOC and vehicle speed, but also can respond to changes in working conditions in real time, adjust the control strategy to ensure the efficient operation of the vehicle under changing road conditions. Compared with traditional single control methods, the fusion control strategy has stronger adaptability and real-time optimization ability, providing a more practical energy management solution.

[0288] In summary, the energy management and control method for complex working conditions of mining vehicles provided by the present invention combines the iterative dynamic programming (IDP) of global planning with the model predictive control (MPC) of local real-time optimization to construct a dual optimization control method that combines global and local optimization; through the prediction of the future speed and slope of the vehicle ahead by LSTM, it assists the MPC module to perform more accurate control optimization, enabling the control method to adapt to the complex working conditions of mines; the MPC combines the prediction information output by LSTM to correct the IDP plan in real time, ensuring that the energy distribution and driving safety remain optimal under dynamic working conditions; through dynamic programming for global power planning, it ensures that the power distribution between the engine and the motor reaches the optimal fuel consumption target throughout the driving path. At the same time, the MPC considers the load and slope to introduce power constraints during local optimization, ensuring the reasonable distribution and practical feasibility of power. Therefore, the specific advantages of the energy management and control method for complex working conditions of mining vehicles are as follows: 1) Combination of global and local optimization: IDP performs global path planning to ensure optimal fuel consumption throughout the journey; MPC then performs real-time optimization of the IDP results during driving to adapt to complex mining working conditions, such as slope changes and changes in the distance to the vehicle ahead; 2) Real-time response and safety control: The MPC combines the predicted speed and slope information of the vehicle ahead by LSTM to achieve precise real-time control under different working conditions, improving the safety and stability of driving; 3) Improving energy efficiency and reducing fuel consumption: Through the optimal energy distribution strategy, especially when the slope changes or the load increases, it can dynamically adjust the power output of the engine and the motor, thereby improving energy efficiency and reducing fuel consumption; 4) Intelligent prediction: The LSTM model can predict the future working conditions of the vehicle ahead based on historical data, significantly improving the intelligent level of energy management. The energy management and control method for complex working conditions of mining vehicles can be widely applied to heavy-duty vehicles such as mining dump trucks, and it performs excellently in dealing with complex working conditions, especially suitable for scenarios that require fine energy management and control.

[0289] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present invention, and the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered within the protection scope of the present invention.

Claims

1. An energy management and control method for complex working conditions of mining vehicles, characterized in that Including: Obtain the dynamic model of the mining vehicle and information related to the operation of the mining vehicle. The information related to the operation of the mining vehicle at least includes vehicle load, driving path, driving map data, and path node information where the load changes; Perform global planning based on the dynamic model of the mining vehicle, the information related to the operation of the mining vehicle, and in combination with the dynamic programming algorithm to obtain the global planning control quantity of the mining vehicle operation; Perform local optimization on the real-time operation information of the mining vehicle according to the model predictive control algorithm to obtain the local planning control quantity of the mining vehicle operation; Perform weighted hybrid coordination processing on the global planning control quantity and the local planning control quantity of the mining vehicle to obtain the actual control quantity of the mining vehicle operation.

2. The energy management and control method for complex working conditions of mining vehicles according to claim 1, characterized in that Performing global planning based on the dynamic model of the mining vehicle, the information related to the operation of the mining vehicle, and in combination with the dynamic programming algorithm includes: Determine the state variables and control variables of the dynamic programming algorithm according to the dynamic model of the mining vehicle and the information related to the operation of the mining vehicle. The state variables include the battery charge state and the current speed of the mining vehicle, and the control variables include the engine output power and the motor output power; Determine the objective function of the dynamic programming algorithm; Form multiple groups of iterative variables by combining the state variables and the control variables. Each group of iterative variables includes a state variable factor and a control variable factor; Iteratively optimize the objective function of the dynamic programming algorithm by polling and using multiple groups of the iterative variables to obtain the global planning control quantity of the mining vehicle operation. One group of iterative variables is selected for each iterative optimization.

3. The energy management and control method for complex working conditions of mining vehicles according to claim 1, wherein, Performing local optimization on the real-time operation information of the mining vehicle according to the model predictive control algorithm to obtain the local planning control quantity of the mining vehicle operation includes: Predict the operation state information of the mining vehicle in the next N time steps according to the current operation information of the mining vehicle. The operation state information at least includes operation speed, battery state information, and the distance information to the vehicle in front; Solve the optimal control input information for the next N time steps through the model predictive control algorithm for each time step; Perform local optimization according to the optimal control input information of the current time step and repeat the above steps to obtain the local planning control quantity of the mining vehicle operation.

4. The energy management and control method for complex working conditions of mining vehicles according to claim 3, characterized in that Predicting the operation state information of the mining vehicle in the next N time steps according to the current operation information of the mining vehicle includes: Input the historical speed and historical slope information of the vehicle in front into the LSTM network to obtain the predicted vehicle speed and predicted slope information of the vehicle in front in the next N time steps; Predict the operation state information of the mining vehicle in the next N time steps according to the predicted vehicle speed and predicted slope information in the next N time steps and the current operation information of the mining vehicle.

5. The energy management and control method for complex working conditions of mining vehicles according to claim 4, characterized in that Solving the optimal control input information for the next N time steps through the model predictive control algorithm for each time step includes: Determine the objective function of the model predictive control algorithm. The expression of the objective function of the model predictive control algorithm is: Among them, γ d represents the vehicle distance constraint weight, d front,k represents the vehicle distance of the vehicle in front of the current mine vehicle, d limit represents the safety distance limit, α v represents the speed weight of the mine vehicle, β SOC represents the deviation weight of the battery state information, δ P represents the power consumption weight; Optimize the objective function according to the preset state variable constraint conditions, preset control variable constraint conditions, and the preset condition of the distance to the vehicle in front of the mining vehicle to solve the optimal control input information for the next N time steps.

6. The energy management and control method for complex working conditions of mining vehicles according to claim 1, wherein, Perform weighted hybrid coordination processing based on the global planning control quantity and the local planning control quantity of the mining vehicle, including: Perform a weighted hybrid strategy based on the global planning control quantity and the local planning control quantity of the mining vehicle; Dynamically adjust the weighted hybrid weight factor in the weighted hybrid strategy according to the real-time working conditions, so that the global planning control quantity and the local planning control quantity of the mining vehicle reach a dynamic balance.

7. The energy management and control method for complex working conditions of mining vehicles according to claim 6, characterized in that, Performing a weighted hybrid strategy based on the global planning control quantity and the local planning control quantity of the mining vehicle includes: When the load of the mining vehicle is less than the preset load threshold, the expression of the weighted hybrid strategy is: P engine,out = α·P engine,DP + (1 - α)·P engine,MPC , P motor,out = α·P motor,DP + (1 - α)·P motor,MPC , When the load of the mining vehicle is not less than the preset load threshold, the expression of the weighted hybrid strategy is: P engine,out = α·P engine,MPC + (1 - α)·P engine,DP , P motor,out = α·P motor,MPC + (1 - α)·P motor,DP , Among them, P engine,out represents the actual output power of the engine of the mining vehicle, P motor,out represents the actual output power of the motor of the mining vehicle, P engine,DP represents the globally planned output power of the engine of the mining vehicle, P motor,DP represents the globally planned output power of the motor of the mining vehicle, P engine,MPC represents the locally planned output power of the engine of the mining vehicle, P motor,MPC represents the locally planned output power of the motor of the mining vehicle, α represents the weighted mixing weight factor, and 0 ≤ α ≤ 1.

8. The energy management and control method for complex working conditions of mining vehicles according to claim 7, characterized in that When the load of the mining vehicle is less than the preset load threshold, dynamically adjusting the weighted hybrid weight factor in the weighted hybrid strategy according to the real-time working conditions includes: When the distance between the mining vehicle and the vehicle in front is greater than the preset distance threshold and the fluctuation range of the real-time working conditions is within the preset range, increase the weighted hybrid weight factor to increase the weight of the global planning control quantity of the mining vehicle; When the distance between the mining vehicle and the vehicle in front is less than the preset distance threshold and the fluctuation range of the real-time working conditions is not within the preset range, reduce the weighted hybrid weight factor to increase the weight of the local planning control quantity of the mining vehicle.

9. The energy management and control method for complex working conditions of mining vehicles according to claim 7, characterized in that When the load of the mining vehicle is not less than the preset load threshold, dynamically adjusting the weighted hybrid weight factor in the weighted hybrid strategy according to the real-time working conditions includes: Calculate the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle; Dynamically adjust the weighted hybrid weight factor according to the TTC, the warning coefficient and the distance to the vehicle in front. The dynamic adjustment expression of the weighted hybrid weight factor is: Among them, K represents the warning coefficient, d front represents the distance between the front vehicle of the mining vehicle, d limit represents the safety distance threshold, d b represents the braking distance.

10. The energy management and control method for complex working conditions of mining vehicles according to claim 9, characterized in that, Calculating the TTC and the warning coefficient in real time according to the current operating state information of the mining vehicle includes: Calculate the TTC and the warning coefficient respectively according to the running speed, the distance to the vehicle in front, the relative speed and the load of the mining vehicle, where the calculation formula of the warning coefficient is: Among them, K represents the warning coefficient, d front represents the distance between the leading vehicle of the mining vehicle, d b represents the braking distance, m represents the total mass of the mining vehicle, v self represents the running speed of the mining vehicle, F brake represents the braking force of the mining vehicle, d w represents the warning distance, d w = d b + d limit d limit represents the safety distance threshold; The calculation formula of the TTC is: Among them, v rel represents the relative speed of the mining vehicle and the vehicle in front, v rel = v self - v front , v front represents the speed of the vehicle in front of the mining vehicle.

Images