Hybrid tractor power matching method and system

Abstract

The invention discloses a hybrid tractor power matching method and system. The hybrid tractor power matching system comprises an engine and a motor. Wherein the output end of the motor and the output end of the engine are respectively connected with the input end of the power coupling device, the output end of the power coupling device respectively drives the gearbox and the generator, and the output end of the gearbox respectively drives the PTO, the transmission device and the hydraulic pump; the output end of the generator charges the power battery, and the power battery supplies power to the motor; the whole vehicle controller is electrically connected with the motor controller, the engine controller, the generator controller and the gearbox controller. According to the hybrid tractor power matching method and system, seamless switching of five working modes is achieved, the impact degree is shortened, and the switching time is shortened; a mechanical clutch is omitted, system structure is simplified, reliability is improved, and maintenance cost is reduced.

Description

Technical Field

[0001] This invention relates to a method and system for power matching of hybrid tractors, belonging to the field of new energy agricultural machinery technology. Background Technology

[0002] Traditional tractors generally use diesel engines as their sole power source, which has drawbacks such as high fuel consumption, severe emissions, and high noise levels. Especially in complex and variable agricultural operating environments, such as plowing, sowing, harvesting, and transporting, the engine often cannot operate in its high-efficiency range, resulting in low energy utilization. Furthermore, traditional mechanical transmission systems have poor adaptability to varying loads, further reducing overall machine efficiency.

[0003] To address these issues, some hybrid tractor solutions have emerged in the existing technology, such as parallel and series hybrid systems. However, most existing systems still employ rule-based energy management strategies, failing to fully integrate real-time operating conditions and power source characteristics for dynamic optimization, leaving considerable room for improvement in overall system efficiency.

[0004] Specifically, while existing hybrid tractor solutions (parallel and series) attempt to improve the above problems, they still have significant limitations:

[0005] Firstly, energy management strategies are mostly based on fixed threshold rules (such as "start the engine to charge when the battery SOC is less than 30%" or "enter parallel mode when the power demand is greater than 100kW"), which cannot dynamically adapt to variables such as soil hardness, type of operation, and driver's operating habits. This can easily lead to "short-sighted decision-making" (such as starting the engine to charge when about to go downhill) or "mode jitter" (frequent switching of modes near the threshold).

[0006] Secondly, the lack of operating condition prediction capabilities and the reliance on real-time status for decision-making make it difficult to cope with sudden load changes (such as farm implements suddenly cutting into hard soil), which can easily lead to engine stalling or overload.

[0007] Third, the power coupling mechanism has a complex design, relies on a mechanical clutch to achieve mode switching, has a response delay of >0.5s, and cannot achieve full-range optimization of the engine operating point.

[0008] Therefore, there is an urgent need to develop a hybrid tractor power matching method and system with intelligent diagnosis, dynamic response and energy optimization management. Summary of the Invention

[0009] Objective: In order to overcome the shortcomings of the existing technology, the present invention provides a method and system for power matching of hybrid tractors.

[0010] Technical solution: To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0011] Firstly, a hybrid tractor power matching system includes: an engine and an electric motor.

[0012] The output terminals of the motor and the engine are respectively connected to the input terminals of the power coupling device. The output terminals of the power coupling device drive the gearbox and the generator, respectively. The output terminals of the gearbox drive the PTO, the transmission device, and the hydraulic pump, respectively. The output terminal of the generator charges the power battery, and the power battery provides power to the motor. The vehicle controller is electrically connected to the motor controller, the engine controller, the generator controller, and the gearbox controller, respectively.

[0013] Secondly, a control method for a hybrid tractor power matching system specifically includes:

[0014] Step 1: Input vehicle and operation data into the prediction model to obtain the types of operation conditions and the rate of change of power demand in the future.

[0015] Step 2: Fuzzify the instantaneous power demand, power battery SOC, operating conditions, and power demand change rate to obtain the fuzzification result. Based on the fuzzification result and the fuzzy rule base, obtain the control command.

[0016] Step 3: Based on the control commands, establish the optimization function and constraints, use the rolling time-domain optimization algorithm to solve for the optimal power allocation, and output the final target power values ​​of the engine, motor, and generator.

[0017] Optionally, the vehicle and operation data include: soil hardness, vehicle speed, throttle opening, PTO load, GPS signal, hydraulic pump pressure, motor speed, motor torque, generator speed, generator torque, power battery SOC, steering angle, crop type, crop row spacing, and crop tillage depth.

[0018] Optionally, the prediction model includes: the prediction model adopts a 3-layer LSTM network, with an input layer dimension of 15, a hidden layer neuron count of 64, and an output layer dimension of 2 (job condition classification probability, demand power change rate).

[0019] The operating conditions include: road transport, light-load operation, medium-load operation, heavy-load operation, and turning at the edge of the field.

[0020] Optionally, the instantaneous power demand, battery SOC, operating conditions, and power demand change rate are fuzzified to obtain the fuzzification result, specifically including:

[0021] The fuzzy subset of the instantaneous power demand is shown in the table below:

[0022] Fuzzy subsets Core interval (membership = 1) Support region (membership > 0) NB (negative big) -180 kW [-180, -120] kW NM (negative medium) -80 kW [-120, -30] kW NS (negative small) -10 kW [-30, 0] kW Z (zero) 0 kW [-10, 10] kW PS (positive small) 30 kW [0, 50] kW PM (positive medium) 80 kW [50, 120] kW PB (positive big) 180 kW [120, 220] kW

[0023] The fuzzy subset of the power battery SOC is shown in the table below:

[0024] Fuzzy subsets Core interval (membership = 1) Support region (membership > 0) Road transport 0%-10% [0%,20%] Vehicle speed: 25 -40 km / h PTO: 0 Nm traction resistance: < 2 kN 20% [10%,40%] Vehicle speed: 20-45 km / h PTO: 0-50 Nm traction resistance: < 3 kN 40%-60% [30%,70%] Light load operation 70% [60%,80%] Vehicle speed: 5-15 km / h PTO: 50-150 Nm traction resistance: 2-5 kN 90%-100% [80%,100%]

[0025] The fuzzy subset of the operating conditions is shown in the table below:

[0026] Vehicle speed: 3-20 km / h PTO: 30-200 Nm traction resistance: 1-6 kN Medium load operation Vehicle speed: 8-25 km / h PTO: 150-300 Nm traction resistance: 5-10 kN Vehicle speed: 5-30 km / h PTO: 100-350 Nm traction resistance: 4-12 kN Heavy load operation Vehicle speed: 3-15 km / h PTO: 300-500 Nm traction resistance: 10-20 kN Vehicle speed: 2-20 km / h PTO: 250-550 Nm traction resistance: 8-25 kN Cornering on rough terrain Vehicle speed: 0-5 km / h hydraulic pump pressure: 15-25 MPa steering angle: > 30° Vehicle speed: 0-8 km / h hydraulic pump pressure: 10-30 MPa steering angle: > 20° Fuzzy subsets Core interval (membership = 1) Support region (membership > 0) Fast_Fall (fast fall) -10 kW / s [-10, -6] kW / s Slow_Fall (slow fall) -3 kW / s

[0027] The fuzzy subset of the rate of change of demand power is shown in the table below:

[0028] [-6, -1] kW / s Steady (steady) 0 kW / s [-1, +1] kW / s Slow_Rise (slow rise) +3 kW / s [+1, +6] kW / s Fast_Rise (fast rise) +10 kW / s [+6, +10] kW / s Rule number Condition Conclusion P_req = PS AND SOC = H AND WorkType = light load operation AND dP_req = Steady AND predicted WorkType = light load operation (for > 5 min) Pure electric drive mode (extended operation) P_req = Z AND WorkType = cornering on rough terrain AND SOC >= M AND predicted WorkType = cornering on rough terrain (for <= 30 s) Pure electric drive mode (steering optimization) ​

[0029] Optionally, the fuzzy rule base is shown in the following table:

[0030] ​ ​ ​ 1 ​ ​ 2 ​ ​ 3 P_req=PM AND SOC=L AND dP_req=Steady AND WorkType = Road Transport AND Predictive WorkType = Road Transport (duration ≥ 10 min) Driving charging mode (high power) 4 WorkType = Road Transport AND SOC=M AND dP_req=Slow_Fall AND Predicted P_req_pred=-20~0kW (future 1s) Charging mode while driving (release accelerator in advance) 5 P_req = PB AND (WorkType = Heavy Work OR dP_req = Fast_Rise) AND Predicted P_req_pred > 200kW (in the next 0.5s) Hybrid drive mode (peak assist) 6 P_req=PM AND WorkType = Medium workload AND dP_req=Slow_Rise AND Forecast dP_req=Fast_Rise (1 second ahead) Hybrid drive mode (pre-charge) 7 P_req=NS AND SOC<VH AND WorkType = Road Transport AND Predicted WorkType = Road Transport (Downhill, duration ≥2min) Braking energy recovery mode (high power) 8 P_req=PB AND WorkType = Heavy workload AND SOC=M AND Predicted dP_req=Fast_Fall (future 0.8s) Hybrid drive mode (progressive power reduction) 9 P_req=PM AND WorkType = Medium Load Operation AND SOC=VH AND Predicted P_req_pred≤0kW (future 1s) Series drive mode (charging stopped) 10 P_req=PS AND WorkType = Light workload AND dP_req=Fast_Rise AND Predicted WorkType = Medium workload (future 3s) Series drive mode (early engine start) 11 P_req=NM AND WorkType = Road Transport (Downhill) AND SOC<H AND Predicted WorkType = Road Transport (Flat Road, Future 2s) Braking energy recovery mode (gradient recovery) 12 P_req=Z AND WorkType = Static AND SOC=VL AND Predicted WorkType = Light workload (future 5s) Series drive mode (idle charging)

[0031] Optionally, step 3 includes:

[0032] Step 3.1: During control period k, obtain the vehicle demand power sequence [P_req(k), P_req(k+1), ..., P_req(k+N)] for a short time window in the future.

[0033] Step 3.2: Within the prediction time domain [k, k+N], run the dynamic programming algorithm to solve for the optimal engine power control sequence [u*(k), u*(k+1), ..., u*(k+N)], which minimizes the total cost J within this time period, and optimizes the solution to obtain the optimal control quantity u*(k).

[0034] Step 3.3: Execute the optimal control quantity u*(k) for the current control cycle k, i.e., the control command. The engine outputs P_eng(k), the motor outputs P_ISG(k), and the generator outputs P_gen(k).

[0035] Step 3.4: Move to the next time step k+1. Based on the new measured state, repeat steps 3.1-3.4 to perform a new round of prediction and optimization.

[0036] Optionally, the optimization function includes:

[0037] min J = ∫[α·m_f(P_eng) + β·(SOC-SOC_ref)² + γ·(P_req-P_actual)² +δ·(T_motor-T_motor_max)²]dt

[0038] Where J is the total cost, m_f(P_eng) is the engine fuel consumption rate, SOC_ref is the target value of battery state of charge, SOC is the actual value of battery state of charge, P_actual is the actual output power, P_req is the actual demand power, T_motor is the actual torque of the motor, T_motor_max is the maximum torque of the motor, α, β, γ, and δ are weighting coefficients, and t is the time unit.

[0039] The constraints include: power balance constraints, component physical constraints, and prediction constraints.

[0040] Optionally, the operating modes specifically include:

[0041] Pure electric drive mode: The engine is not running; the vehicle is driven solely by the ISG motor. The vehicle controller controls the engine controller to shut off the engine, and then controls the generator controller to output a reverse electromagnetic resistance, locking the sun gear and reducing its speed to zero. The vehicle controller then controls the ISG controller to allow the ISG motor to draw power from the battery, outputting positive torque to drive the ring gear, which rotates at a speed greater than zero. In short, the generator "applies the brake," fixing the sun gear, and the ISG motor drives the ring gear; the power coupling device acts like a fixed-axis gear system, delivering power. Switching from this mode to other modes simply requires the generator to release the braking torque and begin speed regulation, without any mechanical shock.

[0042] Series Drive Mode: The engine drives the generator to produce electricity, which powers the ISG motor to drive the vehicle or charge the battery. The vehicle controller controls the engine controller to start the engine and operate it within its most efficient speed-torque range. The vehicle controller also controls the generator controller to produce electricity, with its load precisely controlled to maintain the engine's desired speed. The vehicle controller further controls the ISG controller to allow the ISG motor to draw power from the generator and battery, outputting torque to drive the ring gear to rotate at the speed required for the current vehicle speed. In this mode, engine speed is completely decoupled from vehicle speed, ensuring it remains at its most efficient point. Entering and exiting this mode is achieved solely through electronic adjustments to the power output of the generator and ISG motor.

[0043] Parallel / Hybrid Drive Mode: The engine and MG2 jointly drive the wheels, providing maximum power. The vehicle controller controls the engine controller to operate the engine in its high-efficiency range, outputting positive torque. The vehicle controller also controls the generator controller to maintain the generator's speed at a specific value. This allows the generator to generate electricity slightly to optimize engine load, or to consume a small amount of electrical energy to operate as an electric motor to adjust the engine's operating point. Its core function is "speed regulation," decoupling engine speed from vehicle speed. The vehicle controller further controls the ISG controller to output positive torque from the ISG motor for auxiliary drive. The transition from series mode to parallel mode is smooth, requiring only an increase in engine torque output while simultaneously adjusting the torque of the generator and ISG motor; the process is continuous and without jerks.

[0044] Driving charging mode: This mode is a special case of parallel mode. The vehicle controller controls the generator controller to increase the generator's output power, thereby increasing the engine load. The generated electrical energy exceeds the energy consumed by the ISG motor, and the excess electrical energy charges the power battery. The entire process is also seamless.

[0045] Braking Energy Recovery Mode: With the engine and generator off, the ISG motor recovers braking energy. The vehicle controller controls the engine controller to shut down the engine or cut off fuel. The vehicle controller controls the generator controller to shut down the generator or provide a small amount of torque to keep the sun gear rotating. The vehicle controller controls the ISG controller to make the ISG motor act as a generator, using the wheels to generate negative torque (braking force), converting kinetic energy into electrical energy stored in the battery. The system immediately enters energy recovery mode as soon as the driver releases the accelerator, with a rapid and smooth response.

[0046] Thirdly, a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a control method for a hybrid tractor power matching system as described in any of the second aspects.

[0047] Fourthly, a computer device comprising:

[0048] Memory is used to store instructions.

[0049] A processor is configured to execute the instructions, causing the computer device to perform the operation of a control method for a hybrid tractor power matching system as described in any of the second aspects.

[0050] Beneficial Effects: This invention provides a hybrid tractor power matching method and system. Through an innovative hybrid power architecture, combined with real-time data from multi-source sensors and operating condition prediction technology, it utilizes fuzzy logic and dynamic programming algorithms to achieve intelligent power allocation among the engine, ISG motor, and generator. Simultaneously, it is equipped with a high-efficiency energy recovery system, solving the problems of low energy utilization efficiency, poor operating condition adaptability, and delayed power response in existing technologies. The invention achieves the following objectives: Introducing a deep learning operating condition prediction model to predict operating conditions and load changes 0.5-3 seconds in advance, achieving proactive power matching; increasing the engine's high-efficiency operating time to over 80%, improving fuel economy by 15%-25%; achieving seamless switching between five operating modes, shortening the impact and reducing switching time; eliminating the mechanical clutch, simplifying the system structure, improving reliability, and reducing maintenance costs. Compared to existing technologies, its advantages are as follows:

[0051] 1. Forward-looking power matching, fast response speed, and reduced engine stall rate.

[0052] 2. The proportion of time the engine operates in its high-efficiency zone increases, resulting in a decrease in fuel consumption.

[0053] 3. Seamless and smooth mode switching with fast switching time and low impact.

[0054] 4. Eliminating the clutch increases system reliability, reduces failure rate, and lowers maintenance costs.

[0055] 5. It has strong adaptability to working conditions and is applicable to more than 95% of farmland operation scenarios. Attached Figure Description

[0056] Figure 1 This is a schematic diagram of the power matching system for a hybrid tractor.

[0057] Figure 2 This is a flowchart illustrating the power matching method for hybrid tractors.

[0058] Figure 3 This is a schematic diagram of the working condition prediction layer process.

[0059] Figure 4 This is a schematic diagram of the fuzzy decision-making process.

[0060] Figure 5 This is a schematic diagram of the dynamic optimization layer process. Detailed Implementation

[0061] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0062] The present invention will be further described below with reference to specific embodiments.

[0063] Example 1:

[0064] This embodiment describes a hybrid tractor power matching system, such as... Figure 1 As shown, it includes: engine, ISG (Integrated Starter Generator) motor, power coupling device, PTO (Power Take-Off) device, 3-speed gearbox, hydraulic pump, generator, power battery, and vehicle controller.

[0065] The output terminals of the ISG motor and the engine are respectively connected to the input terminals of the power coupling device. The output terminals of the power coupling device drive the 3-speed gearbox and the generator, respectively. The output terminals of the 3-speed gearbox drive the PTO, the transmission device, and the hydraulic pump, respectively. The output terminal of the generator charges the power battery, and the power battery provides power to the ISG motor. The vehicle controller is electrically connected to the ISG motor controller, the engine controller, the generator controller, and the gearbox controller, respectively.

[0066] Among them, the engine is the main power source of the system, especially when working under continuous high power demand conditions. Its operating point can be optimized by system control and always operates in the high efficiency range. Its output shaft is mechanically connected to the power coupling device.

[0067] The ISG motor has a dual function: firstly, as a drive motor to drive the vehicle and provide torque (especially to assist the engine during start-up, acceleration, and heavy loads); secondly, as a generator to recover kinetic energy to charge the battery during braking or coasting, or to be driven by the engine to generate electricity when needed; its rotor shaft is mechanically connected to the power coupling device.

[0068] The primary function of a generator is to generate electricity. Driven by an engine, it converts the engine's mechanical energy into electrical energy to charge the battery or directly power the electric motor. By adjusting its own load (generating power), it can steplessly regulate the engine's speed and load, keeping it always within its optimal operating range (efficient fuel consumption range). It is rigidly connected to the engine crankshaft on the same axis and does not directly drive the wheels. Its core functions are frequency regulation and power generation.

[0069] The main function of the power battery is as the energy buffer center of the system. It can store electrical energy recovered from the generator and ISG motor to regenerate braking energy, and it can also provide electrical energy to the ISG motor to drive the vehicle. It exchanges electrical power with the ISG motor and generator through high-voltage wiring harness.

[0070] The power coupling device is used to achieve flexible coupling and splitting of power between the engine and the ISG motor. The power coupling device mainly consists of a planetary carrier, a sun gear, and gears. The planetary carrier is connected to the engine output shaft, the sun gear is connected to the generator, and the gear ring is connected to the ISG motor and the final output shaft, leading to the gearbox.

[0071] The gearbox primarily supplies power by changing speed and torque, and distributes power to the wheels, PTO, and hydraulic pump through different speed ratios; the first gearbox can provide power to the wheels, PTO, and hydraulic pump, the second gearbox can provide power to the wheels and PTO, and the third gearbox only provides power to the wheels.

[0072] The vehicle controller receives all sensor signals (throttle, brake, vehicle speed, load, battery SOC, etc.), and based on the intelligent control strategy of this invention, determines the current optimal working mode in real time, sends instructions to each sub-controller (engine ECU, motor MCU, transmission TCU, etc.), coordinates the operation of the entire system, and conducts high-speed data communication with all subsystems through the CAN bus.

[0073] The ISG motor controller receives commands from the vehicle controller to control and drive the ISG motor.

[0074] The generator controller receives commands from the vehicle controller to control the operation of the drive generator.

[0075] The transmission controller receives instructions from the vehicle controller to control the operation of the transmission.

[0076] The engine controller receives instructions from the vehicle controller to control the operation of the drive engine.

[0077] Compared to current mainstream solutions, the power matching system of this invention can seamlessly switch between multiple modes such as series, parallel, and pure electric drive according to operational needs, improving the overall system efficiency, eliminating the clutch, and reducing system bloat.

[0078] Example 2:

[0079] This embodiment introduces a control method for a hybrid tractor power matching system, employing a three-layer control strategy: "operating condition prediction layer - fuzzy decision layer - dynamic optimization layer," such as... Figure 2 As shown, it specifically includes:

[0080] The work condition prediction layer is the core of achieving forward-looking control. Based on a Long Short-Term Memory (LSTM) network model, it collects historical and real-time data from multiple sources of sensors, outputting the work condition classification (WorkType) and demand power change trend (dP_req) for the next 0.5-3 seconds, as well as the reliability of the results. The flowchart is as follows. Figure 3 As shown, the specific process is as follows:

[0081] Data input includes real-time and historical data. Real-time data includes soil hardness, vehicle speed, throttle opening, PTO load, hydraulic pump pressure, ISG motor speed, ISG motor torque, generator speed, generator torque, battery SOC, steering angle, crop type, row spacing laser torque meter, GPS (Global Positioning System), and tillage depth ultrasonic sensor. Historical data includes past real-time data and 1000 hours of farmland operation data collected.

[0082] Data preprocessing includes Kalman filtering for noise reduction, missing value interpolation and imputation, data standardization [0,1], and sliding window construction.

[0083] Model Training and Prediction: The model employs a 3-layer LSTM network with an input layer dimension of 15 (representing the 15 data classes mentioned above), 64 hidden layer neurons, and an output layer dimension of 2 (WorkType classification probability and dP_req predicted value). The reliability of each prediction result is evaluated. Training is performed using 1000 hours of farmland operation data, optimized with a cross-entropy loss function. The classification accuracy exceeds 92%, and the dP_req prediction error is <5%. After deployment, the model is continuously fine-tuned to adapt to specific farmland environments and operational habits. Real-time prediction is primarily performed every 100ms. The system updates the input data once and outputs predictions for the next 0.5s (short cycle - emergency response), 1.5s (medium cycle - major decision-making), and 3s (long cycle - strategic planning). Medium cycle predictions are prioritized for control decisions, while short cycle predictions are used for correction. The prediction reliability assessment mainly involves cross-validating the prediction results with real-time sensor readings. If the WorkType classification accuracy reaches no less than 92% and the dP_req prediction error is no greater than 5%, the system is deemed to have insufficient reliability and will perform an online model update. Incremental learning, parameter fine-tuning, and adaptive optimization are then performed by combining the prediction results and real-time data to improve prediction reliability.

[0084] Prediction results output: WorkType prediction, outputs the classification probability of "road transport / light load operation / medium load operation / heavy load operation / turning at the edge of the field", and takes the working condition with the highest probability as the final prediction result; dP_req prediction, outputs the first derivative of the power demand in the future period (-10 to +10kW / s), reflecting the direction and rate of load change.

[0085] The fuzzy decision layer primarily uses the output of the operating condition prediction layer as its input parameters. It combines fuzzy sets and fuzzification rules to obtain precise information, performs defuzzification processing, outputs accurate control commands, and finally implements the commands based on the prediction results. The flowchart is shown below. Figure 4 As shown, the fuzzy subsets and fuzzy rule bases are as follows.

[0086] Instantaneous power demand (P_req) is calculated based on the accelerator pedal, current vehicle speed, gear ratio, etc., and represents the total power required at the drive wheels to maintain the current state of motion. P_req < 0 indicates that the vehicle has braking or deceleration requirements.

[0087] Its fuzzy set (universe: -180 kW ~ 220 kW) is shown in the table below:

[0088] Fuzzy subsets Core interval (membership degree = 1) Support region (membership degree > 0) Engineering meaning Predicting related information NB (Negative) -180kW [-180,-120]kW Emergency braking, long steep downhill descent (maximum recovery required) When P_req_pred ≤ -150kW (0.5s in the future), the membership level increases by 20%, prioritizing the triggering of high-power recovery. NM (Negative) -80kW [-120,-30]kW Moderate braking, moderate gradient descent (normal recovery) When P_req_pred is predicted to be -90 to -60 kW, adjust the ISG motor recovery torque range 0.2 seconds in advance. NS (Negative Small) -10kW [-30,0]kW Slight braking and coasting (mild recovery) When P_req_pred is predicted to be -20 to 0 kW and the duration is ≥1.5 s, maintain a mild recovery mode. Z (Zero) 0kW [-10,10]kW Static charging or idling (zero power requirement) When WorkType is predicted to be a turn and the duration is ≤30s, pure electric mode should be selected first. PS (Zheng Xiao) 30kW [0,50]kW Low-speed site transfer and spraying (light load) When WorkType is predicted to be light-load operation with a duration of ≥5 minutes, extend the pure electric mode operation threshold (SOC≥65%). PM (center) 80kW [50,120]kW Medium-speed transport, rotary tillage (medium load, engine high-efficiency range) When dP_req is predicted to be (+2~+4kW / s), the engine power reserve is increased 0.5s in advance. PB (Zhengda) 180kW [120,220]kW Plowing and climbing steep slopes (heavy load, requiring peak power) When WorkType is predicted to be heavy workload with a duration of ≥3 minutes, the generator "frequency regulation" function will be activated in advance.

[0089] The state of charge (SOC) of a battery is the remaining charge state of the battery. Its fuzzy set (universe of discourse: 0% ~ 100%) is shown in the table below:

[0090] Fuzzy subsets Core interval (membership degree = 1) Support region (membership degree > 0) Engineering meaning Predicting related information VL (very low) 0%-10% [0%,20%] Battery critically low (forced charging required) When WorkType is predicted to be road transport (lasting ≥10 minutes), the vehicle will be forced to enter the on-the-go charging mode, and the charging power will be increased to 40kW. L (Low) 20% [10%,40%] Low battery (charge first) When P_req_pred is predicted to be ≤50kW (within the next 1.5s), series charging will be prioritized to avoid power consumption in parallel charging. M (middle) 40%-60% [30%,70%] Battery life is moderate (can be optimized freely). When predicting dP_req = Fast_Rise (+8~+10kW / s), reserve 20% of battery power to cope with sudden load changes. H (High) 70% [60%,80%] Fully charged (discharge priority) When WorkType is predicted to be a turn (0.5 seconds in the future), the engine load is reduced in advance to prepare for the switch to pure electric mode. VH (Very High) 90%-100% [80%,100%] Battery fully charged (limit charging) When P_req_pred ≤ 0kW (within the next 1.5s), the generator charging function is turned off, and only regenerative braking is enabled.

[0091] WorkType, output by the work type prediction layer, is one of the key inputs to achieving "forward-looking decision-making" in this invention. It informs the controller of the nature of the work within a future period, and its fuzzy set (universe of discourse: 0% ~ 100%) is shown in the table below:

[0092] Fuzzy subsets Core interval (membership degree = 1) Support region (membership degree > 0) Engineering meaning Predicting related information Road transport Vehicle speed: 25-40 km / h; PTO: 0 Nm; Traction resistance: <2 kN Vehicle speed 20-45km / h, PTO load 0-50Nm, traction resistance <3kN Smooth operation, high speed, low resistance (PTO not working) Based on vehicle speed trend prediction, if the vehicle is still in road transport mode within the next 2 seconds, shift to 3rd gear in advance; if it is predicted that the vehicle will be entering a field, reduce the speed to 15km / h in advance. Light load operation Vehicle speed: 5-15 km / h; PTO: 50-150 Nm; Traction resistance: 2-5 kN Vehicle speed: 3-20 km / h; PTO: 30-200 Nm; Traction resistance: 1-6 kN Low traction, continuous operation (spraying, seeding) Based on the position sensor of the implement and the crop row spacing prediction, if the load is still light within the next 3 seconds, the pure electric mode is maintained; if the implement is predicted to be raised, the power of the ISG motor is reduced in advance. Medium load operation Vehicle speed: 8-25 km / h; PTO: 150-300 Nm; Traction resistance: 5-10 kN Vehicle speed: 5-30km / h; PTO: 100-350Nm; Traction resistance: 4-12kN Load fluctuations, periodicity (rotary tillage, harrowing) By using soil hardness sensors and operating depth feedback, when the load is predicted to fluctuate by ±15% within the next second, the generator's power output is adjusted in advance to avoid mode jitter. Heavy load operation Vehicle speed: 3-15 km / h; PTO: 300-500 Nm; Traction resistance: 10-20 kN Vehicle speed: 2-20 km / h; PTO: 250-550 Nm; Traction resistance: 8-25 kN High power, continuous (plowing, deep loosening) Based on the load trends of the ISG motor and engine, if the power demand exceeds 200kW within the next 0.5s, the peak torque (200N·m) of the ISG motor will be activated in advance. Turning at the edge of the field Vehicle speed: 0-5km / h; Hydraulic pump pressure: 15-25MPa; Steering angle >30° Vehicle speed: 0-8 km / h; Hydraulic pump pressure: 10-30 MPa; Steering angle > 20° Short duration, low speed, high hydraulic resistance (≤30s) By using a steering angle sensor and work path planning, when a turn is expected within 0.5 seconds, the engine is shut off in advance (if the state of charge (SOC) is ≥ 50%), and the system switches to pure electric mode to reduce steering impact.

[0093] The demand power change trend (dP_req), output by the load forecasting layer, is obtained through first-order derivative analysis of the demand power sequence for the next few seconds. It reflects the direction and speed of dynamic load changes, as shown in the table below:

[0094] Fuzzy subsets Core interval (membership degree = 1) Support region (membership degree > 0) Engineering meaning Predicting related information Fast_Fall -10kW / s [-10,-6]kW / s The load is reduced sharply (implements are lifted off the ground, throttle is released suddenly). If the predicted dP_req is ≤-8kW / s for a duration ≥0.5s, the engine will be started early to cut off fuel supply and avoid fuel waste. Slow_Fall -3kW / s [-6,-1]kW / s The load decreases smoothly (smooth deceleration, gentle slope). If the predicted dP_req is -4 to -2 kW / s and the system is expected to switch to Steady mode within the next 1.5 seconds, maintain the current mode to avoid frequent switching. Steady 0kW / s [-1,+1]kW / s With the load remaining constant (uniform speed travel, uniform operation), If the predicted Steady state lasts for ≥2 minutes, optimize the engine operating point to the lowest fuel consumption zone (210g / kWh). Slow Rise +3kW / s [+1,+6]kW / s The load increases steadily (smooth acceleration, farm implements slowly enter the soil). If it is predicted that the Slow Rise will last for ≥0.5s and will transition to Fast Rise within the next 1.5s, the power reserve of the ISG motor should be increased in advance. Fast Rise +10kW / s [+6,+10]kW / s The load increased sharply (farm implements rushed into the soil, encountered stones). When the predicted Fast_Rise peak value is greater than +10kW / s, the generator is triggered to "unload" 0.1s in advance to prioritize the stable operation of the engine.

[0095] The fuzzy rules are mainly based on fuzzy subsets and expert experience. Twelve fuzzy rules are compiled to defuzzify the fuzzy information and finally obtain definite conclusions. The fuzzy rule base is shown in the table below:

[0096] Rule Number condition in conclusion Application Scenario Description 1 P_req=PS AND SOC=H ANDWorkType = Light workload ANDdP_req=Steady AND Predicted WorkType = Light workload (duration ≥ 5 min) Pure electric drive mode (extended operation) For light-load spraying operations, the real-time status meets the requirements for pure electric operation, and the forecast indicates that the light-load condition will continue for the next 5 minutes, eliminating the need for frequent mode switching and improving operational continuity. 2 P_req=Z AND WorkType = Turn at the edge of the field AND SOC≥M AND Predicted WorkType = Turn at the edge of the field (duration ≤30s) Pure electric drive mode (steering optimization) It can enter the corner in real time with a short prediction duration, and the pure electric mode has a fast response (0.05s start-up). It also adjusts the steering assist torque in advance to reduce impact. 3 P_req=PM AND SOC=L AND dP_req=Steady AND WorkType =Road Transport AND Predicted WorkType=Road Transport (duration ≥10min) Driving charging mode (high power) With medium-load transportation and low battery levels, and a forecast of stable transportation for the next 10 minutes, the generator charging power was increased from 30kW to 35kW in advance to accelerate SOC recovery. 4 WorkType = Road Transport AND SOC = M AND dP_req = Slow_Fall AND Predicted P_req_pred = -20~0kW (future 1s) Charging mode while driving (release accelerator in advance) The transport load is about to decrease, and it is predicted that the vehicle will enter a coasting state in the next second. Therefore, the engine power is reduced to 60kW in advance, while maintaining charging to avoid energy waste. 5 P_req = PB AND (WorkType = Heavy Work OR dP_req = Fast_Rise) AND Predicted P_req_pred > 200kW (in the next 0.5s) Hybrid drive mode (peak assist) With real-time heavy load and high power demand, and a predicted power output exceeding 200kW in the next 0.5 seconds, the ISG motor torque was increased from 150Nm to 200Nm in advance to avoid engine overload. 6 P_req=PM AND WorkType = Medium workload AND dP_req=Slow_Rise AND Forecast dP_req=Fast_Rise (1 second ahead) Hybrid drive mode (pre-charge) Under real-time medium load with a slow load increase, and with a predicted sharp increase in the next second, the engine is started ahead of time to increase power from the high-efficiency range (80kW) to 90kW, while the ISG motor has a reserve power of 20kW. 7 P_req=NS AND SOC<VH ANDWorkType = Road Transport AND Predicted WorkType = Road Transport (Downhill, duration ≥2min) Braking energy recovery mode (high power) Based on real-time coasting conditions and predictions of a long downhill slope in the next 2 minutes, the ISG motor's recovery torque is reduced from -50Nm to -100Nm in advance, maximizing the recovery of downhill kinetic energy (recovery efficiency increased to 70%). 8 P_req=PB AND WorkType = Heavy workload AND SOC=M AND Predicted dP_req=Fast_Fall (future 0.8s) Hybrid drive mode (progressive power reduction) Real-time heavy-load plowing predicts that the implements will be lifted off the ground in 0.8 seconds (sudden load drop), and gradually reduces the engine power from 90kW to 70kW in advance to avoid mode fluctuations. 9 P_req=PM AND WorkType = Medium Load Operation AND SOC=VH AND Predicted P_req_pred≤0kW (future 1s) Series drive mode (charging stopped) With medium-load rotary tillage and battery saturation, and anticipating coasting within 1 second, the generator charging function is switched off in advance, maintaining only efficient engine power generation (35kW) to drive the ISG, thus preventing battery overcharging. 10 P_req=PS AND WorkType = Light workload AND dP_req=Fast_Rise AND Forecast WorkType = Medium workload (future 3s) Series drive mode (early engine start) Under real-time light load but with a sharp increase in load, predicting a transition to medium load within 3 seconds, start the engine to 1800 rpm (high-efficiency range) 0.3 seconds in advance to avoid delay in series mode switching. 11 P_req=NM AND WorkType = Road Transport (Downhill) AND SOC<HAND Predict WorkType = Road Transport (Flat Road, Future 2s) Braking energy recovery mode (gradient recovery) Real-time downhill recovery predicts the road level within 2 seconds and gradually increases the recovery torque from -80Nm to -30Nm in advance to avoid power interruption when switching to drive mode. 12 P_req=Z AND WorkType = Static AND SOC=VL AND Predicted WorkType = Light workload (future 5s) Series drive mode (idle charging) The system is currently stationary and has severely low battery power. Predicting that it will enter a period of light operation within the next 5 seconds, the engine (1500 rpm) is started in advance to drive the generator for charging, thus preventing insufficient power during operation.

[0097] The dynamic optimization layer primarily establishes optimization functions and constraints based on the conclusions and precise instructions output by the fuzzy control layer. It then employs a rolling time-domain optimization algorithm to solve for the optimal power allocation, outputting the final target power values ​​for the engine, ISG motor, and generator. The VCU sends final instructions to each sub-controller via the CAN bus; the sub-controllers provide feedback on their execution status, and the VCU adjusts the instructions using a PID controller. If the deviation between the actual operating condition and the predicted operating condition exceeds 15%, dynamic optimization is re-triggered. The flowchart is as follows: Figure 5 As shown.

[0098] Optimize function modeling:

[0099] min J = ∫[α·m_f(P_eng) + β·(SOC-SOC_ref)² + γ·(P_req-P_actual)² +δ·(T_motor-T_motor_max)²]dt

[0100] m_f(P_eng): Engine fuel consumption rate (g / kWh), based on engine universal characteristic curve fitting;

[0101] SOC_ref: Target value for battery state of charge;

[0102] SOC: Actual state of charge of the battery

[0103] P_actual: Actual output power = P_eng (actual output power of engine) + P_ISG (actual output power of ISG motor) - P_gen (actual output power of generator);

[0104] P_req: Actual power demand

[0105] T_motor: Actual torque of the ISG motor; constraints are used to avoid overload.

[0106] T_motor_max: Maximum torque of the ISG motor

[0107] α, β, γ, and δ are weighting coefficients that are dynamically adjusted based on the predicted operating conditions to ensure power and fuel economy.

[0108] Constraints: To ensure the safe and stable operation of the system, optimization solutions must be performed under strict physical and logical constraints. These mainly include power balance constraints, component physical constraints, and predictive constraints.

[0109] The power balance constraint is: engine power + ISG motor power ≈ demand power + generator power + transmission losses;

[0110] The physical constraints of the components are that each component must operate within its safety limits and capabilities. The detailed constraints are as follows: engine idle power is 10kW, engine rated power is 80kW, engine high-efficiency speed range is 1500-2200r / min, engine high-efficiency torque is 200-400Nm, engine power change rate limit is <15 kW / s, ISG motor maximum drive power is 50 kW, ISG motor maximum feedback power is -40 kW, ISG motor maximum drive torque is 200 Nm, ISG motor maximum feedback torque is -150Nm, ISG motor speed range is 0-5000 r / min, generator maximum generating power is 30kW, generator maximum torque is 100Nm, generator speed range is 1500-2500r / min, battery minimum SOC is 0.2, battery maximum SOC is 0.95, battery maximum charging power is 40kW, and battery maximum discharging power is 50kW.

[0111] The predictive constraint is to ensure that the power distribution at future moments meets the predicted operating conditions.

[0112] In the specific optimization process, at each control cycle k, the system, based on the current state, uses the operating condition prediction layer to predict the vehicle demand power sequence [P_req(k), P_req(k+1), ..., P_req(k+N)] for a short time window in the future (e.g., N=10 steps, corresponding to the next 3 seconds). Within this finite prediction time domain [k, k+N], a dynamic programming algorithm is run to solve for a series of optimal engine power control sequences [u*(k), u*(k+1), ..., u*(k+N)], minimizing the total cost J within this period. Only the optimal control quantity u*(k) at the current time k is executed, i.e., the engine is instructed to output P_eng(k), P_ISG(k), and P_gen(k). Then, the controller moves to the next time k+1, and based on the new measured state, repeats the steps to perform a new round of prediction and optimization.

[0113] The optimization solution yields the optimal power allocation values ​​(P_eng, P_ISG, P_gen) for each power source. These values ​​need to be converted into specific execution instructions: Based on the optimal power and predicted operating conditions, the engine universal characteristic diagram is queried to find the engine speed and torque combination point with the lowest fuel consumption rate under the current power demand, and instructions are issued; the target torque of the ISG motor is calculated based on the allocated ISG electric power and the current speed, and the working mode (drive or generator) is determined; the generator torque is calculated based on the system mode (series / driving charging) and engine speed.

[0114] After the command is issued, the underlying controller will perform closed-loop tracking to ensure that the actual state is consistent with the target. At the same time, the system will continuously monitor and optimize performance, such as computation latency and constraint violations, and trigger re-optimization or adjustment of optimization parameters when necessary.

[0115] Furthermore, the aforementioned working mode specifically includes:

[0116] Pure electric drive mode: The engine is not running; the vehicle is driven solely by the ISG motor. The vehicle controller controls the engine controller to shut off the engine, and then controls the generator controller to output a reverse electromagnetic resistance, locking the sun gear and reducing its speed to zero. The vehicle controller then controls the ISG controller to allow the ISG motor to draw power from the battery, outputting positive torque to drive the ring gear, which rotates at a speed greater than zero. In short, the generator "applies the brake," fixing the sun gear, and the ISG motor drives the ring gear; the power coupling device acts like a fixed-axis gear system, delivering power. Switching from this mode to other modes simply requires the generator to release the braking torque and begin speed regulation, without any mechanical shock.

[0117] Series Drive Mode: The engine drives the generator to produce electricity, which powers the ISG motor to drive the vehicle or charge the battery. The vehicle controller controls the engine controller to start the engine and operate it within its most efficient speed-torque range. The vehicle controller also controls the generator controller to produce electricity, with its load precisely controlled to maintain the engine's desired speed. The vehicle controller further controls the ISG controller to allow the ISG motor to draw power from the generator and battery, outputting torque to drive the ring gear to rotate at the speed required for the current vehicle speed. In this mode, engine speed is completely decoupled from vehicle speed, ensuring it remains at its most efficient point. Entering and exiting this mode is achieved solely through electronic adjustments to the power output of the generator and ISG motor.

[0118] Parallel / Hybrid Drive Mode: The engine and MG2 jointly drive the wheels, providing maximum power. The vehicle controller controls the engine controller to operate the engine in its high-efficiency range, outputting positive torque. The vehicle controller also controls the generator controller to maintain the generator's speed at a specific value. This allows the generator to generate electricity slightly to optimize engine load, or to consume a small amount of electrical energy to operate as an electric motor to adjust the engine's operating point. Its core function is "speed regulation," decoupling engine speed from vehicle speed. The vehicle controller further controls the ISG controller to output positive torque from the ISG motor for auxiliary drive. The transition from series mode to parallel mode is smooth, requiring only an increase in engine torque output while simultaneously adjusting the torque of the generator and ISG motor; the process is continuous and without jerks.

[0119] Driving charging mode: This mode is a special case of parallel mode. The vehicle controller controls the generator controller to increase the generator's output power, thereby increasing the engine load. The generated electrical energy exceeds the energy consumed by the ISG motor, and the excess electrical energy charges the power battery. The entire process is also seamless.

[0120] Braking Energy Recovery Mode: With the engine and generator off, the ISG motor recovers braking energy. The vehicle controller controls the engine controller to shut down the engine or cut off fuel. The vehicle controller controls the generator controller to shut down the generator or provide a small amount of torque to keep the sun gear rotating. The vehicle controller controls the ISG controller to make the ISG motor act as a generator, using the wheels to generate negative torque (braking force), converting kinetic energy into electrical energy stored in the battery. The system immediately enters energy recovery mode as soon as the driver releases the accelerator, with a rapid and smooth response.

[0121] Example 3:

[0122] This embodiment describes a computer-readable storage medium storing a computer program that, when executed by a processor, implements a control method for a hybrid tractor power matching system as described in any of Embodiments 2.

[0123] Example 4:

[0124] This embodiment describes a computer device, including:

[0125] Memory is used to store instructions.

[0126] A processor is configured to execute the instructions, causing the computer device to perform the operation of a control method for a hybrid tractor power matching system as described in any of Embodiment 2.

[0127] Example 5:

[0128] This embodiment introduces an innovative principle of a control method for a hybrid tractor power matching system, as detailed below:

[0129] The complete elimination of the clutch simplifies the system structure: Eliminating this vulnerable component and potential point of failure improves system reliability and reduces maintenance costs. The mechanical structure is more compact and lighter, meeting the high requirements of agricultural machinery for reliability and compactness.

[0130] Truly seamless mode switching: All operating mode switching is achieved through precise electromagnetic control of the motor torque, rather than the engagement and disengagement of a mechanical clutch. This makes the switching process extremely smooth, with no power interruption or jolt, significantly improving the tractor's operating comfort and work quality.

[0131] Achieving full-range optimization of engine operating point: Since the generator can steplessly adjust the engine speed, the engine can always be controlled to operate within the "high-efficiency island" in the universal characteristic diagram, resulting in a fundamental improvement in fuel economy compared to traditional tractors.

[0132] Excellent responsiveness: The torque response of the electric motor is much faster than that of the engine. Through the rapid compensation of the ISG motor, the system can respond instantly to sudden load changes (such as encountering hard soil), avoiding drastic fluctuations in engine speed or engine stalling, thus improving the tractor's adaptability to complex working conditions.

[0133] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0135] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0137] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A hybrid tractor power matching system, characterized in that it comprises: Engine, motor; The output terminals of the motor and the engine are respectively connected to the input terminals of the power coupling device. The output terminals of the power coupling device drive the gearbox and the generator respectively. The output terminals of the gearbox drive the PTO, the transmission device and the hydraulic pump respectively. The output terminal of the generator charges the power battery, and the power battery provides power to the motor. The vehicle controller is electrically connected to the motor controller, the engine controller, the generator controller and the gearbox controller respectively.

2. A control method for a hybrid tractor power matching system, characterized in that: Specifically, it includes: Step 1: Input vehicle and operation data into the prediction model to obtain the types of operation conditions and the rate of change of power demand in the future. Step 2: Fuzzify the instantaneous power demand, power battery SOC, operating conditions, and power demand change rate to obtain the fuzzification result. Based on the fuzzification result and the fuzzy rule base, obtain the control command. Step 3: Based on the control commands, establish the optimization function and constraints, use the rolling time-domain optimization algorithm to solve for the optimal power allocation, and output the final target power values ​​of the engine, motor, and generator.

3. The control method according to claim 2, characterized in that: The vehicle and operation data include: soil hardness, vehicle speed, throttle opening, PTO load, GPS signal, hydraulic pump pressure, motor speed, motor torque, generator speed, generator torque, power battery SOC, steering angle, crop type, crop row spacing, and crop tillage depth.

4. The control method according to claim 2, characterized in that: The prediction model includes: a 3-layer LSTM network with an input layer dimension of 15, a hidden layer neuron count of 64, and an output layer dimension of 2 (job condition classification probability and demand power change rate). The operating conditions include: road transport, light-load operation, medium-load operation, heavy-load operation, and turning at the edge of the field.

5. The control method according to claim 2, characterized in that: The process of fuzzifying the instantaneous power demand, battery SOC, operating conditions, and power demand change rate to obtain the fuzzification result specifically includes: The fuzzy subset of the instantaneous power demand is shown in the table below: The fuzzy subset of the power battery SOC is shown in the table below: The fuzzy subset of the operating conditions is shown in the table below: The fuzzy subset of the rate of change of demand power is shown in the table below: 。 6. The control method according to claim 5, characterized in that: The fuzzy rule base is shown in the table below: 。 7. The control method according to claim 2, characterized in that: Step 3 includes: Step 3.1: During control period k, obtain the vehicle demand power sequence [P_req(k), P_req(k+1), ..., P_req(k+N)] for a short future time window; Step 3.2: In the prediction time domain [k, k+N], run the dynamic programming algorithm to solve for the optimal engine power control sequence [u*(k), u*(k+1), ..., u*(k+N)], so that the total cost J in this time period is minimized, and optimize the solution to obtain the optimal control quantity u*(k); Step 3.3: Execute the optimal control quantity u*(k) for the current control cycle k, i.e., the control command. The engine outputs P_eng(k), the motor outputs P_ISG(k), and the generator outputs P_gen(k). Step 3.4: Move to the next time step k+1. Based on the new measured state, repeat steps 3.1-3.4 to perform a new round of prediction and optimization.

8. The control method according to claim 7, characterized in that: The optimization function includes: min J = ∫[α·m_f(P_eng) + β·(SOC-SOC_ref)² + γ·(P_req-P_actual)² + δ·(T_motor-T_motor_max)²]dt Where J is the total cost, m_f(P_eng) is the engine fuel consumption rate, SOC_ref is the target value of battery state of charge, SOC is the actual value of battery state of charge, P_actual is the actual output power, P_req is the actual demand power, T_motor is the actual torque of the motor, T_motor_max is the maximum torque of the motor, α, β, γ, and δ are weighting coefficients, and t is the time unit. The constraints include: power balance constraints, component physical constraints, and prediction constraints.

9. The control method according to claim 6, characterized in that: The aforementioned working modes specifically include: Pure electric drive mode: The engine is not running, and the vehicle is driven solely by the ISG motor. The vehicle controller controls the engine controller to shut off the engine, and the vehicle controller controls the generator controller to output a reverse electromagnetic resistance, locking the sun gear and reducing its speed to zero. The vehicle controller then controls the ISG controller to allow the ISG motor to draw power from the battery and output positive torque to drive the ring gear to rotate (at which point the ring gear's speed is greater than zero). In short, the generator "applies the brake" to fix the sun gear, the ISG motor drives the ring gear, and the power coupling device acts as a fixed-axis gear system to output power. Switching from this mode to other modes simply requires the generator to release the braking torque and begin speed regulation, without any mechanical shock. Series drive mode: The engine drives the generator to generate electricity, which powers the ISG motor to drive the vehicle or charge the battery; the vehicle controller controls the engine controller to start the engine and control it to operate within its most efficient speed-torque range; the vehicle controller controls the generator controller to generate electricity, and its power generation load is precisely controlled to maintain the engine's desired speed; the vehicle controller controls the ISG controller to allow the ISG motor to draw power from the generator and battery, outputting torque to drive the ring gear to rotate at the speed required for the current vehicle speed; in this mode, engine speed and vehicle speed are completely decoupled, and can always be maintained at the efficient point; entering and exiting the mode is achieved simply by electronically adjusting the power of the generator and ISG motor; Parallel / Hybrid Drive Mode: The engine and MG2 drive the wheels together, providing maximum power; the vehicle controller controls the engine controller to keep the engine running in its high-efficiency range and output positive torque; the vehicle controller controls the generator controller to keep the generator speed at a specific value, which can either generate a small amount of electricity to optimize the engine load or consume a small amount of electrical energy to run as an electric motor to adjust the engine operating point. Its core function is "speed regulation," decoupling the engine speed from the vehicle speed; the vehicle controller controls the ISG controller to make the ISG motor output positive torque to assist drive; the transition from series mode to parallel mode is smooth, requiring only an increase in the engine's torque output and simultaneous adjustment of the torque of the generator and ISG motor, a continuous and seamless process; Driving charging mode: This mode is a special case of parallel mode; the vehicle controller controls the generator controller to increase the generator's power output, which increases the engine load and generates more electrical energy than the ISG motor consumes. The excess electrical energy is used to charge the power battery; the whole process is also seamless. Braking energy recovery mode: The engine and generator are not working, and the ISG motor recovers braking energy; the vehicle controller controls the engine controller to shut down the engine or cut off the fuel supply; the vehicle controller controls the generator controller to shut down the generator or provide a small torque to keep the sun gear rotating; the vehicle controller controls the ISG controller to make the ISG motor act as a generator, which is dragged by the wheels to generate negative torque (braking force) and convert kinetic energy into electrical energy stored in the battery; as soon as the driver releases the accelerator, the system immediately enters the energy recovery state, with a rapid and smooth response.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements a control method for a hybrid tractor power matching system as described in any one of claims 1-9.

11. A computer device, characterized in that: include: Memory, used to store instructions; A processor is configured to execute the instructions, causing the computer device to perform the operation of a control method for a hybrid tractor power matching system as described in any one of claims 1-9.

Images