Intelligent agricultural machine complex working condition automatic operation power assembly coordination control method and system

Abstract

The invention discloses an automatic operation power assembly coordination control method and system for an intelligent agricultural machine under complex working conditions. The method comprises the steps that a multi-objective optimization model is constructed, and power assembly control parameters under agricultural machine complex coupling excitation are covered; constructing a prediction model of a torque dynamic response delay rule and an operation quality influence of the power assembly based on the experimental data; working condition parameters are collected in real time, the rollover critical speed is calculated to serve as the constraint condition of the turning-around speed, and the turning-around speed is planned according to the speed and the turning path; by means of the optimization model, the working condition parameters and the turning-around speed, unfavorable excitation is avoided, and the matched gear and the reversing opportunity are solved; and the engine torque demand is predicted in advance based on the prediction model and the matching parameters, and an electronic accelerator pedal signal is controlled to compensate the torque in advance. The speed, the gear and the reversing opportunity of the agricultural machine under complex working conditions such as turning around can be optimized, the fuel economy is improved, and pause, power loss and delay are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent agricultural machinery control, and in particular to a coordinated control method and system for an intelligent agricultural machinery powertrain capable of automatic operation under complex working conditions. Background Art

[0002] With the development of modern agriculture, agricultural machinery is playing an increasingly important role in improving agricultural production efficiency and reducing farmers' labor intensity. As one of the core equipment in agricultural mechanization, tractors play an indispensable role in various processes, including plowing, sowing, fertilizing, and harvesting. Due to their wide applicability and powerful functionality, tractors have become the main source of power on modern farms.

[0003] In recent years, with the continuous advancement of automation and intelligent technologies, research on automatic tractor control has received increasing attention. By integrating sensors, computer vision, GPS positioning systems, and advanced control systems, modern tractors are now capable of autonomous driving to a certain extent, especially when traveling in a straight line. This technology not only improves operational accuracy but also significantly increases efficiency and reduces labor costs. However, despite significant progress in automatic control technology for straight-line driving, many challenges remain for controlling complex operating conditions such as U-turns.

[0004] U-turns are an unavoidable part of tractor operations, especially in fields or on small plots. Under traditional manual operation, U-turns often require the driver to rely on experience to determine the appropriate timing for shifting gears and steering. This not only increases the driver's workload but also easily leads to inaccurate operation due to human factors, thus affecting work quality and efficiency. Furthermore, during a U-turn, the tractor must undergo a series of complex dynamic changes, including speed adjustments, direction changes, and load variations, all of which place additional stress on the powertrain. If handled improperly, this can easily lead to noticeable jerking, severe power loss, and delayed response, seriously impacting driving comfort and work quality.

[0005] Most tractor automatic control systems currently on the market are primarily designed for straight-line driving and lack specific technical support for U-turns. Existing solutions typically focus on a single objective (such as fuel economy, as demonstrated in patent CN105711581A), while ignoring the trade-offs between other important factors. Therefore, developing a coordinated control method for the powertrain of intelligent agricultural machinery operating under complex conditions is crucial. Summary of the Invention

[0006] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a method and system for coordinated control of the powertrain of intelligent agricultural machinery under complex working conditions, which can effectively reduce jerking, power loss and delay under U-turn conditions and improve smoothness and working stability.

[0007] Technical solution: To achieve the above-mentioned purpose, the present invention provides a coordinated control method for the powertrain of an intelligent agricultural machine operating automatically under complex working conditions, the method comprising:

[0008] Construct a multi-objective optimization model for the control parameters of the automatic operation powertrain under complex coupling excitation of agricultural machinery;

[0009] Based on experimental big data, a prediction model is constructed that can reflect the dynamic response delay law of the torque of the agricultural machinery powertrain and the law affecting the operation quality;

[0010] Real-time collection of agricultural machinery operating parameters, including the path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery;

[0011] Calculating a rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and performing U-turn speed planning based on the rollover critical speed and a turning path;

[0012] Based on the multi-objective optimization model, the operating condition parameters, and the planned U-turn speed, solving the matching gear position and reversing timing when performing a U-turn operation under the current operating condition;

[0013] Predicting engine torque demand in advance based on the matching gear position, commutation timing, and the torque dynamic response delay law and prediction model;

[0014] Based on the predicted generator torque, the electronic accelerator pedal signal is controlled to compensate the torque in advance.

[0015] Furthermore, the multi-objective optimization model is expressed as:

[0016] minJ=w1(t)·f1(S)+w2(t)·f2(P)+w3(t)·f3(F)+w4(t)·f4(Q);

[0017] Where: f1(S) is the smoothness objective function, expressed as:

[0018]

[0019] v(t) represents the velocity at time t;

[0020] f2(P) is the dynamic objective function, expressed as:

[0021]

[0022] v f and v i are the speeds before and after the gear shift, respectively. The negative sign indicates maximizing the power performance. It is the fuel economy objective function.

[0023] f3(F) is the fuel economy objective function, which is expressed as the integral of the instantaneous fuel consumption rate:

[0024]

[0025] T is time;

[0026] f4(Q) is the balance target of the work quality, considering the influence of strong adverse excitation, specifically the vibration energy under different excitations:

[0027]

[0028] Where A(ω) represents the vibration amplitude at the excitation frequency ω, ω min and ω max is the excitation frequency range;

[0029] w1(t), w2(t), w3(t), and w4(t) are weight coefficients, w1(t)+w2(t)+w3(t)+w4(t)=1.

[0030] Furthermore, the prediction model is described by the following equation:

[0031]

[0032] in:

[0033] ΔT(t) represents the dynamic response of the engine torque; N(t) is the engine speed, L(t) is the load, A(t) is the accelerator pedal opening, and E(t) is the environmental condition;

[0034] f(N(t), L(t), A(t), E(t)) is a nonlinear function of the torque dynamic response;

[0035] K1 and K2 are influence coefficients, representing the contribution of engine speed and load to the torque response, respectively;

[0036] α1 and α2 are time decay constants that control the decay rate of different input variables;

[0037] ∈ is the compensation term for the system noise or unmodeled part;

[0038] β i and γ iThey represent the effects of the coupling term between the accelerator pedal and the environmental conditions and the second-order derivative of the engine speed on the torque response.

[0039] Furthermore, a rollover critical speed is calculated based on the operating condition parameters as a constraint condition for U-turn speed planning, and U-turn speed planning is performed based on the rollover critical speed and the turning path, specifically including the following steps:

[0040] The critical rollover speed is calculated based on the following formula:

[0041] Among them, v crit is the critical rollover speed, g is the acceleration of gravity, R is the turning radius, and h is the height change of the center of gravity;

[0042] Speed ​​planning for the U-turn process is performed based on the following function:

[0043]

[0044] Among them, v in and v out are the speeds of entering and exiting the U-turn, f(t,v crit ) is the acceleration function constrained by the rollover critical speed during the U-turn process, T is the entire U-turn operation time; t1 is the time when the acceleration segment ends, and t2 is the time when the holding segment ends; k is the empirical coefficient, which represents the speed adjustment factor; R is the turning radius.

[0045] Furthermore, after solving the matching gear position and reversing timing when performing a U-turn operation under the current working condition, the method further includes:

[0046] The matching gear position and reversing timing are optimized based on the following optimization model:

[0047]

[0048] Where: T(t) represents the engine torque at time t; A(t) represents the accelerator pedal opening; λ is the trade-off parameter between acceleration response and gear shifting smoothness; t shift With t end are the shift start time and end time respectively;

[0049] The optimization process is carried out under the following constraints:

[0050]

[0051] Where γ is the allowed vibration energy threshold.

[0052] A coordinated control system for a powertrain of an intelligent agricultural machine capable of automatically operating under complex working conditions, the system comprising:

[0053] The first building block is used to construct a multi-objective optimization model for control parameters of an automatic operation powertrain under complex coupling excitation of agricultural machinery;

[0054] The second building block is used to construct a prediction model for the dynamic response delay law of the agricultural machinery powertrain torque and the law affecting the operation quality based on experimental big data;

[0055] A collection module is used to collect the operating parameters of the agricultural machinery in real time. The operating parameters include the path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery;

[0056] a planning module, configured to calculate a rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and perform U-turn speed planning based on the rollover critical speed and a turning path;

[0057] a solution module for solving, based on the multi-objective optimization model, the operating condition parameters, and the planned U-turn speed, and avoiding the generation moment of strong unfavorable incentives, a matching gear position and a reversing timing for performing a U-turn operation under the current operating condition;

[0058] A prediction module, configured to predict the engine torque demand in advance based on the matching gear position, the switching timing, and the torque dynamic response delay law and prediction model;

[0059] The control module is configured to control an electronic accelerator pedal signal to perform advance compensation on the torque based on the predicted generator torque.

[0060] Beneficial effects: The method and system for coordinated control of the powertrain of intelligent agricultural machinery under complex working conditions for automatic operation of the present invention considers a U-turn process of the intelligent agricultural machinery as a whole, and plans the speed of the U-turn process of the intelligent agricultural machinery by taking into account various indicators of operation quality and avoiding strong unfavorable incentives, thereby ensuring that the intelligent agricultural machinery remains safe and stable during the U-turn process, and adopts a multi-objective global optimal idea to formulate the shifting rules; in addition, the powertrain control method of torque advance prediction and compensation is studied to reduce setbacks, power loss and delay, and improve smoothness and working stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of the coordinated control method for the powertrain of intelligent agricultural machinery operating automatically under complex working conditions;

[0062] Figure 2 This is a schematic diagram of the coordinated control system for the powertrain of intelligent agricultural machinery that automatically operates in complex working conditions. DETAILED DESCRIPTION

[0063] The present invention will be further described below with reference to the accompanying drawings.

[0064] In this embodiment, the fishtail U-turn trajectory of the intelligent agricultural machine is taken as an example for description.

[0065] like Figure 1 The coordinated control method for the powertrain of an intelligent agricultural machine operating automatically under complex working conditions shown in the figure includes the following steps S101-S107:

[0066] Step S101, constructing a multi-objective optimization model for control parameters of an automatic operation powertrain under complex coupling excitation of agricultural machinery;

[0067] In this step, the multi-objective optimization model comprehensively considers strong adverse incentives, shifting time and shifting rules, and uses fuel economy, power and clutch life as evaluation indicators for multi-objective optimization; strong adverse incentives refer to incentives that can cause strong vibration, frustration and other negative effects of intelligent agricultural machinery. The source of the incentive can be shifting, load cutting operation status, external resistance changes, etc.

[0068] Step S102: Based on the experimental big data, a prediction model is constructed that can reflect the dynamic response delay law of the torque of the agricultural machinery powertrain and the law affecting the operation quality. The output of the multi-objective optimization model is used as a control parameter for the automatic operation powertrain of the intelligent agricultural machinery and as an input to the prediction model.

[0069] Step S103: Real-time collection of agricultural machinery operating parameters; the operating parameters are collected in real time by the sensor system; the operating parameters include the path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery;

[0070] Step S104, calculating a rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and performing U-turn speed planning based on the rollover critical speed and the turning path;

[0071] Step S105, based on the multi-objective optimization model, the operating condition parameters, and the planned U-turn speed, and avoiding the generation time of strong unfavorable incentives, solving the matching gear and reversing timing when performing the U-turn operation under the current operating condition;

[0072] Step S106, predicting the engine torque demand in advance based on the matching gear position, the commutation timing, and the torque dynamic response delay law and prediction model;

[0073] Step S107 : Based on the predicted generator torque, controlling the electronic accelerator pedal signal to compensate the torque in advance.

[0074] In the above method, the U-turn process of the intelligent agricultural machinery is considered as a whole. By taking into account various indicators of operation quality and avoiding strong unfavorable incentives, the speed planning of the U-turn process of the intelligent agricultural machinery is carried out to ensure that the intelligent agricultural machinery remains safe and stable during the U-turn process, and the multi-objective global optimal idea is adopted to formulate the shifting rules; in addition, the powertrain control method of torque advance prediction and compensation is studied to reduce setbacks, power loss and delay, and improve smoothness and working stability.

[0075] Specifically, the multi-objective optimization model in step S101 is expressed as:

[0076] minJ=w1(t)·f1(S)+w2(t)·f2(P)+w3(t)·f3(F)+w4(t)·f4(Q);

[0077] Where: f1(S) is the smoothness objective function, expressed as:

[0078]

[0079] v(t) represents the velocity at time t;

[0080] f2(P) is the dynamic objective function, expressed as:

[0081]

[0082] v f and v i are the speeds before and after the gear shift, respectively. The negative sign indicates maximizing the power performance. It is the fuel economy objective function.

[0083] f3(F) is the fuel economy objective function, which is expressed as the integral of the instantaneous fuel consumption rate:

[0084]

[0085] T is time;

[0086] f4(Q) is the balance target of the work quality, considering the influence of strong adverse excitation, specifically the vibration energy under different excitations:

[0087]

[0088] Where A(ω) represents the vibration amplitude at the excitation frequency ω, ω min and ω max is the excitation frequency range;

[0089] w1(t), w2(t), w3(t), and w4(t) are weight coefficients, which can be adjusted dynamically over time.

[0090] Weight coefficient w i The calculation of (t) depends on the operating conditions, such as terrain complexity, operating mode, etc. The calculation formula for each weight is as follows:

[0091]

[0092] in:

[0093] γ i (t) represents the priority of each target, which is affected by real-time parameters;

[0094] To ensure that the sum of all weights is 1.

[0095] Priority function γ i (t) is determined based on real-time environmental data such as slope θ(t), load L(t), and surface roughness U(t). Slope θ(t) prioritizes power, ensuring the tractor maintains power output on steep slopes. Load L(t) prioritizes fuel economy, optimizing fuel consumption. Surface roughness U(t) prioritizes smoothness and work quality, reducing vibration and operational errors.

[0096] Priority function γ i The specific form of (t) is as follows:

[0097] γ1(t)=α1+β1·U(t);

[0098] γ2(t)=α2+β2·θ(t);

[0099] γ3(t)=α3+β3·L(t);

[0100] γ4(t)=α4+β4·U(t)+β5·θ(t);

[0101] α i (i=1, 2, 3, 4) is the basic priority value, reflecting the initial importance of each goal; β i (i=1, 2, 3, 4) is the dynamic response coefficient, which indicates the degree of influence of real-time data on the priority.

[0102] The specific form of the priority function is as follows:

[0103] The prediction model in step S102 is described by the following equation:

[0104]

[0105] in:

[0106] ΔT(t) represents the dynamic response of the engine torque; N(t) is the engine speed, L(t) is the load, A(t) is the accelerator pedal opening, and E(t) is the environmental condition;

[0107] f) N(t), L(t), A(t), E(t)) are nonlinear functions of the torque dynamic response, taking into account the combined effects of engine speed, load, accelerator pedal opening and environmental conditions;

[0108] K1 and K2 are influence coefficients, representing the contribution of engine speed and load to the torque response, respectively;

[0109] ɑ1 and ɑ2 are time decay constants that control the decay rates of different input variables;

[0110] ε is the compensation term for the noise or unmodeled part of the system;

[0111] β i and γ i They represent the effects of the coupling term between the accelerator pedal and the environmental conditions and the second-order derivative of the engine speed on the torque response.

[0112] Based on the above model, the engine torque demand T at the future time t+τ can be predicted e (t+τ).

[0113] In the above step S104, the rollover critical speed is calculated based on the operating condition parameters as a constraint condition for U-turn speed planning, and the U-turn speed planning is performed based on the rollover critical speed and the turning path, which specifically includes the following steps S201-S202:

[0114] Step S201: Calculate the critical rollover speed based on the following formula:

[0115] Among them, v crit is the critical rollover speed, g is the acceleration of gravity, R is the turning radius, and h is the height change of the center of gravity;

[0116] Step S202: Plan the speed of the U-turn process based on the following function:

[0117]

[0118] Among them, v in and v out are the speeds of entering and exiting the U-turn, f(t,v crit ) is the acceleration function constrained by the critical rollover speed during the U-turn process. T is the total U-turn operation time; t1 is the time when the acceleration phase ends, and t2 is the time when the holding phase ends. k is an empirical coefficient representing the speed adjustment factor; R is the turning radius. k is determined based on the turning radius R and site conditions.

[0119] The above-mentioned segmented speed planning ensures that the intelligent agricultural machinery can not only guarantee power output and reduce the time required for U-turn during the U-turn process, but also control the speed within a safe range to avoid dangerous situations such as rollover.

[0120] After solving the matching gear position and reversing timing for the U-turn operation under the current working condition in the above step S105, the following steps are further included:

[0121] The matching gear position and reversing timing are optimized based on the following optimization model:

[0122]

[0123] Where: T(t) represents the engine torque at time t; A(t) represents the accelerator pedal opening; λ is the trade-off parameter between acceleration response and gear shifting smoothness; t shift With t end are the shift start time and end time respectively;

[0124] The shift and accelerator pedal joint optimization model uses a dual closed-loop control design to ensure smooth power transmission and reduce jerks.

[0125] The optimization process is carried out under the following constraints:

[0126]

[0127] Where γ is the permissible vibration energy threshold, ensuring system stability within a specific frequency range. By adding frequency response constraints during the optimization process, the dynamic fluctuation frequency response can be controlled to avoid excitation energy peaks at the resonant frequency.

[0128] This optimization model balances the impact of torque delay on power and shift stability, resulting in optimal gear and shift timing. Dynamic programming is used to determine the optimal shift timing at each moment, ensuring smooth power delivery and maximizing fuel efficiency while avoiding excessive clutch wear. Online rule extraction leverages real-time operating data, allowing for tailored shifting rules tailored to varying U-turn speed profiles and torque dynamic response delays.

[0129] Preferably, the method further comprises the following steps A1-A4:

[0130] Step A1, determining the current mode in real time based on load, slope and speed data;

[0131] Step A2, determining the optimal torque strategy according to the optimization formula of the current mode;

[0132] Step A3: Dynamically adjust torque control using feedback data to ensure that torque output meets the requirements of the current mode;

[0133] Step A4: Dynamically switch modes and execute corresponding optimization strategies under different operating environments to ensure that the tractor's power output and fuel economy are always in the optimal state.

[0134] Where: When L(t) ≥ L1 and θ(t) ≥ θ1, L1 is the high load judgment threshold, θ1 is the steep slope judgment threshold, and the current mode is judged to be heavy load mode. The goal is to maximize power output and reduce torque delay. The optimization formula is:

[0135]

[0136] Where: T(t) is the engine torque, -∫T(t)dt represents the maximum power output;

[0137] represents the rate of change of torque, which is added to reduce sudden changes and improve smoothness; λ1 is the weight coefficient for balancing power output and smoothness; t start With t end The start and end time respectively;

[0138] When L(t) < L1 and θ(t) < θ1, the current mode is determined to be light load mode. The goal is to balance power output and fuel efficiency. The optimization formula is:

[0139]

[0140] Where C(t) is the instantaneous fuel consumption rate, and the term ∫C(t)dt represents the fuel economy;

[0141] λ2 is the weight coefficient of power output and fuel economy; λ3 is the weight coefficient of controlling power smoothness.

[0142] When v(t)<V low And L(t)<L2, V low is the low speed threshold, L2 is the low load judgment threshold, and the current mode is judged to be fuel-saving mode. At this time, fuel economy is prioritized, and the optimization model is:

[0143]

[0144] Among them, λ4 is the weight coefficient for controlling the smooth transition of torque.

[0145] In different modes, the torque response function T(t) will be adjusted according to the real-time operating conditions. The following is an extension of the torque response model:

[0146]

[0147] Among them, f(N(t), L(t), A(t), E(t)) is the basic nonlinear torque response function.

[0148] α mode and β mode It is the torque response coefficient related to the current mode. The parameter value will be adjusted in different modes.

[0149] η is the system noise compensation term.

[0150] Through steps A1-A4, the system adapts to varying loads and terrain conditions, achieving efficient power output and dynamically optimizing fuel consumption based on the operating mode. This significantly reduces fuel consumption in light-load and fuel-saving modes, particularly when operating in low-load mode. Torque smoothing control effectively minimizes power surges, reducing vibration and jerking during operation. Smart agricultural machinery can intelligently adapt to complex operating environments, improving the efficiency and reliability of automated operations.

[0151] The present invention also provides a coordinated control system for the powertrain of intelligent agricultural machinery under complex working conditions. The coordinated control system for the powertrain of intelligent agricultural machinery under complex working conditions may include or be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention and realize the coordinated control method for the powertrain of intelligent agricultural machinery under complex working conditions. The program module referred to in the embodiment of the present invention refers to a series of computer program instruction segments that can perform specific functions, and is more suitable for describing the execution process of the coordinated control method for the powertrain of intelligent agricultural machinery under complex working conditions in a storage medium than the program itself. The following description will specifically introduce the functions of each program module of this embodiment, such as Figure 2 As shown, the system includes:

[0152] The first construction module 301 is used to construct a multi-objective optimization model for control parameters of an automatic operation powertrain under complex coupling excitation of agricultural machinery;

[0153] The second construction module 302 is used to construct a prediction model for the dynamic response delay law of the agricultural machinery powertrain torque and the law affecting the operation quality based on the experimental big data;

[0154] The acquisition module 303 is used to collect the operating parameters of the agricultural machinery in real time. The operating parameters include the path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery;

[0155] a planning module 304 for calculating a rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and performing U-turn speed planning based on the rollover critical speed and a turning path;

[0156] A solution module 305 is configured to solve the matching gear and reversing timing for performing a U-turn operation under the current operating condition based on the multi-objective optimization model, the operating condition parameters, and the planned U-turn speed, while avoiding the generation time of strong unfavorable incentives;

[0157] A prediction module 306 is configured to predict the engine torque demand in advance based on the matching gear position, the switching timing, and the torque dynamic response delay law and prediction model;

[0158] The control module 307 is configured to control the electronic accelerator pedal signal to compensate the torque in advance based on the predicted generator torque.

[0159] Other contents of the method for realizing the coordinated control of the powertrain of the intelligent agricultural machinery under complex working conditions based on the coordinated control system of the powertrain of the intelligent agricultural machinery under complex working conditions have been described in detail in the previous embodiments. Please refer to the corresponding contents in the previous embodiments and will not be repeated here.

[0160] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A coordinated control method for the powertrain of an intelligent agricultural machine under complex working conditions, characterized in that: The method comprises: Construct a multi-objective optimization model for the control parameters of the automatic operation powertrain under complex coupling excitation of agricultural machinery; Based on experimental big data, the dynamic response delay law of agricultural machinery powertrain torque, the influence law of operation quality and the prediction model are constructed; Real-time collection of agricultural machinery operating parameters, including path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery; Calculating a rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and performing U-turn speed planning based on the rollover critical speed and a turning path; Based on the multi-objective optimization model, the operating condition parameters and the planned U-turn speed, and avoiding the generation time of strong unfavorable incentives, solving the matching gear and reversing timing when performing the U-turn operation under the current operating condition; Predicting the engine torque demand in advance based on the matching gear position, the switching timing, and the torque dynamic response delay law and prediction model; Based on the predicted generator torque, the electronic accelerator pedal signal is controlled to compensate the torque in advance.

2. The coordinated control method for the powertrain of an intelligent agricultural machine under complex working conditions according to claim 1 is characterized in that: The multi-objective optimization model is expressed as: minJ=w1(t)·f1(S)+w2(t)·f2(P)+w3(t)·f3(F)+w4(t)·f4(Q); Where: f1(S) is the smoothness objective function, expressed as: v(t) represents the velocity at time t; f2(P) is the dynamic objective function, expressed as: v f and v i are the speeds after and before shifting, respectively, with a negative sign indicating maximization of power; is the fuel economy objective function, f3(F) is the fuel economy objective function, expressed as the integral of the instantaneous fuel consumption rate: T is time; f4(Q) is the balance target of the work quality, considering the influence of strong adverse excitation, specifically the vibration energy under different excitations: Where A(ω) represents the vibration amplitude at the excitation frequency ω, ω min and ω max is the excitation frequency range; w1(t), w2(t), w3(t), and w4(t) are weight coefficients, w1(t)+w2(t)+w3(t)+w4(t)=1.

3. The coordinated control method for the powertrain of an intelligent agricultural machine under complex working conditions according to claim 1 is characterized in that: The prediction model is described by the following equation: in: ΔT(t) represents the dynamic response of the engine torque; N(t) is the engine speed, L(t) is the load, A(t) is the accelerator pedal opening, and E(t) is the environmental condition; f(N(t), L(t), A(t), E(t)) is a nonlinear function of the torque dynamic response; K1 and K2 are influence coefficients, representing the contribution of engine speed and load to the torque response, respectively; α1 and α2 are time decay constants that control the decay rates of different input variables; ε is the compensation term for the noise or unmodeled part of the system; β i and γ i They respectively represent the influence of the coupling term between the accelerator pedal and the environmental conditions and the second-order derivative of the engine speed on the torque response.

4. The coordinated control method for powertrain of intelligent agricultural machinery under complex working conditions according to claim 1 is characterized in that: Calculating the rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and performing U-turn speed planning based on the rollover critical speed and the turning path, specifically comprising the following steps: The critical rollover speed is calculated based on the following formula: Among them, v crit is the critical rollover speed, g is the acceleration of gravity, R is the turning radius, and h is the height change of the center of gravity; The speed planning for the U-turn process is based on the following function: Among them, v in and v out are the speeds of entering and exiting the U-turn, respectively, f(t,v crit ) is the acceleration function constrained by the rollover critical speed during the U-turn process, T is the entire U-turn operation time; t1 is the time when the acceleration segment ends, t2 is the time when the holding segment ends; k is the empirical coefficient, which represents the speed adjustment factor; R is the turning radius.

5. The coordinated control method for the powertrain of an intelligent agricultural machine under complex working conditions according to claim 1 is characterized in that: After solving the matching gear position and the switching timing, the method further includes: The matching gear position and switching timing are optimized based on the following optimization model: Where: T(t) represents the engine torque at time t; A(t) represents the accelerator pedal opening; λ is the trade-off parameter between acceleration response and gear shifting smoothness; t shift With t end are the shift start time and end time respectively; The optimization process is carried out under the following constraints: Where γ is the allowed vibration energy threshold.

6. A coordinated control system for the powertrain of intelligent agricultural machinery in complex working conditions, characterized in that: The system comprises: The first building module is used to build a multi-objective optimization model for control parameters of an automatic operation powertrain under complex coupling excitation of agricultural machinery; The second building module is used to build a prediction model for the dynamic response delay law of the agricultural machinery powertrain torque and the law affecting the operation quality based on the experimental big data; A collection module is used to collect the working condition parameters of the agricultural machinery in real time, wherein the working condition parameters include the path turning radius, center of gravity position change, initial speed, ground roughness, load, and tilt angle of the intelligent agricultural machinery; A planning module, which is used to calculate the rollover critical speed based on the operating condition parameters as a constraint condition for U-turn speed planning, and perform U-turn speed planning based on the rollover critical speed and the turning path; A solution module, which is used to solve the matching gear and reversing timing when performing a U-turn operation under the current working condition based on the multi-objective optimization model, the working condition parameters and the planned U-turn speed, and avoid the generation time of strong unfavorable incentives; A prediction module, which is used to predict the engine torque demand in advance based on the matching gear position, the switching timing and the torque dynamic response delay law and the prediction model; The control module is used for controlling the electronic accelerator pedal signal to compensate the torque in advance based on the predicted generator torque.

Images