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

Abstract

The application discloses a kind of automatic operation power assembly coordination control method and system for intelligent agricultural machine complex working condition.The method comprises: constructing multi-objective optimization model, covering the control parameter of power assembly under the complex coupling excitation of agricultural machine;Based on experimental data, the prediction model of torque dynamic response delay law and the influence of working quality of power assembly is constructed;Real-time acquisition of working condition parameters, calculate the rollover critical speed as the constraint condition of U-turn speed, and plan the U-turn speed according to the speed and turning path;Using optimization model, working condition parameters and U-turn speed, avoid adverse excitation, solve the matching gear and the timing of reversing;And based on the prediction model and matching parameter, predict the engine torque demand in advance, control electronic accelerator pedal signal to compensate torque in advance.The application can optimize the speed, gear and reversing timing of agricultural machine under complex working conditions such as U-turn, improve fuel economy, reduce jerk, power loss and delay.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent agricultural machinery control, in particular to an intelligent agricultural machinery complex working condition automatic operation power assembly coordinated control method and system. BACKGROUND

[0002] With the development of modern agriculture, agricultural machinery plays an increasingly important role in improving agricultural production efficiency and reducing the labor intensity of farmers. As one of the core equipment of agricultural mechanization operation, tractors play an indispensable role in plowing, seeding, fertilizing, harvesting and other aspects. Due to its wide applicability and powerful functionality, tractors have become the main power source in modern farms.

[0003] In recent years, with the continuous progress of automation and intelligent technology, the research on automatic control of tractors has also been increasingly valued. By integrating sensors, computer vision, GPS positioning systems and advanced control systems, modern tractors have been able to achieve automatic driving to a certain extent, especially in straight-line driving. This technology not only improves the operation accuracy, but also greatly improves the operation efficiency and reduces the labor cost. However, although the automatic control technology for straight-line driving has made significant progress, there are still many challenges for the control of complex working conditions such as turning.

[0004] Turning is an inevitable operation link in the process of tractor operation, especially when working in the field or small area. In the traditional manual operation mode, turning often needs the driver to judge the appropriate timing for shifting and steering according to experience, which not only increases the workload of the driver, but also easily leads to inaccurate operation due to human factors, thereby affecting the operation quality and efficiency. In addition, during the turning process, the tractor needs to go through a series of complex dynamic changes, including speed adjustment, direction transformation and load change, etc., which will bring additional pressure to the power assembly. If not handled properly, it is easy to cause obvious jerk, serious power loss and response delay, etc., which seriously affects the driving comfort and operation quality.

[0005] Most of the current automatic control systems of tractors on the market are mainly designed for straight-line driving, and lack targeted technical support for turning conditions. Some existing solutions usually only consider a single objective (for example, fuel economy, as shown in patent CN105711581A), while ignoring the balance between other important factors. Therefore, it is particularly necessary to develop an intelligent agricultural machinery complex working condition automatic operation power assembly coordinated control method. SUMMARY

[0006] Invention purposes: In order to overcome the deficiencies in the prior art, the application provides an intelligent agricultural machinery complex working condition automatic operation power assembly coordination control method and system which can effectively reduce the jerk, power loss and delay under the U-turn working condition, and improve the smoothness and working stability.

[0007] Technical scheme: In order to achieve the above purpose, the intelligent agricultural machinery complex working condition automatic operation power assembly coordination control method of the application comprises:

[0008] Constructing an automatic operation power assembly control parameter multi-objective optimization model under complex coupling excitation of agricultural machinery;

[0009] Based on experimental big data, a prediction model capable of reflecting the torque dynamic response delay law and the working quality influence law of the agricultural machinery power assembly is constructed;

[0010] Real-time acquisition of agricultural machinery working condition parameters, the working condition parameters including the path turning radius, gravity center position change and initial speed of the intelligent agricultural machinery, and the ground unevenness, load and inclination angle;

[0011] Based on the working condition parameters, the rollover critical speed is calculated as a constraint condition for U-turn speed planning, and based on the rollover critical speed and the turning path, the U-turn speed planning is carried out;

[0012] Based on the multi-objective optimization model, the working condition parameters and the planned U-turn speed, the matching gear and the reversing timing when U-turn operation is carried out under the current working condition are solved;

[0013] Based on the matching gear, the reversing timing and the torque dynamic response delay law and the prediction model, the engine torque demand is predicted in advance;

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

[0015] Further, the multi-objective optimization model is represented as:

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

[0017] Wherein: f1(S) is a smoothness objective function, represented as:

[0018]

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

[0020] f2(P) is a power objective function, represented as:

[0021]

[0022] v f and v i are the speed after and before shifting, respectively, with negative sign to maximize the power performance;

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

[0024]

[0025] T is the total time of the U-turn operation;

[0026] f4(Q) is the balance of operation quality objective, which considers the influence of strong adverse excitation, and is specifically the vibration energy under different excitations:

[0027]

[0028] where A(ω) represents the vibration amplitude under excitation frequency ω, ω min and ω max are the excitation frequency range;

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

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

[0031]

[0032] where:

[0033] ΔT(t) represents the torque dynamic response of the engine; 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, respectively representing the contribution of engine speed and load to torque response;

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

[0037] ε is a compensation term for system noise or unmodeled parts;

[0038] β i and γ irespectively represent the coupling term of the accelerator pedal and the environmental condition and the influence of the second derivative of the engine speed on the torque response.

[0039] Further, the rollover critical speed is calculated based on the working condition parameter as a constraint condition of the U-turn speed planning, and the U-turn speed planning is performed based on the rollover critical speed and the turning path, and specifically includes the following steps:

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

[0041] wherein v crit is the rollover critical speed, g is the gravity acceleration, R is the turning radius, and h is the height variation of the gravity center position.

[0042] The U-turn process is speed planned based on the following function:

[0043]

[0044] wherein v in and v out are the entering and exiting U-turn speeds respectively, f(t, v crit ) is an acceleration function in the U-turn process constrained by the rollover critical speed, T is the entire U-turn operation time, t1 is the time at which the acceleration section ends, t2 is the time at which the maintaining section ends, k is an empirical coefficient representing a speed adjustment factor, and R is the turning radius.

[0045] Further, after the matching gear and the reversing timing when the U-turn operation is performed in the current working condition are solved, the system further includes:

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

[0047]

[0048] wherein T(t) represents the engine torque at time t, A(t) represents the accelerator pedal opening degree, λ is a trade-off parameter between the acceleration response and the gear shifting smoothness, t shift and t end are the gear shifting start time and the end time respectively.

[0049] The optimization process is performed under the following constraint conditions:

[0050]

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

[0052] An intelligent agricultural machinery complex working condition automatic operation powertrain coordination control system, the system comprises:

[0053] a first construction module for constructing an automatic operation powertrain control parameter multi-objective optimization model under complex coupling excitation of agricultural machinery;

[0054] a second construction module for constructing a prediction model of torque dynamic response delay law and operation quality influence law of the agricultural powertrain based on experimental big data;

[0055] a collection module for collecting agricultural operation working condition parameters in real time, wherein the working condition parameters include a path turning radius, a gravity center position change and an initial speed of the intelligent agricultural machinery, and further include ground unevenness, load and inclination angle;

[0056] a planning module for calculating a rollover critical speed as a constraint condition of U-turn speed planning based on the working condition parameters, and planning a U-turn speed based on the rollover critical speed and a turning path;

[0057] a solving module for solving a matching gear and a reversing timing when the U-turn operation is performed under the current working condition based on the multi-objective optimization model, the working condition parameters and the planned U-turn speed, and avoiding generation of strong adverse excitation;

[0058] a prediction module for predicting engine torque demand in advance based on the matching gear, the reversing timing, the torque dynamic response delay law and the prediction model;

[0059] a control module for controlling an electronic accelerator pedal signal to compensate for torque in advance based on the predicted engine torque.

[0060] Beneficial effects: the intelligent agricultural machinery complex working condition automatic operation powertrain coordination control method and system consider a U-turn process of the intelligent agricultural machinery as a whole, plan a U-turn speed of the intelligent agricultural machinery by taking into account each index of operation quality and avoiding strong adverse excitation, ensure that the intelligent agricultural machinery is safe and stable during the U-turn process, and adopt a multi-objective global optimal idea to formulate a gear shifting law; in addition, a powertrain regulation and control method of torque prediction and compensation in advance is researched, jerk, power loss and delay are reduced, and smoothness and working stability are improved. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 FIG. 1 is a flowchart of an intelligent agricultural machinery complex working condition automatic operation powertrain coordination control method;

[0062] Figure 2 FIG. 2 is a structure schematic diagram of an intelligent agricultural machinery complex working condition automatic operation powertrain coordination control system. DETAILED DESCRIPTION

[0063] The application will be described further in connection with the drawings.

[0064] In this embodiment, the fish tail type U-turn trajectory of the intelligent agricultural machine is taken as an example for illustration.

[0065] As shown in the intelligent agricultural machine complex working condition automatic operation power assembly coordination control method, the method comprises the following steps S101-S107: Figure 1

[0066] Step S101, construct an automatic operation power assembly control parameter multi-objective optimization model under the complex coupling excitation of the agricultural machine;

[0067] In this step, the multi-objective optimization model comprehensively considers strong adverse excitation, shift time and shift rule, and takes fuel economy, power performance and clutch life as evaluation indexes of multi-objective optimization; the strong adverse excitation refers to the excitation that can cause strong shaking, beating and other negative effects of the intelligent agricultural machine, and the source of the excitation can be shift, cutting off the working state of the load, change of external resistance, etc.

[0068] Step S102, based on experimental big data, construct a prediction model capable of reflecting the torque dynamic response delay rule and the working quality influence rule of the agricultural machine power assembly; the output of the multi-objective optimization model is used as the control parameter of the automatic operation power assembly of the intelligent agricultural machine, and as the input of the prediction model;

[0069] Step S103, real-time acquisition of agricultural machine working condition parameters; the working parameters are acquired by the sensor system in real time; the working condition parameters include the path turning radius, gravity center position change and initial speed of the intelligent agricultural machine, and also include ground unevenness, load and inclination angle;

[0070] Step S104, calculate the rollover critical speed based on the working condition parameters as the constraint condition of the U-turn speed planning, and based on the rollover critical speed and the turning path, plan the U-turn speed;

[0071] Step S105, based on the multi-objective optimization model, the working condition parameters and the planned U-turn speed, and avoiding the generation time of strong adverse excitation, solve the matching gear and the reversing time under the current working condition for U-turn operation;

[0072] Step S106, based on the matching gear, the reversing time and the torque dynamic response delay rule and the prediction model, predict the engine torque demand in advance;

[0073] Step S107, based on the predicted engine torque, control the electronic accelerator pedal signal to compensate the torque in advance.

[0074] ​In the above method, a turning process of the intelligent agricultural machine is considered as a whole, the speed planning of the turning process of the intelligent agricultural machine is performed by taking into account each index of the operation quality and avoiding strong adverse incentives, to ensure that the intelligent agricultural machine remains safe and stable during the turning process, and a multi-objective global optimization idea is used to formulate a shift schedule; in addition, a powertrain control method of torque advance prediction compensation is researched to reduce jerk, power loss and delay, and improve smoothness and working stability.

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

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

[0077] wherein f1(S) is a smoothness objective function, expressed as:

[0078]

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

[0080] f2(P) is a power performance objective function, expressed as:

[0081]

[0082] v f and v i are the speeds after and before shifting, respectively, and the negative sign indicates maximizing power performance;

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

[0084]

[0085] T is the entire turning operation time;

[0086] f4(Q) is a balance objective of operation quality, considering the influence of strong adverse incentives, and is specifically the vibration energy under different incentives:

[0087]

[0088] wherein A(ω) represents the vibration amplitude under an excitation frequency ω, ω min and ω max are the excitation frequency ranges;

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

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

[0091]

[0092] Wherein:

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

[0094] to ensure that the sum of each weight is 1.

[0095] Priority function γ i (t) is determined according to the real-time collected environmental data slope θ(t), load L(t), ground unevenness U(t), etc., wherein the slope θ(t) can increase the power priority to ensure that the tractor maintains the power output on steep slopes. The load L(t) can increase the fuel economy priority to optimize fuel consumption. The ground unevenness U(t) can increase the smoothness and work quality priority to reduce vibration and work error.

[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 target; β i (i = 1, 2, 3, 4) is the dynamic response coefficient, indicating the influence degree of real-time data on the priority.

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

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

[0104]

[0105] Wherein:

[0106] ΔT(t) represents the torque dynamic response of the engine; 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)) is a nonlinear function of the torque dynamic response, considering the combined effects of engine speed, load, accelerator pedal opening, and environmental conditions;

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

[0109] α1 and α2 are time decay constants, controlling the decay rates of different input variables;

[0110] ε is a compensation term for system noise or unmodeled parts;

[0111] β i and γ i represent the coupling of the accelerator pedal and environmental conditions, and the influence of the second derivative of engine speed on torque response, respectively.

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

[0113] The above step S104 calculates the rollover critical speed based on the working condition parameters as a constraint condition for the U-turn speed planning, and performs U-turn speed planning based on the rollover critical speed and the turning path, specifically including the following steps S201-S202:

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

[0115] where v crit is the rollover critical speed, g is the gravitational acceleration, R is the turning radius, and h is the height variation of the center of gravity;

[0116] Step S202 performs speed planning for the U-turn process based on the following function:

[0117]

[0118] where v in and v out are the entering and exiting U-turn speeds, respectively, and f(t, v crit) is the acceleration function constrained by the rollover critical speed during the turning process, T is the whole turning operation time; t1 is the time when the acceleration section ends, t2 is the time when the maintaining section ends; k is an empirical coefficient, representing the speed adjustment factor; R is the turning radius. k is determined according to the turning radius R and the field conditions.

[0119] The segmented speed planning ensures that the intelligent agricultural machine can guarantee power output and reduce the time required for turning during the turning process, and can control the speed within a safe range to avoid dangerous situations such as rollover.

[0120] The above-mentioned solving of the matching gear and the reversing timing when turning operation is performed under the current working condition in step S105 further includes:

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

[0122]

[0123] Wherein: T(t) represents the engine torque at time t; A(t) represents the accelerator pedal opening degree; λ is a trade-off parameter between acceleration response and shift smoothness; t shift And t end are the shift start time and end time, respectively;

[0124] The shift and accelerator pedal joint optimization model ensures smooth power transmission and reduces jerk through double closed-loop control design.

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

[0126]

[0127] Wherein γ is the allowed vibration energy threshold, which ensures the smoothness of the system in a certain frequency range. By adding frequency response constraints in the optimization process, the power fluctuation frequency response can be controlled to avoid excitation energy peaks at the resonance frequency.

[0128] Using the above optimization model, the influence of torque delay on power and shift stability can be balanced to obtain a more optimal gear and reversing timing. The dynamic programming is used to determine the optimal shift timing at each moment to ensure smooth power transmission and maximize fuel efficiency, while avoiding excessive wear of the clutch. Real-time working condition data is used for online rule extraction, and the shift rule is adjusted for different turning speed curves and torque dynamic response delays.

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

[0130] Step A1, real-time judgment of the current mode according to load, slope and speed data;

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

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

[0133] Step A4: dynamically switch modes and execute the corresponding optimization strategy in different working 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 threshold, θ1 is the large slope threshold, the current mode is judged as 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 maximizing power output;

[0137] The rate of change of torque is added to reduce mutations and improve smoothness; λ1 is the weight coefficient of balancing power output and smoothness; t start and t end are the start and end times respectively;

[0138] When L(t)<L1 and θ(t)<θ1, the current mode is judged as 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, ∫C(t)dt represents 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 threshold, the current mode is judged as the fuel saving mode, fuel economy is prioritized, the optimization model is:

[0143]

[0144] Where, λ4 is the weight coefficient of controlling torque smooth transition.

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

[0146]

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

[0148] α mode and β mode are the torque response coefficients related to the current mode, and the parameter values in different modes will be adjusted;

[0149] η is the system noise compensation term.

[0150] Through the above steps A1-A4, the system can adapt to different loads and terrain conditions, realize efficient power output, dynamically optimize fuel consumption according to the working mode, significantly reduce fuel consumption in light load and fuel saving mode, and effectively reduce power mutation, vibration and jerk in the working process. Intelligent agricultural machinery can intelligently adapt to complex working environment, improve the efficiency and reliability of automatic operation.

[0151] The application also provides an intelligent agricultural machinery complex working condition automatic operation power assembly coordination control system, which can 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 application, and the above-mentioned intelligent agricultural machinery complex working condition automatic operation power assembly coordination control method can be realized. The program module referred to in the embodiment of the application refers to a series of computer program instruction segments that can complete a specific function, and is more suitable for describing the execution process of the intelligent agricultural machinery complex working condition automatic operation power assembly coordination control method in the storage medium. The following description will specifically introduce the functions of each program module in the embodiment, as shown in Figure 2 The system comprises:

[0152] A first construction module 301 for constructing an automatic operation power assembly control parameter multi-objective optimization model under complex coupling excitation of agricultural machinery;

[0153] A second construction module 302 for constructing a prediction model of torque dynamic response delay law and working quality influence law of the agricultural machinery power assembly based on experimental big data;

[0154] A collection module 303 for collecting agricultural working condition parameters in real time, wherein the working condition parameters include the path turning radius, the center of gravity position change and the initial speed of the intelligent agricultural machinery, and further include the ground unevenness, the load and the inclination angle;

[0155] a planning module 304, configured to calculate a rollover critical speed as a constraint of the U-turn speed planning based on the working condition parameters, and to plan the U-turn speed based on the rollover critical speed and the turning path;

[0156] a solving module 305, configured to solve the matching gear and the shifting timing when the U-turn operation is performed under the current working condition based on the multi-objective optimization model, the working condition parameters, and the planned U-turn speed, and to avoid the generation of strong adverse incentives at the moment;

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

[0158] a control module 307, configured to control the electronic accelerator pedal signal to compensate for the torque in advance based on the predicted engine torque.

[0159] The other contents of the intelligent agricultural machine complex working condition automatic operation powertrain coordination control method based on the above intelligent agricultural machine complex working condition automatic operation powertrain coordination control system have been described in detail in the previous embodiments, and the corresponding contents in the previous embodiments can be referred to. Here, no further description is given.

[0160] The above is only the preferred embodiment of the present application. It should be noted that those skilled in the art can make several improvements and refinements without departing from the principles of the present application. These improvements and refinements should also be considered within the scope of protection of the present application.

Claims

1. A method for coordinated control of the powertrain of intelligent agricultural machinery under complex working conditions, characterized in that, The method includes: Construct a multi-objective optimization model for the control parameters of the powertrain of agricultural machinery under complex coupled excitation; Based on experimental big data, we constructed the dynamic response delay law of agricultural machinery powertrain torque, the influence law of operation quality, and a prediction model. Real-time collection of agricultural machinery operating condition parameters, including the intelligent agricultural machinery's path turning radius, center of gravity position change, initial speed, ground unevenness, load, and tilt angle; The critical rollover speed is calculated based on the aforementioned operating parameters and used as a constraint for the U-turn speed planning. The U-turn speed is then planned based on the critical rollover speed and the turning path. Based on the multi-objective optimization model, the operating parameters, and the planned U-turn speed, and avoiding the occurrence of strong adverse stimuli, the matching gear and reversing timing for U-turn operations under the current operating conditions are solved. Based on the matching gear, the timing of the shift, and the dynamic torque response delay law and prediction model, the engine torque demand is predicted in advance. Based on the predicted engine torque, the electronic accelerator pedal signal is controlled to compensate for the torque in advance.

2. The intelligent agricultural machinery powertrain coordination control method for complex working conditions according to claim 1, characterized in that, The multi-objective optimization model is expressed as follows: 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 These are the speeds before and after the gear shift, respectively, with the negative sign indicating that the power is maximized. f3(F) is the fuel economy objective function, expressed as the integral of the instantaneous fuel consumption rate: T represents the total turning time; C(t) represents the instantaneous fuel consumption rate. f4(Q) represents the balance target of work quality, considering the influence of strong adverse excitations, specifically the vibration energy under different excitations: Where A(ω) represents the vibration amplitude at the excitation frequency ω, ω min and ω max The range of excitation frequencies; w1(t), w2(t), w3(t), and w4(t) are weighting coefficients, and w1(t) + w2(t) + w3(t) + w4(t) = 1.

3. The intelligent agricultural machinery powertrain coordination control method for complex working conditions according to claim 1, characterized in that, The prediction model is described by the following equation: in: ΔT(t) represents the engine's torque dynamic response; 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 contributions of engine speed and load to torque response, respectively. α1 and α2 are time decay constants that control the decay rate of different input variables; ∈ is a compensation term for system noise or unmodeled parts; β i and γ i These represent the effects of the coupling term between the accelerator pedal and environmental conditions, and the second derivative of engine speed on torque response, respectively.

4. The intelligent agricultural machinery powertrain coordination control method for complex working conditions according to claim 1, characterized in that, The critical rollover speed is calculated based on the aforementioned operating parameters and used as a constraint for U-turn speed planning. Based on the critical rollover speed and the turning path, U-turn speed planning is performed, specifically including the following steps: The critical rollover velocity is calculated based on the following formula: Among them, v crit denoted as the critical rollover velocity, g as the acceleration due to gravity, R as the turning radius, and h as the change in height of the center of gravity. Speed ​​planning for the U-turn process is based on the following function: Among them, v in and v out f(t,v) represents the speed at which the U-turn is initiated and deflected. 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 to end the acceleration phase; t2 is the time to end the holding phase; k is an empirical coefficient, representing the speed adjustment factor; R is the turning radius.

5. The intelligent agricultural machinery powertrain coordination control method for complex working conditions according to claim 1, characterized in that, After determining the matching gear and shift timing, the process also includes: The matching gear and reversing 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 shift smoothness; t shift With t end These are the start and end times of the gear shift, respectively. The optimization process is carried out under the following constraints: Where γ is the permissible vibration energy threshold.

6. A coordinated control system for the powertrain of intelligent agricultural machinery operating under complex conditions, characterized in that, The system includes: The first building module is used to build a multi-objective optimization model of the control parameters of the automatic operation powertrain under complex coupled excitation of agricultural machinery. The second building module is used to construct predictive models of the dynamic response delay law of agricultural machinery powertrain torque and the influence law of operation quality based on experimental big data. The data acquisition module is used to collect agricultural machinery operating condition parameters in real time. These parameters include the intelligent agricultural machinery's path turning radius, center of gravity position change, initial speed, ground unevenness, load, and tilt angle. The planning module is used to calculate the rollover critical speed based on the working parameters as a constraint condition for the U-turn speed planning, and to plan the U-turn speed based on the rollover critical speed and the turning path. The solution module is used to solve the matching gear and reversing timing when performing a U-turn under the current working conditions, based on the multi-objective optimization model, the working condition parameters and the planned U-turn speed, and avoiding the occurrence of strong adverse stimuli. The prediction module is used to predict the engine torque demand in advance based on the matching gear, the reversing timing, the torque dynamic response delay law, and the prediction model. The control module is used to pre-compensate for torque by controlling the electronic accelerator pedal signal based on the predicted engine torque.

Images