Shovel loading control method and device of loader, loader, medium and program product

Abstract

The invention provides a shovel loading control method and device of a loader, the loader, a computer readable storage medium and a computer program product, and the shovel loading control method comprises the following steps: constructing a target loss function model according to a decision variable of shovel loading control; determining a model constraint corresponding to the target loss function model; determining a control mode according to the type of the shoveled material, and determining a shoveling operation link of the loader in the control mode; according to the state parameters and the model constraints of the loader, a target loss function model is utilized to obtain control parameters corresponding to the shoveling operation link; and according to the state parameters and the control parameters, the loader is controlled to execute corresponding operation in the shoveling operation link. The problems that in the shoveling process of the loader, the automation control degree is not high, and energy consumption is high are solved, it can be guaranteed that output control parameters are accurate, working efficiency is improved, and energy consumption is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of loaders, and in particular to a shoveling control method and device for a loader, a loader, a computer-readable storage medium, and a computer program product. Background Art

[0002] A loader is a type of engineering machinery widely used in engineering construction, mining, port logistics, agriculture and other fields. It is mainly used for shoveling, transporting, and unloading of loose materials. Due to its strong adaptability and other characteristics, loaders are widely used in mining, construction, ports, railways, industry and other fields. They can adapt to a variety of complex terrains, such as muddy and rugged mine roads and construction sites. The shoveling process of a loader mainly includes inserting the shovel into the pile, shoveling materials, lifting the bucket, and raising the arm. At present, the shoveling control of the loader relies on manual operation handles. The shoveling process requires the operator to pay attention and precise control at all times. It not only requires high skills and experience of the operator, but also has high labor intensity, affecting work efficiency and accuracy, and the energy consumption during the shoveling process is high. Summary of the Invention

[0003] The present disclosure provides a shovel loading control method and device for a loader, a loader, a computer-readable storage medium, and a computer program product.

[0004] According to a first aspect of the present disclosure, a shoveling control method for a loader is provided, comprising: constructing a target loss function model based on decision variables of shoveling control; determining model constraints corresponding to the target loss function model, wherein the model constraints include at least one of mechanical performance constraints, working environment constraints, and safety constraints; determining a control mode based on the type of shoveling material, and determining the shoveling operation link of the loader under the control mode; obtaining control parameters corresponding to the shoveling operation link using the target loss function model based on the state parameters of the loader and the model constraints; and controlling the loader to perform corresponding operations in the shoveling operation link based on the state parameters and the control parameters.

[0005] Optionally, constructing the target loss function model based on the decision variables of the shoveling control includes: constructing a shoveling efficiency function based on the control decision variables and the bucket energy consumption coefficient, wherein the shoveling efficiency function characterizes the energy consumption of the bucket movement of the loader; constructing an energy consumption function based on the control decision variables and the walking energy consumption coefficient, wherein the energy consumption function characterizes the vehicle driving energy loss of the loader; and performing a weighted combination of the shoveling efficiency function and the energy consumption function based on the weight coefficient to obtain the target loss function model.

[0006] Optionally, the mechanical performance constraints include constraints on the bucket angle and / or boom angle of the loader; the working environment constraints include constraints on the loader's shoveling work site; and the safety constraints include constraints on the torque output by the loader.

[0007] Optionally, obtaining the control parameters corresponding to the shoveling operation link by using the target loss function model based on the state parameters of the loader and the model constraints includes: when entering the shoveling operation link and, based on the state parameters, determining that the model constraints are satisfied, solving the target loss function model by using the online gradient descent method to determine the corresponding gradient; and updating the current control parameters of the loader based on the gradient and the learning rate to obtain the control parameters.

[0008] Optionally, after all operations in the shoveling operation link are completed, an adjustment coefficient is obtained according to the decay rate and decay time; and the learning rate is adjusted according to the adjustment coefficient.

[0009] Optionally, determining the control mode according to the type of the shoveled material includes: when the type of the shoveled material is dry material, determining the control mode to be the first mode; when the type of the shoveled material is wet material, determining the control mode to be the second mode.

[0010] Optionally, the shoveling operation of the loader in the first mode includes: adjusting the boom, leveling the bucket, inserting the shovel into the pile, lifting the bucket at a small angle, lifting the boom at a small angle, shoveling, lifting the bucket, shoveling, raising the boom, and retreating.

[0011] Optionally, the controlling of the loader to perform corresponding operations in the shoveling operation link according to the state parameters and the control parameters includes: entering the boom lowering link in the first mode, and controlling the boom angle of the loader to be a target boom angle according to the control parameters corresponding to the boom lowering link; entering the bucket leveling link, and controlling the bucket angle of the loader to be a target bucket angle according to the control parameters corresponding to the bucket leveling link; entering the shovel insertion into the material pile link, and controlling the loader to perform the shovel insertion operation according to the control parameters corresponding to the shovel insertion into the material pile link until the loader's walking torque is within the torque range; entering the small-angle bucket lifting link, and controlling the current angle value of the bucket to increase by a first angle according to the control parameters corresponding to the small-angle bucket lifting link; entering the small-angle lifting link The boom link controls the current angle value of the boom to increase by a second angle according to the control parameters corresponding to the small-angle boom lifting link; enters the shovel link, controls the loader to perform the shovel lifting operation according to the control parameters corresponding to the shovel lifting link, until the vehicle torque is within the torque range; cycles once or multiple times to enter the small-angle bucket lifting link, the small-angle boom lifting link and the shovel lifting link to perform corresponding operations; enters the bucket lifting and shovel lifting links, controls the bucket angle to the bucket setting angle according to the control parameters corresponding to the bucket lifting and shovel lifting links; enters the boom lifting link, controls the boom angle to the boom setting angle based on the control parameters corresponding to the boom lifting link; enters the retreat link, controls the loader to reach a predetermined position according to the control parameters corresponding to the retreat link.

[0012] Optionally, in the bucket lifting and shovel punching link and the boom lifting link, a first parameter is determined based on the set angle, the actual angle and the angle threshold; a second parameter is determined based on the minimum value of the control parameter, the control parameter and the angle threshold; an adjustment amount is determined based on the first parameter and the second parameter; and the control parameter is adjusted based on the adjustment amount to obtain the adjusted control parameter.

[0013] Optionally, the shoveling operation of the loader in the second mode includes: adjusting the boom, leveling the bucket, inserting the shovel into the pile, raising the bucket at a large angle, raising the boom at a large angle, shoveling, and retreating.

[0014] Optionally, in the second mode, the boom lowering link is entered, and the boom angle of the loader is controlled to be a target boom angle according to the control parameters corresponding to the boom lowering link; the bucket leveling link is entered, and the bucket angle of the loader is controlled to be a target bucket angle according to the control parameters corresponding to the bucket leveling link; the shovel insertion into the material pile link is entered, and the loader is controlled to perform a shovel operation according to the control parameters corresponding to the shovel insertion into the material pile link until the loader's travel torque is within the torque range; the bucket raising link is entered, and the current angle value of the bucket is controlled to increase by a third angle according to the control parameters corresponding to the bucket raising link; the boom raising link is entered, and the current angle value of the boom is controlled to increase by a fourth angle according to the control parameters corresponding to the boom raising link; the shovel striking link is entered, and the loader is controlled to perform a shovel striking operation according to the control parameters corresponding to the shovel striking link until the vehicle torque is within the torque range; The process loops through the small-angle bucket lifting link, the small-angle boom lifting link, and the shovel impact link once or multiple times, and performs corresponding operations until the bucket angle reaches the maximum bucket angle; the process enters the backward link, and controls the loader to reach a predetermined position according to the control parameters corresponding to the backward link.

[0015] Optionally, the decision variables and the control parameters include: the current output to the bucket, the current output to the boom, and the travel torque of the loader; the state parameters include: the bucket angle, the boom angle, the loader position, and the vehicle torque of the loader.

[0016] According to a second aspect of the present disclosure, a shoveling control device of a loader is provided, comprising: a model construction module for constructing a target loss function model based on decision variables of shoveling control; a constraint establishment module for determining model constraints corresponding to the target loss function model, wherein the model constraints include at least one of mechanical performance constraints, working environment constraints, and safety constraints; a link determination module for determining a control mode according to the type of shoveling material, and determining the shoveling operation link of the loader under the control mode; a parameter determination module for obtaining control parameters corresponding to the shoveling operation link using the target loss function model according to the state parameters of the loader and the model constraints; and a control processing module for controlling the loader to perform corresponding operations in the shoveling operation link according to the state parameters and the control parameters.

[0017] According to a third aspect of the present disclosure, a shoveling control device of a loader is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the method described above based on instructions stored in the memory.

[0018] According to a fourth aspect of the present disclosure, a loader is provided, comprising the above shoveling control device for the loader.

[0019] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and when the instructions are executed by a processor, the steps of the method described above are implemented.

[0020] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described above when executed by a processor.

[0021] The loader shoveling control method, device, loader, computer-readable storage medium and computer program product disclosed in the present invention establish a target loss function model and determine model constraints based on decision variables, obtain control parameters based on the target loss function model, and control the loader operation, thereby solving the problems of low degree of automation control and high energy consumption in the loader shoveling process, and can ensure the accuracy of the output control parameters, improve work efficiency, reduce energy consumption, and improve the safety of the loader. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other purposes and advantages of the present disclosure will be further described below in conjunction with specific embodiments and with reference to the accompanying drawings. In the accompanying drawings, the same or corresponding technical features or components will be represented by the same or corresponding figure marks.

[0023] Figure 1 1 is a flow chart of some embodiments of a shovel loading control method for a loader according to the present disclosure;

[0024] Figure 2 1 is a flow chart of constructing a target loss function model in some embodiments of the shovel loading control method of a loader according to the present disclosure;

[0025] Figure 3-Figure 6 This is a schematic diagram of the shoveling process of the loader;

[0026] Figure 7 1 is a flow chart of determining a control mode in some embodiments of the shovel loading control method of a loader according to the present disclosure;

[0027] Figure 8 Schematic diagram of the shoveling operation of the loader in the first mode and the second mode;

[0028] Figure 9 1 is a flow chart of a first mode in some embodiments of the shovel loading control method of a loader according to the present disclosure;

[0029] Figure 10 is a flow chart of the second mode in some embodiments of the shovel loading control method of a loader according to the present disclosure;

[0030] Figure 11 Schematic diagram of modules of some embodiments of the shovel loading control device of a loader according to the present disclosure;

[0031] Figure 12 Schematic diagram of a control processing module in some embodiments of the shovel loading control device of a loader according to the present disclosure

[0032] Figure 13 Schematic diagrams of modules of other embodiments of the shovel loading control device of a loader according to the present disclosure. DETAILED DESCRIPTION

[0033] Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of the embodiments are described in the specification. However, it should be understood that many implementation-specific settings must be made in the process of implementing the embodiments in order to achieve the developer's specific goals, such as meeting those restrictions related to equipment and services, and these restrictions may vary depending on the implementation. In addition, it should be understood that although the development work may be very complex and time-consuming, it is only a routine task for those skilled in the art who benefit from the contents of this disclosure.

[0034] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0035] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, and do not represent any specific technical meanings, nor do they indicate a necessary logical order between them.

[0036] It should also be understood that in the embodiments of the present disclosure, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0037] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0038] In addition, the term "and / or" in this disclosure is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the related objects are in an "or" relationship.

[0039] It should also be understood that the description of the various embodiments in this disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0040] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0041] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0042] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0043] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0044] In addition, in order to avoid obscuring the present disclosure with unnecessary details, only the processing steps and / or device structures that are closely related to at least the solution according to the present disclosure are shown in the drawings, while other details that are not closely related to the present disclosure are omitted. It should also be noted that similar reference numerals and letters in the drawings indicate similar items, and therefore once an item is defined in one drawing, it does not need to be discussed again for subsequent drawings.

[0045] Figure 1 FIG. 1 is a flow chart of some embodiments of the shoveling control method of a loader according to the present disclosure. Figure 1 As shown, the shoveling control method of the loader includes steps S101-S105.

[0046] Step S101: constructing a target loss function model based on the decision variables of shovel loading control.

[0047] The loader can be a manned loader or a loader, etc. The loader is a vehicle including a bucket, a boom, etc. The decision variables of the loader's shoveling control can be set, and the decision variables can be current, torque, etc. The target loss function model can be constructed based on the decision variables, and the target loss function model can be a variety of function models.

[0048] Step S102: determining a model constraint corresponding to the target loss function model, wherein the model constraint includes at least one of a mechanical performance constraint, a working environment constraint, and a safety constraint.

[0049] Step S103: determining a control mode according to the type of shoveled material, and determining the shoveled operation link of the loader under the control mode.

[0050] Step S104 , according to the state parameters and model constraints of the loader, the target loss function model is used to obtain the control parameters corresponding to the shoveling operation link.

[0051] Step S105 , controlling the loader to perform corresponding operations in the shoveling operation according to the state parameters and the control parameters.

[0052] The shoveling control method of the loader disclosed in the present invention establishes a target loss function model and determines the model constraints according to the decision variables, obtains control parameters based on the target loss function model, and controls the loader operation, thereby solving the problems of low degree of automation control and high energy consumption in the loader shoveling process, and can ensure the accuracy of the output control parameters and improve work efficiency. It can not only save fuel expenses caused by energy consumption, but also greatly reduce the operating cost of the loader, reduce the operator's work intensity, improve the work efficiency and safety of the loader, and make the shoveling operation more stable.

[0053] Figure 2 FIG. 1 is a flow chart of constructing a target loss function model in some embodiments of the shovel loading control method of a loader according to the present disclosure, as shown in FIG. Figure 2 As shown:

[0054] Step S201 : constructing a shoveling efficiency function according to the control decision variables and the bucket energy consumption coefficient, wherein the shoveling efficiency function represents the energy consumption of the bucket movement of the loader.

[0055] Step S202 : constructing an energy consumption function according to the control decision variables and the travel energy consumption coefficient, wherein the energy consumption function represents the vehicle travel energy loss of the loader.

[0056] Step S203 : performing a weighted combination of the shoveling efficiency function and the energy consumption function according to the weight coefficient to obtain a target loss function model.

[0057] In some embodiments, various sensors and other detection devices may be used to collect state parameters of the loader. The state parameters include bucket angle, boom angle, loader position, and loader vehicle torque. State parameters may also include boom cavity pressure, bucket cavity pressure, loader vehicle speed, and bucket material weight. A loader is a type of vehicle, and the loader vehicle torque and vehicle speed refer to the torque and speed of the loader's vehicle engine.

[0058] Set the decision variables of the loader during the shoveling process, that is, set the decision variables of the shoveling control to , where x t is the decision variable for step t (the tth loading operation) during the loading process. The decision variables for loading control include bucket output current (the current output to the bucket), boom output current (the current output to the boom), and travel torque (the loader's travel torque). The loader's travel torque is the torque output by the engine when the loader is moving.

[0059] Establish a target loss function model, which can be a variety of function models. For example, the target loss function model can be a weighted combination of the shoveling efficiency function and the energy consumption function, such as the following formula (1-1):

[0060] (1-1);

[0061] Among them, the shovel loading efficiency function Represents the energy consumption during the boom bucket movement time. The higher the shoveling efficiency, the lower the energy consumption. Energy consumption function It is expressed as the energy loss during vehicle driving, which is also a convex function. Used to balance shoveling efficiency and energy consumption, ranging from 0 to 1.

[0062] Weight coefficient It can be set according to the state of the loader. For example, the weight coefficient for the independent movement of the boom and bucket =1, for a single moving vehicle, the weight coefficient =0, both move at the same time, weight coefficient Take a number between 0-1, which can be 0.5.

[0063] It can be a variety of functions, for example, = ; It can be a variety of functions, such as = ; The target loss function model can be the following formula (1-2);

[0064] (1-2);

[0065] Where q1 is the energy consumption coefficient of the boom bucket, q2 is the energy consumption coefficient of the vehicle travel, and t represents the movement time.

[0066] In some embodiments, the mechanical performance constraints include constraints on the bucket angle and / or boom angle of the loader, the working environment constraints include constraints on the loader's loading site, and the safety constraints include constraints on the torque output by the loader.

[0067] Constraints must be placed on the target loss function model based on factors such as the decision variables, the target loss function model, and the loader's mechanical structure. These constraints include mechanical performance constraints, working environment constraints, and safety constraints. Mechanical performance constraints include constraints on the loader's bucket angle and / or boom angle, working environment constraints include constraints on the loader's loading area, and safety constraints include constraints on the loader's output torque.

[0068] For example, a mechanical constraint could be the bucket angle and boom angle The working environment constraint is the target site (x, y) constraint, and the safety constraint is the loader's vehicle torque T constraint. Model constraints can be selected from mechanical performance constraints and safety constraints, as shown below:

[0069]

[0070] in, and Can be the same or different, and Can be the same or different.

[0071] In some embodiments, various methods can be used to utilize the target loss function model to obtain control parameters corresponding to the shoveling operation. The target loss function model can be solved using online gradient descent. Based on the basic concept of gradient descent, the online gradient descent method continuously updates model parameters along the negative gradient of the objective function to gradually minimize the objective function. In each iteration, the gradient of the target loss function model with respect to the model parameters can be calculated to update the control parameters.

[0072] When entering the shoveling operation phase and determining whether the model constraints are met based on the state parameters, the online gradient descent method is used to solve the target loss function model and determine the corresponding gradient; based on the gradient and learning rate, the current control parameters of the loader are updated to obtain the control parameters.

[0073] The initial decision variables of the shovel loading control can be preset based on empirical data. When entering the shovel loading operation phase and satisfying the model constraints according to the state parameters, the gradient of the target loss function model is calculated at each time step (shovel loading operation phase) through the online gradient descent method. , we can use a variety of existing methods to calculate the gradient, such as derivatives.

[0074] Update the control variable (decision variable) along the gradient direction, that is, ,in, is the learning rate, the step size for controlling parameter updates. The target loss function model can be solved one or more times during each shoveling operation, and the corresponding control parameters can be obtained and executed one or more times. These control parameters include the current output to the bucket, the current output to the boom, and the travel torque of the loader.

[0075] The shovel loading process of the loader is as follows Figure 3-Figure 6 As shown, Figure 3 Preparation for shoveling, including lowering the boom and leveling the bucket, Figure 4 To insert into the stockpile, Figure 5 The shovel loading process includes putting away the bucket, raising the boom, Figure 6 The shoveling is complete and the loader has shoveled full of materials.

[0076] Figure 7 FIG. 1 is a flow chart of determining a control mode in some embodiments of the shovel loading control method of a loader according to the present disclosure, as shown in FIG. Figure 7 As shown:

[0077] Step S701: When the type of the shoveled material is dry material, determine that the control mode is the first mode.

[0078] Step S702: When the type of the shoveled material is wet material, determine that the control mode is the second mode.

[0079] like Figure 8 As shown, the loader's shoveling operations in the first mode include: lowering the boom, leveling the bucket, inserting the shovel into the pile, raising the bucket at a small angle, raising the boom at a small angle, shoveling, raising the bucket, and shoveling, raising the boom, and retreating. The loader's shoveling operations in the second mode include: lowering the boom, leveling the bucket, inserting the shovel into the pile, raising the bucket at a large angle, raising the boom at a large angle, shoveling, and retreating. Inserting the shovel into the pile can be considered a single operation, and inserting the shovel into the pile can also be divided into two operations: shoveling and inserting into the pile.

[0080] The loader's loading control decisions can be made using a state machine. The state machine's control parameters utilize the optimal control variables obtained from each solution of the target loss function model. Each state in the state machine corresponds to a loading operation. Loading is categorized into dry and wet materials, with dry materials corresponding to Mode 0 (the first mode) and wet materials corresponding to Mode 1 (the second mode).

[0081] like Figure 8 As shown in the figure, when the decision control sends a mode 0 signal, the intelligent shoveling will execute the state machine process of mode 0. The whole process is divided into 9 steps (shoveling operation links): lowering the boom, leveling the bucket, punching the shovel, inserting into the pile, raising the bucket at a small angle, raising the boom at a small angle, quickly raising the boom, quickly raising the bucket, and retreating.

[0082] When the decision control sends a signal for mode 1, the state machine process of mode 1 is executed. The entire process is divided into 7 steps (shoveling operation links): lowering the boom, leveling the bucket, punching the shovel, inserting it into the pile, raising the bucket at a large angle, raising the boom at a large angle, and retreating.

[0083] After each round of control, iteratively updating the decision can avoid the fixed learning rate in the online gradient descent method causing the algorithm to get stuck when approaching the local optimal solution. By dynamically adjusting the learning rate, the online gradient descent method can converge to the optimal solution more accurately.

[0084] Figure 9 FIG. 1 is a flow chart of the first mode in some embodiments of the shovel loading control method of a loader according to the present disclosure, as shown in FIG. Figure 9 As shown:

[0085] Step S901: Entering the boom lowering link in the first mode, and controlling the boom angle of the loader to be the target boom angle according to the control parameters corresponding to the boom lowering link.

[0086] The loader is controlled to reach a predetermined distance from the pile, where the predetermined distance can be pre-set according to the decision-making plan and coordination, and the predetermined distance is the optimal shoveling point. The loader is controlled to execute the boom lowering at the optimal shoveling point.

[0087] By solving the target loss function model to output the control parameter x1, the target boom angle can be obtained through actual calibration; when the loader's boom angle reaches the target boom angle based on the loader's state parameters, the second step (bucket leveling link) is executed.

[0088] Step S902: Entering the bucket leveling phase, controlling the bucket angle of the loader to be the target bucket angle according to the control parameters corresponding to the bucket leveling phase.

[0089] By solving the target loss function model to output the control parameter x2, the target bucket angle can be obtained through actual calibration; when the loader's bucket angle reaches the target bucket angle based on the loader's state parameters, the third step (inserting the shovel into the pile) is executed.

[0090] Step S903, entering the shovel insertion into the material pile phase, and controlling the loader to perform the shovel insertion operation according to the control parameters corresponding to the shovel insertion into the material pile phase until the loader's travel torque is within the torque range.

[0091] By solving the target loss function model, the control parameter x3 is output; when the actual control vehicle torque (the loader's travel torque) is between the torque range of 0-50, it indicates that the vehicle has been inserted into the pile, and the fourth step (lifting the bucket at a small angle) is executed.

[0092] Step S904: Entering the small-angle bucket lifting link, and controlling the current angle value of the bucket to increase by a first angle according to the control parameters corresponding to the small-angle bucket lifting link.

[0093] By solving the target loss function model, the control parameter x4 is output. The small angle of the bucket refers to adding the first angle to the current actual angle. The first angle can be 5 degrees, etc. When the change angle of the current angle of the bucket is 5 degrees, the fifth step (small angle lifting boom link) is executed.

[0094] Step S905, enter the small-angle lifting boom link, and control the current angle value of the boom to increase by a second angle according to the control parameters corresponding to the small-angle lifting boom link.

[0095] By solving the target loss function model, the control parameter x5 is output. The small angle of the boom refers to adding a second angle on the basis of the current actual angle. The second angle can be 3 degrees, etc. When the change angle of the current angle value of the boom is 3 degrees, the sixth step (shovel link) is executed; the first angle and the second angle can be set according to actual experience data.

[0096] Step S906, entering the shovel-shoveling phase, controlling the loader to perform the shovel-shoveling operation according to the control parameters corresponding to the shovel-shoveling phase until the vehicle torque is within the torque range;

[0097] By solving the target loss function model, the control parameter x6 is output; when the actual controlled vehicle torque (the loader's traveling torque) is between the torque range of 0-50, it means that the vehicle can no longer move forward.

[0098] Step S907, cycle once or multiple times to enter the small-angle bucket lifting link, small-angle boom lifting link and shovel impact link, and perform corresponding operations.

[0099] Steps S905-S907 may be executed one or more times in a loop. For example, steps S905-S907 may be executed three times in a loop. After the three cycles are completed, step 7 (lifting the bucket and flushing the shovel) is executed.

[0100] Step S908: Entering the bucket lifting and shoveling phase, the bucket angle is controlled to be the bucket setting angle according to the control parameters corresponding to the bucket lifting and shoveling phase.

[0101] The bucket lifting and shovel punching steps are to quickly lift the bucket and punch the shovel at the same time; the control parameter x7 is output by solving the target loss function model; when the bucket angle reaches the bucket setting angle, the eighth step (lifting the boom step) is executed.

[0102] Step S909, enter the boom raising link, and control the boom angle to the boom setting angle based on the control parameters corresponding to the boom raising link.

[0103] The boom lifting link is to quickly lift the boom; the control parameter x8 is output by solving the target loss function model; when the boom angle reaches the boom setting angle, the ninth step (backward link) is executed.

[0104] Step S910: Enter the backward phase, and control the loader to reach a predetermined position according to the control parameters corresponding to the backward phase.

[0105] The control parameter x9 is output by solving the target loss function model; when the retreat reaches the designated position target point (x, y) of the decision plan, the entire first mode is executed.

[0106] In the bucket lifting and shovel punching stages and the boom lifting stages, the first parameter can be determined based on the set angle, the actual angle, and the angle threshold; the second parameter can be determined based on the minimum value of the control parameter, the control parameter, and the angle threshold; the adjustment amount can be determined based on the first parameter and the second parameter; the control parameter can be adjusted based on the adjustment amount to obtain the adjusted control parameter.

[0107] When performing rapid bucket and boom lifting, in order to achieve control stability and avoid oscillation during the control quantity output process, the control quantity performs a ramp-down design when it is about to reach the target set angle.

[0108] The adjusted control parameter x is as follows:

[0109] Among them, x represents the current output control quantity (adjusted control parameter), x minis the minimum value of the current output (the minimum value of the control parameter), which is equivalent to the dead zone value of the hydraulic valve; x7 represents the control quantity (control parameter) solved by the target loss function model in the bucket lifting and shovel punching stages and the boom lifting stages; represents the target setting angle (setting angle), represents the current actual angle (actual angle), Represents the threshold value (angle threshold).

[0110] The first parameter is , the second parameter is .

[0111] Figure 10 FIG. 1 is a flow chart of the second mode in some embodiments of the shovel loading control method of a loader according to the present disclosure, as shown in FIG. Figure 10 As shown:

[0112] Step S1001: Entering the boom lowering link in the second mode, and controlling the boom angle of the loader to be the target boom angle according to the control parameters corresponding to the boom lowering link.

[0113] The loader is controlled to reach a predetermined distance from the pile, where the predetermined distance can be pre-set according to the decision-making plan and coordination, and the predetermined distance is the optimal shoveling point. The loader is controlled to execute the boom lowering at the optimal shoveling point.

[0114] By solving the target loss function model to output the control parameter x1, the target boom angle can be obtained through actual calibration; when the loader's boom angle reaches the target boom angle based on the loader's state parameters, the second step (bucket leveling link) is executed.

[0115] Step S1002, entering the bucket leveling phase, and controlling the bucket angle of the loader to be the target bucket angle according to the control parameters corresponding to the bucket leveling phase.

[0116] By solving the target loss function model to output the control parameter x2, the target bucket angle can be obtained through actual calibration; when the loader's bucket angle reaches the target bucket angle based on the loader's state parameters, the third step (inserting the shovel into the pile) is executed.

[0117] Step S1003: Entering the shovel insertion phase, controlling the loader to perform the shovel insertion operation according to the control parameters corresponding to the shovel insertion phase until the loader's travel torque is within the torque range;

[0118] By solving the target loss function model, the control parameter x3 is output. When the actual controlled vehicle torque (the loader's travel torque) is between the torque range of 0 and 50, it indicates that the vehicle has entered the pile, and the fourth step (lifting the bucket at a large angle) is executed.

[0119] Step S1004: Entering a large-angle bucket raising step, controlling the current angle value of the bucket to increase by a third angle according to control parameters corresponding to the large-angle bucket raising step;

[0120] The control parameter x4 is output by solving the target loss function model; the large angle of the bucket refers to adding a third angle on the basis of the current actual angle, and the third angle can be 10 degrees, etc.; when the change angle of the current angle of the bucket is 10 degrees, execute the fifth step (large angle lifting boom link).

[0121] Step S1005, enter the large-angle lifting boom link, and control the current angle value of the boom to increase by a fourth angle according to the control parameters corresponding to the small-angle lifting boom link.

[0122] The control parameter x5 is output by solving the target loss function model; the large angle of the boom refers to adding the fourth angle on the basis of the current actual angle, and the fourth angle can be 5 degrees, etc.; when the change angle of the current angle value of the boom is 5 degrees, the sixth step (shovel link) is executed, and the third angle and the fourth angle can be set according to the actual angle sensor value.

[0123] Step S1006: Enter the shovel-shoveling phase, and control the loader to perform the shovel-shoveling operation according to the control parameters corresponding to the shovel-shoveling phase until the vehicle torque is within the torque range.

[0124] By solving the target loss function model, the control parameter x6 is output; when the actual control vehicle torque (the loader's traveling torque) is between the torque range of 0-50, it means that the vehicle can no longer move forward.

[0125] Step S1007, looping once or multiple times to enter the small-angle bucket lifting link, small-angle boom lifting link and shovel impact link, and performing corresponding operations until the bucket angle reaches the maximum bucket angle.

[0126] Steps S1005-S1007 can be executed one or more times in a loop. For example, steps S1005-S1007 may be executed n times, where n is determined by the bucket angle. When the bucket angle reaches its maximum angle, the loop terminates and step 7 (backward phase) is executed. The maximum bucket angle can be set based on the type of loader.

[0127] Step S1008, enter the backward phase, and control the loader to reach a predetermined position according to the control parameters corresponding to the backward phase.

[0128] The control parameter x7 is output by solving the target loss function model; when the retreat reaches the designated position target point (x, y) of the decision plan, the entire second mode is executed.

[0129] In some embodiments, after all shoveling operations in the first or second mode are completed, an adjustment coefficient is obtained based on the decay rate and decay time. The learning rate is then adjusted based on the adjustment coefficient. After each round of loader control, the decision-making control parameters are iteratively updated. By dynamically adjusting the learning rate, more accurate convergence to the optimal solution is achieved.

[0130] The state quantities (state parameters) collected by sensors include bucket angle, boom angle, loader position, boom cavity pressure, bucket cavity pressure, torque, speed, material weight in the bucket, etc., as well as the control output quantity (control parameter) of each step at the previous moment. The optimal control quantity is output according to the established objective function model. The learning rate can be dynamically adjusted to enable the algorithm to converge to the optimal solution more accurately.

[0131] By comparing the control effects of linear decay learning rate, exponential decay learning rate and reverse time decay learning rate, exponential decay is more effective in adjusting the learning rate. Therefore, exponential decay is used to adjust the learning rate. The learning rate is dynamically adjusted as follows:

[0132] ;

[0133] in, represents the adjusted learning rate, Represents the initial learning rate or the current learning rate, represents the decay rate, t represents the decay time, which can be time or the number of shovel loading operations performed; the adjustment coefficient is .

[0134] For example, the initial learning rate can be 0.01, the decay rate can be 0.5, and t represents time, which is equivalent to exponentially decreasing with time on the basis of 0.01. The time is 1 second, 2 seconds, 3 seconds, etc., and the final learning rate value is different. The learning rate can be adjusted dynamically.

[0135] The loader shoveling control method in the above embodiment establishes a target loss function model and determines the model constraints based on the decision variables, obtains control parameters based on the target loss function model, and controls the loader operation, which solves the problems of low degree of automation control and high energy consumption in the loader shoveling process. It can ensure the accuracy of the output control parameters and improve work efficiency. It can not only save fuel expenses caused by energy consumption, but also greatly reduce the operating cost of the loader, reduce the operator's workload, improve the work efficiency and safety of the loader, and make the shoveling operation more stable.

[0136] The shoveling control method of the loader in the above embodiment can be applied to manned loaders, unmanned loaders, etc., and can improve work efficiency; based on the different properties of the materials, a shoveling control method based on dry and wet materials is proposed, which can ensure the full bucket rate of the loader during shoveling operations, greatly shortening the operation time; the loader information can be monitored in real time without human participation throughout the process, solving the problem that the loader shoveling operation depends on manual operation handles, which can reduce the operator's work intensity and improve work efficiency and safety; when controlling, a slope descent control method is adopted, and when the target angle is about to be reached, the target current is made to decrease in the direction of the slope until the current is 0 when the target angle is reached, which can solve the problem of oscillation generated during the output of the control quantity and make the control more stable.

[0137] In some embodiments, as Figure 11 As shown, the present disclosure provides a shoveling control device 1100 for a loader, comprising a model building module 1101 , a constraint establishing module 1102 , a link determining module 1103 , a parameter determining module 1104 and a control processing module 1105 .

[0138] The model building module 1101 constructs a target loss function model based on the decision variables of the shoveling control; the constraint building module 1102 determines the model constraints corresponding to the target loss function model, wherein the model constraints include at least one of mechanical performance constraints, working environment constraints, safety constraints, etc.

[0139] The link determination module 1103 determines the control mode according to the type of shoveling material, and determines the shoveling operation link of the loader under the control mode; the parameter determination module 1104 obtains the control parameters corresponding to the shoveling operation link based on the state parameters and model constraints of the loader and the target loss function model; the control processing module 1105 controls the loader to perform corresponding operations in the shoveling operation link based on the state parameters and control parameters.

[0140] In some embodiments, the model construction module 1101 constructs a shoveling efficiency function based on the control decision variables and the bucket energy consumption coefficient, wherein the shoveling efficiency function represents the energy efficiency of the bucket movement of the loader; the model construction module 1101 constructs an energy consumption function based on the control decision variables and the walking energy consumption coefficient, wherein the energy consumption function represents the vehicle driving energy loss of the loader; according to the weight coefficient, the shoveling efficiency function and the energy consumption function are weightedly combined to obtain the target loss function model.

[0141] When entering the shoveling operation phase and, based on the state parameters, determining that the model constraints are met, the parameter determination module 1104 uses the online gradient descent method to solve the target loss function model and determine the corresponding gradient; the parameter determination module 1104 updates the current control parameters of the loader according to the gradient and learning rate to obtain the control parameters.

[0142] After all operations in the shoveling operation link are completed, the parameter determination module 1104 obtains an adjustment coefficient according to the decay rate and the decay time; the parameter determination module 1104 adjusts the learning rate according to the adjustment coefficient.

[0143] The link determination module 1103 determines that the control mode is the first mode when the type of the shoveled material is dry material; the link determination module 1103 determines that the control mode is the second mode when the type of the shoveled material is wet material.

[0144] In some embodiments, as Figure 12 As shown, the control processing module 1105 includes a first processing unit 1107 and a first processing unit 1108. In the first mode, the first processing unit 1107 enters the boom lowering phase and controls the boom angle of the loader to a target boom angle according to the control parameters corresponding to the boom lowering phase. The first processing unit 1107 enters the bucket leveling phase and controls the bucket angle of the loader to a target bucket angle according to the control parameters corresponding to the bucket leveling phase.

[0145] The first processing unit 1107 enters the shovel insertion into the material pile link, and controls the loader to perform the shovel insertion operation according to the control parameters corresponding to the shovel insertion into the material pile link until the loader's walking torque is within the torque range; the first processing unit 1107 enters the small-angle bucket lifting link, and controls the current angle value of the bucket to increase by a first angle according to the control parameters corresponding to the small-angle bucket lifting link.

[0146] The first processing unit 1107 enters the small-angle boom lifting link, and controls the current angle value of the boom to increase by a second angle according to the control parameters corresponding to the small-angle boom lifting link; the first processing unit 1107 enters the shovel flushing link, and controls the loader to perform the shovel flushing operation according to the control parameters corresponding to the shovel flushing link until the vehicle torque is within the torque range.

[0147] The first processing unit 1107 cycles once or multiple times to enter the small-angle bucket lifting link, the small-angle boom lifting link and the flushing shovel link to perform corresponding operations; the first processing unit 1107 enters the bucket lifting and flushing shovel links, and controls the bucket angle to the bucket setting angle according to the control parameters corresponding to the bucket lifting and flushing shovel links.

[0148] The first processing unit 1107 enters the boom raising link, and controls the boom angle to the boom setting angle based on the control parameters corresponding to the boom raising link; the first processing unit 1107 enters the backward link, and controls the loader to reach the predetermined position based on the control parameters corresponding to the backward link.

[0149] The first processing unit 1107 determines the first parameter according to the set angle, actual angle and angle threshold in the bucket lifting and shovel punching stages and the boom lifting stages; the first processing unit 1107 determines the second parameter according to the minimum value of the control parameter, the control parameter and the angle threshold; the first processing unit 1107 determines the adjustment amount according to the first parameter and the second parameter; the first processing unit 1107 adjusts the control parameter according to the adjustment amount to obtain the adjusted control parameter.

[0150] The second processing unit 1108 enters the boom lowering link in the second mode, and controls the boom angle of the loader to be the target boom angle according to the control parameters corresponding to the boom lowering link; the second processing unit 1108 enters the bucket leveling link, and controls the bucket angle of the loader to be the target bucket angle according to the control parameters corresponding to the bucket leveling link.

[0151] The second processing unit 1108 enters the shovel insertion into the material pile link, and controls the loader to perform the shovel insertion operation according to the control parameters corresponding to the shovel insertion into the material pile link until the loader's walking torque is within the torque range; the second processing unit 1108 enters the large-angle bucket lifting link, and controls the current angle value of the bucket to increase by a third angle according to the control parameters corresponding to the large-angle bucket lifting link.

[0152] The second processing unit 1108 enters the large-angle lifting boom link, and controls the current angle value of the boom to increase by a fourth angle according to the control parameters corresponding to the small-angle lifting boom link; the second processing unit 1108 enters the shovel-shoveling link, and controls the loader to perform the shovel-shoveling operation according to the control parameters corresponding to the shovel-shoveling link until the vehicle torque is within the torque range; the second processing unit 1108 cycles once or multiple times to enter the small-angle lifting bucket link, the small-angle lifting boom link and the shovel-shoveling link, and performs corresponding operations until the bucket angle is the maximum bucket angle; the second processing unit 1108 enters the backward link, and controls the loader to reach a predetermined position according to the control parameters corresponding to the backward link.

[0153] In some embodiments, as Figure 13 As shown, the loader shovel control device may include a memory 1301, a processor 1302, a communication interface 1303, and a bus 1304. The memory 1301 is used to store instructions, and the processor 1302 is coupled to the memory 1301. The processor 1302 is configured to execute the instructions stored in the memory 1301 to implement the above-mentioned loader shovel control method.

[0154] Memory 1301 can be high-speed RAM, non-volatile memory, or a memory array. Memory 1301 can also be divided into blocks, which can be combined into virtual volumes according to certain rules. Processor 1302 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the loader loading control method or atmospheric pollution information prediction method disclosed herein.

[0155] In some embodiments, the present disclosure provides a loader, including the shovel loading control device of any of the above embodiments. The loader can be a manned loader, an unmanned loader, etc.

[0156] In some embodiments, the present disclosure provides a computer-readable storage medium storing computer instructions. When the instructions are executed by a processor, the shovel loading control method of a loader as described in any of the above embodiments is implemented.

[0157] Computer-readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples (non-exhaustive) of readable storage media can include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0158] The embodiments of the present disclosure may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0159] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0160] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0161] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0162] It should also be noted that in the apparatus, device, and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0163] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0164] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, it will be understood by those skilled in the art that the above embodiments are merely illustrative and do not limit the scope of the present disclosure. It will be understood by those skilled in the art that the above embodiments may be combined, modified, or replaced without departing from the scope and essence of the present disclosure.

Claims

1. A shovel loading control method for a loader, comprising: According to the decision variables of shovel loading control, the target loss function model is constructed; Determining a model constraint corresponding to the target loss function model, wherein the model constraint includes at least one of a mechanical performance constraint, a working environment constraint, and a safety constraint; Determine a control mode according to the type of shoveled material, and determine the shoveled operation link of the loader under the control mode; According to the state parameters of the loader and the model constraints, the control parameters corresponding to the shoveling operation link are obtained using the target loss function model; According to the state parameters and the control parameters, the loader is controlled to perform corresponding operations in the shoveling operation link.

2. The shovel loading control method according to claim 1, wherein: The target loss function model is constructed based on the decision variables of the shovel loading control, including: Constructing a shoveling efficiency function according to the control decision variables and the bucket energy consumption coefficient, wherein the shoveling efficiency function represents the energy consumption of the bucket movement of the loader; constructing an energy consumption function according to the control decision variables and the travel energy consumption coefficient, wherein the energy consumption function represents the vehicle travel energy loss of the loader; The shoveling efficiency function and the energy consumption function are weightedly combined according to the weight coefficient to obtain the target loss function model.

3. The shovel loading control method according to claim 1, wherein: The mechanical performance constraints include constraints on the bucket angle and / or boom angle of the loader; The working environment constraints include constraints on the shoveling work site of the loader; The safety constraints include torque constraints output by the loader.

4. The shovel loading control method according to claim 1, wherein: The method of obtaining the control parameters corresponding to the shoveling operation link by using the target loss function model according to the state parameters of the loader and the model constraints includes: When entering the shoveling operation phase and, based on the state parameters, determining that the model constraints are satisfied, solving the target loss function model using an online gradient descent method to determine the corresponding gradient; According to the gradient and the learning rate, the current control parameters of the loader are updated to obtain the control parameters.

5. The shovel loading control method according to claim 4, comprising: After all operations in the shoveling operation link are completed, an adjustment coefficient is obtained according to the decay rate and decay time; The learning rate is adjusted according to the adjustment coefficient.

6. The shovel loading control method according to claim 1, wherein: Determining the control mode according to the type of shoveled material includes: When the type of the shoveled material is dry material, determining the control mode to be the first mode; In a case where the type of the shoveled material is wet material, the control mode is determined to be the second mode.

7. The shovel loading control method according to claim 6, wherein: The shoveling operation steps of the loader in the first mode include: adjusting the boom, leveling the bucket, inserting the shovel into the pile, raising the bucket at a small angle, raising the boom at a small angle, shoveling, raising the bucket, shoveling, raising the boom, and retreating.

8. The shovel loading control method according to claim 7, wherein: The controlling the loader to perform corresponding operations in the shoveling operation according to the state parameter and the control parameter includes: Entering the boom lowering link in the first mode, and controlling the boom angle of the loader to be a target boom angle according to control parameters corresponding to the boom lowering link; Entering the bucket leveling step, controlling the bucket angle of the loader to a target bucket angle according to control parameters corresponding to the bucket leveling step; Entering the shovel insertion phase, controlling the loader to perform the shovel insertion operation according to control parameters corresponding to the shovel insertion phase until the travel torque of the loader is within the torque range; Entering the small-angle bucket lifting phase, controlling the current angle value of the bucket to increase by a first angle according to the control parameters corresponding to the small-angle bucket lifting phase; Entering the small-angle boom raising link, controlling the current angle value of the boom to increase by a second angle according to the control parameters corresponding to the small-angle boom raising link; Entering the shoveling stage, controlling the loader to perform a shoveling operation according to control parameters corresponding to the shoveling stage until the vehicle torque is within the torque range; Cycle once or multiple times to enter the small-angle bucket lifting link, the small-angle boom lifting link, and the shovel impacting link to perform corresponding operations; Entering the bucket lifting and shoveling step, controlling the bucket angle to a bucket setting angle according to control parameters corresponding to the bucket lifting and shoveling step; Entering the boom raising link, and controlling the boom angle to the boom setting angle based on the control parameters corresponding to the boom raising link; Entering the backward link, the loader is controlled to reach a predetermined position according to the control parameters corresponding to the backward link.

9. The method of claim 8, further comprising: In the bucket lifting and shovel flushing steps and the boom lifting step, a first parameter is determined according to a set angle, an actual angle, and an angle threshold; determining a second parameter according to the minimum value of the control parameter, the control parameter, and the angle threshold; determining an adjustment amount according to the first parameter and the second parameter; The control parameter is adjusted according to the adjustment amount to obtain the adjusted control parameter.

10. The shovel loading control method according to claim 6, wherein: The shoveling operation steps of the loader in the second mode include: adjusting the boom, leveling the bucket, inserting the shovel into the pile, raising the bucket at a large angle, raising the boom at a large angle, shoveling, and retreating.

11. The shovel loading control method according to claim 10, wherein: Entering the boom lowering link in the second mode, and controlling the boom angle of the loader to a target boom angle according to control parameters corresponding to the boom lowering link; Entering the bucket leveling step, controlling the bucket angle of the loader to a target bucket angle according to control parameters corresponding to the bucket leveling step; Entering the shovel insertion phase, controlling the loader to perform the shovel insertion operation according to control parameters corresponding to the shovel insertion phase until the travel torque of the loader is within the torque range; Entering the large-angle bucket lifting phase, controlling the current angle value of the bucket to increase by a third angle according to the control parameters corresponding to the large-angle bucket lifting phase; Entering the large-angle boom raising link, controlling the current angle value of the boom to increase by a fourth angle according to the control parameters corresponding to the small-angle boom raising link; Entering the shoveling stage, controlling the loader to perform a shoveling operation according to control parameters corresponding to the shoveling stage until the vehicle torque is within the torque range; Cycle once or multiple times to enter the small-angle bucket lifting link, the small-angle boom lifting link, and the shovel punching link, and perform corresponding operations until the bucket angle reaches the maximum bucket angle; Entering the backward link, the loader is controlled to reach a predetermined position according to the control parameters corresponding to the backward link.

12. The shovel loading control method according to any one of claims 1 to 11, wherein: The decision variables and the control parameters include: the current output to the bucket, the current output to the boom, and the travel torque of the loader; The state parameters include: bucket angle, boom angle, loader position, and vehicle torque of the loader.

13. A shovel loading control device for a loader, comprising: A model building module is used to build a target loss function model based on the decision variables of shovel loading control; a constraint establishing module, configured to determine a model constraint corresponding to the target loss function model, wherein the model constraint comprises at least one of a mechanical performance constraint, a working environment constraint, and a safety constraint; A link determination module is used to determine a control mode according to the type of shovel material and determine the shovel operation link of the loader under the control mode; a parameter determination module, configured to obtain control parameters corresponding to the shoveling operation link using the target loss function model according to the state parameters of the loader and the model constraints; A control processing module is used to control the loader to perform corresponding operations in the shoveling operation link according to the state parameters and the control parameters.

14. A shovel loading control device for a loader, comprising: Memory; and a processor coupled to the memory, wherein the processor is configured to execute the method according to any one of claims 1 to 11 based on instructions stored in the memory.

15. A loader comprising: The shovel loading control device of a loader according to claim 13 or 14. 16 . A computer-readable storage medium storing computer instructions, wherein the instructions are executed by a processor to implement the steps of the method according to claim 1 .

17. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images