Parameter prediction method and apparatus, model training method and apparatus, and loader

Abstract

The present disclosure relates to the technical field of engineering machinery. Provided are a parameter prediction method and apparatus, a model training method and apparatus, and a loader. The prediction method comprises: determining the current operating condition of a loader; acquiring operating data of the loader at the current first moment under the current operating condition; and inputting the operating data into a machine learning model corresponding to the current operating condition, so as to predict the state of charge of a battery of the loader at a second moment and the vehicle speed of the loader at the second moment, the second moment being later than the first moment, wherein the current operating condition is one of a plurality of operating conditions, and a machine learning model corresponding to one of at least two operating conditions is different from a machine learning model corresponding to the other.

Description

Parameter prediction method and device, model training method and device, and loader

[0001] Cross-reference to related applications

[0002] The present disclosure is based on and claims priority to the application with Chinese Application No. 202411796229.0 and filing date of December 6, 2024, the disclosure of which is hereby incorporated by reference in its entirety into the present disclosure. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of engineering machinery, and in particular to a parameter prediction method and device, a model training method and device, and a loader. BACKGROUND

[0004] The loader is a kind of engineering machinery widely used in construction. The main function of the loader is to load and unload soil, sand and other bulk materials. SUMMARY

[0005] According to an aspect of an embodiment of the present disclosure, a parameter prediction method is provided, including determining a current working condition of a loader; obtaining working data of the loader at a first time point in the current working condition; and inputting the working data into a machine learning model corresponding to the current working condition to predict a state of charge of a battery of the loader at a second time point and a vehicle speed at the second time point, the second time point being after the first time point, wherein the current working condition is one of a plurality of working conditions, and a machine learning model corresponding to one of the at least two working conditions is different from a machine learning model corresponding to another of the at least two working conditions.

[0006] In some embodiments, the working data includes one or more of a vehicle speed, a gear position, an accelerator pedal opening degree, a brake pedal opening degree, and a walking motor power.

[0007] In some embodiments, the determining of the current working condition of the loader includes determining the current working condition of the loader according to a pressure value of a working pump of the loader, the working pump being used to drive at least one of a steering cylinder of the loader, a bucket cylinder of the loader, and a boom cylinder of the loader.

[0008] In some embodiments, the determining the current working condition of the loader according to the pressure value of the working pump of the loader comprises: in a case where the pressure value of the working pump is greater than a first preset pressure value, determining the current working condition as one of a first group of working conditions, the first group of working conditions comprising one or more of a first working condition, a second working condition, a third working condition, a fourth working condition, and a fifth working condition, wherein: in the first working condition, the working phases of the loader in time sequence comprise, in order: an empty forward travel phase of straight-line travel, a loading operation phase, a loaded backward travel phase of straight-line travel, and a loaded forward travel phase of curved-line travel; in the second working condition, the working phases of the loader in time sequence comprise, in order: the empty forward travel phase of straight-line travel, the loading operation phase, the loaded backward travel phase of straight-line travel, and the loaded forward travel phase of straight-line travel; in the third working condition, the working phases of the loader in time sequence comprise, in order: an empty forward travel phase of curved-line travel, the loading operation phase, a loaded backward travel phase of curved-line travel, and a loaded forward travel phase of curved-line travel; in the fourth working condition, the working phases of the loader in time sequence comprise, in order: the empty forward travel phase of straight-line travel, the loading operation phase, a loaded backward travel phase of curved-line travel, and the loaded forward travel phase of straight-line travel; and in the fifth working condition, the working phases of the loader in time sequence comprise, in order: the empty forward travel phase, the loading operation phase, and an unloading phase.

[0009] In some embodiments, the determining the current working condition as one of the first group of working conditions in the case where the pressure value of the working pump is greater than the first preset pressure value comprises: in a case where a first condition is met, determining the current working condition as the third working condition, wherein the first condition comprises: the loader performs the loading operation after the empty forward travel, and a displacement of a steering cylinder of the loader during the empty forward travel of the loader is not equal to a first preset displacement amount.

[0010] In some embodiments, the determining the current working condition as one of the first group of working conditions in the case where the pressure value of the working pump is greater than the first preset pressure value comprises: in a case where a second condition is met, determining the current working condition as any one of the first group of working conditions except the third working condition, wherein the second condition comprises: the loader performs the loading operation after the empty forward travel, and the displacement of the steering cylinder of the loader during the empty forward travel of the loader is equal to the first preset displacement amount.

[0011] In some embodiments, the determining the current working condition as any one of the first group of working conditions except the third working condition in the case that the second condition is met comprises at least one of the following: determining the current working condition as the fifth working condition in the case that the loader performs unloading after performing the loading operation; determining the current working condition as the fourth working condition in the case that a third condition is met; determining the current working condition as the second working condition in the case that a fourth condition is met; and determining the current working condition as the first working condition in the case that a fifth condition is met; wherein the third condition comprises that the loader backs up with load after performing the loading operation, and the steering cylinder displacement is not equal to the first preset displacement during the backing up with load; the fourth condition comprises that the loader sequentially performs the backing up with load and the forward driving with load after performing the loading operation, and the steering cylinder displacement is equal to the first preset displacement during the backing up with load and the forward driving with load; the fifth condition comprises that the loader sequentially performs the backing up with load and the forward driving with load after performing the loading operation, the steering cylinder displacement is equal to the first preset displacement during the backing up with load, and the steering cylinder displacement is not equal to the first preset displacement during the forward driving with load.

[0012] In some embodiments, the determining the current working condition of the loader according to the pressure value of the working pump of the loader comprises: determining the current working condition as one of a second group of working conditions in the case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0, the second group of working conditions comprising one or more of a straight driving working condition, a non-horizontal driving working condition, and a steering driving working condition, the straight driving working condition comprising at least one of a first straight driving working condition and a second straight driving working condition, the non-horizontal driving working condition comprising at least one of an uphill driving working condition and a downhill driving working condition, the vehicle speed of the first straight driving working condition being greater than a first preset vehicle speed, and the vehicle speed of the second straight driving working condition being less than or equal to the first preset vehicle speed.

[0013] In some embodiments, the determining that the current working condition is one of the second group of working conditions in the case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0 comprises at least one of the following: determining that the current working condition is the steering travel working condition in the case that the steering cylinder displacement of the loader is not equal to a first preset displacement amount; determining that the current working condition is the uphill travel working condition in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is not 0, and the accelerator pedal opening degree is greater than a first preset opening degree; determining that the current working condition is the downhill travel working condition in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is not 0, and the accelerator pedal opening degree is equal to the first preset opening degree; determining that the current working condition is the first straight-line travel working condition in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is 0, and the vehicle speed is greater than the first preset speed; and determining that the current working condition is the second straight-line travel working condition in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is 0, and the vehicle speed is less than or equal to the first preset speed.

[0014] According to still another aspect of the embodiments of the present disclosure, a training method of a model is provided, comprising: obtaining working data of a first loader in a preset working condition at a third time; obtaining a state of charge of a battery of the first loader in the preset working condition at a fourth time and a vehicle speed at the fourth time, the fourth time being after the third time; and training a machine learning model corresponding to the preset working condition by taking the working data at the third time as input and taking the state of charge at the fourth time and the vehicle speed at the fourth time as output, wherein the preset working condition is one of a plurality of working conditions, and a machine learning model corresponding to one of the at least two working conditions is different from a machine learning model corresponding to another of the at least two working conditions.

[0015] In some embodiments, working data of a second loader in which the machine learning model is deployed in a current working condition is obtained at a fifth time, the preset working condition including the current working condition; a state of charge of a battery of the second loader in the preset working condition is obtained at a sixth time and a vehicle speed at the sixth time, the sixth time being after the fifth time; and the machine learning model corresponding to the current working condition is trained by taking the working data at the fifth time as input and taking the state of charge at the sixth time and the vehicle speed at the sixth time as output.

[0016] In some embodiments, the second loader is different from the first loader.

[0017] In some embodiments, the working data comprises one or more of a vehicle speed, a gear position, an accelerator pedal opening degree, a brake pedal opening degree, and a walking motor power.

[0018] In some embodiments, the preset working conditions include a straight traveling working condition, the straight traveling working condition includes a first straight traveling working condition and a second straight traveling working condition, a vehicle speed of the first straight traveling working condition is greater than a first preset vehicle speed, a vehicle speed of the second straight traveling working condition is less than or equal to the first preset vehicle speed, and a machine learning model corresponding to the first straight traveling working condition is different from a machine learning model corresponding to the second straight traveling working condition.

[0019] In some embodiments, the working data further includes a slope angle, the preset working conditions include a non-horizontal traveling working condition, the non-horizontal traveling working condition includes at least one of an uphill traveling working condition and a downhill traveling working condition, and a machine learning model corresponding to the uphill traveling working condition is different from a machine learning model corresponding to the downhill traveling working condition.

[0020] In some embodiments, the working data further includes one or more of a heading angle, a steering cylinder displacement, and a steering cylinder pressure, and the preset working conditions include a steering traveling working condition.

[0021] In some embodiments, the working data further includes one or more of a bucket cylinder displacement, a boom cylinder displacement, a bucket cylinder pressure, a boom cylinder pressure, and a working motor power, and the preset working conditions include at least one of a second working condition and a fifth working condition, wherein: in the second working condition, working phases of the loader include, in chronological order, an empty forward traveling phase of straight traveling, a loading working phase, a loaded backward traveling phase of straight traveling, and a loaded forward traveling phase of straight traveling; and in the fifth working condition, working phases of the loader include, in chronological order, the empty forward traveling phase, the loading working phase, and an unloading phase.

[0022] In some embodiments, the preset working conditions include at least one of a first working condition, a third working condition, and a fourth working condition, and the working data further include one or more of a heading angle, a bucket cylinder displacement, a boom cylinder displacement, a steering cylinder displacement, a bucket cylinder pressure, a boom cylinder pressure, a steering cylinder pressure, and a working motor power, wherein: in the first working condition, the working phases of the loader sequentially include, in time sequence, a straight-line traveling empty advancing phase, a bucket loading working phase, a straight-line traveling loaded retreating phase, and a curved-line traveling loaded advancing phase; in the third working condition, the working phases of the loader sequentially include, in time sequence, a curved-line traveling empty advancing phase, a bucket loading working phase, a curved-line traveling loaded retreating phase, and a curved-line traveling loaded advancing phase; and in the fourth working condition, the working phases of the loader sequentially include, in time sequence, a straight-line traveling empty advancing phase, a bucket loading working phase, a curved-line traveling loaded retreating phase, and a straight-line traveling loaded advancing phase.

[0023] According to still another aspect of the embodiments of the present disclosure, a parameter prediction device is provided, including a module configured to perform the prediction method of any one of the above embodiments.

[0024] According to still another aspect of the embodiments of the present disclosure, a model training device is provided, including a module configured to perform the training method of any one of the above embodiments.

[0025] According to still another aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory and a processor coupled to the memory, the processor being configured to perform the method of any one of the above embodiments based on instructions stored in the memory.

[0026] According to still another aspect of the embodiments of the present disclosure, a loader is provided, including at least one of the parameter prediction device of any one of the above embodiments, the model training device of any one of the above embodiments, and the electronic device of any one of the above embodiments.

[0027] In some embodiments, the loader further includes: a first sensor installed on a steering cylinder of the loader and configured to acquire a steering cylinder displacement and a steering cylinder pressure of the loader; a second sensor installed on a bucket cylinder of the loader and configured to acquire a bucket cylinder displacement and a bucket cylinder pressure of the loader; a third sensor installed on a boom cylinder of the loader and configured to acquire a boom cylinder displacement and a boom cylinder pressure of the loader; and an inertial navigation system configured to acquire a heading angle of the loader.

[0028] According to still another aspect of the embodiments of the present disclosure, a computer readable storage medium is provided, including computer program instructions, wherein the computer program instructions, when executed by a processor, implement the steps of the method according to any one of the preceding embodiments.

[0029] According to still another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of the preceding embodiments.

[0030] According to still another aspect of the embodiments of the present disclosure, a computer program is provided, wherein the computer program, when executed by a processor, implements the method according to any one of the preceding embodiments.

[0031] In the embodiments of the present disclosure, the current working condition of the loader is one of the plurality of working conditions, and the machine learning models corresponding to the at least two different working conditions are different. By inputting the working data of the loader at the first time in the current working condition into the machine learning model corresponding to the current working condition of the loader, the SOC of the battery of the loader at the second time after the first time and the speed of the loader at the second time can be predicted, so that the SOC of the battery of the loader and the speed of the loader after the current time in the current working condition can be accurately predicted.

[0032] The technical solutions of the present disclosure will be further described in detail below with the aid of the accompanying drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, brief descriptions will be given below of the drawings needed in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present disclosure, and other drawings can also be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0034] FIG. 1 is a flowchart of a parameter prediction method according to some embodiments of the present disclosure.

[0035] FIG. 2A is a schematic diagram of a first working condition according to some embodiments of the present disclosure.

[0036] FIG. 2B is a schematic diagram of a second working condition according to some embodiments of the present disclosure.

[0037] FIG. 2C is a schematic diagram of a third working condition according to some embodiments of the present disclosure.

[0038] FIG. 2D is a schematic diagram of a fourth working condition according to some embodiments of the present disclosure.

[0039] FIG. 3 is a flowchart of a model training method according to some embodiments of the present disclosure.

[0040] FIG. 4 is a structural schematic diagram of a parameter prediction apparatus according to some embodiments of the present disclosure.

[0041] FIG. 5 is a structural schematic diagram of a model training apparatus according to some embodiments of the present disclosure.

[0042] FIG. 6 is a structural schematic diagram of an electronic device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present disclosure.

[0044] Unless specifically stated, the relative arrangement of the components and steps, numerical expressions, and numerical values set forth in the various embodiments described herein are not limiting.

[0045] Meanwhile, it should be understood that the sizes of the various portions shown in the drawings are not necessarily drawn to scale.

[0046] Techniques, methods, and apparatus known to those of ordinary skill in the relevant art can not be discussed in detail herein. However, where appropriate, the described techniques, methods, and apparatus should be considered as being part of the specification.

[0047] In all the examples shown and discussed herein, any specific values should be interpreted as merely illustrative and not as a limitation. Thus, other examples of the example embodiments can have different values.

[0048] It should be noted that like reference numerals and letters refer to like items in the following drawings and that, as such, a discussion of some items in one drawing should not be further discussed in subsequent drawings.

[0049] In addition, in the description of the present disclosure, the terms "first", "second", "third", and the like are used only for descriptive purposes, and should not be construed as indicating or implying relative importance and sequence. Similarly, although the operations are depicted in a particular order in the drawings, this should not be understood as requiring the operations to be performed in the particular order shown or in sequential order, or requiring all of the illustrated operations to be performed to achieve the desired result. In some cases, multi-task processing and parallel processing can be advantageous.

[0050] In the related art, the state of charge (SOC) of the battery of the loader and the speed of the loader cannot be accurately predicted.

[0051] It is found through analysis that there are various working conditions of the loader when the loader is working. In the related art, the SOC of the battery of the loader and the speed of the loader in the future cannot be accurately obtained when the loader is working. That is, the SOC of the battery of the loader and the speed of the loader cannot be accurately predicted.

[0052] To solve the above problems, the embodiments of the present disclosure propose the following solutions.

[0053] FIG. 1 is a flowchart of a parameter prediction method according to some embodiments of the present disclosure.

[0054] In step 102, the current working condition of the loader is determined.

[0055] In some embodiments, according to one or more of the working route and the working parameters of the loader when the loader is working, it can be determined which working condition the loader is currently in.

[0056] In step 104, the working data of the loader in the current first time in the current working condition is obtained.

[0057] It should be understood that the working data is the data generated by the loader when the loader is working, and the working data in the current time is related to the SOC of the battery of the loader and the speed of the loader in the time after the current time.

[0058] In step 106, the working data of the loader in the current first time in the current working condition is input into the machine learning model corresponding to the current working condition to predict the SOC of the battery of the loader in the second time and the speed of the loader in the second time.

[0059] Here, the second time is after the first time. The second time can be any time after the first time.

[0060] That is, there are at least two working conditions in the multiple working conditions in which the machine learning models are different, the current working condition is one of the multiple working conditions of the loader, and the machine learning model corresponding to one of the at least two working conditions is different from the machine learning model corresponding to the other of the at least two working conditions.

[0061] As some implementations, the second time has a preset time interval from the first time. For example, the preset time interval is a fixed time interval; for another example, the preset time interval is a dynamically changing time interval.

[0062] In the above embodiment, the current working condition of the loader is one of the plurality of working conditions, and the machine learning model corresponding to the different at least two working conditions is different. By inputting the working data of the first time of the loader in the current working condition into the machine learning model corresponding to the current working condition of the loader, the SOC of the battery and the vehicle speed of the loader at the second time after the first time can be predicted, so that the SOC of the battery and the vehicle speed of the loader after the current time in the current working condition can be accurately predicted.

[0063] In some embodiments, the working data includes one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power.

[0064] As some implementations, the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power can be obtained by using a controller area network (CAN) bus of the loader.

[0065] For example, the working data includes the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, or the walking motor power; for another example, the working data includes any two of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power; for yet another example, the working data includes any three of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power; for still another example, the working data includes any four of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power; for yet another example, the working data includes the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power.

[0066] In the above embodiment, the working data includes one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power, and by establishing the correlation between such working data and the SOC of the battery and the vehicle speed of the loader, the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader.

[0067] As some implementations, the plurality of working conditions include a working condition and a driving condition. It can be understood that in the working condition, the loader not only performs work (for example, performs a shovel loading operation, unloading, etc.), but also travels; in the driving condition, the loader only travels and does not perform other additional work, etc.

[0068] As some implementations, the working condition can include one or more of a first working condition, a second working condition, a third working condition, a fourth working condition, and a fifth working condition.

[0069] For example, the first working condition can be a V-shaped working condition; for another example, the second working condition can be an I-shaped working condition; for yet another example, the third working condition can be a T-shaped working condition; for still another example, the fourth working condition can be an L-shaped working condition; for yet another example, the fifth working condition can be a stacking working condition.

[0070] As some embodiments, the driving working conditions can include one or more of a straight driving working condition, a non-horizontal driving working condition, and a turning driving working condition. For example, the straight driving working condition includes at least one of a high-speed straight driving working condition and a low-speed straight driving working condition; for another example, the non-horizontal driving working condition includes at least one of an uphill driving working condition and a downhill driving working condition.

[0071] Next, the first working condition, the second working condition, the third working condition, and the fourth working condition in the working conditions are introduced in conjunction with FIGS. 2A-2D. Here, the loader 202 needs to load material from the working platform 201 and unload the material to the dump truck 203.

[0072] FIG. 2A is a schematic diagram of the first working condition according to some embodiments of the present disclosure.

[0073] As shown in FIG. 2A, in the first working condition, the working stages of the loader 202 in time sequence include: a straight driving empty advancing stage 2021a, a shovel loading working stage (not shown), a straight driving loaded retreating stage 2022a, and a curve driving loaded advancing stage 2023a. In some other embodiments, in the first working condition, the working stages of the loader 202 further include a curve driving empty retreating stage 2024a after the curve driving loaded advancing stage 2023a.

[0074] As some embodiments, the loaded can refer to the presence of material in the bucket of the loader, and the empty can refer to the absence of material in the bucket of the loader.

[0075] As some embodiments, the shovel loading working can represent the process of loading material in the bucket of the loader.

[0076] As some embodiments, there is an included angle a between the center line of the dump truck 203 and the working platform 201. For example, a is 50-55 degrees.

[0077] As some embodiments, in the straight driving loaded retreating stage 2022a, the loader 202 backs off the working platform 201.

[0078] As some embodiments, after the straight driving loaded retreating stage 2022a and before the curve driving loaded advancing stage 2023a, the front frame of the loader 202 is turned to the direction of the dump truck 203. For example, the angle of the turning is 35-45 degrees.

[0079] FIG. 2B is a schematic diagram of a second work condition, according to some embodiments of the present disclosure.

[0080] As shown in FIG. 2B, in the second work condition, the work phases of the loader 202 in time sequence include: a straight-line driving empty advancing phase 2021b, a shovel loading work phase (not shown), a straight-line driving loaded retreating phase 2022b, and a straight-line driving loaded advancing phase 2023b. In other embodiments, in the second work condition, the work phases of the loader 202 further include a straight-line driving empty retreating phase 2024b after the straight-line driving loaded advancing phase 2023b.

[0081] As some implementations, the dump truck 203 reciprocates advancing and retreating, and the orientation of the head of the dump truck 203 is crossed with the orientation of the head of the loader 202. The crossing angle is, for example, 90 degrees.

[0082] As some implementations, in the straight-line driving loaded retreating phase 2022b, the loader 202 backs off the work platform 201. As other implementations, in the straight-line driving empty retreating phase 2024b, the loader 202 backs off the dump truck 203.

[0083] FIG. 2C is a schematic diagram of a third work condition, according to some embodiments of the present disclosure.

[0084] As shown in FIG. 2C, in the third work condition, the work phases of the loader 202 in time sequence include: a curve driving empty advancing phase 2021c, a shovel loading work phase (not shown), a curve driving loaded retreating phase 2022c, and a curve driving loaded advancing phase 2023c. In other embodiments, in the third work condition, the work phases of the loader 202 further include a curve driving empty retreating phase 2024c after the curve driving loaded advancing phase 2023c.

[0085] As some implementations, the orientation of the head of the dump truck 203 is parallel to the orientation of the head of the loader 202 at the beginning of the curve driving empty advancing phase 2021c, and the distance from the center of gravity of the dump truck 203 to the work platform 201 is greater than the distance from the center of gravity of the loader 202 to the work platform 201.

[0086] FIG. 2D is a schematic diagram of a fourth work condition, according to some embodiments of the present disclosure.

[0087] As shown in FIG. 2D, in the fourth working condition, the working phases of the loader 202 in time sequence include: the empty forward traveling phase 2021d along a straight line, the loading operation phase (not shown), the loaded backward traveling phase 2022d along a curve, and the loaded forward traveling phase 2023d along a straight line. In other embodiments, in the fourth working condition, the working phases of the loader 202 further include the empty backward traveling phase 2024d along a curve after the loaded forward traveling phase 2023d along a straight line.

[0088] As some embodiments, the orientation of the front of the dump truck 203 is parallel to the orientation of the front of the loader 202 at the beginning of the empty forward traveling phase 2021d along a straight line.

[0089] As some embodiments, the loader 202 backs up and turns after loading the material at the working platform 201, and then travels forward to unload the material at the dump truck 203, backs up and turns after unloading the material. The angle of turning is, for example, 90 degrees.

[0090] Next, the fifth working condition is introduced in combination with some embodiments of the present disclosure. Here, in the fifth working condition, the loader needs to gather the material at the working platform into a pile.

[0091] As some embodiments, in the fifth working condition, the working phases of the loader in time sequence include: the empty forward traveling phase, the loading operation phase, and the unloading phase.

[0092] Next, how to determine the working phases of the loader is introduced in combination with some embodiments of the present disclosure.

[0093] Table 1

[0094] In some embodiments, as shown in Table 1, P C represents the current bucket cylinder pressure, P C0 represents the second preset pressure value, L d represents the current boom cylinder displacement, L d0 represents the second preset displacement value. For example, the second preset pressure value represents the initial pressure value of the bucket cylinder, i.e. the pressure value when the bucket cylinder is in a non-working state; for another example, the second preset displacement value represents the initial displacement amount of the boom cylinder, i.e. the displacement amount of the piston of the boom cylinder when the boom cylinder is in a non-working state.

[0095] As some embodiments, in the case that the gear of the loader is the forward gear, and P C = P C0 , it is determined that the loader is in the empty forward traveling phase.

[0096] As some embodiments, when the gear of the loader is forward gear, P C > P C0 , and L d = L d0 , it is determined that the loader is in the loading operation stage.

[0097] As some embodiments, when the gear of the loader is reverse gear, and P C > P C0 , it is determined that the loader is in the loaded reverse stage.

[0098] As some embodiments, when the gear of the loader is forward gear, P C > P C0 , and L d > L d0 , it is determined that the loader is in the loaded forward stage.

[0099] As some embodiments, when the gear of the loader is reverse gear, and P C = P C0 , it is determined that the loader is in the unloaded reverse stage.

[0100] As some embodiments, when the gear of the loader is neutral gear, P C > P C0 , and L d > L d0 , it is determined that the loader is in the unloading stage.

[0101] In the above embodiments, the operation stage of the loader can be accurately determined through the gear of the loader, the bucket cylinder pressure and the boom cylinder displacement, so as to help accurately determine the current working condition of the loader in combination with the operation stage of the loader, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader.

[0102] In some embodiments, the machine learning models corresponding to the plurality of working conditions are different from each other. That is, each working condition has a machine learning model unique to the working condition. In this way, the SOC of the battery and the vehicle speed of the loader in each working condition can be more accurately predicted.

[0103] In some embodiments, the current working condition of the loader is determined according to the pressure value of a working pump of the loader. Here, the working pump is used to drive at least one of the steering cylinder of the loader, the bucket cylinder of the loader and the boom cylinder of the loader.

[0104] For example, the working pump is used to drive the steering cylinder of the loader, the bucket cylinder of the loader, or the boom cylinder of the loader; for another example, the working pump is used to drive any two of the steering cylinder of the loader, the bucket cylinder of the loader, and the boom cylinder of the loader; for yet another example, the working pump is used to drive the steering cylinder of the loader, the bucket cylinder of the loader, and the boom cylinder of the loader.

[0105] It should be understood that the steering cylinder of the loader is used to drive the steering of the loader, the bucket cylinder of the loader is used to drive the lifting and tilting of the bucket, and the boom cylinder of the loader is used to drive the movement of the mechanical arm of the loader.

[0106] In the above embodiment, according to the pressure value of the working pump of the loader, it can be determined whether at least one of the steering cylinder of the loader, the bucket cylinder of the loader, and the boom cylinder of the loader is in a driven state, thereby helping to determine the current working condition of the loader, so that the machine learning model accurately predicts the SOC of the battery and the vehicle speed of the loader.

[0107] In some embodiments, in a case where the pressure value of the working pump is greater than the first preset pressure value, it is determined that the current working condition is one of a first group of working conditions, and here, the first group of working conditions includes one or more of the first working condition, the second working condition, the third working condition, the fourth working condition, and the fifth working condition.

[0108] For example, the first group of working conditions includes the first working condition, the second working condition, the third working condition, the fourth working condition, or the fifth working condition. For another example, the first group of working conditions includes any two, any three, any four, or all of the first working condition, the second working condition, the third working condition, the fourth working condition, and the fifth working condition.

[0109] As some implementations, the first preset pressure value is an initial pressure value of the working pump, i.e., a pressure value when the loader is in a non-working state. That is, in a case where the pressure value of the working pump is greater than the first preset pressure value, it is determined that the working pump is in a working state, i.e., the working pump is in a state of driving at least one of the steering cylinder of the loader, the bucket cylinder of the loader, and the boom cylinder of the loader.

[0110] In the above embodiment, by the size relationship between the pressure value of the working pump and the first preset pressure value, it can be accurately determined whether at least one of the steering cylinder of the loader, the bucket cylinder of the loader, and the boom cylinder of the loader is in a driven state, thereby helping to accurately determine the current working condition of the loader, so that the machine learning model more accurately predicts the SOC of the battery and the vehicle speed of the loader.

[0111] Next, how to determine which working condition in the first group of working conditions the current working condition is will be introduced in combination with some embodiments of the present disclosure.

[0112] In some embodiments, the current working condition is determined as the third working condition if the first condition is met, for example, the current working condition is determined as the T-shaped operation working condition.

[0113] Here, the first condition includes that the loader performs the loading operation after the empty forward movement, and that the displacement of the steering cylinder of the loader is not equal to a first preset displacement during the empty forward movement of the loader. For example, the first preset displacement is the initial displacement of the steering cylinder, that is, the displacement of the piston of the steering cylinder when the steering cylinder is in a non-working state.

[0114] In the above embodiments, in the case where it is determined that the loader enters the loading operation stage from the empty forward movement stage along the curve, the current working condition of the loader can be accurately determined as the third working condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader for this working condition.

[0115] In some embodiments, the current working condition is determined as any one working condition in the first group of working conditions except the third working condition if the second condition is met.

[0116] Here, the second condition includes that the loader performs the loading operation after the empty forward movement, and that the displacement of the steering cylinder of the loader is equal to the first preset displacement during the empty forward movement of the loader.

[0117] That is, in the other working conditions in the first group of working conditions except the third working condition, the loader enters the loading operation stage after the empty forward movement stage, and the displacement of the steering cylinder of the loader is equal to the first preset displacement when in the empty forward movement stage. That is, the other working conditions in the first group of working conditions except the third working condition (in the case of including multiple working conditions) have commonalities.

[0118] In the above embodiments, in the case where it is determined that the current working condition of the loader is not the third working condition, the machine learning model of any one working condition other than the third working condition can be used to quickly predict the SOC of the battery and the vehicle speed of the loader.

[0119] Next, how to further determine which working condition the current working condition of the loader is in the case where it is determined that the current working condition of the loader is not the third working condition is described in combination with some embodiments.

[0120] In some embodiments, the current working condition is determined as the fifth working condition if the second condition is met and the loader performs the unloading operation after the loading operation. For example, the current working condition is determined as the stacking operation working condition.

[0121] In the above embodiment, in a case where it is determined that the loader enters the loading operation phase from the empty forward driving phase along the straight line and enters the unloading phase from the loading operation phase, the current working condition of the loader can be accurately determined as the stacking operation working condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader for the working condition.

[0122] In some embodiments, in a case where the second condition and a third condition are met, the current working condition is determined as a fourth working condition, for example, the current working condition is determined as the L-shaped operation working condition.

[0123] Here, the third condition includes that the loader performs loaded backward driving after the loading operation, and that the steering cylinder displacement is not equal to the first preset displacement during the loaded backward driving of the loader.

[0124] In the above embodiment, in a case where it is determined that the loader enters the loading operation phase from the empty forward driving phase along the straight line and enters the loaded backward driving phase along the curve from the loading operation phase, the current working condition of the loader can be accurately determined as the fourth working condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader for the working condition.

[0125] In some embodiments, in a case where the second condition and a fourth condition are met, the current working condition is determined as the second working condition, for example, the current working condition is determined as the I-shaped operation working condition.

[0126] Here, the fourth condition includes that the loader sequentially performs loaded backward driving and loaded forward driving after the loading operation. Here, the steering cylinder displacement is equal to the first preset displacement during the loaded backward driving and the loaded forward driving of the loader.

[0127] In the above embodiment, in a case where it is determined that the loader enters the loading operation phase from the empty forward driving phase along the straight line, enters the loaded backward driving phase along the straight line from the loading operation phase, and enters the loaded forward driving phase along the straight line from the loaded backward driving phase, the current working condition of the loader can be accurately determined as the second working condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader for the working condition.

[0128] In some embodiments, in a case where the second condition and a fifth condition are met, the current working condition is determined as the first working condition, for example, the current working condition is determined as the V-shaped operation working condition.

[0129] Here, the fifth condition includes that the loader sequentially performs loaded backward driving and loaded forward driving after the loading operation. Here, the steering cylinder displacement is equal to the first preset displacement during the loaded backward driving of the loader, and the steering cylinder displacement is not equal to the first preset displacement during the loaded forward driving of the loader.

[0130] In the above embodiment, in a case where it is determined that the loader enters the loading operation phase from the straight-line driving empty advancing phase, enters the straight-line driving loaded retreating phase from the loading operation phase, and enters the curve driving loaded advancing phase from the straight-line driving loaded retreating phase, the current working condition of the loader can be accurately determined as the first working condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader for this working condition.

[0131] It should be understood that in the case of satisfying the second condition, the current working condition can be determined as other working conditions in the first group of working conditions except the third working condition through the combination of the above embodiment.

[0132] In some embodiments, in a case where the pressure value of the working pump is equal to the first preset pressure value and the vehicle speed of the loader is greater than 0, the current working condition of the loader is determined as one of the second group of working conditions. The second group of working conditions includes one or more of a straight-line driving working condition, a non-horizontal driving working condition, and a turning driving working condition.

[0133] Here, the straight-line driving working condition includes at least one of a first straight-line driving working condition and a second straight-line driving working condition, the non-horizontal driving working condition includes at least one of an uphill driving working condition and a downhill driving working condition, the vehicle speed of the first straight-line driving working condition is greater than the first preset vehicle speed, and the vehicle speed of the second straight-line driving working condition is less than or equal to the first preset vehicle speed. For example, the first straight-line driving working condition can be referred to as a high-speed straight-line driving working condition, and the second straight-line driving working condition can be referred to as a low-speed straight-line driving working condition.

[0134] In the above embodiment, by the size relationship between the pressure value of the working pump and the first preset pressure value, it can be accurately determined whether the loader is in one of the straight-line driving working condition, the non-horizontal driving working condition, and the turning driving working condition, thereby helping to accurately determine the current working condition of the loader, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader.

[0135] In some embodiments, in a case where the pressure value of the working pump is equal to the first preset pressure value, the vehicle speed of the loader is greater than 0, and the displacement of the turning cylinder of the loader is not equal to the first preset displacement amount, the current working condition is determined as the turning driving working condition.

[0136] In some embodiments, in a case where the pressure value of the working pump is equal to the first preset pressure value, the vehicle speed of the loader is greater than 0, the displacement of the turning cylinder is equal to the first preset displacement amount, the slope angle is not 0, and the opening degree of the accelerator pedal is greater than the first preset opening degree, the current working condition is determined as the uphill driving working condition. For example, the first preset opening degree is the initial opening degree of the accelerator pedal, i.e., the opening degree of the accelerator pedal when the accelerator pedal is not stepped on.

[0137] In some embodiments, the current working condition is determined as the uphill driving condition when the pressure value of the working pump is equal to the first preset pressure value, the vehicle speed of the loader is greater than 0, the displacement of the steering cylinder is equal to the first preset displacement, the slope angle is not 0, and the opening degree of the accelerator pedal is equal to the first preset opening degree.

[0138] In some embodiments, the current working condition is determined as the first straight-line driving condition when the pressure value of the working pump is equal to the first preset pressure value, the vehicle speed of the loader is greater than 0, the displacement of the steering cylinder is equal to the first preset displacement, the slope angle is 0, and the vehicle speed is greater than the first preset speed.

[0139] In some embodiments, the current working condition is determined as the second straight-line driving condition when the pressure value of the working pump is equal to the first preset pressure value, the vehicle speed of the loader is greater than 0, the displacement of the steering cylinder is equal to the first preset displacement, the slope angle is 0, and the vehicle speed of the loader is less than or equal to the first preset speed.

[0140] It should be understood that the current working condition can be determined as one of the second group of working conditions through the combination of the above embodiments.

[0141] In the above embodiments, the current working condition of the loader can be accurately determined as the steering driving condition, the first straight-line driving condition, the second straight-line driving condition, the uphill driving condition, or the downhill driving condition, so that the machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader.

[0142] In some embodiments, the working data and the current working condition of the loader can be sent to the user. In this way, the user can be helped to understand the working state of the loader.

[0143] In some embodiments, the energy management strategy of the loader can be formulated based on the predicted SOC of the battery and the vehicle speed of the loader. For example, the energy management strategy includes a power distribution strategy and a battery charging and discharging strategy. In this way, based on the predicted SOC of the battery and the vehicle speed of the loader by the prediction method of the present disclosure, the energy management strategy of the loader can be accurately formulated, thereby helping to accurately implement the energy management of the loader.

[0144] The present disclosure also proposes a model training method.

[0145] FIG. 3 is a flow diagram of a model training method according to some embodiments of the present disclosure.

[0146] In step 302, the working data of the first loader at a third time in a preset working condition is obtained.

[0147] The first loader can be any one of the loaders, and the preset working condition can be any one of the working conditions of the first loader. The working data at the third time is used as a training sample for training the machine learning model.

[0148] At step 304, the SOC of the battery at a fourth time and the vehicle speed at the fourth time of the first loader in the preset working condition are obtained. Here, the fourth time is after the third time.

[0149] The third time can be any one of the times during the historical operation of the first loader in the preset working condition, and the fourth time can be any one of the times after the third time during the historical operation of the first loader in the preset working condition. The SOC of the battery at the fourth time and the vehicle speed at the fourth time are used as a training sample for training the machine learning model.

[0150] At step 306, the working data at the third time is used as an input, and the SOC at the fourth time and the vehicle speed at the fourth time are used as an output to train the machine learning model corresponding to the preset working condition.

[0151] Here, the preset working condition is one of the multiple working conditions, and the machine learning model corresponding to one of the at least two working conditions is different from the machine learning model corresponding to another working condition. That is, the machine learning models corresponding to the at least two working conditions are different.

[0152] During the training of the machine learning model, the training sample can be increased in multiple ways to train the machine learning model and improve the training effect.

[0153] For example, for the same loader, at least one of the third time and the fourth time can be changed to change the training sample for training the machine learning model.

[0154] For example, for the same loader, the type of the preset working condition can be changed to change the training sample for training the machine learning model.

[0155] For example, multiple loaders can be used as the first loader respectively, and steps 302-306 can be repeatedly executed to train the machine learning model corresponding to the preset working condition. By changing the type of the preset working condition, the machine learning model corresponding to different working conditions can be trained by using the training samples of different loaders.

[0156] In the above embodiment, the working data of the first loader in the third time under the preset working condition is taken as the input, the SOC of the battery of the first loader in the fourth time under the preset working condition and the vehicle speed in the fourth time are taken as the output, the machine learning model corresponding to the preset working condition is trained, and the preset working condition is one of the plurality of working conditions. The machine learning model corresponding to one of the at least two working conditions is different from the machine learning model corresponding to another working condition. In this way, the machine learning model trained for the preset working condition can more accurately predict the SOC of the battery of the loader and the vehicle speed under the working condition.

[0157] In some embodiments, the working data of the first loader in the third time under a plurality of random working conditions (hereinafter referred to as random working data) can be obtained, and the random working data under the plurality of working conditions can be dimensionally reduced and clustered to obtain the working data of the first loader in the third time under each working condition. For example, principal component analysis (PCA) can be used to reduce the dimension of the random working data.

[0158] As some implementations, the random working data includes working data of the loader under various working conditions randomly occurring in actual use or testing.

[0159] As some implementations, the plurality of cluster sets can be obtained by clustering the dimensionally reduced random working data, the types of the working conditions can be determined by analyzing the features of the plurality of cluster sets, and the working conditions can be determined as preset working conditions after determining the types of the working conditions.

[0160] For example, the working data in the cluster set can be analyzed to determine the types of the working conditions.

[0161] In the above embodiment, on the one hand, the working data of the first loader in the third time is obtained by using the random working data reflecting the random working conditions of the loader in daily operation, and the machine learning model can be accurately trained; on the other hand, the working data under different working conditions can be obtained by dimensionally reducing and clustering the random working data, and the working data under different working conditions does not need to be obtained by the loader under different working conditions respectively, which can reduce the pressure of data processing and improve the efficiency of training the machine learning model.

[0162] In some embodiments, the machine learning model corresponding to one of the plurality of working conditions is different from the machine learning model corresponding to another working condition. That is, each working condition of the plurality of working conditions has a machine learning model unique to the working condition, and the machine learning models corresponding to the plurality of working conditions are different from each other. In this way, the machine learning model trained for each working condition can more accurately predict the SOC of the battery of the loader and the vehicle speed under the working condition.

[0163] It can be understood that after the machine learning model is trained (for example, offline training), the trained machine learning model can be deployed on different loaders. The loader can use the trained machine learning model to predict the SOC and the vehicle speed of the battery of the loader at a certain moment. Then, the training data of the loader in a certain working condition during work can be obtained, and the machine learning model deployed on the loader is further trained using the training data. Next, some embodiments will be described in combination.

[0164] In some embodiments, the working data of the second loader in which the machine learning model is deployed in the current working condition at the fifth moment is obtained, and the SOC and the vehicle speed of the battery of the second loader in a preset working condition at the sixth moment after the fifth moment are obtained. After obtaining the training sample, the working data at the fifth moment is taken as the input, and the SOC at the sixth moment and the vehicle speed at the sixth moment are taken as the output, and the machine learning model corresponding to the current working condition is trained.

[0165] For example, the preset working condition includes the current working condition. In this way, the machine learning model corresponding to a certain working condition can be trained before and after being deployed on the loader, respectively. That is, the second loader carrying the machine learning model can update the machine learning model online in the case of the current working condition. For example, at least one of the weight matrix and the bias vector in the machine learning model is updated.

[0166] As some implementations, a training window with a size of A can be set as the length of collecting working data, and n online training iterations are performed. For example, n is 1.

[0167] In the case where the cumulative running time of the loader reaches a preset threshold T, the machine learning model is updated. Here, T=A*n.

[0168] After updating the machine learning model, the training number counter n is incremented (that is, n=n+1).

[0169] For example, in the case where n is 1, the machine learning model is updated when the cumulative running time of the loader reaches A, and the training number counter is incremented (at this time, n is 2); in the case where the loader runs for another time A (that is, the cumulative running time reaches 2A), the machine learning model is updated again, and the training number counter is incremented, and so on.

[0170] In the case where the cumulative running time of the loader does not reach the preset threshold T, the machine learning model is not updated, that is, the original machine learning model is used for prediction.

[0171] In the above embodiments, the online updating of the machine learning model can enable continuous optimization of the machine learning model, enhance the adaptability and flexibility of the machine learning model to different working conditions, and thus more accurately predict the SOC and vehicle speed of the battery of the loader.

[0172] In some embodiments, the second loader is different from the first loader. That is, the machine learning model can be trained using the working data of the first loader, and after the machine learning model is deployed on the second loader, the working data of the current working condition of the second loader when actually working can be used to update the machine learning model.

[0173] In the above embodiments, on the one hand, the machine learning model can be trained using the working data of the first loader, which speeds up the efficiency of training the machine learning model; on the other hand, the machine learning model trained using the working data of the first loader can be updated using the working data of the second loader, so that the updated machine learning model is more in line with the actual working condition of the second loader, and thus more accurately predicts the SOC and vehicle speed of the battery of the second loader.

[0174] In some embodiments, the model of the second loader is the same as that of the first loader. In this way, the machine learning model trained using the working data of the first loader is more suitable for the second loader, and thus the machine learning model can more accurately predict the SOC and vehicle speed of the battery of the second loader.

[0175] In some embodiments, the working data as the training sample includes one or more of the vehicle speed of the loader, the gear of the loader, the accelerator pedal opening degree of the loader, the brake pedal opening degree of the loader, and the walking motor power of the loader. Here, the walking motor of the loader is used to drive the loader to walk.

[0176] For example, the working data includes any one, any two, any three, any four, or all of the vehicle speed of the loader, the gear of the loader, the accelerator pedal opening degree of the loader, the brake pedal opening degree of the loader, and the walking motor power of the loader.

[0177] In the above embodiments, the working data includes one or more of the vehicle speed, the gear, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power, and thus the machine learning model can be more accurately trained, and thus the trained machine learning model can more accurately predict the SOC and vehicle speed of the battery of the loader.

[0178] In some embodiments, the preset working conditions include a straight driving working condition. Here, the straight driving working condition includes a first straight driving working condition and a second straight driving working condition, the vehicle speed of the first straight driving working condition is greater than the first preset vehicle speed, and the vehicle speed of the second straight driving working condition is less than or equal to the first preset vehicle speed. In this way, the training data in the driving working conditions with different vehicle speeds can be used to train the machine learning model corresponding to the straight driving working condition, which helps to improve the training effect.

[0179] As some implementations, the machine learning model corresponding to the first straight driving working condition is different from the machine learning model corresponding to the second straight driving working condition. In this way, different machine learning models can be trained for the first straight driving working condition and the second straight driving working condition, so that the trained machine learning model can more accurately predict the SOC and vehicle speed of the battery of the loader in the two straight driving working conditions.

[0180] In some embodiments, the preset working conditions include a non-horizontal driving working condition. Here, the non-horizontal driving working condition includes at least one of an uphill driving working condition and a downhill driving working condition. In this case, the working data includes the slope angle in addition to one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power. In this way, the working data including the slope angle is used to train the machine learning model corresponding to the non-horizontal driving working condition, which helps to improve the training effect.

[0181] As some implementations, the machine learning model corresponding to the uphill driving working condition is different from the machine learning model corresponding to the downhill driving working condition. In this way, different machine learning models can be trained for the uphill driving working condition and the downhill driving working condition, so that the trained machine learning model can more accurately predict the SOC and vehicle speed of the battery of the loader in the corresponding working condition.

[0182] In some embodiments, the preset working conditions include a turning driving working condition. In this case, the working data includes one or more of the heading angle, the steering cylinder displacement, and the steering cylinder pressure in addition to one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power.

[0183] For example, the working data includes any one, any two, or all of the heading angle, the steering cylinder displacement, and the steering cylinder pressure. As some implementations, the working data includes the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, the walking motor power, the heading angle, the steering cylinder displacement, and the steering cylinder pressure.

[0184] In the above embodiments, the working data including one or more of the heading angle, the steering cylinder displacement, and the steering cylinder pressure is used as the training sample to train the machine learning model corresponding to the steering travel working condition, so that the trained machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader in the steering travel working condition.

[0185] In some embodiments, the preset working condition includes at least one of the second working condition and the fifth working condition. In this case, the working data includes one or more of the bucket cylinder displacement, the boom cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, and the work motor power in addition to one or more of the vehicle speed, the gear position, the accelerator pedal opening, the brake pedal opening, and the travel motor power. For example, the preset working condition includes the second working condition or the fifth working condition; for another example, the preset working condition includes the second working condition and the fifth working condition.

[0186] For example, the working data includes any one, any two, any three, any four, or all of the bucket cylinder displacement, the boom cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, and the work motor power in addition to the vehicle speed, the gear position, the accelerator pedal opening, the brake pedal opening, and the travel motor power.

[0187] In the above embodiments, the working data including one or more of the bucket cylinder displacement, the boom cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, and the work motor power is used to train the machine learning model corresponding to at least one of the second working condition and the fifth working condition, so that the trained machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader in the corresponding working condition.

[0188] In some embodiments, the preset working condition includes at least one of the first working condition, the third working condition, and the fourth working condition. In this case, the working data includes one or more of the heading angle, the bucket cylinder displacement, the boom cylinder displacement, the steering cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, the steering cylinder pressure, and the work motor power in addition to one or more of the vehicle speed, the gear position, the accelerator pedal opening, the brake pedal opening, and the travel motor power.

[0189] For example, the preset working condition includes the first working condition, the third working condition, or the fourth working condition; for another example, the preset working condition includes any two of the first working condition, the third working condition, and the fourth working condition; for yet another example, the preset working condition includes the first working condition, the third working condition, and the fourth working condition.

[0190] It should be understood that the working data includes any one, any two, any three, any four, any five, any six, any seven, or all of the heading angle, the bucket cylinder displacement, the boom cylinder displacement, the steering cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, the steering cylinder pressure, and the work motor power.

[0191] In the above embodiments, the working data including one or more of the heading angle, the bucket cylinder displacement, the boom cylinder displacement, the steering cylinder displacement, the bucket cylinder pressure, the boom cylinder pressure, the steering cylinder pressure, and the working motor power is used to train the machine learning model corresponding to at least one of the first working condition, the third working condition, and the fourth working condition (for example, the machine learning model can be trained for the V-shaped working condition, the T-shaped working condition, and the L-shaped working condition, respectively), so that the trained machine learning model can more accurately predict the SOC of the battery and the vehicle speed of the loader in the corresponding working condition.

[0192] In some embodiments, the machine learning model includes but is not limited to a hierarchical recurrent neural network (HRNN) model.

[0193] As some implementations, the HRNN model is constructed and trained with the working data as input and the SOC of the battery of the loader and the vehicle speed of the loader as output.

[0194] For example, the hidden layer of the HRNN model has two layers, the first layer is a recurrent neural network (RNN), and the expression is

[0195] Here, is the hidden state of the first layer RNN at time step t, and is a weight matrix, b h (1) is a bias vector, and σ is an activation function.

[0196] For example, the second layer of the hidden layer of the HRNN model is an RNN, and the expression is:

[0197] In the above formula, is the activation value of the forget gate, is the activation value of the input gate, is the activation value of the output gate, is the candidate cell state, is the cell state, is the hidden state of the current time step, and ⊙ represents element-wise multiplication, is a weight matrix, is a bias vector, and σ is an activation function.

[0198] For example, the output layer of the HRNN model can be represented as:

[0199] In the above formula, is the hidden state of the last layer RNN of the hidden layer at the last time step T,​ is a weight matrix, b ysoc is a bias vector. yv is a bias vector.

[0200] In the above embodiments, the HRNN can process sequence data with a complex hierarchical structure, and the hierarchical structure can more sensitively capture the hierarchical relationship and dependency relationship in the working data, thereby improving the accuracy of the machine learning model in predicting the SOC and the vehicle speed of the loader.

[0201] Each of the embodiments in the specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. For the device embodiments, since they are basically corresponding to the method embodiments, the description is relatively simple, and the relevant parts are referred to the part of the method embodiment.

[0202] In some embodiments, the parameter prediction device comprises a module configured to perform the parameter prediction method of any one of the above embodiments.

[0203] FIG. 4 is a structural schematic diagram of a parameter prediction device according to some embodiments of the present disclosure.

[0204] In some embodiments, as shown in FIG. 4, the parameter prediction device comprises a determination module 401, an acquisition module 402, and a prediction module 403.

[0205] The determination module 401 is configured to determine the current working condition of the loader.

[0206] The acquisition module 402 is configured to acquire working data of the loader in a current first time under the current working condition. In some embodiments, the working data comprises one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power.

[0207] The prediction module 403 is configured to input the working data into a machine learning model corresponding to the current working condition, to predict the state of charge of the battery of the loader at a second time and the vehicle speed of the loader at the second time. Here, the second time is after the first time, the current working condition is one of a plurality of working conditions, and the machine learning model corresponding to one of the at least two working conditions is different from the machine learning model corresponding to another working condition.

[0208] In some embodiments, the determination module 401 is further configured to determine the current working condition of the loader according to a pressure value of a working pump of the loader, the working pump being used to drive at least one of a steering cylinder of the loader, a bucket cylinder of the loader, and a boom cylinder of the loader.

[0209] In some embodiments, the determining module 401 is further configured to determine that the current working condition is one of the first group of working conditions in a case that the pressure value of the working pump is greater than the first preset pressure value, the first group of working conditions comprising one or more of the first working condition, the second working condition, the third working condition, the fourth working condition and the fifth working condition.

[0210] In some embodiments, the determining module 401 is further configured to determine that the current working condition is the third working condition in a case that a first condition is satisfied, wherein the first condition comprises that the loader performs the shovel loading operation after the empty forward movement, and that the displacement of the steering cylinder of the loader is not equal to the first preset displacement during the empty forward movement of the loader.

[0211] In some embodiments, the determining module 401 is further configured to determine that the current working condition is any one of the first group of working conditions except the third working condition in a case that a second condition is satisfied, wherein the second condition comprises that the loader performs the shovel loading operation after the empty forward movement, and that the displacement of the steering cylinder of the loader is equal to the first preset displacement during the empty forward movement of the loader.

[0212] In some embodiments, the determining module 401 is further configured to determine that the current working condition is any one of the first group of working conditions except the third working condition in a case that the second condition is satisfied, comprising at least one of the following: determining that the current working condition is the fifth working condition in a case that the loader performs the unloading operation after the shovel loading operation; determining that the current working condition is the fourth working condition in a case that a third condition is satisfied; determining that the current working condition is the second working condition in a case that a fourth condition is satisfied; and determining that the current working condition is the first working condition in a case that a fifth condition is satisfied; wherein the third condition comprises that the loader performs the loaded backward movement after the shovel loading operation, and that the displacement of the steering cylinder is not equal to the first preset displacement during the loaded backward movement of the loader; the fourth condition comprises that the loader sequentially performs the loaded backward movement and the loaded forward movement after the shovel loading operation, wherein the displacement of the steering cylinder is equal to the first preset displacement during the loaded backward movement and the loaded forward movement of the loader; the fifth condition comprises that the loader sequentially performs the loaded backward movement and the loaded forward movement after the shovel loading operation, wherein the displacement of the steering cylinder is equal to the first preset displacement during the loaded backward movement of the loader, and the displacement of the steering cylinder is not equal to the first preset displacement during the loaded forward movement of the loader.

[0213] In some embodiments, the determining module 401 is further configured to determine that the current working condition is one of the second group of working conditions in a case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0, the second group of working conditions comprising one or more of the straight-line driving working condition, the non-horizontal driving working condition and the steering driving working condition.

[0214] In some embodiments, the determining module 401 is further configured to determine, in the case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0, that the current working condition is one of the second set of working conditions, including at least one of the following: in the case that the steering cylinder displacement of the loader is not equal to the first preset displacement amount, determining that the current working condition is the steering traveling working condition; in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is not 0, and the accelerator pedal opening degree is greater than the first preset opening degree, determining that the current working condition is the uphill traveling working condition; in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is not 0, and the accelerator pedal opening degree is equal to the first preset opening degree, determining that the current working condition is the downhill traveling working condition; in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is 0, and the vehicle speed is greater than the first preset speed, determining that the current working condition is the first straight-line traveling working condition; and in the case that the steering cylinder displacement is equal to the first preset displacement amount, the slope angle is 0, and the vehicle speed is less than or equal to the first preset speed, determining that the current working condition is the second straight-line traveling working condition.

[0215] In some embodiments, the parameter prediction device can further include other modules to perform the parameter prediction method of any one of the above-mentioned embodiments.

[0216] In some embodiments, the model training device includes a module configured to perform the model training method of any one of the above-mentioned embodiments.

[0217] FIG. 5 is a structural schematic diagram of a model training device according to some embodiments of the present disclosure.

[0218] In some embodiments, as shown in FIG. 5, the model training device includes a first acquisition module 501, a second acquisition module 502, and a training module 503.

[0219] The first acquisition module 501 is configured to acquire working data of a first loader in a third time under a preset working condition. In some embodiments, the working data includes one or more of the vehicle speed, the gear position, the accelerator pedal opening degree, the brake pedal opening degree, and the walking motor power.

[0220] The second acquisition module 502 is configured to acquire the state of charge of the battery at a fourth time and the vehicle speed at the fourth time of the first loader in the preset working condition. Here, the fourth time is after the third time.

[0221] The training module 503 is configured to train a machine learning model corresponding to the preset working condition by taking the working data at the third time as input, and taking the state of charge at the fourth time and the vehicle speed at the fourth time as output. Here, the preset working condition is one of a plurality of working conditions, and the machine learning model corresponding to one of the at least two working conditions is different from the machine learning model corresponding to another working condition.

[0222] In some embodiments, the first obtaining module 501 is configured to obtain working data of the second loader in a preset working condition at a fifth time point, the preset working condition including the current working condition; the second obtaining module 502 is configured to obtain the state of charge of the battery and the vehicle speed of the second loader in the preset working condition at a sixth time point, the sixth time point being after the fifth time point; and the training module 503 is configured to train the machine learning model corresponding to the current working condition by taking the working data at the fifth time point as input and taking the state of charge at the sixth time point and the vehicle speed at the sixth time point as output.

[0223] In some embodiments, the second loader is different from the first loader.

[0224] In some embodiments, the model training apparatus can further include other modules to perform the model training method of any one of the above-mentioned embodiments.

[0225] FIG. 6 is a structural schematic diagram of an electronic device according to some embodiments of the present disclosure.

[0226] As shown in FIG. 6, the electronic device 600 includes a memory 601 and a processor 602 coupled to the memory 601, the processor 602 being configured to perform the method of any one of the above-mentioned embodiments based on instructions stored in the memory 601. As some implementations, the processor 602 is configured to perform the parameter prediction method or the model training method of any one of the above-mentioned embodiments based on instructions stored in the memory 601.

[0227] The memory 601 may, for example, include system memory, fixed non-volatile storage media, etc. The system memory may, for example, store an operating system, application programs, a Boot Loader, and other programs, etc.

[0228] In some embodiments, the electronic device 600 can further include an input / output interface 603, a network interface 604, a storage interface 605, etc. The input / output interface 603, the network interface 604, the storage interface 605, and the memory 601 and the processor 602 may, for example, be connected through a bus 606. The input / output interface 603 provides a connection interface for display, mouse, keyboard, touch screen, and other input / output devices. The network interface 604 provides a connection interface for various networking devices. The storage interface 605 provides a connection interface for external storage devices such as SD card and U disk.

[0229] Embodiments of the present disclosure also provide a loader including at least one of the parameter prediction apparatus of any one of the above-mentioned embodiments, the model training apparatus of any one of the above-mentioned embodiments, and the electronic device of any one of the above-mentioned embodiments.

[0230] In some embodiments, the loader further comprises a first sensor, a second sensor, a third sensor, and an inertial navigation system.

[0231] Here, the first sensor is installed at a steering cylinder of the loader, and the first sensor is configured to acquire a steering cylinder displacement and a steering cylinder pressure of the loader.

[0232] The second sensor is installed at a bucket cylinder of the loader, and the second sensor is configured to acquire a bucket cylinder displacement and a bucket cylinder pressure of the loader.

[0233] The third sensor is installed at a boom cylinder of the loader, and the third sensor is configured to acquire a boom cylinder displacement and a boom cylinder pressure of the loader.

[0234] The inertial navigation system is configured to acquire a heading angle of the loader.

[0235] For example, the first sensor comprises a first displacement sensor configured to acquire the steering cylinder displacement of the loader and a first pressure sensor configured to acquire the steering cylinder pressure of the loader.

[0236] For another example, the second sensor comprises a second displacement sensor configured to acquire the bucket cylinder displacement of the loader and a second pressure sensor configured to acquire the bucket cylinder pressure of the loader.

[0237] For yet another example, the third sensor comprises a third displacement sensor configured to acquire the boom cylinder displacement of the loader and a third pressure sensor configured to acquire the boom cylinder pressure of the loader.

[0238] In the above embodiments, the loader further comprises the first sensor, the second sensor, the third sensor, and the inertial navigation system, so that the steering cylinder displacement and the steering cylinder pressure of the loader, the bucket cylinder displacement and the bucket cylinder pressure of the loader, the boom cylinder displacement and the boom cylinder pressure of the loader, and the heading angle of the loader can be directly measured, so that the machine learning model can be trained with the actually measured working data, and the machine learning model can predict the SOC and the vehicle speed of the loader by using the actually measured working data.

[0239] The embodiments of the present disclosure further provide a computer-readable storage medium comprising computer program instructions, which, when executed by a processor, implement the steps of the method of any one of the above embodiments.

[0240] The embodiments of the present disclosure further provide a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method of any one of the above embodiments.

[0241] The embodiments of the present disclosure further provide a computer program which, when executed by a processor, implements the method of any one of the above-mentioned embodiments.

[0242] So far, the embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein according to the above description.

[0243] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0244] The present disclosure 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 disclosure. It should be understood that the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0245] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction devices that implement the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0246] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0247] Although some specific embodiments of the present disclosure have been described in detail by way of example with reference to the drawings, it is to be understood that the above examples are intended to be illustrative only and are not intended to limit the scope of the present disclosure. It is to be understood that modifications or equivalent arrangements of the above embodiments can be made by those skilled in the art without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for predicting parameters, comprising: determining a current working condition of a loader; obtaining working data of the loader in a current first time under the current working condition; and inputting the working data into a machine learning model corresponding to the current working condition to predict a state of charge of a battery of the loader in a second time and a vehicle speed in the second time, the second time being after the first time, wherein the current working condition is one of a plurality of working conditions, and a corresponding machine learning model of one of at least two working conditions is different from a corresponding machine learning model of another working condition. The working data comprises one or more of a vehicle speed, a gear position, an accelerator pedal opening degree, a brake pedal opening degree, and a traveling motor power.

2. The prediction method of claim 1, wherein, The determining of the current working condition of the loader comprises:

3. The prediction method of claim 1 or 2, wherein, determining the current working condition of the loader according to a pressure value of a working pump of the loader, the working pump being used to drive at least one of a steering cylinder of the loader, a bucket cylinder of the loader, and a boom cylinder of the loader. The determining of the current working condition of the loader according to the pressure value of the working pump of the loader comprises:

4. The prediction method of claim 3, wherein, in a case where the pressure value of the working pump is greater than a first preset pressure value, determining that the current working condition is one of a first group of working conditions, the first group of working conditions comprising one or more of a first working condition, a second working condition, a third working condition, a fourth working condition, and a fifth working condition, wherein: in the first working condition, working phases of the loader in chronological order comprise, in sequence, an empty forward traveling phase of straight line traveling, a loading operation phase, a loaded backward traveling phase of straight line traveling, and a loaded forward traveling phase of curve line traveling; in the second working condition, working phases of the loader in chronological order comprise, in sequence, the empty forward traveling phase of straight line traveling, the loading operation phase, the loaded backward traveling phase of straight line traveling, and the loaded forward traveling phase of straight line traveling; in the third working condition, working phases of the loader in chronological order comprise, in sequence, an empty forward traveling phase of curve line traveling, the loading operation phase, a loaded backward traveling phase of curve line traveling, and a loaded forward traveling phase of curve line traveling; in the fourth working condition, working phases of the loader in chronological order comprise, in sequence, the empty forward traveling phase of straight line traveling, the loading operation phase, a loaded backward traveling phase of curve line traveling, and the loaded forward traveling phase of straight line traveling; in the fifth working condition, working phases of the loader in chronological order comprise, in sequence, the empty forward traveling phase, the loading operation phase, and an unloading phase. The determining of the current working condition as one of the first group of working conditions in the case where the pressure value of the working pump is greater than the first preset pressure value comprises:

5. The prediction method of claim 4, wherein, in a case where a first condition is met, determining that the current working condition is the third working condition, wherein the first condition comprises that the loader performs the loading operation after the empty forward traveling, and a displacement of the steering cylinder of the loader during the empty forward traveling of the loader is not equal to a first preset displacement amount. ​ 6. The prediction method of claim 4 or 5, wherein, The determining that the current working condition is one of the first group of working conditions in the case that the pressure value of the working pump is greater than the first preset pressure value comprises: The determining that the current working condition is any one of the first group of working conditions except the third working condition in the case that the second condition is met, wherein the second condition comprises: The loader performs the loading operation after advancing in an empty load state, and during the advancing of the loader in the empty load state, the displacement of the steering cylinder of the loader is equal to a first preset displacement.

7. The prediction method of claim 6, wherein, The determining that the current working condition is any one of the first group of working conditions except the third working condition in the case that the second condition is met comprises at least one of: In the case that the loader performs the unloading operation after the loading operation, the current working condition is determined to be the fifth working condition; In the case that the third condition is met, the current working condition is determined to be the fourth working condition; In the case that the fourth condition is met, the current working condition is determined to be the second working condition; And In the case that the fifth condition is met, the current working condition is determined to be the first working condition; The third condition comprises that the loader retreats in a loaded state after the loading operation, and during the retreating of the loader in the loaded state, the displacement of the steering cylinder is not equal to the first preset displacement; The fourth condition comprises that the loader retreats in the loaded state and advances in the loaded state in sequence after the loading operation, wherein during the retreating and advancing of the loader in the loaded state, the displacement of the steering cylinder is equal to the first preset displacement; The fifth condition comprises that the loader retreats in the loaded state and advances in the loaded state in sequence after the loading operation, wherein during the retreating of the loader in the loaded state, the displacement of the steering cylinder is equal to the first preset displacement, and during the advancing of the loader in the loaded state, the displacement of the steering cylinder is not equal to the first preset displacement.

8. The prediction method according to any one of claims 3 to 7, wherein, The determining that the current working condition of the loader is determined according to the pressure value of the working pump of the loader comprises: In the case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0, the current working condition is determined to be one of a second group of working conditions, the second group of working conditions comprising one or more of a straight-line traveling working condition, a non-horizontal traveling working condition and a steering traveling working condition, the straight-line traveling working condition comprising at least one of a first straight-line traveling working condition and a second straight-line traveling working condition, the non-horizontal traveling working condition comprising at least one of an uphill traveling working condition and a downhill traveling working condition, and the vehicle speed of the first straight-line traveling working condition being greater than a first preset vehicle speed, and the vehicle speed of the second straight-line traveling working condition being less than or equal to the first preset vehicle speed.

9. The prediction method of claim 8, wherein, The determining that the current working condition is one of the second group of working conditions in the case that the pressure value is equal to the first preset pressure value and the vehicle speed is greater than 0 comprises at least one of: In the case that the displacement of the steering cylinder of the loader is not equal to the first preset displacement, the current working condition is determined to be the steering traveling working condition; In a case where the steering oil cylinder displacement is equal to the first preset displacement, the ramp angle is not 0, and the accelerator pedal opening degree is greater than the first preset opening degree, it is determined that the current working condition is the uphill driving working condition; In a case where the steering oil cylinder displacement is equal to the first preset displacement, the ramp angle is not 0, and the accelerator pedal opening degree is equal to the first preset opening degree, it is determined that the current working condition is the downhill driving working condition; In a case where the steering oil cylinder displacement is equal to the first preset displacement, the ramp angle is 0, and the vehicle speed is greater than the first preset speed, it is determined that the current working condition is the first straight driving working condition; and In a case where the steering oil cylinder displacement is equal to the first preset displacement, the ramp angle is 0, and the vehicle speed is less than or equal to the first preset speed, it is determined that the current working condition is the second straight driving working condition.

10. A training method of a model, comprising: obtaining working data of a first loader in a preset working condition at a third time; obtaining a state of charge of a battery of the first loader in the preset working condition at a fourth time and a vehicle speed of the first loader at the fourth time, the fourth time being after the third time; and training a machine learning model corresponding to the preset working condition by taking the working data at the third time as input and taking the state of charge at the fourth time and the vehicle speed at the fourth time as output, wherein the preset working condition is one of multiple working conditions, and a machine learning model corresponding to one of at least two working conditions is different from a machine learning model corresponding to another of the at least two working conditions.

11. The training method of claim 10, further comprising: obtaining working data of a second loader in a current working condition at a fifth time, the preset working condition including the current working condition; obtaining a state of charge of a battery of the second loader in the preset working condition at a sixth time and a vehicle speed of the second loader at the sixth time, the sixth time being after the fifth time; and training the machine learning model corresponding to the current working condition by taking the working data at the fifth time as input and taking the state of charge at the sixth time and the vehicle speed at the sixth time as output.

12. The training method of claim 11, wherein, The second loader is different from the first loader.

13. The training method of any one of claims 10-12, wherein, The working data includes one or more of a vehicle speed, a gear position, an accelerator pedal opening degree, a brake pedal opening degree, and a traveling motor power.

14. The training method of claim 13, wherein, The preset working condition includes a straight driving working condition, the straight driving working condition including a first straight driving working condition and a second straight driving working condition, the vehicle speed of the first straight driving working condition being greater than a first preset vehicle speed, the vehicle speed of the second straight driving working condition being less than or equal to the first preset vehicle speed, and a machine learning model corresponding to the first straight driving working condition being different from a machine learning model corresponding to the second straight driving working condition.

15. The training method of claim 13 or 14, wherein, The working data further includes a ramp angle, the preset working condition including a non-horizontal driving working condition, the non-horizontal driving working condition including at least one of an uphill driving working condition and a downhill driving working condition, and a machine learning model corresponding to the uphill driving working condition being different from a machine learning model corresponding to the downhill driving working condition.

16. The training method of any one of claims 13-15, wherein, The working data further include one or more of a heading angle, a steering cylinder displacement, and a steering cylinder pressure, and the preset working condition includes a steering traveling working condition.

17. The training method of any one of claims 13-16, wherein, The working data further include one or more of a bucket cylinder displacement, a boom cylinder displacement, a bucket cylinder pressure, a boom cylinder pressure, and a working motor power, and the preset working condition includes at least one of a second working condition and a fifth working condition, wherein: In the second working condition, the working phases of the loader in time sequence include a straight-line traveling empty advancing phase, a bucket loading working phase, a straight-line traveling loaded retreating phase, and a straight-line traveling loaded advancing phase. In the fifth working condition, the working phases of the loader in time sequence include an empty advancing phase, a bucket loading working phase, and an unloading phase.

18. The training method of any one of claims 13-17, wherein, The preset working condition includes at least one of a first working condition, a third working condition, and a fourth working condition, and the working data further include one or more of a heading angle, a bucket cylinder displacement, a boom cylinder displacement, a steering cylinder displacement, a bucket cylinder pressure, a boom cylinder pressure, a steering cylinder pressure, and a working motor power, wherein: In the first working condition, the working phases of the loader in time sequence include a straight-line traveling empty advancing phase, a bucket loading working phase, a straight-line traveling loaded retreating phase, and a curve-line traveling loaded advancing phase. In the third working condition, the working phases of the loader in time sequence include a curve-line traveling empty advancing phase, a bucket loading working phase, a curve-line traveling loaded retreating phase, and a curve-line traveling loaded advancing phase. In the fourth working condition, the working phases of the loader in time sequence include a straight-line traveling empty advancing phase, a bucket loading working phase, a curve-line traveling loaded retreating phase, and a straight-line traveling loaded advancing phase.

19. A parameter prediction apparatus, comprising: a module configured to perform the prediction method of any one of claims 1-9.

20. A model training apparatus, comprising: a module configured to perform the training method of any one of claims 10-18.

21. An electronic device, comprising: a memory; and a processor coupled to the memory and configured to perform the method of any one of claims 1-18 based on instructions stored in the memory.

22. A loader, comprising at least one of: the parameter prediction apparatus of claim 19; the model training apparatus of claim 20; and the electronic device of claim 21.

23. The loader of claim 22, further comprising: a first sensor mounted on a steering cylinder of the loader and configured to acquire a steering cylinder displacement and a steering cylinder pressure of the loader; a second sensor mounted on a bucket cylinder of the loader and configured to acquire a bucket cylinder displacement and a bucket cylinder pressure of the loader; a third sensor mounted on a boom cylinder of the loader and configured to acquire a boom cylinder displacement and a boom cylinder pressure of the loader; An inertial navigation system configured to obtain a heading angle of the loader.

24. A computer readable storage medium comprising a computer program, wherein, The computer program, which when executed by a processor, implements the steps of the method of any one of claims 1-18.

25. A computer program product comprising a computer program, wherein, The computer program, which when executed by a processor, implements the steps of the method of any one of claims 1-18.

26. A computer program, wherein, The computer program, which when executed by a processor, implements the method of any one of claims 1-18. The computer program, which when executed by a processor, implements the method of any one of claims 1-18.

Images