Energy control method and system for hybrid corn machine

Abstract

The invention discloses an energy control method and system for a hybrid power corn machine, and belongs to the technical field of hybrid power corn machines. The method comprises the following steps: inputting obtained working condition data in a previous preset time period under a current operation working condition into a preset working condition identification model, and predicting current operation working condition information and a vehicle speed; the rotating speed of a header is obtained, and the running state of the hybrid power corn machine is determined according to the rotating speed of the header and the predicted vehicle speed; and searching an optimal energy control strategy for performing energy control on the hybrid power corn machine in a preset energy control parameter library according to the predicted operation condition information and the determined operation state. Through the working condition identification model, the operation working condition information of the hybrid power corn machine is effectively predicted; and based on the predicted operation condition information and the ECMS model, on the basis of an equivalent fuel consumption minimum strategy, an optimal energy control strategy corresponding to each piece of operation condition information is obtained by using an optimization algorithm, so that the fuel consumption is effectively reduced.

Description

Technical Field

[0001] The present application relates to the technical field of hybrid power corn harvesters, and in particular to an energy control method and system for a hybrid power corn harvester. Background Art

[0002] When the hybrid corn harvester is in operation, in order to ensure the operating efficiency of each working part, the engine needs to be maintained at 2200rpm, at which time the engine is in a high fuel consumption and low torque operating range. With the development of technology and increasingly stringent emission regulations, the traditional power system of corn harvesters has become more and more inefficient and has high emissions, and the energy and environmental costs are high. The hybrid corn harvester transmits energy through an electric motor instead of a traditional mechanical pulley, which can reduce transmission process losses.

[0003] In the prior art, the harvesting technology of hybrid corn harvesters mainly focuses on electrical design optimization, and there is no reasonable solution for allocating energy supply between the engine and the electric motor (power battery). Summary of the invention

[0004] The purpose of the embodiment of the present invention is to provide an energy control method for a hybrid corn harvester to solve the problem in the prior art that the energy supply of the engine and the motor cannot be reasonably allocated.

[0005] In order to achieve the above-mentioned objectives, the first aspect of the present application provides an energy control method for a hybrid corn harvester, the energy control method comprising: obtaining the operating condition data of the hybrid corn harvester within a predetermined time period before the current operating condition; inputting the obtained operating condition data within a predetermined time period before the current operating condition into a preset operating condition identification model to predict the current operating condition information and vehicle speed; obtaining the cutter speed, and determining the operating state of the hybrid corn harvester based on the cutter speed and the predicted vehicle speed; and based on the predicted operating condition information and the determined operating state, searching for the optimal energy control strategy for energy control of the hybrid corn harvester in a preset energy control parameter library.

[0006] In an embodiment of the present invention, the operating condition data includes one or more of the vehicle acceleration ratio, deceleration ratio, uniform speed ratio, idle speed ratio, average speed, maximum speed, maximum acceleration, and driving distance when the hybrid corn harvester is in different operating states.

[0007] In an embodiment of the present invention, before obtaining the operating condition data of the hybrid corn harvester within a predetermined time period before the current operating condition, the energy control method also includes: dividing the operating condition of the hybrid corn harvester according to the road surface flatness information and road surface slope information of the hybrid corn harvester's operating environment to obtain multiple operating condition information.

[0008] In an embodiment of the present invention, after obtaining a plurality of operating condition information, the energy control method further includes: obtaining historical operating condition data, predicted historical operating condition information and historical vehicle speed of the test hybrid corn harvester; constructing a training set based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; training a machine model for operating condition identification through the training set; and solving parameters of the machine model for operating condition identification in combination with a particle swarm optimization algorithm to obtain the preset operating condition identification model.

[0009] In an embodiment of the present invention, after obtaining the historical operating condition data, predicted historical operating condition information and historical vehicle speed of the test hybrid corn harvester, the energy control method also includes: using a principal component analysis method to perform dimensionality reduction processing on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; and constructing the training set based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed after dimensionality reduction processing.

[0010] In an embodiment of the present invention, the particle swarm optimization algorithm is combined to solve the parameters of the machine model for working condition identification, including: setting the number of particle swarms in the training set, the number of iterations, the model parameters to be solved, and the value range of the model parameters to be solved; initializing the particle swarm includes: setting the initial position of the particle swarm. Execution starts from the particle swarm at the initial position: solving the machine model for working condition identification through the current particle swarm to obtain the values ​​of multiple model parameters, and then calculating the fitness of the multiple model parameters according to the objective function to obtain the current optimal model parameters, wherein the accuracy of working condition identification is used as the objective function; updating the position of the particle swarm until the termination condition is reached, and repeating the above steps to obtain multiple currently optimal model parameters. The optimal model parameters are determined by the fitness corresponding to the multiple currently optimal model parameters.

[0011] In an embodiment of the present invention, the operating state includes a field transfer state and a harvesting operation state, and the operating state of the hybrid corn harvester is determined based on the cutter speed and the predicted vehicle speed, including: when the predicted vehicle speed is greater than 0 and the cutter speed is greater than 0, determining that the operating state of the hybrid corn harvester is the harvesting operation state; and when the predicted vehicle speed is greater than 0 and the cutter speed is equal to 0, determining that the operating state of the hybrid corn harvester is the field transfer state.

[0012] In an embodiment of the present invention, the optimal energy control strategy includes an optimal equivalent factor for characterizing the conversion of the power battery output power into the engine output power and an optimal power distribution method for the engine and the electric motor under the optimal equivalent factor.

[0013] In an embodiment of the present invention, before obtaining the operating condition data of the hybrid corn harvester within a predetermined time period before the current operating condition, the energy control method further includes: for the field transfer state and the harvesting operation state, respectively establishing an equivalent fuel consumption minimum strategy model for energy control of the hybrid corn harvester. For any equivalent fuel consumption minimum strategy model, execute: for each operating condition, in combination with the equivalent fuel consumption minimum strategy model, through a double-layer multi-objective particle swarm optimization algorithm, obtain the optimal equivalent factor and the optimal power allocation method corresponding to the operating condition; under the equivalent fuel consumption minimum strategy model, store the optimal equivalent factor and the optimal power allocation method corresponding to each operating condition in the preset energy control parameter library.

[0014] In an embodiment of the present invention, establishing any of the above-mentioned equivalent fuel consumption minimum strategy models includes: calculating the torque and power required for each operating mechanism of the test hybrid corn harvester based on the operating condition information and vehicle speed of the test hybrid corn harvester; obtaining the total power required for the test hybrid corn harvester based on the calculated torque and power required for each operating mechanism; and allocating the output power of the engine and the output power of the motor within the power range of the engine and the motor based on the required total power, so that the sum of the instantaneous fuel consumption of the engine and the equivalent fuel consumption of the power battery consumption is minimized, so as to establish any of the above-mentioned equivalent fuel consumption minimum strategy models.

[0015] In the embodiment of the present invention, any equivalent fuel consumption minimum strategy model is represented by the following formula:

[0016]

[0017] in, is the total fuel consumption at time t, P e (t) is the output power of the engine, b e is the specific fuel consumption rate, ρ e is the diesel density, s(t) is the equivalent factor, P m (t) is the output power of the motor, q oil The fuel has a low calorific value.

[0018] In an embodiment of the present invention, the optimal equivalent factor and the optimal power distribution method corresponding to the operating condition are obtained through a double-layer multi-objective particle swarm optimization algorithm, including: taking the power distribution method as the inner optimization target, optimizing the power distribution method of the engine and the motor under the current equivalent factor to obtain the optimal power distribution method corresponding to the current equivalent factor; and taking the equivalent factor as the outer optimization target, optimizing the equivalent factor of the current operating condition to obtain the optimal equivalent factor.

[0019] In an embodiment of the present invention, the optimal equivalent factor and the optimal power allocation method corresponding to the operating condition are obtained by using a double-layer multi-objective particle swarm optimization algorithm, including: setting the number of outer particle swarms, the number of iterations, and the parameters of the solution model; setting the number of inner particle swarms, the number of iterations, and the parameters of the solution model. Initializing the outer particle swarm includes: setting the initial position of the outer particle swarm; starting from the particle swarm at the initial position of the outer particle swarm: Initializing the inner particle swarm includes: setting the initial position of the inner particle swarm. Starting from the particle swarm at the initial position of the inner particle swarm, executing: solving the machine model for condition identification through the current inner particle swarm to obtain multiple power allocation methods, and then calculating the fitness of the multiple power allocation methods according to the inner objective function to obtain the current optimal power allocation method; updating the position of the inner particle swarm until the termination condition is reached, and repeating the above steps to obtain multiple current optimal power allocation methods. The optimal power allocation method corresponding to the current outer particle swarm is determined by the fitness corresponding to the multiple current optimal power allocation methods. Through the current outer particle group, solve the machine model for working condition identification, obtain multiple equivalent factors, and then calculate the fitness of the multiple equivalent factors according to the outer objective function to obtain the current optimal equivalent factor; update the position of the outer particle group until the termination condition is reached, repeat the above steps to obtain multiple current optimal equivalent factors. Determine the optimal equivalent factor and the corresponding optimal power allocation method through the fitness corresponding to the multiple current optimal equivalent factors.

[0020] The second aspect of the present application provides a system for energy control of a hybrid corn harvester, the system comprising: a control device, the control device comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the above-mentioned energy control method; an ECU, a power battery, motors of various operating mechanisms and a generator connected to the control device via a CAN bus; the ECU is electrically connected to the engine, the motors of various operating mechanisms, the generator is electrically connected to the power battery, and the power battery is used to supply energy to the motors of various operating mechanisms.

[0021] In an embodiment of the present invention, the system further comprises a remote terminal for: generating and updating an operating condition identification model and / or an energy control parameter library; and sending the operating condition identification model and / or the energy control parameter library to the control device.

[0022] Through the above technical scheme, the embodiment of the present invention inputs the acquired working condition data within the previous predetermined time period under the current operating condition into the preset working condition identification model to predict the current operating condition information and vehicle speed; obtains the cutting table speed, and determines the operating state of the hybrid corn harvester according to the cutting table speed and the predicted vehicle speed; according to the predicted operating condition information and the determined operating state, finds the optimal energy control strategy for energy control of the hybrid corn harvester in the preset energy control parameter library. The embodiment of the present invention collects a large amount of working condition data of hybrid corn harvesters under different working conditions, combines machine learning algorithms, and constructs a corn harvester working condition identification model, thereby effectively predicting the operating condition information of the hybrid corn harvester.

[0023] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0025] Figure 1 A schematic diagram of a flow chart of an energy control method for a hybrid corn harvester according to an embodiment of the present invention is shown;

[0026] Figure 2 An exemplary flow chart of an energy control method for a hybrid corn harvester according to an embodiment of the present invention is schematically shown;

[0027] Figure 3 A schematic diagram of a process flow of an example particle swarm optimization algorithm according to an embodiment of the present invention is shown;

[0028] Figure 4 A schematic diagram of a process flow of an exemplary double-layer multi-objective particle swarm optimization algorithm according to an embodiment of the present invention is shown;

[0029] Figure 5 A system block diagram for energy control of a hybrid corn harvester according to an embodiment of the present invention is schematically shown; and

[0030] Figure 6 An example system block diagram for energy control of a hybrid corn harvester according to an embodiment of the present invention is schematically shown.

[0031] Description of Reference Numerals

[0032] 10 Controls 20 ECU 30 Motors of each operating mechanism 40 Power battery 51 dynamo 52 engine DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described in conjunction with the drawings in the embodiment of the present invention. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiment of the present invention, and are not used to limit the embodiment of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0034] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0035] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0036] Since the hybrid corn harvester works in the field, its driving conditions are greatly affected by the geographical environment. The slopes and road roughness of plains, hills, mountains and other regions vary greatly. If the hybrid corn harvester is not properly controlled and distributed, the energy consumption efficiency of the vehicle may be seriously affected.

[0037] Figure 1 The following is a schematic diagram showing a flow chart of an energy control method for a hybrid corn harvester according to an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for energy control of a hybrid corn harvester, and the method may include the following steps:

[0038] Step S110: Acquire the operating condition data of the hybrid corn harvester within a predetermined time period under the current operating condition.

[0039] The preferred operating condition data of the embodiment of the present invention includes one or more of the vehicle acceleration ratio, deceleration ratio, uniform speed ratio, idle speed ratio, average speed, maximum speed, maximum acceleration, and driving distance when the hybrid corn harvester is in different operating states.

[0040] By way of example, the operating state of the hybrid corn harvester may include a field transfer state and a harvesting operation state. In the harvesting operation state, the travel motor, the header motor, the lifting motor, the peeling motor and other operating mechanisms are working; in the field transfer state, the header lifting and other operating mechanisms are not working. Therefore, one or more of the above working condition data may be obtained according to the operating state of the hybrid corn harvester.

[0041] Preferably, before step S110, the energy control method may further include: dividing the operating conditions of the hybrid corn harvester according to the road surface flatness information and road surface slope information of the hybrid corn harvester's operating environment to obtain a plurality of operating condition information.

[0042] For example, the complexity of the corn harvester's operating conditions (or driving conditions) can be divided according to the unevenness of the road surface and the slope. For example, according to the current road grading standard, the road surface unevenness can be divided into 8 levels (A to H). Since the corn harvester is operating in the field most of the time, the road surface unevenness can be divided into 3 levels, such as AC, DE, and FH. The slope can also be divided according to the regional environment, as shown in Table 1.

[0043] Table 1 Examples of road slopes in different areas

[0044] area Smooth the road Dirt road in the field Plains 4％-6％ 7％-8％ hills 5％-7％ 8％-10％ Mountain area 7％-8％ 10％-12％

[0045] Next, the slope can be divided into three levels, for example, 4%-7%, 8%-10%, and 10-12%. Based on this, the operating conditions can be divided into 9 levels, as shown in Table 2:

[0046] Table 2 Example of operating conditions

[0047]

[0048]

[0049] As shown in Table 1 and Table 2, the operating conditions of the hybrid corn harvester can be divided according to the road surface flatness information and road surface slope information of the hybrid corn harvester operating environment to obtain a plurality of operating condition information, namely, S1-S9.

[0050] Preferably, after obtaining multiple operating condition information, the energy control method may also include: obtaining historical operating condition data, predicted historical operating condition information and historical vehicle speed of the test hybrid corn harvester; constructing a training set based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; training a machine model for operating condition identification through the training set; and solving parameters of the machine model for operating condition identification in combination with a particle swarm optimization algorithm to obtain the preset operating condition identification model.

[0051] Please refer to Figure 2 , by way of example, the embodiment of the present invention can establish a preset working condition recognition model based on a machine learning algorithm, which may include: 1) the samples of the training set are a matrix of sample number (n) × feature parameter (m). Among them, the feature parameter (m) includes working condition data (category) (i.e., when the hybrid corn machine is in different operating states, one or more of its vehicle acceleration ratio, deceleration ratio, uniform speed ratio, idle speed ratio, average speed, maximum speed, maximum acceleration, and driving distance), predicted historical operating condition information and historical vehicle speed, and the sample number (n) represents the number of working condition data vectors.

[0052] Preferably, after obtaining the historical operating condition data, predicted historical operating condition information and historical vehicle speed of the test hybrid corn harvester, the energy control method may also include: using the principal component analysis method to perform dimensionality reduction processing on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; and constructing the training set based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed after the dimensionality reduction processing.

[0053] Continuing with the above example, 2) Since the sample has many characteristic parameters, we can first use the principal component analysis method to replace all characteristic parameters with a few comprehensive indicators without losing the information contained in the variables, and perform dimensionality reduction on the data: a) Find the sample X n×m eigenvalues ​​and eigenvectors. b) Calculate the variance contribution rate and cumulative variance contribution rate. The contribution rate of each principal component represents the percentage of the total information content of the original data. For example, select the first m principal components whose eigenvalues ​​are greater than 1 and whose cumulative contribution rates reach a preset percentage (for example, 80%). c) Select the first m principal components as input parameters in the modeling process of the working condition identification model to construct a training set.

[0054] Preferably, the combination of the particle swarm optimization algorithm to solve the parameters of the machine model for working condition identification may include: setting the number of particle swarms in the training set, the number of iterations, the model parameters to be solved, and the value range of the model parameters to be solved; initializing the particle swarm includes: setting the initial position of the particle swarm. Starting from the particle swarm at the initial position, the following steps are performed: solving the machine model for working condition identification through the current particle swarm to obtain the values ​​of multiple model parameters, and then calculating the fitness of the multiple model parameters according to the objective function to obtain the current optimal model parameters, wherein the accuracy of working condition identification is used as the objective function; updating the position of the particle swarm until the termination condition is reached, and repeating the above steps to obtain multiple currently optimal model parameters. The optimal model parameters are determined by the fitness corresponding to the multiple currently optimal model parameters.

[0055] Please refer to Figure 3 , Continuing with the above example, 3) the particle swarm optimization support vector machine model is used to predict the operating condition information of the next operating cycle of the hybrid corn harvester. Among them, the support vector machine, combined with Figure 3 The particle swarm optimization algorithm shown in the figure can realize automatic optimization of model parameters, and can build a reasonable and adaptive working condition identification model based on the prediction performance of the model in different situations. The termination condition is, for example, reaching the number of iterations.

[0056] Step S120: inputting the acquired operating condition data within a predetermined time period under the current operating condition into a preset operating condition recognition model to predict the current operating condition information and vehicle speed.

[0057] Please refer to Figure 2 , following the above example, the operating condition data of the corn harvester within a period of time is obtained, the obtained operating condition data is input into the above preset operating condition identification model, and the upcoming operating condition information and vehicle speed are predicted.

[0058] Step S130: Acquire the cutting table rotation speed, and determine the operating state of the hybrid corn harvester according to the cutting table rotation speed and the predicted vehicle speed.

[0059] As described above, the operating state described in the embodiment of the present invention may include a transfer state and a harvesting operation state, and determining the operating state of the hybrid corn harvester based on the cutter speed and the predicted vehicle speed may include: when the predicted vehicle speed is greater than 0 and the cutter speed is greater than 0, determining that the operating state of the hybrid corn harvester is the harvesting operation state; and when the predicted vehicle speed is greater than 0 and the cutter speed is equal to 0, determining that the operating state of the hybrid corn harvester is the transfer state.

[0060] Step S140: according to the predicted operating condition information and the determined operating state, an optimal energy control strategy for energy control of the hybrid corn harvester is searched in a preset energy control parameter library.

[0061] The optimal energy control strategy preferably in the embodiment of the present invention may include an optimal equivalent factor for characterizing the conversion of the power battery output power into the engine output power and an optimal power distribution method for the engine and the electric motor under the optimal equivalent factor.

[0062] Preferably, before step S110, the energy control method may further include: for the field transfer state and the harvesting operation state, respectively establishing an equivalent fuel consumption minimum strategy model for energy control of the corn harvester. For any equivalent fuel consumption minimum strategy model, executing: for each operating condition, combining the equivalent fuel consumption minimum strategy model, using a double-layer multi-objective particle swarm optimization algorithm, obtaining the optimal equivalent factor and the optimal power allocation method corresponding to the operating condition; under the equivalent fuel consumption minimum strategy model, storing the optimal equivalent factor and the optimal power allocation method corresponding to each operating condition in the preset energy control parameter library.

[0063] Please refer to Figure 2 , by way of example, the embodiment of the present invention further includes the step of presetting an energy control parameter library, which may include: 1) establishing an equivalent fuel consumption minimum strategy model (ECMS) for energy control of the hybrid corn harvester for the field transition state and the harvesting operation state. Among them, through ECMS, the power consumption of the hybrid corn harvester can be obtained to be equivalent to the fuel consumption (i.e., the equivalent factor), and the equivalent total fuel consumption is used as a standard indicator for optimal control, with the goal of minimizing the sum of the engine fuel consumption and the equivalent fuel consumption of the power battery at each instant, and optimizing the control parameters (i.e., the equivalent factor and the power distribution method) through an algorithm, and obtaining the optimal solution, i.e., the optimal energy control strategy, while satisfying the relevant constraints.

[0064] Preferably, establishing any of the above-mentioned equivalent fuel consumption minimum strategy models may include: calculating the torque and power required for each operating mechanism of the test hybrid corn harvester based on the operating condition information and vehicle speed of the test hybrid corn harvester; obtaining the total power required for the test hybrid corn harvester based on the calculated torque and power required for each operating mechanism; and allocating the output power of the engine and the output power of the electric motor within the power range of the engine and the electric motor based on the required total power, so that the sum of the instantaneous fuel consumption of the engine and the equivalent fuel consumption of the power consumed by the power battery is minimized, so as to establish any of the above-mentioned equivalent fuel consumption minimum strategy models.

[0065] As can be seen from the above, the difference between the transition state and the harvesting operation state is that in the transition state, the operation mechanisms such as the header lifting and transportation do not work. Therefore, for the ECMS corresponding to different operation states, the process of establishing the model is similar.

[0066] Taking an example, the establishment of ECMS includes: according to the requested power of the whole vehicle, within the power range of the engine and the motor, reasonably allocate the output power of the engine and the motor so that the instantaneous fuel consumption of the engine Equivalent fuel consumption of the power battery The sum of is the smallest, and the calculation process is as follows:

[0067]

[0068] in, is the total fuel consumption at time t, is the engine fuel consumption at time t, according to the engine fuel consumption model Calculate, P e (t) is the output power of the engine, b e is the specific fuel consumption rate, ρ e is the density of diesel.

[0069] is the equivalent fuel consumption of the electric motor at time t, s(t) is the equivalent factor, P m (t) is the output power of the motor, q oil The fuel has a low calorific value.

[0070] Formula (1) is modified. Preferably, any equivalent fuel consumption minimum strategy model is represented by the following formula:

[0071]

[0072] When the corn harvester is in the harvesting operation state, the required torque of the harvesting table motor is expressed as:

[0073]

[0074] Among them, M g is the motor torque of the header, M pf 、M cf 、M af are the friction torques of the reel, cutter and auger, i p , J p 、i a , J a are the transmission ratio and moment of inertia of the reel and auger, ω g is the rotation speed, k p , k c, k a are the cutter, reel and auger feeding load factors respectively, q is the feeding amount (related to vehicle speed), q(v) = 4*(v / h)m eq , h is the corn planting distance, m eq is the average mass of corn, and v is the vehicle speed.

[0075] Similarly, the lifting motor and the peeling motor require torque M s 、M b They are respectively expressed as follows:

[0076]

[0077] Among them, M sf , J s 、i s ,ω s , k s They are the corresponding elevator idling friction torque, rotational inertia, transmission ratio, speed and feed load factor.

[0078]

[0079] Among them, M bf 、M yf , J b , J y 、i b 、i y , k b , k y are the idling friction torque, moment of inertia, transmission ratio, speed and feeding load factor of the corresponding peeling roller and presser respectively, and ωb is the speed of the peeling motor.

[0080] Let the torque distributed by the walking motor be M v (t), the speed is ωv, which can be calculated by the transmission ratio and speed ratio. The power required by the motor of each operating mechanism is expressed as:

[0081] P m (t) = M g *ω g +M s *ω s +M b *ω b +M v (t)*ω v (6)

[0082] The power required when the corn machine is moving P v It is expressed as:

[0083]

[0084] Among them, f is the rolling friction coefficient, m is the vehicle mass, θ is the slope, C d is the drag coefficient, A is the frontal area, and δ is the moment of inertia coefficient.

[0085] The field return machine is mechanically driven by the engine. Its required power P can be obtained through its rotational inertia, transmission ratio and other data. h , other components have little influence, therefore, the total power demand of the corn harvester in the harvesting operation state is expressed as:

[0086] P req =P v +P h +M g *ω g +M s *ω s +M b *ω b (8)

[0087] Furthermore, with the minimum total fuel consumption as the goal, the objective function of ECMS is defined by the following formula:

[0088]

[0089] The following constraints need to be met:

[0090] P mL ≤P m (t)≤P mH

[0091] 0≤P e (t)≤P emax

[0092] P req (t) = P e (t)+P m (t) (10)

[0093] Among them, P mL , P mH are the minimum and maximum output power of the motor, P emax is the maximum output power of the engine, P req (t) is the required power.

[0094] Within the constraints, the output power of the engine and the motor can be combined in different ways according to the power demand at any time. The total equivalent fuel consumption under this allocation method can be calculated by applying the engine fuel consumption MAP diagram and the above engine fuel consumption model, and the minimum total equivalent fuel consumption can be obtained through the objective function. The output power of the engine and the motor corresponding to the minimum value is used as the optimal power allocation method for the engine and the motor at that moment.

[0095] Similarly, when the corn harvester is in the transfer state, the cutting platform, lifting, peeling and other operating mechanisms are not working, so its total required power is expressed as P v , the total motor power is the walking motor distribution power, P m (t) = M v (t)*ω v , also taking the minimum total fuel consumption as the goal, an objective function is established to obtain the optimal power distribution method of the engine and the motor under the transition state.

[0096] Preferably, the method of obtaining the optimal equivalent factor and the optimal power distribution method corresponding to the operating condition through a double-layer multi-objective particle swarm optimization algorithm may include: taking the power distribution method as the inner optimization target, optimizing the power distribution method of the engine and the motor under the current equivalent factor to obtain the optimal power distribution method corresponding to the current equivalent factor; and taking the equivalent factor as the outer optimization target, optimizing the equivalent factor of the current operating condition to obtain the optimal equivalent factor.

[0097] To illustrate with an example, for any operating condition, the equivalent factor can be a constant, and the power allocated to the engine and the motor changes continuously with the change in driving power demand. Therefore, it is necessary to find the optimal equivalent factor under the operating condition and obtain the optimal power distribution method for the engine and the motor under the equivalent factor. As mentioned above, the operating conditions can be divided into 9 types of operating condition information such as S1-S9. For any ECMS model corresponding to the transition state and the harvesting operation state, the equivalent factor and the power distribution method under different operating conditions are optimized based on the double-layer multi-objective particle swarm optimization algorithm. Among them, the inner optimization is to optimize the power distribution method of the engine and the motor under a certain fixed equivalent factor, and the outer optimization is to optimize the equivalent factor corresponding to the operating condition, and the optimal equivalent factor and the optimal power distribution method for the engine and the motor are obtained under the transition state and the harvesting operation state. The optimal equivalent factor and the optimal power distribution method corresponding to each operating condition are stored in a preset energy control parameter library, so as to find the optimal energy control strategy for energy control of the corn harvester in the preset energy control parameter library through the predicted operating condition information and the determined operating state.

[0098] Please refer to Figure 4 Preferably, the method of obtaining the optimal equivalent factor and the optimal power allocation method corresponding to the operating condition by using a double-layer multi-objective particle swarm optimization algorithm may include:

[0099] 1) Set the number of outer particle swarms, the number of iterations, and the solution model parameters.

[0100] 2) Set the number of inner particle swarms, the number of iterations, and the solution model parameters.

[0101] 3) Initializing the outer particle group includes: setting the initial position of the outer particle group.

[0102] 4) Starting from the particle group at the initial position of the outer particle group, execute:

[0103] 4.1) Initializing the inner particle group includes: setting the initial position of the inner particle group.

[0104] 4.2) Start from the particle group at the initial position of the inner particle group: solve the machine model for working condition identification through the current inner particle group, obtain multiple power allocation methods, and then calculate the fitness of the multiple power allocation methods according to the inner objective function (where the total fuel consumption is minimized under the equivalent factor of the current working condition) to obtain the current optimal power allocation method. Update the position of the inner particle group until the termination condition is reached, and repeat the above steps to obtain multiple current optimal power allocation methods.

[0105] 4.3) Determine the optimal power allocation method corresponding to the current outer particle group through the fitness corresponding to the multiple currently optimal power allocation methods.

[0106] 5) Solve the machine model for working condition identification through the current outer particle group to obtain multiple equivalent factors, and then calculate the fitness of the multiple equivalent factors according to the outer objective function (where the minimum total fuel consumption is the outer objective function) to obtain the current optimal equivalent factor. Update the position of the outer particle group until the termination condition is reached, and repeat the above steps to obtain multiple current optimal equivalent factors.

[0107] 6) Determine the optimal equivalent factor and the corresponding optimal power allocation method through the fitness corresponding to the multiple currently optimal equivalent factors.

[0108] The optimal equivalent factor and the optimal power allocation method corresponding to each operating condition calculated by the above-mentioned double-layer multi-objective particle swarm optimization algorithm are stored in a preset energy control parameter library, so as to find the optimal energy control strategy for energy control of the corn harvester in the preset energy control parameter library through the predicted operating condition information and the determined operating state.

[0109] Further preferably, the embodiment of the present invention may also include: updating the above-mentioned preset working condition identification model and / or the above-mentioned preset energy control parameter library according to the acquired real-time data.

[0110] Accordingly, the embodiment of the present invention inputs the acquired working condition data within the previous predetermined time period under the current operating condition into a preset working condition identification model to predict the current operating condition information and vehicle speed; obtains the cutting table speed, and determines the operating state of the hybrid corn harvester according to the cutting table speed and the predicted vehicle speed; and searches for the optimal energy control strategy for energy control of the hybrid corn harvester in a preset energy control parameter library according to the predicted operating condition information and the determined operating state. The embodiment of the present invention collects a large amount of working condition data of hybrid corn harvesters under different working conditions, combines machine learning algorithms, and constructs a corn harvester working condition identification model, thereby effectively predicting the operating condition information of the hybrid corn harvester.

[0111] Furthermore, the embodiment of the present invention calculates the feed amount of the whole vehicle and the required power of each operating component based on the predicted operating condition information, and constructs ECMS models of the transfer state and the harvesting operation state respectively. On the basis of the equivalent fuel consumption minimum strategy, a double-layer multi-objective particle swarm optimization algorithm is used to optimize the equivalent factor of fuel consumption and the parameters of the power distribution method, so as to obtain the optimal energy control strategy corresponding to each operating condition information. Based on this, an energy control parameter library is established to adjust the energy control strategy in real time, effectively reduce fuel consumption, and reduce harmful gas emissions.

[0112] An embodiment of the present invention further provides a control device, which may include: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned energy control method.

[0113] An embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored, and the instructions enable a machine to execute the above-mentioned energy control method.

[0114] Figure 5 The following schematically shows a system block diagram for energy control of a hybrid corn harvester according to an embodiment of the present invention. Figure 5 As shown, the system provided by the embodiment of the present invention may include: the above-mentioned control device 10; an ECU 20, a power battery 40, a motor 30 of each operating mechanism, and a generator 51 connected to the control device 10 via a CAN bus. An engine 52 connected to the ECU 20, the motor 30 of each operating mechanism, and the generator 51 are electrically connected to the power battery 40, and the power battery 40 supplies energy to the motor 30 of each operating mechanism.

[0115] Please refer to Figure 6 For example, the motors of the various operating mechanisms in the embodiment of the present invention may preferably include a cutting table motor, a lifting motor, a peeling motor, and a walking motor.

[0116] In the preferred embodiment of the present invention, the engine is mechanically connected to the field return machine and the hydraulic oil pump, and the torque coupler is mechanically connected to the engine, the travel motor and the travel power output mechanism.

[0117] Please refer to Figure 6 For example, the control device is preferably a vehicle controller, and the generator and the travel motor are connected via a CAN bus.

[0118] Preferably, the system may further include a remote terminal, which may be used to: generate and update an operating condition identification model and / or an energy control parameter library; and send the operating condition identification model and / or the energy control parameter library to the control device.

[0119] Among them, the steps of generating and updating the operating condition identification model and / or the energy control parameter library can refer to the embodiment of the energy control method provided in the embodiment of the present invention, and will not be repeated here.

[0120] Accordingly, the system for energy control of a corn harvester provided by the embodiment of the present invention can adjust the optimal energy control strategy for energy control of the corn harvester in real time through the acquired working condition data through its control device, thereby effectively reducing fuel consumption and reducing harmful gas emissions. Other technical details and technical effects of the system embodiment can be referred to the embodiment of the energy control method provided by the embodiment of the present invention, which will not be repeated here.

[0121] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0122] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0126] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0127] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0128] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0129] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An energy control method for a hybrid corn harvester, characterized in that: The energy control method comprises: Acquiring operating condition data of the hybrid corn harvester within a predetermined time period under the current operating condition; Inputting the acquired operating condition data within a predetermined time period under the current operating condition into a preset operating condition identification model to predict the current operating condition information and vehicle speed; Acquiring a header rotation speed, and determining an operating state of the hybrid corn harvester according to the header rotation speed and the predicted vehicle speed; and According to the predicted operating condition information and the determined operating state, the optimal energy control strategy for energy control of the hybrid corn harvester is found in a preset energy control parameter library.

2. The energy control method according to claim 1, characterized in that: The operating condition data includes one or more of the vehicle acceleration ratio, deceleration ratio, uniform speed ratio, idle speed ratio, average speed, maximum speed, maximum acceleration, and driving distance when the hybrid corn harvester is in different operating states.

3. The energy control method according to claim 1, characterized in that: Before obtaining the operating condition data of the hybrid corn harvester within a predetermined time period under the current operating condition, the energy control method further includes: According to the road surface flatness information and road surface slope information of the hybrid power corn harvester's operating environment, the operating conditions of the hybrid power corn harvester are divided to obtain a plurality of operating condition information.

4. The energy control method according to claim 3, characterized in that: After obtaining the plurality of operating condition information, the energy control method further includes: Obtain the historical operating condition data, predicted historical operating condition information and historical vehicle speed of the tested hybrid corn harvester; Construct a training set based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; Using the training set, training a machine model for working condition identification; and In combination with a particle swarm optimization algorithm, parameters of the machine model used for operating condition identification are solved to obtain the preset operating condition identification model.

5. The energy control method according to claim 4, characterized in that: After acquiring the historical operating condition data, the predicted historical operating condition information and the historical vehicle speed of the test hybrid power corn harvester, the energy control method further includes: Using principal component analysis to reduce the dimensionality of the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed; and The training set is constructed based on the acquired historical operating condition data, predicted historical operating condition information and historical vehicle speed after dimensionality reduction processing.

6. The energy control method according to claim 4, characterized in that: The method of combining the particle swarm optimization algorithm to solve the parameters of the machine model used for working condition identification includes: Setting the number of particle swarms, the number of iterations, the solution model parameters and the value range of the solution model parameters of the training set; Initializing the particle swarm includes: setting the initial position of the particle swarm; Start with the particle swarm at the initial position: By using the current particle swarm, the machine model for working condition identification is solved to obtain the values ​​of multiple model parameters, and then the fitness of the multiple model parameters is calculated according to the objective function to obtain the current optimal model parameters. Wherein, the accuracy of working condition identification is taken as the objective function; Update the position of the particle swarm until the termination condition is reached, and repeat the above steps to obtain multiple current optimal model parameters; and The optimal model parameters are determined by the fitness corresponding to the multiple currently optimal model parameters.

7. The energy control method according to claim 1, characterized in that: The operating state includes a field transfer state and a harvesting operation state. The operating state of the hybrid corn harvester is determined according to the harvesting table rotation speed and the predicted vehicle speed, including: When the predicted vehicle speed is greater than 0 and the harvesting table speed is greater than 0, determining that the operating state of the hybrid corn harvester is the harvesting operation state; and When the predicted vehicle speed is greater than 0 and the harvesting table rotation speed is equal to 0, it is determined that the operating state of the hybrid corn harvester is the field transfer state.

8. The energy control method according to claim 7, characterized in that: The optimal energy control strategy includes an optimal equivalent factor for characterizing the conversion of the power battery output power into the engine output power and an optimal power distribution method for the engine and the electric motor under the optimal equivalent factor.

9. The energy control method according to claim 8, characterized in that: Before obtaining the operating condition data of the hybrid corn harvester within a predetermined time period under the current operating condition, the energy control method further includes: For the field transfer state and the harvesting operation state, respectively establish an equivalent fuel consumption minimum strategy model for energy control of the hybrid corn harvester; and For any equivalent fuel consumption minimum strategy model, execute: For each operating condition, combined with the equivalent fuel consumption minimum strategy model, the optimal equivalent factor and the optimal power allocation method corresponding to the operating condition are obtained through a double-layer multi-objective particle swarm optimization algorithm; Under the equivalent fuel consumption minimum strategy model, the optimal equivalent factor and the optimal power allocation method corresponding to each operating condition are stored in the preset energy control parameter library.

10. The energy control method according to claim 9, characterized in that: Establishing any of the above-mentioned equivalent fuel consumption minimum strategy models includes: Calculate the torque and power required by each operating mechanism of the tested hybrid power corn harvester according to the operating condition information and vehicle speed of the tested hybrid power corn harvester; According to the calculated torque and power required by each operating mechanism, the total power required by the tested hybrid corn harvester is obtained; According to the required total power, the output power of the engine and the output power of the electric motor are allocated within the power range of the engine and the electric motor, so that the sum of the instantaneous fuel consumption of the engine and the equivalent fuel consumption of the power battery consumption is minimized, so as to establish any equivalent fuel consumption minimum strategy model.

11. The energy control method according to claim 10, characterized in that: The following formula is used to represent any of the minimum equivalent fuel consumption strategies: in, is the total fuel consumption at time t, P e (t) is the output power of the engine, b e is the specific fuel consumption rate, ρ e is the diesel density, s(t) is the equivalent factor, P m (t) is the output power of the motor, q oil The fuel has a low calorific value.

12. The energy control method according to claim 9, characterized in that: The optimal equivalent factor and the optimal power allocation method corresponding to the operating condition are obtained by using a double-layer multi-objective particle swarm optimization algorithm, including: Taking the power distribution mode as the inner optimization target, optimizing the power distribution mode of the engine and the motor under the current equivalent factor to obtain the optimal power distribution mode corresponding to the current equivalent factor; and Taking the equivalent factor as the outer optimization target, the equivalent factor of the current operating condition is optimized to obtain the optimal equivalent factor.

13. The energy control method according to claim 12, characterized in that: The optimal equivalent factor and the optimal power allocation method corresponding to the operating condition are obtained by using a double-layer multi-objective particle swarm optimization algorithm, including: Set the number of outer particle swarms, number of iterations, and solution model parameters; Set the number of inner particle swarms, number of iterations, and solution model parameters; Initializing the outer particle group includes: setting the initial position of the outer particle group; Starting from the particle swarm at the initial position of the outer particle swarm, execute: Initializing the inner particle group includes: setting the initial position of the inner particle group; Starting from the particle group at the initial position of the inner particle group, the following is executed: Solving the machine model for working condition identification through the current inner particle swarm to obtain multiple power allocation methods, and then calculating the fitness of the multiple power allocation methods according to the inner objective function to obtain the current optimal power allocation method; Update the position of the inner particle group until the termination condition is reached, and repeat the above steps to obtain multiple current optimal power allocation methods; Determining the optimal power allocation method corresponding to the current outer particle group through the fitness corresponding to the multiple currently optimal power allocation methods; Solving the machine model for working condition identification through the current outer particle group to obtain multiple equivalent factors, and then calculating the fitness of the multiple equivalent factors according to the outer objective function to obtain the current optimal equivalent factor; Update the position of the outer particle group until the termination condition is reached, and repeat the above steps to obtain multiple current optimal equivalent factors; The optimal equivalent factor and the corresponding optimal power allocation method are determined through the fitness corresponding to the multiple currently optimal equivalent factors.

14. A system for energy control of a hybrid corn harvester, characterized in that: The system comprises: A control device, the control device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the energy control method according to any one of claims 1 to 13; An ECU, a power battery, a motor of each operating mechanism, and a generator connected to the control device via a CAN bus; The ECU is electrically connected to the engine, the motors of each operating mechanism, and the generator is electrically connected to the power battery, and the power battery is used to supply energy to the motors of each operating mechanism.

15. The system according to claim 14, characterized in that The system also includes a remote terminal for: Generate and update the operating condition identification model and / or energy control parameter library; and The operating condition identification model and / or the energy control parameter library are sent to the control device.

Images