Transplanting performance testing method and system for rapeseed seedling transplanter

Abstract

The present invention provides a transplanting performance test method and system of a rape seedling pot transplanter, which relates to the technical field of transplanting performance of a transplanter. The specific steps include: firstly, carrying out transplanting tests with different working parameter combinations to obtain loss and transplanting parameters such as substrate loss rate, pot seedling damage rate, seedling success rate and transplanting success rate; constructing a transplanting prediction model, using the working parameters of the transplanter as input, and the loss and transplanting parameters as labels to train the model; randomly combining parameters to obtain loss and transplanting indicators; performing data processing and correlation analysis to generate risk coefficients and survival coefficients, and comprehensively calculating a comprehensive evaluation coefficient; finally, comparing the comprehensive evaluation coefficient with a preset threshold value to evaluate the performance of the transplanter. The present invention is more helpful in identifying potential risk factors, improving the success rate of transplanting, and can also effectively reflect the overall performance of the transplanter under specific conditions, providing users with clear performance evaluation results.

Description

Technical Field

[0001] The invention relates to the technical field of transplanting performance of a transplanter, and in particular to a method and system for testing the transplanting performance of a rapeseed seedling transplanter. Background Art

[0002] Rapeseed seedling transplanter is an important equipment for efficient and accurate transplanting of rapeseed seedlings in modern agriculture. With the improvement of agricultural mechanization, the traditional manual transplanting method is gradually replaced by mechanized operation to achieve higher labor efficiency and better growth effect. As an important oil crop, the growth and survival rate of rapeseed is directly related to the economic benefits of farmers. Therefore, it is particularly important to develop an efficient rapeseed seedling transplanter and its performance test method.

[0003] In the prior art, a transplanting performance test method and system for a transplanter provided by publication number CN107101842A, the system includes a control device and a detection device installed on the transplanter, the control device is a data acquisition system, the detection device includes a microcontroller and a sensor, the control device and the microcontroller are connected to each other through a wireless communicator: there are multiple sensors, and the multiple sensors are used to detect transplanting information when transplanting seedlings; the microcontroller is used to obtain the transplanting information detected by the sensor and send the transplanting information to the control device; after receiving the transplanting information, the control device analyzes the transplanting performance of the transplanter according to the transplanting information to obtain the transplanting performance parameters, and the transplanting performance parameters include at least one of the following: the slip rate of the transplanter ground wheel and the transplanter transplanting disc, the surface subsidence of the ground passed by the transplanter ground wheel, the number of seedlings transplanted by the transplanter, and the planting depth of the seedlings transplanted by the transplanter.

[0004] However, there are still the following deficiencies. From the above statements, it can be seen that although the system obtains some transplanting information through sensors, it fails to effectively consider the systematic impact of different environments, soils and seedling health conditions on the transplanting results, which may lead to insufficient representativeness of the data; there is a lack of comprehensive consideration of important loss indicators such as pot seedling damage and substrate loss, which limits the comprehensive evaluation of the transplanting effect and cannot effectively judge the risks and survival probabilities during the transplanting process.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a method and system for testing the transplanting performance of a rapeseed seedling transplanter, so as to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for testing the transplanting performance of a rapeseed seedling transplanter, the specific steps comprising:

[0009] S1. Select healthy and uniform-sized rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, transplant the rape seedlings in pots under different combinations of transplanter working parameters, collect the same number of rape seedlings in pots in each area before transplanting, obtain loss index parameters and transplanting parameters after average processing, the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and perform maximum-minimum normalization processing on similar data;

[0010] S2. construct a transplanting prediction model, take the working parameter combinations of different transplanters as input, and use the averaged loss index parameters and transplanting parameters as label training models to train the transplanting prediction model;

[0011] S3. Establishing constraints on the working parameters of the transplanter, under the constraints of the working parameters of the transplanter, randomly combining the working parameters of the transplanter, constructing individuals of the initial population of working parameters of the transplanter, and inputting the individuals of the initial population of working parameters of the transplanter into the transplant prediction model to obtain the loss index parameters and transplant parameters of the averaged processing;

[0012] S4. Processing the loss index parameters and performing correlation analysis to generate a risk coefficient for evaluating the risk of damage to rape seedlings in pots, processing the transplanting parameters and performing correlation analysis to generate a survival coefficient for evaluating the probability of survival of rape seedlings in pots, and processing the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of rape seedlings in pots;

[0013] S5. Compare the comprehensive evaluation coefficient with a preset threshold value, and obtain the performance of the transplanter in transplanting rapeseed seedlings according to the comparison result.

[0014] Furthermore, the working parameters of the transplanter are randomly combined to construct individuals of the initial population of the working parameters of the transplanter. The specific process is as follows:

[0015] The initial population is labeled , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively The individual push rod movement speed, push rod diameter and clamping speed of the clamping jaws.

[0016] Furthermore, the calculation method of the average substrate loss rate, the average pot seedling damage rate, the average seedling success rate and the average transplanting success rate is as follows:

[0017]

[0018] in, is the average matrix loss rate, For the Individuals before transplanting The matrix quality of the region, For the After transplanting, The matrix quality of the region, is the index of the region, , is the number of regions;

[0019]

[0020] in, is the average seedling damage rate in pots, For the Individuals at the time of transplanting The number of damaged seedlings in the area, For the Individuals before transplanting The number of seedlings in pots in the area;

[0021]

[0022] in, is the average success rate of seedling extraction, For the Individuals at the time of transplanting The number of potted seedlings successfully removed from the area without damage;

[0023]

[0024] in, is the average transplant success rate, For the After transplanting, The number of potted seedlings that survive and grow normally in the area.

[0025] Furthermore, the transplant prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function;

[0026] The process of training the transplant prediction model is as follows:

[0027] Different combinations of transplanter working parameters are used as input, and the averaged loss index parameters and transplanting parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When it is within the range, the training of the transplanting prediction model is completed.

[0028] Furthermore, the loss index parameters processed by averaging were subjected to data processing and correlation analysis to generate a risk coefficient for assessing the risk level of rapeseed seedling damage, based on the following formula:

[0029]

[0030] in, For the The risk coefficient of each individual is used to reflect the degree of damage risk of the individual from two levels: the average matrix loss rate and the average pot seedling damage rate. , are the weight coefficients of the height and rooting depth of rapeseed seedlings, respectively. On the basis of .

[0031] Furthermore, the transplanting parameters with mean value processing were processed and correlation analysis was performed to generate the survival coefficient for evaluating the survival probability of rapeseed seedlings in pots, based on the following formula:

[0032]

[0033] in, For the The survival coefficient of each individual is used to reflect the probability of growth and survival of the individual from two levels: the average seedling success rate and the average transplanting success rate.

[0034] Furthermore, the risk coefficient and the survival coefficient are processed to generate a comprehensive evaluation coefficient for comprehensively evaluating the effect of transplanting rapeseed seedlings in pots, based on the following formula:

[0035]

[0036] in, For the The comprehensive evaluation coefficient of each individual, and are the weights in the calculation of survival coefficient and risk coefficient respectively, and and The specific value of is determined by the hierarchical analysis method.

[0037] Furthermore, the comprehensive evaluation coefficient is compared with a preset threshold value, and the performance of the transplanter for transplanting rapeseed seedlings is obtained according to the comparison result. The specific process is as follows:

[0038] When The comprehensive evaluation coefficient of each individual is greater than the threshold, that is, , then the rape seedlings transplanted under any combination of the transplanter's working parameters have a good effect, which means that the rape seedlings transplanter has superior transplanting performance;

[0039] When The comprehensive evaluation coefficient of each individual is less than or equal to the threshold, that is, , then the rape seedlings transplanted under any combination of the transplanter's working parameters have poor results, which means that the rape seedlings transplanter has poor transplanting performance;

[0040] in, is a preset threshold.

[0041] To achieve the above object, the present invention also provides the following technical solutions:

[0042] A system for testing the transplanting performance of a rapeseed seedling transplanter, the system being used to execute any of the above-mentioned methods for testing the transplanting performance of a rapeseed seedling transplanter, comprising:

[0043] The data acquisition module is used to select healthy and uniform rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, and transplant the rape seedlings in pots under different combinations of transplanter working parameters. Before transplanting, the same number of rape seedlings in pots are collected in each area to obtain loss index parameters and transplanting parameters after average processing, wherein the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, and the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and the same type of data is subjected to maximum-minimum normalization processing;

[0044] The prediction model building module is used to build a transplant prediction model, taking the working parameter combinations of different transplanters as input, and the averaged loss index parameters and transplant parameters as label training models to train the transplant prediction model;

[0045] A parameter combination and output module is used to establish constraints on the working parameters of the transplanter, randomly combine the working parameters of the transplanter under the constraints of the working parameters of the transplanter, construct individuals of the initial population of the working parameters of the transplanter, input the individuals of the initial population of the working parameters of the transplanter into the transplant prediction model, and obtain the loss index parameters and transplant parameters of the averaged processing;

[0046] The data processing and analysis module is used to process the loss index parameters and perform correlation analysis to generate a risk coefficient for evaluating the risk degree of damage to the rape seedlings in pots, process the transplanting parameters and perform correlation analysis to generate a survival coefficient for evaluating the probability of survival of the rape seedlings in pots, and process the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of the rape seedlings in pots;

[0047] The performance evaluation module is used to compare the comprehensive evaluation coefficient with a preset threshold value, and obtain the performance of the transplanter transplanting rapeseed seedlings according to the comparison result.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention ensures the uniformity and representativeness of data by selecting healthy and uniform-sized rapeseed seedlings in the experimental design and conducting tests under uniform soil and environmental conditions. This improvement makes the obtained transplanting performance parameters more universally applicable and can better reflect the effects in practical applications.

[0050] By introducing loss indicators such as substrate loss rate and pot seedling damage rate, and transplanting parameters such as seedling success rate and transplanting success rate, the risk factor and survival factor are comprehensively processed to generate a comprehensive evaluation coefficient, making the evaluation of transplanting effect more comprehensive and accurate. This comprehensiveness helps to identify potential risk factors, improve the success rate of transplanting, and effectively reflect the overall performance of the transplanter under specific conditions, providing users with clear performance evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0052] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] Embodiment 1:

[0056] See also Figure 1 , the present invention provides a technical solution:

[0057] A method for testing the transplanting performance of a rapeseed seedling transplanter, the specific steps comprising:

[0058] S1. Select healthy and uniform-sized rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, transplant the rape seedlings in pots under different combinations of transplanter working parameters, collect the same number of rape seedlings in pots in each area before transplanting, obtain loss index parameters and transplanting parameters after average processing, the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and perform maximum-minimum normalization processing on similar data;

[0059] S2. construct a transplanting prediction model, take the working parameter combinations of different transplanters as input, and use the averaged loss index parameters and transplanting parameters as label training models to train the transplanting prediction model;

[0060] S3. Establishing constraints on the working parameters of the transplanter, under the constraints of the working parameters of the transplanter, randomly combining the working parameters of the transplanter, constructing individuals of the initial population of working parameters of the transplanter, and inputting the individuals of the initial population of working parameters of the transplanter into the transplant prediction model to obtain the loss index parameters and transplant parameters of the averaged processing;

[0061] S4. Processing the loss index parameters and performing correlation analysis to generate a risk coefficient for evaluating the risk of damage to rape seedlings in pots, processing the transplanting parameters and performing correlation analysis to generate a survival coefficient for evaluating the probability of survival of rape seedlings in pots, and processing the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of rape seedlings in pots;

[0062] S5. Compare the comprehensive evaluation coefficient with a preset threshold value, and obtain the performance of the transplanter in transplanting rapeseed seedlings according to the comparison result.

[0063] Based on the above embodiment, the moving speed of the push rod refers to the moving speed of the push rod in the transplanter when performing seedling removal or seedling placement operations. Appropriate moving speed of the push rod is crucial to ensuring the integrity of the seedlings in the pot and reducing damage. Too fast speed may cause the seedlings in the pot to be impacted and increase the damage rate, while too slow speed may affect work efficiency.

[0064] The diameter of the push rod refers to the diameter of the push rod used to clamp and remove the seedlings from the pot in the transplanter. The choice of the push rod diameter directly affects the clamping effect on the seedlings. Too large a diameter may cause squeezing and damage to the seedlings, while too small a diameter may lead to unstable clamping, which in turn causes the substrate to fall. Choosing a suitable push rod diameter will help improve the success rate of seedling removal.

[0065] The clamping speed of the clamp refers to the movement speed of the clamp in the transplanter when clamping and releasing the seedlings in the pot. The clamping speed affects the accuracy of the clamp in grasping and releasing the seedlings in the pot. Clamping too fast may cause the seedlings in the pot to fail to be firmly clamped, thereby increasing the risk of damage and substrate falling; clamping too slowly may affect the overall work efficiency.

[0066] On the basis of the above embodiment, the working parameters of the transplanter are randomly combined to construct individuals of the initial population of working parameters of the transplanter. The specific process is as follows:

[0067] The initial population is labeled , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively The individual push rod movement speed, push rod diameter and clamping speed of the clamping jaws.

[0068] On the basis of the above-mentioned embodiment, the calculation method of the average substrate loss rate, the average pot seedling damage rate, the average seedling success rate and the average transplanting success rate is as follows:

[0069]

[0070] in, is the average matrix loss rate, For the Individuals before transplanting The matrix quality of the region, For the After transplanting, The matrix quality of the region, is the index of the region, , is the number of regions;

[0071]

[0072] in, is the average seedling damage rate in pots, For the Individuals at the time of transplanting The number of damaged seedlings in the area, For the Individuals before transplanting The number of seedlings in pots in the area;

[0073]

[0074] in, is the average success rate of seedling extraction, For the Individuals at the time of transplanting The number of potted seedlings successfully removed without damage in the area;

[0075]

[0076] in, is the average transplant success rate, For the After transplanting, The number of potted seedlings that survive and grow normally in the area.

[0077] On the basis of the above embodiment, the transplant prediction model is composed of a deep learning network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function;

[0078] In this embodiment, the input features of the deep learning network of the multilayer perceptron include three features: the moving speed of the push rod, the diameter of the push rod, and the clamping speed of the clamp.

[0079] The structure of the deep learning network of multi-layer perceptron is:

[0080] Input layer: receives input of 3 features;

[0081] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0082] The second hidden layer has 32 neurons and also uses the ReLU activation function.

[0083] The third hidden layer has 16 neurons and uses the ReLU activation function.

[0084] Output layer: has 2 neurons, averaged loss parameter and transplantation parameter.

[0085] The process of training the transplant prediction model is as follows:

[0086] Different combinations of transplanter working parameters are used as input, and the averaged loss index parameters and transplanting parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When it is within the range, the training of the transplanting prediction model is completed.

[0087] Based on the above examples, the correlation between the substrate loss rate, the pot seedling damage rate and the rapeseed pot seedling loss risk level is as follows:

[0088] Generally speaking, the substrate loss rate is positively correlated with the risk of rapeseed seedling loss, because the reduction of substrate makes it impossible for seedlings to obtain sufficient water and nutrients, reducing their ability to survive and grow, thereby increasing the risk of loss.

[0089] Generally speaking, there is a positive correlation between the seedling damage rate and the loss risk. The increase in the seedling damage rate makes it more likely for the seedlings to grow poorly or die during their growth, which in turn increases the risk of rapeseed seedling loss.

[0090] According to the correlation between substrate loss rate, seedling damage rate and rapeseed seedling loss risk, the loss index parameters with mean value processing are processed and correlation analysis is performed to generate a risk coefficient for assessing the risk of rapeseed seedling damage. The formula is as follows:

[0091]

[0092] in, For the The risk coefficient of each individual is used to reflect the degree of damage risk of the individual from two levels: the average matrix loss rate and the average pot seedling damage rate. The larger the risk coefficient, the higher the damage risk.

[0093] , They are the weight coefficients of the average substrate loss rate and the average pot seedling damage rate, respectively, which are used to reflect the influence of different loss indicators on the risk coefficient;

[0094] The reasons for setting the above functional form to express the functional relationship between the risk coefficient and the average substrate loss rate and the average pot seedling damage rate are as follows:

[0095] First, the substrate loss rate reflects the amount of substrate lost during the transplanting process, which directly affects the growth environment of rapeseed seedlings. The reduction of substrate will lead to insufficient water and nutrients, thus affecting the growth and survival of plants. It can effectively reflect the positive impact of substrate loss on damage risk. The more serious the substrate loss, the higher the damage risk of rapeseed seedlings.

[0096] Second, the pot seedling damage rate reflects the damage to the pot seedlings themselves during the transplanting process. Damaged pot seedlings are more likely to have problems such as poor growth and death during the growth process. It can reflect the positive impact of seedling damage on damage risk, and the increase in damage rate will directly increase the risk of loss.

[0097] Third, the matrix loss rate and pot seedling damage rate are loss index parameters from two different angles. Therefore, the two parameters are in parallel. The weighted sum of the matrix loss rate and the pot seedling damage rate is used to express the functional relationship between the matrix loss rate, pot seedling damage rate and the risk coefficient.

[0098] Fourth, introduce weight coefficient and This allows the model to be adjusted according to actual conditions and flexibly adapt to different application scenarios and specific needs. This flexibility can make the evaluation process more accurate, thereby providing a more suitable basis for the performance testing of different types of rapeseed seedling transplanters.

[0099] Fifth, risk factor As the weighted sum of substrate loss rate and seedling damage rate, it reflects the assessment of the combined impact of these two factors. This comprehensive assessment method is more comprehensive than a single indicator and can better reflect the overall damage risk faced by rapeseed seedlings during transplanting. This is consistent with the actual rapeseed seedling performance test and helps to fully understand the source and extent of the risk.

[0100] The substrate is the base for plant root growth and is mainly responsible for providing water and nutrients. If the substrate is seriously lost, the plant will face the risk of lack of water and nutrients, resulting in growth restriction or even death. Therefore, the impact of substrate loss is often direct and significant.

[0101] Moreover, during the transplanting process, substrate loss is often unavoidable, and this loss may have a greater impact on the plants in a short period of time. Compared with substrate loss, damage to potted seedlings may be reversible to a certain extent. Although damage will affect plant growth, if timely measures are taken, such as proper management and maintenance, potted seedlings may still be able to recover. Therefore, the impact of potted seedling damage may be considered lower than substrate loss in some cases.

[0102] In summary, when assessing risk, the weight of matrix loss is set higher. On the basis of .

[0103] As an implementation method, The value range is an open interval of 0.5-0.6. The value range is an open interval of 0.4-0.5. The specific value is set by the technicians according to the actual situation and is not limited here.

[0104] Based on the above embodiment, the correlation between the success rate of seedling removal, the success rate of transplanting and the probability of rapeseed seedlings growing and surviving is as follows:

[0105] The success rate of seedling retrieval is positively correlated with the survival rate of rapeseed seedlings in pots. The higher the success rate of seedling retrieval, the more healthy and strong seedlings can be successfully collected, which usually increases the survival rate of rapeseed seedlings in pots. Healthy seedlings in pots can better adapt to the new environment after transplantation, thereby increasing the survival rate.

[0106] The transplanting success rate is positively correlated with the survival rate of rapeseed seedlings. The higher the transplanting success rate, the stronger the rooting and adaptability of the seedlings after transplantation, which directly affects the survival rate of rapeseed seedlings. Successful transplanting can help plants grow rapidly and stably, reduce setbacks in the survival process, and thus improve the survival rate.

[0107] According to the correlation between the success rate of seedling removal, the success rate of transplanting and the probability of survival of rapeseed seedlings in pots, the transplanting parameters with mean value processing are processed and correlation analysis is performed to generate the survival coefficient for evaluating the probability of survival of rapeseed seedlings in pots. The formula is as follows:

[0108]

[0109] in, For the The survival coefficient of each individual is used to reflect the probability of survival of the individual from two aspects: the average success rate of seedlings and the average success rate of transplanting. The larger the survival coefficient, the higher the probability of survival.

[0110] The reasons for setting the above function form to express the functional relationship between the survival coefficient and the seedling success rate and transplanting success rate are as follows:

[0111] First, the survival coefficient The product of the two success rates reflects the interdependence between the success rate of seedling removal and the success rate of transplantation. Only on the basis of successful seedling removal can successful transplantation play a role. Therefore, the product of the two success rates can more truly reflect the survival probability.

[0112] Second, a high seedling retrieval success rate means that the collected seedlings are of higher quality. Healthy seedlings are more likely to adapt to the new environment, thereby increasing the probability of growth and survival. The function reflects the positive correlation between the seedling retrieval success rate and the probability of growth and survival of rapeseed seedlings in pots.

[0113] Third, the high transplanting success rate indicates that the seedlings have strong rooting and adaptability after transplantation, which directly promotes the improvement of the survival probability. Similarly, the function reflects the positive correlation between the transplanting success rate and the survival probability of rapeseed seedlings.

[0114] Fourth, this positive correlation is reflected in the product form. Only when both success rates are high, the survival coefficient will increase significantly, and vice versa.

[0115] On the basis of the above embodiment, the risk coefficient and the survival coefficient are processed to generate a comprehensive evaluation coefficient for comprehensively evaluating the effect of transplanting rape seedlings in pots, based on the following formula:

[0116]

[0117] in, For the The comprehensive evaluation coefficient of each individual is used to comprehensively evaluate the transplanting effect of rapeseed seedlings in pots by combining the risk coefficient and the survival coefficient. The transplanting effect of rapeseed seedlings in pots includes the degree of damage risk and the probability of growth and survival. The larger the comprehensive evaluation coefficient, the better the transplanting effect of rapeseed seedlings in pots.

[0118] It should be noted that, as can be seen from the above description, the risk factor The larger the size, the higher the risk of injury and the survival coefficient The larger the value, the higher the probability of survival. Therefore, the comprehensive evaluation coefficient and risk factor Negative correlation, comprehensive evaluation coefficient Survival coefficient Positive correlation, so the above weighted summation form of comprehensive evaluation coefficient calculation formula is set;

[0119] In the formula, and are the weights in the calculation of survival coefficient and risk coefficient respectively, and and The specific value of is determined by the hierarchical analysis method, and the specific logic is as follows:

[0120] The two indicators, survival coefficient and risk coefficient, are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the index of the survival coefficient is marked as 1 and the index of the risk coefficient is marked as 2. The constructed judgment matrix for:

[0121]

[0122] in, , denotes the index of the coefficient, and , , indicating that the index is The importance of the coefficient of index v to the comprehensive evaluation coefficient. The specific value is determined by relevant experts using a 1-9 scoring method. Indicates that the index is The coefficient of is extremely important for the comprehensive evaluation coefficient compared to the coefficient with index v. Indicates that the index is The coefficient of is extremely unimportant to the comprehensive evaluation coefficient compared to the coefficient with index v;

[0123] Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the proportional coefficient of the survival coefficient, and the mean of the element values ​​in the second row is used as the proportional coefficient of the risk coefficient. With the constraint that the sum of the scaled values ​​is equal to 1, the two proportional coefficients are scaled in equal proportion, and the values ​​obtained after scaling are used as the weights of the corresponding coefficients.

[0124] On the basis of the above embodiment, the comprehensive evaluation coefficient is compared with the preset threshold value, and the performance of the transplanter for transplanting rapeseed seedlings is obtained according to the comparison result. The specific process is as follows:

[0125] When The comprehensive evaluation coefficient of each individual is greater than the threshold, that is, , then the rape seedlings transplanted under any combination of the transplanter's working parameters have a good effect, which means that the rape seedlings transplanter has superior transplanting performance;

[0126] When The comprehensive evaluation coefficient of each individual is less than or equal to the threshold, that is, , then the rapeseed seedlings transplanted under any combination of the transplanter's working parameters have poor results, which means that the rapeseed seedlings transplanter has poor transplanting performance.

[0127] in, For pre-set thresholds, small-scale tests can be conducted under specific transplanting conditions to record the transplanting effects corresponding to different comprehensive evaluation coefficients. The value corresponds to a good transplanting effect, and then set .

[0128] See also Figure 2 , the present invention also provides a technical solution:

[0129] A system for testing the transplanting performance of a rapeseed seedling transplanter, the system being used to execute any of the above-mentioned methods for testing the transplanting performance of a rapeseed seedling transplanter, comprising:

[0130] The data acquisition module is used to select healthy and uniform-sized rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, and transplant the rape seedlings in pots under different combinations of transplanter working parameters. Before transplanting, the same number of rape seedlings in pots are collected in each area to obtain loss index parameters and transplanting parameters after average processing, wherein the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, and the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and the same type of data is subjected to maximum-minimum normalization processing;

[0131] The prediction model building module is used to build a transplant prediction model, taking the working parameter combinations of different transplanters as input, and the averaged loss index parameters and transplant parameters as label training models to train the transplant prediction model;

[0132] A parameter combination and output module is used to establish constraints on the working parameters of the transplanter, randomly combine the working parameters of the transplanter under the constraints of the working parameters of the transplanter, construct individuals of the initial population of the working parameters of the transplanter, input the individuals of the initial population of the working parameters of the transplanter into the transplant prediction model, and obtain the loss index parameters and transplant parameters of the averaged processing;

[0133] The data processing and analysis module is used to process the loss index parameters and perform correlation analysis to generate a risk coefficient for evaluating the risk degree of damage to the rape seedlings in pots, process the transplanting parameters and perform correlation analysis to generate a survival coefficient for evaluating the probability of survival of the rape seedlings in pots, and process the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of the rape seedlings in pots;

[0134] The performance evaluation module is used to compare the comprehensive evaluation coefficient with a preset threshold value, and obtain the performance of the transplanter transplanting rapeseed seedlings according to the comparison result.

[0135] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0136] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for testing the transplanting performance of a rapeseed seedling transplanter, characterized in that: The specific steps include: S1. Select healthy and uniform-sized rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, transplant the rape seedlings in pots under different combinations of transplanter working parameters, collect the same number of rape seedlings in pots in each area before transplanting, obtain loss index parameters and transplanting parameters after average processing, the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and perform maximum-minimum normalization processing on similar data; S2. construct a transplant prediction model, take the working parameter combinations of different transplanters as input, and use the averaged loss index parameters and transplant parameters as label training models to train the transplant prediction model; S3. Establishing constraints on the working parameters of the transplanter, under the constraints of the working parameters of the transplanter, randomly combining the working parameters of the transplanter, constructing individuals of the initial population of working parameters of the transplanter, and inputting the individuals of the initial population of working parameters of the transplanter into the transplant prediction model to obtain the loss index parameters and transplant parameters of the averaged processing; S4. Processing the loss index parameters and performing correlation analysis to generate a risk coefficient for evaluating the risk of damage to rape seedlings in pots, processing the transplanting parameters and performing correlation analysis to generate a survival coefficient for evaluating the probability of survival of rape seedlings in pots, and processing the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of rape seedlings in pots; S5. Compare the comprehensive evaluation coefficient with the preset threshold value, and obtain the performance of the transplanter for transplanting rapeseed seedlings according to the comparison result; The working parameters of the transplanter are randomly combined to construct individuals of the initial population of the working parameters of the transplanter. The specific process is as follows: The initial population is labeled , and the initial population , is the first Individuals, is the index of the individual in the initial population, and , is the number of individuals in the initial population, ,in, Respectively Individual push rod moving speed, push rod diameter and gripping speed of the gripper; The calculation method of average substrate loss rate, average pot seedling damage rate, average seedling success rate and average transplanting success rate is as follows: in, is the average matrix loss rate, For the Individuals before transplanting The matrix quality of the region, For the After transplanting, The matrix quality of the region, is the index of the region, , is the number of regions; in, is the average seedling damage rate in pots, For the Individuals at the time of transplanting The number of damaged seedlings in the area, For the Individuals before transplanting The number of seedlings in pots in the area; in, is the average success rate of seedling extraction, For the Individuals at the time of transplanting The number of potted seedlings successfully removed without damage in the area; in, is the average transplant success rate, For the After transplanting, The number of potted seedlings that survived and grew normally in the area; The loss index parameters processed by averaging were subjected to data processing and correlation analysis to generate a risk coefficient for assessing the risk level of rapeseed seedling damage, based on the following formula: in, For the The risk coefficient of each individual is used to reflect the degree of damage risk of the individual from two levels: the average matrix loss rate and the average pot seedling damage rate. , are the weight coefficients of the height and rooting depth of rapeseed seedlings, respectively. On the basis of ; The transplanting parameters with mean value processing were processed and correlation analysis was performed to generate the survival coefficient for evaluating the survival probability of rape seedlings in pots. The formula is as follows: in, For the The survival coefficient of each individual is used to reflect the probability of growth and survival of the individual from two levels: the average success rate of seedlings and the average success rate of transplanting; The risk coefficient and the survival coefficient were processed to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of rapeseed seedlings in pots, based on the following formula: in, For the The comprehensive evaluation coefficient of each individual, and are the weights in the calculation of survival coefficient and risk coefficient respectively, and and The specific value of is determined by the hierarchical analysis method.

2. The method for testing the transplanting performance of the rape seedling pot transplanter according to claim 1, characterized in that: The transplant prediction model is composed of a deep learning network based on a multi-layer perceptron, wherein the deep neural network of the multi-layer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, wherein the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; The process of training the transplant prediction model is as follows: Different combinations of transplanter working parameters are used as input, and the averaged loss index parameters and transplanting parameters are used as output labels for training. The mean square error is used as the loss function. When the mean square error is When it is within the range, the training of the transplanting prediction model is completed.

3. The method for testing the transplanting performance of the rape seedling pot transplanter according to claim 1, characterized in that: The comprehensive evaluation coefficient is compared with the preset threshold value, and the performance of the transplanter in transplanting rapeseed seedlings is obtained according to the comparison result. The specific process is as follows: When The comprehensive evaluation coefficient of each individual is greater than the threshold, that is, , then the rape seedlings transplanted under any combination of the transplanter's working parameters have a good effect, which means that the rape seedlings transplanter has superior transplanting performance; When The comprehensive evaluation coefficient of each individual is less than or equal to the threshold, that is, , then the rape seedlings transplanted under any combination of the transplanter's working parameters have poor results, which means that the rape seedlings transplanter has poor transplanting performance; in, is a preset threshold.

4. A system for testing the transplanting performance of a rapeseed seedling transplanter, the system being used to execute the method for testing the transplanting performance of a rapeseed seedling transplanter according to any one of claims 1 to 3, characterized in that: include: The data acquisition module is used to select healthy and uniform rape seedlings in pots, as well as test plots with uniform soil conditions and environmental factors, divide the test plots into multiple areas, and transplant the rape seedlings in pots under different combinations of transplanter working parameters. Before transplanting, the same number of rape seedlings in pots are collected in each area to obtain loss index parameters and transplanting parameters after average processing, wherein the loss index parameters include substrate loss rate and seedling damage rate, the transplanting parameters include seedling success rate and transplanting success rate, and the transplanter working parameters include mandrel moving speed, mandrel diameter and clamping speed, and the same type of data is subjected to maximum-minimum normalization processing; The prediction model building module is used to build a transplant prediction model, taking the working parameter combinations of different transplanters as input, and the averaged loss index parameters and transplant parameters as label training models to train the transplant prediction model; A parameter combination and output module is used to establish constraints on the working parameters of the transplanter, randomly combine the working parameters of the transplanter under the constraints of the working parameters of the transplanter, construct individuals of the initial population of the working parameters of the transplanter, input the individuals of the initial population of the working parameters of the transplanter into the transplant prediction model, and obtain the loss index parameters and transplant parameters of the averaged processing; The data processing and analysis module is used to process the loss index parameters and perform correlation analysis to generate a risk coefficient for evaluating the risk degree of damage to the rape seedlings in pots, process the transplanting parameters and perform correlation analysis to generate a survival coefficient for evaluating the probability of survival of the rape seedlings in pots, and process the risk coefficient and the survival coefficient to generate a comprehensive evaluation coefficient for comprehensively evaluating the transplanting effect of the rape seedlings in pots; The performance evaluation module is used to compare the comprehensive evaluation coefficient with a preset threshold value, and obtain the performance of the transplanter transplanting rapeseed seedlings according to the comparison result.

Images