Intelligent Decision-making Method, System and Electronic Device for Operating Parameters of Cotton Picking Machine in Picking Environment

Abstract

The present invention provides an intelligent decision-making method, system and electronic device for the operating parameters of a cotton picker in a picking environment. A decision tree model is established based on the operating parameters, operating parameters and picking environment type of the cotton picker to obtain an impurity rate optimization equation for the cotton picker. The grey wolf optimization algorithm is used to optimize the impurity rate optimization equation to obtain the corresponding decision result of the operating parameters. The present invention can not only better reveal the relationship between the operating parameters and the optimization objectives, effectively improve the working efficiency and working quality of the cotton harvesting operation, but also add the picking environment type as an input in the decision tree model, enabling the present invention to cope with the operations in different picking environments, avoiding the problem that the selection of operating parameters mainly relied on the historical work experience of the machine operator in the past and the poor adaptability to the picking environment. By using the present invention, the operating parameters can be selected only based on the operating parameters of the cotton picker, improving the working quality and intelligent level of the cotton picker.

Description

Technical Field

[0001] The present invention belongs to the technical field of impurity content prediction of cotton pickers, and particularly relates to an intelligent decision-making method, system and electronic device for operating parameters and picking environment of cotton pickers. Background Art

[0002] Cotton is an important economic crop and strategic material in China, and cotton picking is an important link in the cotton industry. The cotton planting areas in China are mainly divided into three major cotton regions: the Yangtze River Valley cotton region, the Yellow River Valley cotton region and the Xinjiang cotton region. Among them, the Xinjiang cotton region has been listed as a high-quality cotton production base as early as 1989 due to its unique natural ecological conditions and geographical environment. In 2021, the national cotton sown area was 3.0281 million hectares, and the cotton planting area in the Xinjiang cotton region alone reached 2.5061 million hectares, with a yield of 5.129 million tons, accounting for about 89.39% of China's cotton output. In recent years, although China's cotton planting area has decreased to some extent, it has always been above 3 million hectares and always accounts for more than 10% of the global sown area.

[0003] Currently, when domestic cotton pickers operate, the selection of operating parameters mainly relies on the historical work experience of the machine operator, and the adaptability to the picking environment is poor. If the operating parameters are set unreasonably or cannot match the corresponding picking environment, problems such as high impurity content of seed cotton (referred to as "impurity content" for short) and more loss of fallen cotton will occur. Summary of the Invention

[0004] In view of the above technical problems, one of the purposes of one aspect of the present invention is to provide an intelligent decision-making method for operating parameters and picking environment of a cotton picker, which establishes a decision tree model based on the operating parameters, operating parameters and picking environment type of the cotton picker, obtains an optimization equation for the impurity content of the cotton picker, and uses the grey wolf optimization algorithm to optimize the optimization equation for the impurity content to obtain the corresponding decision result of the operating parameters. This method can adjust the operating parameters of the cotton picker in different picking environments, and effectively reduce the impurity content of the cotton picker to further improve the operation quality on the premise of ensuring the cotton harvesting operation efficiency.

[0005] One of the objectives of one embodiment of the present invention is to provide an intelligent decision-making system for cotton picker operation parameters and picking environment, including a model establishment module, an optimization equation module, a grey wolf algorithm module, and a parameter setting module; the model establishment module is used to establish a decision tree model based on the operating parameters, operation parameters, and picking environment types of the cotton picker; the optimization equation module is used to obtain an impurity rate optimization equation for the cotton picker according to the decision tree model; the grey wolf algorithm module is used to optimize the impurity rate optimization equation by using the grey wolf optimization algorithm to obtain the corresponding operation parameter decision result; the parameter setting module is used to set the operation parameters of the cotton picker according to the operation parameter decision result of the steps. This system can adjust the operation parameters of the cotton picker in different picking environments, and effectively reduce the impurity rate of the cotton picker to further improve the operation quality on the premise of ensuring the cotton harvesting operation efficiency.

[0006] One of the objectives of one embodiment of the present invention is to provide an electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the intelligent decision-making method for cotton picker operation parameters and picking environment are completed.

[0007] Note that the recording of these objectives does not prevent the existence of other objectives. One embodiment of the present invention does not need to achieve all the above objectives. Objectives other than the above can be extracted from the descriptions of the specification, drawings, and claims.

[0008] The present invention achieves the above technical objectives through the following technical means.

[0009] An intelligent decision-making method for cotton picker operation parameters and picking environment includes the following steps:

[0010] Step S1: Establish a decision tree model based on the operating parameters, operation parameters, and picking environment types of the cotton picker;

[0011] Step S2: Obtain an impurity rate optimization equation for the cotton picker according to the decision tree model described in Step S1;

[0012] Step S3: Use the grey wolf optimization algorithm to optimize the impurity rate optimization equation described in Step S2 to obtain the corresponding operation parameter decision result;

[0013] Step S4: Set the operation parameters of the cotton picker according to the operation parameter decision result described in Step S3.

[0014] In the above solution, the operating parameters and operation parameters of the cotton picker in Step S1 at least include the operating state, forward speed, cotton picking roller speed, spindle speed, doffer speed, fan speed, and fan opening.

[0015] In the above solution, the type of picking environment in step S1 is affected by at least the plant height and density of cotton plants.

[0016] In the above solution, the specific steps of step S1 include:

[0017] Step S1.1: Obtain the operating parameters, operation parameters, and picking environment type of the cotton picker from the cotton picker.

[0018] Step S1.2: Combine the operating parameters and operation parameters of the cotton picker obtained in step S1.1 with the picking environment type at the corresponding position to obtain a set of characteristic sample points, and label the corresponding sample points in the sample point set with the impurity content rate of the cotton picker.

[0019] Step S1.3: Perform data preprocessing on the sample point set in step S1.2. According to the operating state parameters in the operating parameters of the cotton picker, select the sample points when the cotton picker is in the "working" state, and remove the sample points when the cotton picker is in the "grain unloading" and "shutdown" states.

[0020] Step S1.4: Select a certain proportion of sample points from the sample point set preprocessed in step S1.3 as the training set, and the remaining sample points as the test set.

[0021] Step S1.5: Input the training set data in step S1.4 into the decision tree model, establish an impurity content rate prediction model for the picking environment type, operation parameters, and impurity content rate, and verify the effectiveness of the decision tree model with the test set data to obtain the final decision tree model.

[0022] In the above solution, the impurity content rate optimization equation in step S2 takes the minimum impurity content rate as the goal and the operation parameters as the control variables. The expression of the impurity content rate optimization equation is:

[0023] f(x 1 ,x 2 ,……x n ,s,t)

[0024]

[0025] Among them, x 1 ,x 2 ,……x n are the n input operation parameters respectively,

[0026] s is the plant height,

[0027] t is the density,

[0028] x i is the i-th operation parameter,

[0029] is the lower bound of the constraint of the i-th operation parameter,

[0030] is the upper bound constraint of the i-th operation parameter.

[0031] Furthermore, the optimization range of the control variables of the decision tree model in step S2 needs to set constraint boundaries, and the constraint boundaries at least include the forward speed, the rotation speed of the cotton picking roller, the rotation speed of the picker head, the rotation speed of the doffer, the rotation speed of the fan, and the fan opening constraint; according to the type of picking environment, set the constraint range for the forward speed; establish the target value constraint of the impurity content rate, and combine with the impurity content rate prediction model to solve the constraint range of the operation parameters.

[0032] In the above solution, the specific steps of the gray wolf algorithm optimization in step S3 include:

[0033] Step S3.1: Initialize the number of iterations and several impurity content rate prediction results;

[0034] Step S3.2: For each prediction result, calculate the distance from each operating parameter data to the impurity content rate prediction result, and assign each operating parameter data to the class of the impurity content rate prediction result closest to it to form a group;

[0035] Step S3.3: For each group, randomly select multiple operating parameter data from it, calculate the fitness of each selected operating parameter data, and select the α wolf, β wolf, δ wolf, and ω wolf based on the fitness value. Based on the selected α wolf, β wolf, and δ wolf, update the best hunting position of each ω wolf, and recalculate the fitness value of all the updated gray wolves to update the α wolf, and use it as the new impurity content rate prediction result;

[0036] Step S3.4: If the iteration converges or meets the stop condition, retain the impurity content rate prediction result with the optimal fitness value and output the group corresponding to the impurity content rate prediction result; otherwise, increment the number of iterations by 1 and return to step S3.2.

[0037] Furthermore, the expression of the best hunting position in step S3.3 is:

[0038]

[0039] In the formula, θ is the inertia weight, θ = 0.5·(1 + rand), and rand is a random number;

[0040] λ 1 、λ 2 、λ 3 respectively represent the weights of the current α, β, and δ wolves before the best hunting position in the (i + 1)-th iteration;

[0041] r 1 r 2 r3 is a random number modulo [0, 1];

[0042] is the position of the k-th best hunt in the i-th generation;

[0043] is the position of the k-th best hunt in the (i + 1)-th generation;

[0044] is the velocity of the k-th ω-wolf in the determined i-th generation;

[0045] is the velocity of the k-th ω-wolf in the determined (i + 1)-th generation

[0046] is the position of the prey relative to the positions of the α, β, and δ wolves.

[0047] Furthermore, the mathematical model of the position of the prey relative to the positions of the α, β, and δ wolves is as follows:

[0048]

[0049] In the formula, respectively represent the positions of the α, β, and δ wolves and the ω-wolf in the i-th generation;

[0050] respectively represent the distances between the current α, β, and δ wolves and the ω-wolf;

[0051] is the coefficient vector, and its calculation formula is:

[0052]

[0053] Among them, is an arbitrary vector between [0, 1];

[0054] is the scaling factor, which linearly decreases from 2 to 0 with time during the iteration process, and its expression is:

[0055]

[0056] where i is the current iteration number, and I max is the maximum iteration number.

[0057] An intelligent decision-making system for the operating parameters of a cotton picker in the picking environment includes a model establishment module, an optimization equation module, a gray wolf algorithm module, and a parameter setting module;

[0058] The model establishment module is used to establish a decision tree model according to the operating parameters, operating parameters, and picking environment types of the cotton picker;

[0059] The optimization equation module is used to obtain the impurity rate optimization equation of the cotton picker according to the decision tree model;

[0060] The grey wolf algorithm module is used to optimize the impurity rate optimization equation by using the grey wolf optimization algorithm to obtain the corresponding operation parameter decision result;

[0061] The parameter setting module is used to set the operation parameters of the cotton picker according to the operation parameter decision result of the step.

[0062] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the above-mentioned intelligent decision-making method for the operation parameters of the cotton picker in the picking environment are completed.

[0063] Compared with the prior art, the beneficial effects of the present invention are:

[0064] According to one aspect of the present invention, an intelligent decision-making method for the operation parameters of a cotton picker in a picking environment is provided. By establishing a model using a decision tree model and optimizing it using the grey wolf algorithm, the optimal operation parameters in different situations can be obtained. The data processing of this method is accurate and reliable. It can not only better reveal the relationship between operation parameters and optimization objectives, effectively improve the working efficiency and operation quality of cotton harvesting operations, but also does not rely on work experience when judging operation parameters, and can select operation parameters only based on the running parameters of the cotton picker. The present invention fills the gap in the technical field of decision-making for operation parameters of current cotton harvesting machinery, and improves the working quality and intelligent level of the cotton picker.

[0065] According to one aspect of the present invention, the picking environment type is added as an input in the decision tree model, enabling the present invention to handle operations in different picking environments and avoiding the problem that the previous selection of operation parameters mainly relied on the historical work experience of the machine operator and had poor adaptability to the picking environment.

[0066] According to one aspect of the present invention, an intelligent decision-making system for the operation parameters of a cotton picker in a picking environment is provided, including a model establishment module, an optimization equation module, a grey wolf algorithm module, and a parameter setting module; the model establishment module is used to establish a decision tree model according to the running parameters, operation parameters, and picking environment type of the cotton picker; the optimization equation module is used to obtain the impurity rate optimization equation of the cotton picker according to the decision tree model; the grey wolf algorithm module is used to optimize the impurity rate optimization equation by using the grey wolf optimization algorithm to obtain the corresponding operation parameter decision result; the parameter setting module is used to set the operation parameters of the cotton picker according to the operation parameter decision result of the step. This system can adjust the operation parameters of the cotton picker in different picking environments, and effectively reduce the impurity rate of the cotton picker to further improve the operation quality on the premise of ensuring the efficiency of cotton harvesting operations.

[0067] According to one aspect of the present invention, there is provided an electronic device, including a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the intelligent decision-making method for the operation parameters of the cotton picker in the picking environment are completed.

[0068] Note that the description of these effects does not preclude the existence of other effects. One aspect of the present invention does not necessarily have all of the above effects. Effects other than the above can be obviously seen and extracted from the descriptions in the specification, drawings, claims, etc. Description of the Drawings

[0069] Figure 1 It is a schematic flowchart of Embodiment 1 of the present invention.

[0070] Figure 2 It is a schematic diagram of the decision tree model of Embodiment 1 of the present invention.

[0071] Figure 3 It is a schematic diagram of the effect of the impurity content prediction model of Embodiment 1 of the present invention;

[0072] Figure 4 It is a schematic diagram of the effect of the impurity content prediction model obtained by the traditional method;

[0073] Figure 5a It is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in Test Site 1 of the Xinjiang cotton area of the present invention;

[0074] Figure 5b It is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in Test Site 2 of the Xinjiang cotton area of the present invention; Detailed Embodiments

[0075] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0076] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "front", "rear", "left", "right", "upper", "lower", "axial", "radial", "vertical", "horizontal", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0077] In the present invention, unless otherwise clearly specified and defined, the terms "mounted", "connected", "connected to", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0078] Embodiment 1

[0079] Figure 1 Shown is a preferred embodiment of the intelligent decision-making method for the operation parameters and picking environment of the cotton picker.

[0080] An intelligent decision-making method for the operation parameters and picking environment of a cotton picker includes the following steps:

[0081] Step S1: Establish a decision tree model based on the operating parameters, operation parameters, and picking environment type of the cotton picker;

[0082] Step S2: Obtain the impurity rate optimization equation of the cotton picker according to the decision tree model described in Step S1;

[0083] Step S3: Use the grey wolf optimization algorithm to optimize the impurity rate optimization equation described in Step S2 to obtain the corresponding operation parameter decision result;

[0084] Step S4: Set the operation parameters of the cotton picker according to the operation parameter decision result described in Step S3.

[0085] According to this embodiment, preferably, the cotton picker operating parameters and operation parameters of step S1 at least include operating status, forward speed, cotton picking drum speed, spindle speed, doffing disc speed, fan speed and fan opening.

[0086] According to this embodiment, preferably, the picking environment type in step S1 is determined by the plant height and density of the cotton plants.

[0087] According to this embodiment, preferably, the specific steps of step S1 include:

[0088] Step S1.1: Acquire the running parameters, operating parameters and picking environment type of the cotton picker from the cotton picker; according to this embodiment, preferably, the running parameters and operating parameters are collected by the monitoring system of the cotton picker at regular intervals or at regular distances, and there is no restriction on the setting of the predetermined time or predetermined distance, which can be specifically set according to the forward speed of the cotton picker during the harvesting operation. At the same time, the picking environment type during field operation is collected to obtain a picking environment label.

[0089] Step S1.2: combining the running parameters and operating parameters of the cotton picker obtained in step S1.1 with the picking environment type at the corresponding position to obtain a characteristic sample point set, and labeling the corresponding sample points in the sample point set for the impurity content of the cotton picker;

[0090] Step S1.3: performing data preprocessing on the sample point set of step S1.2, selecting sample points where the cotton picker is in the "working" state according to the operating state parameters in the operating parameters of the cotton picker, and removing sample points where the cotton picker is in the "unloading" or "stopping" states;

[0091] Step S1.4: Select a certain proportion of sample points from the sample point set preprocessed in step S1.3 as a training set, and the other sample points as a test set; according to this embodiment, preferably, 70% of the sample points are selected as the training set.

[0092] Step S1.5: Input the training set data described in step S1.4 into the decision tree model, filter all possible decision conditions, select the decision tree partitioning node that brings the maximum information gain rate to the data set, and then establish a picking environment type, operating parameters and impurity rate prediction model. Test the training model with the test set data. If the accuracy of the test result is greater than or equal to 95%, the model training and testing are completed. Otherwise, it is necessary to optimize it through data enhancement and other methods to verify the effectiveness of the decision tree model, and finally obtain Figure 2 The decision tree model shown. According to this embodiment, preferably, the input parameters of the decision tree prediction model include forward speed, cotton picking drum speed, spindle speed, cotton stripping disk speed, fan speed, fan opening and picking environment type label number.

[0093] According to this embodiment, preferably, the impurity rate optimization equation in step S2 aims at the minimum impurity rate, takes the operating parameters as control variables, and the expression of the impurity rate optimization equation is:

[0094] f(x 1 ,x 2 ,……x n ,s,t)

[0095]

[0096] where s is the plant height,

[0097] t is the density,

[0098] x i is the i-th operating parameter,

[0099] is the lower bound of the constraint of the i-th operating parameter,

[0100] is the upper bound of the constraint of the i-th operating parameter,

[0101] x 1 ,x 2 ,……x n are respectively the n input operating parameters,

[0102] According to this embodiment, preferably, six different operating parameters of the cotton picker are input into the decision tree model, so n = 6.

[0103] According to this embodiment, preferably, the optimization range of the control variables of the decision tree model in step S2 needs to set constraint boundaries, and the constraint boundaries include forward speed, cotton picking roller speed, spindle speed, doffer speed, fan speed and fan opening constraint; according to the type of picking environment, set the constraint range for the forward speed; establish the impurity rate target value constraint, and combine the impurity rate prediction model to solve the constraint range of the operating parameters; according to this embodiment, preferably, the impurity rate target value is set between 8% and 10%.

[0104] In order to verify the accuracy of the impurity rate prediction model, the sample data obtained from the impurity rate prediction model in the present invention, the sample data obtained from the traditional impurity rate prediction method, and the actual impurity rate data are subjected to deviation standardization processing so that all data fall into the interval [0, 1].

[0105] According to this embodiment, preferably, the function expression of the deviation standardization processing is:

[0106]

[0107] In the formula, x is the original data,

[0108] max is the maximum value of the sample data,

[0109] min is the minimum value of the sample data.

[0110] Figure 3 is the effect schematic diagram of the impurity content prediction model of the present invention, as Figure 3 shown, the horizontal axis is the true impurity content data after processing, and the vertical axis is the sample data after processing by the impurity content prediction model of the present invention;

[0111] Figure 4 is the effect schematic diagram of the impurity content prediction model obtained by the traditional method, as Figure 4 shown, the horizontal axis is the true impurity content data after processing, and the vertical axis is the sample data obtained by predicting the impurity content by the traditional method after processing;

[0112] From Figure 3 and Figure 4 it can be concluded that: Figure 3 Relative to Figure 4 the predicted data is more concentrated and has a higher correlation. It can be known that compared with the traditional method of relying on the operator's experience to select operating parameters, the present invention has a greater positive effect on reducing the impurity content of cotton.

[0113] According to this embodiment, preferably, the specific steps of optimizing the gray wolf algorithm in step S3 include:

[0114] Step S3.1: Initialize the number of iterations and several impurity content prediction results;

[0115] Step S3.2: For each prediction result, calculate the distance from each operating parameter data to the impurity content prediction result, and assign each operating parameter data to the class of the impurity content prediction result closest to it to form a group;

[0116] Step S3.3: For each group, randomly select multiple operating parameter data from it, calculate the fitness of each selected operating parameter data, and select the α wolf, β wolf, δ wolf and ω wolf based on the fitness value. Based on the selected α wolf, β wolf and δ wolf, update the best hunting position of each ω wolf, and recalculate the fitness value of all the updated gray wolves to update the α wolf, and use it as the new impurity content prediction result;

[0117] Step S3.4: If the iteration converges or meets the stop condition, retain the impurity content prediction result with the optimal fitness value and output the group corresponding to the impurity content prediction result; otherwise, increment the number of iterations by 1 and return to step S3.2.

[0118] Furthermore, the expression of the best hunting position in step S3.3 is:

[0119]

[0120]

[0121] Where θ is the inertia weight, and θ = 0.5·(1 + rand);

[0122] λ 1 、λ 2 、λ 3 respectively represent the weights of the current α, β, and δ wolves and the ω wolf before the best hunting position in the (i + 1)-th iteration;

[0123] r 1 r 2 r 3 is a random number in the range of modulo [0, 1];

[0124] is the position of the k-th best hunting in the i-th generation;

[0125] is the position of the k-th best hunting in the (i + 1)-th generation;

[0126] is the velocity of the k-th ω wolf determined in the i-th generation;

[0127] is the velocity of the k-th ω wolf determined in the (i + 1)-th generation

[0128] is the position of the prey relative to the positions of the α, β, and δ wolves.

[0129] According to this embodiment, preferably, the mathematical model for the gray wolf individual to track the prey position is as follows:

[0130]

[0131] Then it can be obtained that

[0132]

[0133] Where respectively represent the positions of the α, β, and δ wolves and the ω wolf in the i-th generation;

[0134] respectively represent the distances between the current α, β, and δ wolves and the ω wolf;

[0135] is the coefficient vector, and its calculation formula is:

[0136]

[0137] Where is an arbitrary vector between [0, 1];

[0138] is the scaling factor, which linearly decreases from 2 to 0 over time during the iteration process, and its expression is:

[0139]

[0140] where i is the current iteration number, and I max is the maximum number of iterations.

[0141] According to this embodiment, preferably, when the coefficient vector < 1, α wolves, β wolves, and δ wolves will attack in the direction of the prey; when the coefficient vector > 1, α wolves, β wolves, and δ wolves will move away from the prey;

[0142] According to this embodiment, preferably, the construction idea of the grey wolf optimization algorithm is:

[0143] The grey wolf algorithm is an algorithm inspired by the leadership hierarchy and hunting mechanism of grey wolves in nature. There is a strict hierarchical system in the grey wolf group. According to the habits of grey wolves, the wolf pack is divided into four levels: α, β, δ, and ω, and each level of wolf has different divisions of labor.

[0144] Specifically, the α wolf is the dictator in the wolf pack and is responsible for all decisions of the group, including hunting; the β wolf is the best candidate when the α wolf is sick or dies, assists the α wolf in making decisions, and feeds back information of other levels of wolf packs to the α wolf; the δ wolf obeys the orders of the α wolf and the β wolf, and at the same time can also command the actions of the ω wolf, mainly responsible for scouting and guarding in the population; the ω wolf obeys the α wolf and the β wolf by listening to the command of the δ wolf.

[0145] The optimization result of the grey wolf algorithm has not been verified. Example 1 provides schematic diagrams of the change trends of fitness values in the optimization process of the grey wolf optimization algorithm under 2 different picking environments, Figure 5a is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in the picking environment of Test Site 1 in the Xinjiang cotton area of the present invention; Figure 5b is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in the picking environment of Test Site 2 in the Xinjiang cotton area of the present invention;

[0146] Figure 5a is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in Test Site 1 in the Xinjiang cotton area of the present invention, Figure 5b is a schematic diagram of the change trend of the fitness value in the optimization process of the grey wolf optimization algorithm in Test Site 2 in the Xinjiang cotton area of the present invention, as Figure 5a and Figure 5bAs shown in the figure, the horizontal axis represents the number of iterations, with the unit of times, and the vertical axis represents the fitness value, which is a dimensionless value. It can be seen that the optimization of the prediction model by the Grey Wolf Optimization Algorithm can reduce the impact of the environment on the impurity content rate, and lower the impurity content rate of the cotton picker in two different picking environments (the plant height and density of cotton plants) at the test sites 1 and 2 in the Xinjiang cotton region.

[0147] From the optimization effects in the above-mentioned picking environments of the test sites, it can be known that the present invention establishes a model through a decision tree model and uses the Grey Wolf Algorithm for optimization, so as to obtain the optimal operation parameters in different situations. While ensuring the harvesting efficiency, the harvesting quality is improved. And by adding the picking environment type as an input in the decision tree model, the present invention can cope with the operations in different picking environments, avoiding the problem that the selection of operation parameters mainly relied on the historical work experience of the machine operator in the past and had poor adaptability to the picking environment.

[0148] Embodiment 2

[0149] An intelligent decision-making system for the picking environment of the operation parameters of a cotton picker includes a model establishment module, an optimization equation module, a Grey Wolf Algorithm module, and a parameter setting module;

[0150] The model establishment module is used to establish a decision tree model according to the operation parameters, operating parameters, and picking environment type of the cotton picker;

[0151] The optimization equation module is used to obtain the impurity content rate optimization equation of the cotton picker according to the decision tree model;

[0152] The Grey Wolf Algorithm module is used to optimize the impurity content rate optimization equation by using the Grey Wolf Optimization Algorithm to obtain the corresponding operation parameter decision result;

[0153] The parameter setting module is used to set the operation parameters of the cotton picker according to the step operation parameter decision result.

[0154] This system can adjust the operation parameters of the cotton picker in different picking environments, and effectively reduce the impurity content rate of the cotton picker to further improve the operation quality on the premise of ensuring the efficiency of the cotton harvesting operation.

[0155] Embodiment 3

[0156] An electronic device includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the intelligent decision-making method for the picking environment of the operation parameters of the cotton picker described in Embodiment 1 are completed.

[0157] It should be understood that although this specification is described in accordance with various embodiments, not every embodiment contains only an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0158] The series of detailed descriptions listed above are only specific descriptions of the feasible embodiments of the present invention, and they are not intended to limit the protection scope of the present invention. Any equivalent embodiments or changes made without departing from the technical spirit of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent decision-making method for the operating parameters of a cotton picker in the picking environment, characterized in that, it includes the following steps: Step S1: Establish a decision tree model based on the operating parameters, operation parameters, and picking environment type of the cotton picker; Step S2: According to the decision tree model described in Step S1, obtain the impurity rate optimization equation of the cotton picker; Step S3: Use the grey wolf optimization algorithm to optimize the impurity rate optimization equation described in Step S2 to obtain the corresponding operation parameter decision result; Step S4: Set the operation parameters of the cotton picker according to the operation parameter decision result described in Step S3; The specific steps of the said Step S1 include: Step S1.1: Obtain the operating parameters, operation parameters, and picking environment type of the cotton picker from the cotton picker; Step S1.2: Combine the operating parameters and operation parameters of the cotton picker obtained in Step S1.1 with the picking environment type at the corresponding position to obtain a set of characteristic sample points, and label the corresponding sample points in the sample point set with the impurity rate of the cotton picker; Step S1.3: Perform data preprocessing on the sample point set in Step S1.

2. According to the operating state parameters in the operating parameters of the cotton picker, select the sample points when the cotton picker is in the "working" state, and remove the sample points when the cotton picker is in the "grain unloading" and "shutdown" states; Step S1.4: Select a certain proportion of sample points from the sample point set preprocessed in Step S1.3 as the training set, and the remaining sample points as the test set; Step S1.5: Input the training set data described in Step S1.4 into the decision tree model to establish an impurity rate prediction model for the picking environment type, operation parameters, and impurity rate, and verify the effectiveness of the decision tree model with the test set data to obtain the final decision tree model; The impurity rate optimization equation of the said Step S2 takes the minimum impurity rate as the goal and the operation parameters as the control variables. The expression of the impurity rate optimization equation is: f(x 1 ,x 2 ,……x n ,s,t) where x 1 , x 2 , …… x n are respectively n input operation parameters s is the plant height, t is the density, x i is the i-th operation parameter, is the lower bound constraint for the i-th operation parameter, is the upper bound constraint of the i-th operating parameter; The specific steps of the grey wolf algorithm optimization in the said Step S3 include: Step S3.1: Initialize the number of iterations and several impurity rate prediction results; Step S3.2: For each prediction result, calculate the distance from each operating parameter data to the impurity rate prediction result, and assign each operating parameter data to the class of the impurity rate prediction result closest to it to form a group; Step S3.3: For each group, randomly select multiple operating parameter data from it, calculate the fitness of each selected operating parameter data, and select the α wolf, β wolf, δ wolf, and ω wolf based on the fitness value. Based on the selected α wolf, β wolf, and δ wolf, update the best hunting position of each ω wolf, and recalculate the fitness value of all grey wolves after the update to update the α wolf and use it as the new impurity rate prediction result; Step S3.4: If the iteration converges or meets the stop condition, retain the impurity rate prediction result with the optimal fitness value and output the group corresponding to the impurity rate prediction result; otherwise, increment the number of iterations by 1 and return to Step S3.

2.

2. The intelligent decision-making method for the operating parameters of a cotton picker in the picking environment according to claim 1, characterized in that, The operating parameters and operation parameters of the cotton picker in step S1 at least include the operating state, forward speed, cotton picking roller speed, spindle speed, doffer speed, fan speed, and fan opening.

3. The intelligent decision-making method for the picking environment of the cotton picker operating parameters according to claim 1, wherein, the type of the picking environment in step S1 is at least affected by the plant height and density of the cotton plants.

4. The intelligent decision-making method for the picking environment of the cotton picker operating parameters according to claim 1, wherein, the optimization range of the control variables of the decision tree model in step S2 needs to set constraint boundaries, and the constraint boundaries at least include constraints on the forward speed, cotton picking roller speed, spindle speed, doffer speed, fan speed, and fan opening; according to the type of the picking environment, set the constraint range for the forward speed; establish a target value constraint for the impurity content rate, and combine with the impurity content rate prediction model to solve the constraint range of the operation parameters.

5. The intelligent decision-making method for the picking environment of the cotton picker operating parameters according to claim 1, wherein, the expression of the best hunting position in step S3.3 is: In the formula, θ is the inertia weight, θ = 0.5·(1 + rand), and rand is a random number; λ 1 , λ 2 , λ 3 respectively represent the weights of the current three wolves α, β, δ and the position before the best hunting position of the i-th generation in the (i + 1)-th iteration; r 1 、r 2、 r 3 is a random number in the modulo range of [0, 1]; is the position of the k-th best hunt in the i-th generation; is the position of the k-th best hunt in the (i + 1)-th generation; is the velocity of the k-th ω-wolf in the i-th generation that is determined; is the velocity of the k-th ω-wolf in the (i + 1)-th generation that has been determined; is the position of the prey relative to the positions of three wolves, α, β, and δ; In the formula, respectively represent the positions of three wolves α, β, δ and wolf ω in the i-th generation; respectively represent the distances between the current three wolves α, β, δ and the omega wolf ω; is the coefficient vector, and its calculation formula is: Among them, is an arbitrary vector between [0, 1]; is the scaling factor, which linearly decreases from 2 to 0 over time during the iteration process, and its expression is: where i is the current iteration number and I max is the maximum number of iterations.

6. A system for the intelligent decision-making method for the picking environment of the cotton picker operating parameters according to any one of claims 1-5, wherein, it includes a model establishment module, an optimization equation module, a grey wolf algorithm module, and a parameter setting module; the model establishment module is used to establish a decision tree model according to the operating parameters, operation parameters, and picking environment type of the cotton picker; the optimization equation module is used to obtain the impurity content rate optimization equation of the cotton picker according to the decision tree model; the grey wolf algorithm module is used to optimize the impurity content rate optimization equation by using the grey wolf optimization algorithm to obtain the corresponding decision result of the operation parameters; the parameter setting module is used to set the operation parameters of the cotton picker according to the decision result of the step operation parameters.

7. An electronic device, wherein, it includes a memory, a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the steps of the method according to any one of claims 1-5 are completed.

Images