Construction method, control method and system of hierarchical control model for plug-in hybrid truck

Abstract

The present invention discloses a method for constructing a hierarchical control model for a plug-in hybrid truck, a control method, and a system. The method constructs an energy control model for a plug-in hybrid vehicle based on an improved DDPG, determines a state set S, an action set action, a reward function J adaptively changing based on truck driving data, and a constraint function based on the improved DDPG plug-in hybrid vehicle energy control model; collects standard operating conditions and slopes as sample sets, and inputs the sample sets into the energy control model for the plug-in hybrid vehicle based on the improved DDPG constructed in step 1 for training, thereby obtaining a trained energy control model for the plug-in hybrid vehicle based on the improved DDPG; and establishes a mixed integer nonlinear programming model T by coordinate processing of a mining platform survey map. total , solving the main queue's driving path and the driving path of each vehicle to meet transportation planning requirements. This effectively solves problems such as congestion at mining intersections, waiting time for shovel transport, and inefficient decision-making due to information silos.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy vehicle design, and relates to a hierarchical coordinated optimization and energy management control method, specifically a construction method, control method and system of a hierarchical control model for a plug-in hybrid power truck. Background Art

[0002] For a long time, mining transportation has faced three common pain points: safety, efficiency, and cost. Autonomous truck platooning offers an opportunity to address these issues. The closer distances between vehicles in a platoon improve the aerodynamic performance of the following autonomous vehicles, significantly reducing energy consumption. Simultaneously, the automated "mining-transportation-dispatching" process enables 24 / 7 continuous operation, achieving automated efficiency that matches or even exceeds manual operations. This enables the transition from single trucks to fleets and then to systematic dispatch management. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a method for constructing a hierarchical control model, a control method and a system for a plug-in hybrid truck, so as to solve the technical problem of high energy consumption in the mining area transportation process in the existing technology.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0005] A method for constructing a plug-in hybrid electric vehicle control model comprises the following steps:

[0006] Step 1: construct an improved DDPG plug-in hybrid electric vehicle energy control model, and determine the state set of the improved DDPG plug-in hybrid electric vehicle energy control model. , action set , a reward function that adapts to truck driving data and constraint functions;

[0007]

[0008]

[0009]

[0010] in:

[0011] The speed of the vehicle in the main queue's driving path, ;

[0012] is the acceleration of truck i, ;

[0013] is the amount of electricity of truck i at time t;

[0014] is the battery health status of truck i at time t;

[0015] is the engine output power of truck i, ;

[0016] is the weight of fuel consumption;

[0017] is the weight of battery charge maintenance;

[0018] is the weight of battery degradation cost;

[0019] is the fuel consumption at time t;

[0020] is the electricity consumption at time t;

[0021] It is the reference value of the battery health status;

[0022] The driving distance is The spatial domain index SoC of time;

[0023] is the SoC decrease rate in the spatial domain;

[0024] For the initial SoC;

[0025] For the target SoC;

[0026] The expected driving range after fully charging the battery;

[0027] is the initial value of the equivalence factor;

[0028] is the value of the equivalent factor when the slope is 0;

[0029] is the slope value;

[0030] is the minimum slope value;

[0031] is the maximum slope value;

[0032] The constraint function of the improved DDPG plug-in hybrid electric vehicle energy control model is as follows:

[0033]

[0034] in:

[0035] is the battery charge;

[0036] is the minimum value of SoC;

[0037] is the maximum value of SoC;

[0038] , eng is the engine, MG1 is the electric motor, and MG2 is the generator;

[0039] is the torque of the power unit x, ;

[0040] is the minimum torque of the power unit x, ;

[0041] is the maximum torque of the power unit x, ;

[0042] is the speed of the power unit x, rpm;

[0043] is the minimum speed of the power unit x, rpm;

[0044] is the maximum speed of the power unit x, rpm;

[0045] In step 2, standard operating conditions and slopes are collected as sample sets, and the sample sets are input into the improved DDPG-based plug-in hybrid electric vehicle energy control model constructed in step 1 for training to obtain a trained improved DDPG-based plug-in hybrid electric vehicle energy control model.

[0046] A method for controlling a platoon of plug-in hybrid electric trucks comprises the following steps:

[0047] Get the slope of the mining platform and the speed of truck i , and input it into the improved DDPG plug-in hybrid vehicle energy control model according to claim 1 to obtain the truck i engine output power , the truck engine output power The engine speed and torque are calculated by inputting them into the engine's optimal fuel operating curve, and the engine speed and torque are respectively input into the motor transmission path and the generator transmission path to calculate the corresponding motor speed and torque and generator speed and torque.

[0048] The slope of the mining platform and the speed of truck i are obtained , specifically including the following steps:

[0049] Step 1: Obtain a survey map of the mining platform where the truck platoon is performing the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform;

[0050] Step 2: Establish a mixed integer nonlinear programming model based on the coordinates of the survey map of the mining platform obtained in step 1 , solve mixed integer nonlinear programming models Get the driving path of the main queue and the driving path of truck i;

[0051] The driving path of the main queue is the coordinates of the truck leaving the main queue and the coordinates of the truck merging into the main queue The line connecting the two, the driving path of truck i is the coordinate of truck i leaving the main queue , task point coordinates Coordinates for joining the main queue The connection;

[0052]

[0053] in:

[0054] The main queue is the starting point of the mining platform To the coordinates of the first truck leaving the main queue The time taken, ,s;

[0055] The maximum speed of the main queue, ;

[0056] The coordinates of the last truck to be sent to the main queue for the mission End of the mining platform The time taken, ,s;

[0057] The value of indicates whether there are trucks performing tasks at task point n and task point (n+1) at the same time. If so, Take 1, otherwise Take 0;

[0058] represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes the task point n, s;

[0059] represents the coordinates of the i-th truck merging into the main queue;

[0060] represents the coordinates of the i-th truck leaving the main queue;

[0061] Step 3: Establish the longitudinal dynamic model of the plug-in hybrid truck as shown below;

[0062]

[0063]

[0064]

[0065] in:

[0066] For trucks exist The speed of time, ;

[0067] For trucks exist The acceleration of time, ;

[0068] For trucks exist The differential of the actual torque at the moment

[0069] The speed of the vehicle in the main queue's driving path, ;

[0070] is the acceleration due to gravity;

[0071] For trucks The frontal area, ;

[0072] For trucks Rolling resistance coefficient;

[0073] For trucks Time delay constant of the longitudinal dynamic system;

[0074] For trucks quality, ;

[0075] For trucks The wheel radius, ;

[0076] For trucks transmission system efficiency;

[0077] For trucks The air resistance coefficient;

[0078] is the air density, ;

[0079] For trucks exist The expected torque at time t, ;

[0080] is the truck's serial number, Take 0, 1, 2, ...;

[0081] Step 4: Construct a DMPC-based longitudinal control model for the queue; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the queue according to the driving path of the main queue obtained in step 2. and the objective function Determine the state variables of the DMPC-based platoon longitudinal control model according to the plug-in hybrid truck longitudinal dynamics model constructed in step 3 and control variables ;

[0082] Step 5: Use the ADMM algorithm to solve the objective function of the DMPC-based queue longitudinal control model constructed in step 4 to obtain the speed of truck i in the driving path of the main queue. .

[0083] Step 2 specifically includes the following steps:

[0084] Step 2.1, build a mixed integer nonlinear programming model :

[0085]

[0086] in:

[0087] The main queue is the starting point of the mining platform To the coordinates of the first truck leaving the main queue The time taken, ;

[0088] The maximum speed of the main queue;

[0089] The coordinates of the last truck to be sent to the main queue for the mission End of the mining platform The time taken, ;

[0090] The value of indicates whether there are trucks performing tasks at task point n and task point (n+1) at the same time. If so, Take 1, otherwise Take 0;

[0091] represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes through task point n;

[0092] represents the coordinates of the i-th truck merging into the main queue;

[0093] represents the coordinates of the i-th truck leaving the main queue;

[0094] Step 2.3, use mixed integer nonlinear programming method to solve the optimal , get the coordinates of the truck leaving the main queue , the coordinates where the truck meets the main queue ;

[0095] Step 2.4, the coordinates of the truck leaving the main queue obtained in step 2.3 and the coordinates of the truck merging into the main queue Connect them in sequence to get the driving path of the main queue; the coordinates of the truck leaving the main queue , task point coordinates and the coordinates of the truck merging into the main queue Connect them in sequence to obtain I truck driving paths.

[0096] Step 4 specifically includes the following steps:

[0097] Step 4.1: The position of the main queue is given by the main queue's driving path obtained in step 2. and vehicle speed , the expected state variables of each truck are obtained according to the following formula ;

[0098]

[0099] in:

[0100] For the Expected displacement of the truck, m;

[0101] For the The expected speed of the truck, ;

[0102] is the distance between two adjacent trucks, m;

[0103] Step 4.2: Define the state variable of the plug-in hybrid truck longitudinal dynamics model established in step 3 as the current state of truck i , the controlled variable is the torque of truck i ;

[0104] Step 4.3, establish the objective function ;

[0105]

[0106] in:

[0107] is the predicted state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0108] is the predicted torque of the i-th truck at time t+k;

[0109] is the hypothetical state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0110] For the Trucks in The hypothetical state at time t, which includes the position and speed of truck i at time t+k;

[0111] is the assumed torque of the i-th truck at time t+k;

[0112] is the expected state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0113] is the truck's drag coefficient;

[0114] is the air density, ;

[0115] is the frontal area of ​​the truck, ;

[0116] is the mass of the i-th truck, kg;

[0117] is the acceleration due to gravity;

[0118] is the truck's rolling resistance coefficient;

[0119] is the wheel radius of truck i, m;

[0120] is the truck's transmission efficiency;

[0121] is the penalty weight matrix for the deviation between the actual state and the expected state of the i-th truck at time t;

[0122] is the penalty weight matrix of the error between the actual state and the expected torque of the i-th truck;

[0123] is the penalty weight matrix for the deviation between the actual state and the assumed state of the i-th truck;

[0124] is the penalty weight matrix for the deviation between the expected output of the i-th truck and the expected output of its neighboring vehicles. If the vehicle is adjacent to the lead vehicle, then ;

[0125] is the distance between the i-th truck and the j-th truck, m.

[0126] Step 5 specifically includes the following steps:

[0127] Step 5.1, for the objective function in step 4.3 Introducing dummy variables and , and obtain the improved objective function ;

[0128]

[0129] in:

[0130] is the Lagrangian function of the i-th vehicle at time t;

[0131] is the set of constraints for the i-th truck at time t;

[0132] and are the dual variables corresponding to the i-th truck at time t;

[0133] is the torque of the i-th truck at time t;

[0134] 、 is the penalty coefficient;

[0135] Step 5.2: Improve the objective function obtained in step 5.1 The dual variable in and Update and get the improved objective function after updating the variables , using ADMM algorithm to improve the objective function after updating variables Solve and get the original residual and the dual residual ;

[0136]

[0137]

[0138]

[0139]

[0140]

[0141] in:

[0142] is the update step size of the Lagrangian term;

[0143] is the penalty coefficient;

[0144] Step 5.3: Determine whether both the original residual and the dual residual satisfy the following formula. If so, the control variable is obtained.

[0145] The control variables include the vehicle speed of the main queue along its travel path. ;

[0146]

[0147] in:

[0148] is the original residual termination condition;

[0149] is the dual residual termination condition.

[0150] A control system for the plug-in hybrid electric truck platoon, based on the plug-in hybrid electric vehicle control model construction method and the plug-in hybrid electric truck platoon control method, comprising a map processing unit, a model construction unit, a model training unit, and an output unit;

[0151] The map processing unit is used to obtain a survey map of the mining platform where the truck queue performs the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform;

[0152] The model building unit is used to build a mixed integer nonlinear programming model based on the coordinates of the surveying map of the mining platform , solve mixed integer nonlinear programming models Get the driving path of the main queue and the driving path of truck i;

[0153]

[0154] Establish a longitudinal dynamics model for a plug-in hybrid electric truck;

[0155]

[0156]

[0157]

[0158] Construct a DMPC-based longitudinal control model for the queue; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the queue according to the obtained driving path of the main queue and the objective function Determine the state variables of the DMPC-based platoon longitudinal control model based on the constructed plug-in hybrid truck longitudinal dynamics model and control variables ;

[0159] The ADMM algorithm is used to solve the objective function of the DMPC-based queue longitudinal control model to obtain the vehicle speed under the driving path of the main queue. The second model building unit builds an improved DDPG plug-in hybrid electric vehicle energy control model, and determines the state set based on the improved DDPG plug-in hybrid electric vehicle energy control model. , action set , a reward function that adapts to truck driving data and constraint functions;

[0160]

[0161]

[0162]

[0163] The model training unit is used to collect standard operating conditions and slopes and use them as sample sets, inputting the sample sets into the constructed energy control model of the plug-in hybrid electric vehicle based on the improved DDPG for training, thereby obtaining a trained energy control model of the plug-in hybrid electric vehicle based on the improved DDPG;

[0164] The output unit is used to output the vehicle speed obtained in step 5 The slope of the mining platform is input into the trained DDPG plug-in hybrid vehicle energy control model to obtain the engine output power of truck i. , the truck engine output power The engine speed and torque are calculated by inputting them into the engine's optimal fuel operating curve, and the engine speed and torque are respectively input into the motor transmission path and the generator transmission path to calculate the corresponding motor speed and torque and generator speed and torque.

[0165] Compared with the prior art, the present invention has the following beneficial technical effects:

[0166] (I) In the present invention, a mixed integer nonlinear programming model is established by coordinate processing of the mining platform survey map. , solving the main queue's driving path and the driving path of each vehicle to meet transportation planning requirements. This effectively solves problems such as congestion at mining intersections, waiting time for shovel transport, and inefficient decision-making due to information silos.

[0167] (II) In the present invention, a DMPC-based longitudinal control model for a platoon is constructed and the ADMM algorithm is used to solve the model, thereby achieving good vehicle following for each truck in the platoon under various unidirectional communication topology structures.

[0168] (III) The invention utilizes a trained DDPG-based plug-in hybrid electric vehicle energy control model to obtain power component control variables, thereby improving fuel economy and reducing vehicle driving costs. This effectively improves the energy efficiency of the PHET in coal mine transportation scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0169] Figure 1 This is a framework diagram of the hierarchical energy management method for plug-in hybrid truck platoons.

[0170] Figure 2It is a schematic diagram of the changing law of equivalent factor and slope.

[0171] Figure 3 is the path planning result diagram of the truck platoon in this embodiment;

[0172] Figure 4 is the absolute position diagram of the truck platoon in this embodiment;

[0173] Figure 5 This is a diagram showing queue speed changes under different unidirectional topologies in this embodiment;

[0174] Figure 6 is the operating point distribution diagram of the truck engine in this embodiment;

[0175] Figure 7 It is the lead vehicle in this embodiment Global SOC change diagram under each control strategy;

[0176] Figure 8 is a battery degradation trend diagram during a driving cycle in this embodiment;

[0177] Figure 9 This is a speed data diagram of the standard working condition in this embodiment;

[0178] Figure 10 It is the slope data diagram in this embodiment.

[0179] The specific contents of the present invention are further explained in detail below with reference to the embodiments. DETAILED DESCRIPTION

[0180] It should be noted that, unless otherwise specified, all components in the present invention are components known in the art.

[0181] Specific embodiments of the present invention are given below. It should be noted that the present invention is not limited to the following specific embodiments, and all equivalent modifications made on the basis of the technical solution of this application fall within the protection scope of the present invention.

[0182] Example:

[0183] This embodiment provides a method for constructing a plug-in hybrid electric vehicle control model, which specifically includes the following steps:

[0184] Step 1: Construct an energy control model for plug-in hybrid electric vehicles based on the improved DDPG, and determine the state set of the energy control model for plug-in hybrid electric vehicles based on the improved DDPG. , action set , a reward function that adapts to truck driving data and constraint functions;

[0185]

[0186]

[0187]

[0188] in:

[0189] The speed of the vehicle in the main queue's driving path, ;

[0190] is the acceleration of truck i, ;

[0191] is the amount of electricity of truck i at time t;

[0192] is the battery health status of truck i at time t;

[0193] is the engine output power of truck i, ;

[0194] is the weight of fuel consumption;

[0195] is the weight of battery charge maintenance;

[0196] is the weight of battery degradation cost;

[0197] is the fuel consumption at time t;

[0198] is the electricity consumption at time t;

[0199] It is the reference value of the battery health status;

[0200] The driving distance is The spatial domain index SoC of time;

[0201] is the SoC decrease rate in the spatial domain;

[0202] For the initial SoC;

[0203] For the target SoC;

[0204] The expected driving range after fully charging the battery;

[0205] is the initial value of the equivalence factor;

[0206] is the value of the equivalent factor when the slope is 0;

[0207] is the slope value;

[0208] is the minimum slope value;

[0209] is the maximum slope value;

[0210] The constraint function of the energy control model of plug-in hybrid electric vehicles based on the improved DDPG is as follows:

[0211]

[0212] in:

[0213] is the battery charge;

[0214] is the minimum value of SoC;

[0215] is the maximum value of SoC;

[0216] , eng is the engine, MG1 is the electric motor, and MG2 is the generator;

[0217] is the torque of the power unit x, ;

[0218] is the minimum torque of the power unit x, ;

[0219] is the maximum torque of the power unit x, ;

[0220] is the speed of the power unit x, rpm;

[0221] is the minimum speed of the power unit x, rpm;

[0222] is the maximum speed of the power unit x, rpm;

[0223] In step 2, standard operating conditions and slopes are collected as sample sets, and the sample sets are input into the improved DDPG-based plug-in hybrid electric vehicle energy control model constructed in step 1 for training to obtain a trained improved DDPG-based plug-in hybrid electric vehicle energy control model.

[0224] In the above scheme, the general training process is: starting from the initial state set S, optimizing the action set action so that the action set action can get higher and higher scores in the reward function J, thereby achieving training. For details, please refer to the authorized Chinese patent CN202211627066.4.

[0225] In this embodiment:

[0226] according to The solution is obtained;

[0227] To solve the quantity that changes with time;

[0228] To solve the quantity that changes with time;

[0229] for Figure 7 middle Curve, SoC degradation rate in the spatial domain Available in Figure 7 get;

[0230] is the mileage value of specific working conditions;

[0231] The value of is related to the remaining mileage of the specific working conditions;

[0232] is the minimum value of the slope under specific working conditions;

[0233] is the maximum value of the slope under specific working conditions;

[0234] The sample set is the standard working condition and slope. The standard working condition includes the curve that changes with time, and its data is as follows Figure 9 As shown, the slope data is Figure 10 As shown;

[0235] The specific description of each parameter in the energy control model of plug-in hybrid electric vehicle based on the improved DDPG is shown in the table:

[0236]

[0237] A method for controlling a platoon of plug-in hybrid electric trucks comprises the following steps:

[0238] Get the slope of the mining platform and the speed of truck i , and input it into the improved DDPG plug-in hybrid vehicle energy control model in claim 1 to obtain the truck i engine output power , the truck engine output power The engine speed and torque are calculated by inputting them into the engine's optimal fuel operating curve, and the engine speed and torque are respectively input into the motor transmission path and the generator transmission path to calculate the corresponding motor speed and torque and generator speed and torque.

[0239] Get the slope of the mining platform and the speed of truck i , specifically including the following steps:

[0240] Step 1: Obtain a survey map of the mining platform where the truck platoon is performing the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform;

[0241] Step 2: Establish a mixed integer nonlinear programming model based on the coordinates of the survey map of the mining platform obtained in step 1 , solve mixed integer nonlinear programming models Get the driving path of the main queue and the driving path of truck i;

[0242] The driving path of the main queue is the coordinates of the truck leaving the main queue and the coordinates of the truck merging into the main queue The path of truck i is the coordinate of truck i leaving the main queue. , task point coordinates Coordinates for joining the main queue The connection;

[0243]

[0244] in:

[0245] The main queue is the starting point of the mining platform To the coordinates of the first truck leaving the main queue The time taken, ,s;

[0246] The maximum speed of the main queue, ;

[0247] The coordinates of the last truck to be sent to the main queue for the mission End of the mining platform The time taken, ,s;

[0248] The value of indicates whether there are trucks performing tasks at task point n and task point (n+1) at the same time. If so, Take 1, otherwise Take 0;

[0249] represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes the task point n, s;

[0250] represents the coordinates of the i-th truck merging into the main queue;

[0251] represents the coordinates of the i-th truck leaving the main queue;

[0252] Step 3: Establish the longitudinal dynamic model of the plug-in hybrid truck as shown below;

[0253]

[0254]

[0255]

[0256] in:

[0257] For trucks exist The speed of time, ;

[0258] For trucks exist The acceleration of time, ;

[0259] For trucks exist The differential of the actual torque at the moment

[0260] The speed of the vehicle in the main queue's driving path, ;

[0261] is the acceleration due to gravity;

[0262] For trucks The frontal area, ;

[0263] For trucks Rolling resistance coefficient;

[0264] For trucks Time delay constant of the longitudinal dynamic system;

[0265] For trucks quality, ;

[0266] For trucks The wheel radius, ;

[0267] For trucks transmission system efficiency;

[0268] For trucks The air resistance coefficient;

[0269] is the air density, ;

[0270] For trucks exist The expected torque at time t, ;

[0271] is the truck's serial number, Take 0, 1, 2, ...;

[0272] Step 4: Construct a DMPC-based longitudinal control model for the platoon; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the platoon based on the driving path of the main platoon obtained in step 2. and the objective function Determine the state variables of the DMPC-based platoon longitudinal control model based on the plug-in hybrid truck longitudinal dynamics model constructed in step 3 and control variables ;

[0273] Step 5: Use the ADMM algorithm to solve the objective function of the DMPC-based queue longitudinal control model constructed in step 4 to obtain the speed of truck i in the driving path of the main queue. .

[0274] In this embodiment, Vehicle speed The maximum value of

[0275] In this embodiment, Collected under specific working conditions;

[0276] In this embodiment, the specific descriptions of the parameters in the longitudinal dynamics model of the plug-in hybrid truck are shown in the table:

[0277]

[0278] In this embodiment, the starting point of the mining platform is , the destination of the vehicle queue leaving the mining platform is And the coordinates of the task point are , get the coordinates of the truck leaving the main queue and the coordinates where the truck will meet up with the main queue , as shown in Table 1; the driving path of the main queue and the driving path of the single vehicle are obtained as follows Figure 4 As shown; the position of the main queue is obtained like Figure 5 As shown; the speed of the main queue is obtained like Figure 6 As shown; the engine power obtained is Figure 7 As shown;

[0279] Depend on Figure 7 It can be seen that the engine power distribution is relatively concentrated under the present invention, which effectively avoids the phenomenon that some engines are in extreme working conditions. The engine always works stably and evenly in the high fuel consumption rate range. The battery SOC and SOH changes under the control of the improved DDPG plug-in hybrid vehicle energy control model are as follows: Figure 8 and Figure 9 As shown, Figure 8 Shows the lead vehicle in a real driving scenario The global changes of SOC under each control strategy. Figure 8 As can be seen, the present invention achieves a uniform SOC decrease throughout the entire driving cycle, demonstrating that the EMS effectively accounts for the dynamic reference trajectory. Furthermore, the present invention further adds an equivalent factor and battery degradation cost to the cost function. By sacrificing the reward for SOC deviation, the agent achieves an overall optimal driving cost, resulting in a more gradual SOC decrease. Therefore, the results presented by the present invention are a representative solution that reflects overall optimization performance. Figure 9 The battery degradation trend during the driving cycle is shown in Figure 2. Under the premise of good thermal management of the battery and assuming a constant average internal battery temperature, it can be seen that the present invention can effectively suppress battery health degradation compared to the most advanced existing strategies.

[0280] Table 1

[0281]

[0282] By coordinate processing the mining platform survey map, a mixed integer nonlinear programming model is established , solving for the main queue and individual vehicle paths to meet transportation planning requirements. This effectively addresses issues such as congestion at mining intersections, waiting times for electric shovel transport, and inefficient decision-making due to information silos. By constructing a DMPC-based queue longitudinal control model and solving it using the ADMM algorithm, good vehicle following is achieved for each truck in the queue under various one-way communication topologies. Using a trained energy control model for plug-in hybrid electric vehicles based on an improved DDPG, control variables for the power components are derived, improving fuel economy, reducing vehicle driving costs, and effectively increasing the energy efficiency of PHET in coal mine transportation scenarios.

[0283] Step 2 specifically includes the following steps:

[0284] Step 2.1, build a mixed integer nonlinear programming model :

[0285]

[0286] in:

[0287] The main queue is the starting point of the mining platform To the coordinates of the first truck leaving the main queue The time taken, ;

[0288] The maximum speed of the main queue;

[0289] The coordinates of the last truck to be sent to the main queue for the mission End of the mining platform The time taken, ;

[0290] The value of indicates whether there are trucks performing tasks at task point n and task point (n+1) at the same time. If so, Take 1, otherwise Take 0;

[0291] represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes through task point n;

[0292] represents the coordinates of the i-th truck merging into the main queue;

[0293] represents the coordinates of the i-th truck leaving the main queue;

[0294] Step 2.3, use mixed integer nonlinear programming method to solve the optimal , get the coordinates of the truck leaving the main queue , the coordinates where the truck meets the main queue ;

[0295] Step 2.4, the coordinates of the truck leaving the main queue obtained in step 2.3 and the coordinates of the truck merging into the main queue Connect them in sequence to get the driving path of the main queue; the coordinates of the truck leaving the main queue , task point coordinates and the coordinates of the truck merging into the main queue Connect them in sequence to obtain I truck driving paths.

[0296] Step 4 specifically includes the following steps:

[0297] Step 4.1: The position of the main queue is given by the main queue's driving path obtained in step 2. and vehicle speed , the expected state variables of each truck are obtained according to the following formula ;

[0298]

[0299] in:

[0300] For the Expected displacement of the truck, m;

[0301] For the The expected speed of the truck, ;

[0302] is the distance between two adjacent trucks, m;

[0303] Step 4.2: Define the state variable of the plug-in hybrid truck longitudinal dynamics model established in step 3 as the current state of truck i , the controlled variable is the torque of truck i ;

[0304] Step 4.3, establish the objective function ;

[0305]

[0306] in:

[0307] is the predicted state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0308] is the predicted torque of the i-th truck at time t+k;

[0309] is the hypothetical state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0310] For the Trucks in The hypothetical state at time t, which includes the position and speed of truck i at time t+k;

[0311] is the assumed torque of the i-th truck at time t+k;

[0312] is the expected state of truck i at time t+k, which includes the position and speed of truck i at time t+k;

[0313] is the truck's drag coefficient;

[0314] is the air density, ;

[0315] is the frontal area of ​​the truck, ;

[0316] is the mass of the i-th truck, kg;

[0317] is the acceleration due to gravity;

[0318] is the truck's rolling resistance coefficient;

[0319] is the wheel radius of truck i, m;

[0320] is the truck's transmission efficiency;

[0321] is the penalty weight matrix for the deviation between the actual state and the expected state of the i-th truck at time t;

[0322] is the penalty weight matrix of the error between the actual state and the expected torque of the i-th truck;

[0323] is the penalty weight matrix for the deviation between the actual state and the assumed state of the i-th truck;

[0324] is the penalty weight matrix for the deviation between the expected output of the i-th truck and the expected output of its neighboring vehicles. If the vehicle is adjacent to the lead vehicle, then ;

[0325] is the distance between the i-th truck and the j-th truck, m.

[0326] In the above technical solution, The value depends on the vehicle Can you get the information of the leading vehicle? If the vehicle behind If the lead vehicle information cannot be obtained, =0, otherwise ;

[0327] In the above technical solution, The initial value satisfies , , Step 5 specifically includes the following steps:

[0328] Step 5.1, for the objective function in step 4.3 Introducing dummy variables and , and obtain the improved objective function ;

[0329]

[0330] in:

[0331] is the Lagrangian function of the i-th vehicle at time t;

[0332] is the set of constraints for the i-th truck at time t;

[0333] and are the dual variables corresponding to the i-th truck at time t;

[0334] is the torque of the i-th truck at time t;

[0335] 、 is the penalty coefficient;

[0336] Step 5.2: Improve the objective function obtained in step 5.1 The dual variable in and Update and get the improved objective function after updating the variables , using ADMM algorithm to improve the objective function after updating variables Solve and get the original residual and the dual residual ;

[0337]

[0338]

[0339]

[0340]

[0341]

[0342] in:

[0343] is the update step size of the Lagrangian term;

[0344] is the penalty coefficient;

[0345] Step 5.3: Determine whether both the original residual and the dual residual satisfy the following formula. If so, the control variable is obtained.

[0346] The control variables include the speed of the vehicles in the main queue along the driving path ;

[0347]

[0348] in:

[0349] is the original residual termination condition;

[0350] is the dual residual termination condition.

[0351] In this embodiment, The value of is updated over time during the solution process;

[0352] In this embodiment, The value of is updated over time during the solution process;

[0353] In this embodiment, and The value of is updated over time during the solution process;

[0354] In this embodiment, ;

[0355] In this embodiment, ;

[0356] In this embodiment, ;

[0357] In this embodiment, the original residual termination condition ;

[0358] In this embodiment, the dual residual termination condition .

[0359] The present invention provides a control system for a plug-in hybrid electric truck platoon, which is based on a method for constructing a plug-in hybrid electric vehicle control model and a method for controlling a plug-in hybrid electric truck platoon. The control system includes a map processing unit, a model construction unit, a model training unit, and an output unit.

[0360] The map processing unit is used to obtain the survey map of the mining platform where the truck queue performs the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform;

[0361] The model building unit is used to build a mixed integer nonlinear programming model based on the coordinates of the survey map of the mining platform , solve mixed integer nonlinear programming models Get the driving path of the main queue and the driving path of truck i;

[0362]

[0363] Establish a longitudinal dynamics model for a plug-in hybrid electric truck;

[0364]

[0365]

[0366]

[0367] Construct a DMPC-based longitudinal control model for the platoon; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the platoon based on the obtained driving path of the main platoon. and the objective function Determine the state variables of the DMPC-based platoon longitudinal control model based on the constructed plug-in hybrid truck longitudinal dynamics model and control variables ;

[0368] The ADMM algorithm is used to solve the objective function of the DMPC-based queue longitudinal control model to obtain the vehicle speed under the driving path of the main queue. The second model building unit builds an energy control model based on the improved DDPG plug-in hybrid electric vehicle, and determines the state set based on the improved DDPG plug-in hybrid electric vehicle energy control model. , action set , a reward function that adapts to truck driving data and constraint functions;

[0369]

[0370]

[0371]

[0372] The model training unit is used to collect standard working conditions and slopes and use them as sample sets. The sample sets are input into the constructed energy control model of the plug-in hybrid electric vehicle based on the improved DDPG for training, thereby obtaining a trained energy control model of the plug-in hybrid electric vehicle based on the improved DDPG.

[0373] The output unit is used to output the vehicle speed obtained in step 5 The slope of the mining platform is input into the trained DDPG plug-in hybrid vehicle energy control model to obtain the engine output power of truck i. , the truck engine output power The engine speed and torque are calculated by inputting them into the engine's optimal fuel operating curve, and the engine speed and torque are respectively input into the motor transmission path and the generator transmission path to calculate the corresponding motor speed and torque and generator speed and torque.

Claims

1. A control method for a plug-in hybrid electric truck platoon, characterized in that: The construction method of the plug-in hybrid electric vehicle control model specifically includes the following steps: The method for constructing the plug-in hybrid electric vehicle control model specifically includes the following steps: Step 1: Constructing an energy control model for a plug-in hybrid electric vehicle based on an improved DDPG, determining a state set S, an action set action, a reward function J adaptively changing based on truck driving data, and a constraint function based on the energy control model for the plug-in hybrid electric vehicle based on the improved DDPG; S={v i (t),acc i ,SoC i (t),SoH i (t)},i=1,2...I in: v i (t) The speed of the vehicle in the main queue’s driving path, km / h; acc i is the acceleration of truck i, m / s 2 ; SOC i (t) is the amount of electricity of truck i at time t; SOH i (t) is the battery health status of truck i at time t; is the engine output power of truck i, kW; α is the weight of fuel consumption; β is the weight of battery charge maintenance; γ is the weight of battery degradation cost; fuel(t) is the fuel consumption at time t; elec(t) is the energy consumption at time t; SOH ref It is the reference value of the battery health status; SoC ref (t) is the spatial domain index SoC when the driving distance is d(t); λ is the SoC decrease rate in the spatial domain; SoC ini For the initial SoC; SoC tgt For the target SoC; L is the expected driving range after the battery is fully charged; eq ini is the initial value of the equivalence factor; eq′ is the value of the equivalent factor when the slope is 0; gr is the slope value; gr min is the minimum slope value; gr max is the maximum slope value; The constraint function of the improved DDPG plug-in hybrid electric vehicle energy control model is as follows: in: SoC is the battery capacity; SoC min is the minimum value of SoC; SoC max is the maximum value of SoC; x = eng, MG1, MG2, where eng is the engine, MG1 is the electric motor, and MG2 is the generator; T x is the torque of the power unit x, N·m; is the minimum torque of the power unit x, N·m; is the maximum torque of the power unit x, N·m; w x is the speed of the power unit x, rpm; is the minimum speed of the power unit x, rpm; is the maximum speed of the power unit x, rpm; Step 2: Collect standard operating conditions and slopes as a sample set, and input the sample set into the improved DDPG plug-in hybrid electric vehicle energy control model constructed in Step 1 for training, thereby obtaining a trained improved DDPG plug-in hybrid electric vehicle energy control model; Get the slope of the mining platform and the speed v of truck i i (t), and input it into the trained plug-in hybrid vehicle energy control model based on the improved DDPG obtained by the construction method of the plug-in hybrid vehicle control model to obtain the truck i engine output power The truck engine output power Inputting the data into the optimal fuel operating curve of the engine to calculate the engine speed and torque, inputting the engine speed and torque into the motor transmission path and the generator transmission path respectively, and calculating the corresponding motor speed and torque and generator speed and torque; The slope of the mining platform and the speed v of the truck i are obtained i (t), specifically comprising the following steps: Step 1: Obtain a survey map of the mining platform where the truck platoon is performing the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform; Step 2: Based on the coordinates of the survey map of the mining platform obtained in step 1, a mixed integer nonlinear programming model T is established. total , solve the mixed integer nonlinear programming model T total Get the driving path of the main queue and the driving path of truck i; The driving path of the main queue is the coordinate l where the truck leaves the main queue i and the coordinate c where the truck merges into the main queue i The driving path of truck i is the coordinate l where truck i leaves the main queue. i , task point coordinates q n Coordinate c where it merges with the main queue i The connection; in: T1 is the main queue from the starting point of the mining platform q s The time it takes for the first truck to leave the main queue at coordinate l1, T1 = ||q s -l1|| / v platoon ,s; v platoon The maximum speed of the main queue, km / h; T I The coordinate c of the last truck to perform the task and merge into the main queue I To the end point of the mining platform q f Time taken, T I =||q f -c I || / v platoon ,s; G n The value of indicates whether there are trucks performing tasks at both task point n and task point (n+1). If so, G n Take 1, otherwise G n Take 0; j n represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes the task point n, s; c i represents the coordinates of the i-th truck merging into the main queue; l i represents the coordinates of the i-th truck leaving the main queue; Step 3: Establish the longitudinal dynamic model of the plug-in hybrid truck as shown below; in: is the speed of truck i at time t, km / h; is the acceleration of truck i at time t, m / s 2 ; is the differential of the actual torque of truck i at time t; v i (t) The speed of the vehicle in the main queue’s driving path, km / h; g is the acceleration due to gravity; A is the frontal area of ​​truck i, m 2 ; f i is the rolling resistance coefficient of truck i; τ i is the time delay constant of the longitudinal dynamic system of truck i; m i is the mass of truck i, kg; r i is the wheel radius of truck i, m; η i is the transmission system efficiency of truck i; C i_air is the air resistance coefficient of truck i; ρ is the air density, kg / m 2 ; u i (t) is the expected torque of truck i at time t, N·m; i is the serial number of the truck, i is 0, 1, 2...; Step 4: Construct a DMPC-based longitudinal control model for the queue; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the queue according to the driving path of the main queue obtained in step 2. and the objective function The state variable y of the DMPC-based platoon longitudinal control model is determined based on the plug-in hybrid truck longitudinal dynamics model constructed in step 3. i (t) and control variable u i (t); Step 5: Use the ADMM algorithm to solve the objective function of the DMPC-based queue longitudinal control model constructed in step 4 to obtain the speed v of truck i in the driving path of the main queue. i (t).

2. The method for controlling a plug-in hybrid electric truck platoon according to claim 1, wherein: Step 2 specifically includes the following steps: Step 2.1, construct the mixed integer nonlinear programming model T total : in: T1 is the main queue from the starting point of the mining platform q s The time it takes for the first truck to leave the main queue at coordinate l1, T1 = ||q s -l1|| / v platoon ; v platoon The maximum speed of the main queue; T I The coordinate c of the last truck to perform the task and merge into the main queue I To the end point of the mining platform q f Time taken, T I =||q f -c I || / v platoon ; G n The value of indicates whether there are trucks performing tasks at both task point n and task point (n+1). If so, G n Take 1, otherwise G n Take 0; j n represents the sum of the time when all trucks leave the main queue and the time when no trucks leave the main queue when the main queue passes through task point n; c i represents the coordinates of the i-th truck merging into the main queue; l i represents the coordinates of the i-th truck leaving the main queue; Step 2.3, use the mixed integer nonlinear programming method to solve the optimal T total , get the coordinates l where the truck leaves the main queue i , the coordinate c where the truck merges with the main queue i ; Step 2.4, the coordinates l of the truck leaving the main queue obtained in step 2.3 i and the coordinate c where the truck merges into the main queue i Connect them in sequence to get the driving path of the main queue; the coordinate l of the truck leaving the main queue i , task point coordinates q n and the coordinate c where the truck merges into the main queue i Connect them in sequence to obtain I truck driving paths.

3. The control method of a plug-in hybrid electric truck platoon according to claim 1, characterized in that: Step 4 specifically includes the following steps: Step 4.1: Given the position s0(t) and speed v0(t) of the main queue obtained in step 2, the expected state variables of each truck are obtained according to the following formula: in: is the expected displacement of the i-th truck, m; is the expected speed of the i-th truck, km / h; d des is the distance between two adjacent trucks, m; Step 4.2: Based on the plug-in hybrid truck longitudinal dynamics model established in step 3, define the state variable as the current state y of truck i i (t)=[s i (t),v i (t)] T , the controlled variable is the torque u of truck i i (t); Step 4.3, establish the objective function in: is the predicted state of truck i at time t+k, which includes the position and speed of truck i at time t+k; is the predicted torque of the i-th truck at time t+k; is the hypothetical state of truck i at time t+k, which includes the position and speed of truck i at time t+k; is the hypothetical state of truck j at time t+k, which includes the position and speed of truck i at time t+k; is the assumed torque of the i-th truck at time t+k; is the expected state of truck i at time t+k, which includes the position and speed of truck i at time t+k; C D is the truck's drag coefficient; ρ is the air density, kg / m 2 ; A is the frontal area of ​​the truck, m 2 ; m i is the mass of the i-th truck, kg; g is the acceleration due to gravity; f is the truck's rolling resistance coefficient; r i is the wheel radius of truck i, m; η is the transmission efficiency of the truck; is the penalty weight matrix for the deviation between the actual state and the expected state of the i-th truck at time t; is the penalty weight matrix of the error between the actual state and the expected torque of the i-th truck; is the penalty weight matrix for the deviation between the actual state and the assumed state of the i-th truck; is the penalty weight matrix for the deviation between the expected output of the i-th truck and the expected output of its neighboring vehicles. If the vehicle is adjacent to the lead vehicle, then d i,j is the distance between the i-th truck and the j-th truck, m.

4. The method for controlling a platoon of plug-in hybrid electric trucks according to claim 3, wherein: Step 5 specifically includes the following steps: Step 5.1, for the objective function in step 4.3 Introducing dummy variables and Get the improved objective function L ρ ; in: is the Lagrangian function of the i-th vehicle at time t; is the set of constraints for the i-th truck at time t; and are the dual variables corresponding to the i-th truck at time t; u i (t) is the torque of truck i at time t; ρ1 and ρ2 are penalty coefficients; Step 5.2: Improve the objective function L obtained in step 5.1 ρ The dual variable in and Update and get the improved objective function L after updating the variables ρ ', using ADMM algorithm to improve the objective function L after updating variables ρ 'Solve and get the original residual and the dual residual in: τ is the update step size of the Lagrangian term; is the penalty coefficient; Step 5.3: Determine whether both the original residual and the dual residual satisfy the following formula. If so, the control variable is obtained. The control variables include the vehicle speed v under the driving path of the main queue i (t); in: ε pri is the original residual termination condition; ε dual is the dual residual termination condition.

5. A control system for the plug-in hybrid electric truck platoon, characterized in that: The control method for a plug-in hybrid electric truck platoon according to any one of claims 1 to 4, comprising a map processing unit, a model building unit, a model training unit, and an output unit; The map processing unit is used to obtain a survey map of the mining platform where the truck queue performs the task, coordinate the survey map of the mining platform, and collect the slope of the mining platform; The model building unit is used to build a mixed integer nonlinear programming model T according to the coordinates of the survey map of the mining platform. total , solve the mixed integer nonlinear programming model T total Get the driving path of the main queue and the driving path of truck i; Establish a longitudinal dynamics model for a plug-in hybrid electric truck; Construct a DMPC-based longitudinal control model for the queue; determine the expected state variables of each truck in the DMPC-based longitudinal control model for the queue according to the obtained driving path of the main queue and the objective function The state variable y of the DMPC-based platoon longitudinal control model is determined based on the constructed plug-in hybrid truck longitudinal dynamics model. i (t) and control variable u i (t); The ADMM algorithm is used to solve the objective function of the DMPC-based longitudinal control model to obtain the vehicle speed v under the driving path of the main queue. i (t); The model construction unit constructs an energy control model of a plug-in hybrid electric vehicle based on an improved DDPG, and determines a state set S, an action set action, a reward function J and a constraint function based on the energy control model of the improved DDPG plug-in hybrid electric vehicle; S={v i (t),acc i ,SoC i (t),SoH i (t)},i=1,2...I The model training unit is used to collect standard operating conditions and slopes and use them as sample sets, inputting the sample sets into the constructed energy control model of the plug-in hybrid electric vehicle based on the improved DDPG for training, thereby obtaining a trained energy control model of the plug-in hybrid electric vehicle based on the improved DDPG; The output unit is used to convert the vehicle speed v obtained in step 5 into i (t) and the obtained slope of the mining platform are input into the trained DDPG-based plug-in hybrid vehicle energy control model to obtain the engine output power of truck i The truck engine output power The engine speed and torque are calculated by inputting them into the engine's optimal fuel operating curve, and the engine speed and torque are respectively input into the motor transmission path and the generator transmission path to calculate the corresponding motor speed and torque and generator speed and torque.

Images