Mechanized transplanting seedling quality analysis method and device

Abstract

The invention provides a mechanical transplanting seedling quality analysis method and device, and the method comprises the steps: carrying out the dimensionless processing of a plurality of soil physical property parameters, obtaining a first dimensionless sequence, and carrying out the dimensionless processing of a plurality of transplanting quality evaluation indexes under the condition of completing the mechanical transplanting of a plurality of transplanting seedlings through target soil, so as to obtain a second dimensionless sequence; obtaining a second dimensionless sequence; analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence to obtain the correlation degree between the multiple soil characteristics and the transplanting quality; and carrying out regression analysis on the multiple correlation degrees based on a stepwise regression analysis algorithm of statistical quantiles and a significance test algorithm, and predicting the transplanting quality of the transplanted seedlings by utilizing actual soil physical properties through an empirical formula obtained through analysis. By means of the method, the efficiency of mechanical seedling transplanting is improved, and the appropriate trends of duckbilled mechanical transplanting of plug seedlings in different soil environments are defined.

Description

Technical Field

[0001] The invention relates to the technical field of cultivated land planting, and in particular to a method and a device for analyzing the quality of mechanized transplanted seedlings. Background Art

[0002] As the vegetable planting area continues to expand, mechanized operations are conducive to improving the quality and yield of vegetable production, reducing manual labor input, and improving operational efficiency.

[0003] In order to improve the survival rate of transplanted leafy vegetables such as cabbage, it is usually necessary to use regular plug trays for sowing and seedling raising, and transplant the vegetable seedlings after their growth state is relatively stable. When planting the previous crop, a large amount of agricultural inputs such as pesticides, fertilizers, and agricultural films are applied to the cultivated soil. After the previous crop is harvested, weeds, residues, insect eggs, grass seeds, green manure or manure and other substances will remain in the soil, which seriously threaten the safety of the soil, crops and the environment. Therefore, more tillage and land preparation operations are carried out before transplanting, such as deep loosening of the soil, rotary tillage, ridge formation and application of organic fertilizers, to provide a suitable soil environment for the growth of transplanted seedlings.

[0004] In related technologies, research on mechanized seedling cultivation mostly focuses on the relationship between seedling phenotypic characteristics and the structure of the transplanting device. However, the soil disturbance caused by actual tillage and land preparation operations will lead to interactions between the physical and chemical properties of the seedlings, which will hinder the operation quality of the machinery and the growth of the seedlings, resulting in a low survival rate of the seedlings in the soil after tillage and land preparation operations, thereby affecting the efficiency of mechanized transplanting of seedlings. Summary of the invention

[0005] The present invention provides a mechanized transplant seedling quality analysis method and device, which are used to solve the defect of low efficiency of mechanized transplant seedling when cultivating seedlings by studying the relationship between seedling phenotypic characteristics and transplant device structure in the prior art, thereby improving the efficiency of mechanized transplant seedling and the survival rate of seedling.

[0006] The present invention provides a mechanized transplant seedling quality analysis method, comprising: A plurality of soil physical property parameters are dimensionally processed to obtain a first dimensionless sequence, and when a plurality of transplanted seedlings are mechanized transplanted through the target soil, a plurality of transplanting quality evaluation indicators are dimensionally processed to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to the plurality of soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to the plurality of transplanting quality evaluation indicators; Analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, and obtaining the correlation between multiple soil characteristics and transplanting quality; A stepwise regression analysis algorithm based on statistical quantiles and a significance test algorithm are used to perform regression analysis on multiple correlations to obtain an empirical formula, and the transplanting quality of the transplanted seedlings is predicted based on the empirical formula according to actual soil physical properties.

[0007] According to a mechanized transplant seedling quality analysis method provided by the present invention, the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence is analyzed to obtain the correlation between multiple soil characteristics and transplant quality, including: According to the rank obtained by sorting each element in the first dimensionless sequence and the rank obtained by sorting each element in the second dimensionless sequence, the rank difference and the sum of squares between multiple target sample pairs are obtained; each target sample pair includes a dimensionless number corresponding to a soil physical property parameter and a dimensionless number corresponding to a transplanting quality evaluation index; The Spearman correlation coefficient between soil health and transplanting quality in each target sample was calculated based on the rank difference and sum of squares between each target sample pair; The mean values ​​of the Spearman correlation coefficients corresponding to the target samples are calculated to obtain the correlation between the multiple soil characteristics and the transplanting quality.

[0008] According to a mechanized transplant seedling quality analysis method provided by the present invention, the multiple transplant quality evaluation indicators include transplant depth qualified rate, seedling leakage rate, bare root rate and replanting rate; The dimensionless processing of the plurality of transplanting quality evaluation indicators comprises: The following formula is used to perform dimensionless Z-score standardization on the multiple transplanting quality evaluations: ; in, yes The mean of is a collection of multiple transplanting quality evaluation indicators. yes The standard deviation of i is the number of transplanting quality evaluation indicators, k is the number of samples, For the i The first of the transplanting quality evaluation indicators k Sample values, for The dimensionless value of .

[0009] According to a mechanized transplant seedling quality analysis method provided by the present invention, the multiple soil physical property parameters include soil moisture content, soil surface hardness, soil subsurface hardness and soil particles; The dimensionless processing of multiple soil physical property parameters includes: The plurality of soil physical property parameters are dimensionlessly processed using a membership function, and the membership function is shown in the following formula: ; in, X are multiple soil physical property parameters, F(X) for X The corresponding dimensionless number; X 1 , X 2 , X 3 and X 4 There are four different critical values.

[0010] According to a mechanized transplant seedling quality analysis method provided by the present invention, the multiple soil physical property parameters also include soil bulk density, soil moisture content, soil surface hardness, sub-surface hardness and soil particle composition; The multiple soil physical property parameters are obtained by the following steps: The soil moisture content is obtained from the target soil by using a drying method; the target soil bulk density is obtained from the target soil by using a ring knife method; the soil surface hardness and sub-surface hardness of the target soil are measured by using a hardness meter; and the soil particle composition of the target soil is measured by using a Malvern laser particle size analyzer.

[0011] According to a mechanized transplant seedling quality analysis method provided by the present invention, the target soil includes brown soil, brown loam, sandy soil and yellow loam; The target soil is cultivated and prepared by the following steps: performing tillage and land preparation operations on the target soil, the cinnamon soil, the brown loam soil, the sandy soil, and the yellow loam soil, and collecting a full data set from the soil after the tillage and land preparation operations; Data cleaning is performed on each sample data in the full data set to obtain a new full data set.

[0012] The present invention also provides a mechanized transplant seedling quality analysis device, comprising: The dimensionless calculation module is used to perform dimensionless processing on multiple soil physical property parameters to obtain a first dimensionless sequence, and when mechanized transplanting of multiple transplanted seedlings is completed through the target soil, perform dimensionless processing on multiple transplanting quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to multiple soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to multiple transplanting quality evaluation indicators; A correlation analysis module, used to analyze the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, and obtain the correlation between multiple soil characteristics and transplanting quality; The regression analysis module is used to perform regression analysis on multiple correlations based on a stepwise regression analysis algorithm of statistical quantiles and a significance test algorithm to obtain an empirical formula, and predict the transplanting quality of the transplanted seedlings based on the actual soil physical properties based on the empirical formula.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned mechanized transplanted seedling quality analysis methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the mechanized transplanted seedling quality analysis method as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the mechanized transplanted seedling quality analysis method as described above is implemented.

[0016] The mechanized transplant seedling quality analysis method and device provided by the present invention perform dimensionless processing on soil physical property parameters and transplant quality evaluation indicators respectively, and obtain the correlation between soil characteristics and transplant quality according to the correlation between each element in the corresponding dimensionless sequence. Finally, multiple correlations are screened based on the stepwise regression analysis algorithm of statistical quantiles and the significance test algorithm to obtain the target correlation. The correlation between the physical properties of cultivated land soil and the mechanized transplanting of seedlings is quantified, and the coordination between the mechanized transplanting characteristics of different leafy vegetable seedlings and the soil physical properties is achieved, the efficiency of mechanized transplanting of seedlings is improved, and the suitable trend of duckbill mechanized transplanting of plug seedlings under different soil environments is clarified. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow diagrams of the mechanized transplanted seedling quality analysis method provided by the present invention.

[0019] Figure 2It is a schematic diagram of the coupling relationship between the physical properties of cultivated soil and the cabbage transplanting quality and transplanting efficiency provided by the present invention.

[0020] Figure 3 This is the second flow chart of the mechanized transplanted seedling quality analysis method provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of the mechanized transplanted seedling quality analysis device provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Combine the following Figure 1-Figure 4 The invention describes a method and a device for analyzing the quality of mechanized transplanted seedlings.

[0025] Figure 1 This is one of the flow diagrams of the mechanized transplanted seedling quality analysis method provided by the present invention, such as Figure 1 As shown, the mechanized transplanting seedling quality analysis method comprises the following steps: Step 110, dimensionlessly process a plurality of soil physical property parameters to obtain a first dimensionless sequence, and when mechanized transplanting of a plurality of transplanted seedlings is completed through the target soil, dimensionlessly process a plurality of transplanting quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to a plurality of soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to a plurality of transplanting quality evaluation indicators.

[0026] In this step, the target soil is the planting soil for seedlings of different leafy vegetables, for example, the target soil may be the planting soil for seedlings of leafy vegetables such as cabbage, spinach, lettuce or chrysanthemum.

[0027] Specifically, in the laboratory, the collected soil samples are free of debris such as stones and plant residues, and large lumps of soil are crushed, mixed, air-dried, and ground through a 0.25 mm, 1 mm, or 2 mm sieve for the determination of soil physical properties. Based on the Cornell soil physical property parameter system, multiple physical indicators of the above-mentioned target soils are determined, namely, soil bulk density, soil moisture content, soil surface hardness, soil sub-surface hardness, and soil particle composition.

[0028] Specifically, the physical properties of the soil in the target soil are measured to obtain multiple soil physical property parameters including: obtaining soil moisture content from the target soil by a drying method; obtaining soil bulk density from the target soil by a ring knife method; measuring the soil surface hardness and sub-surface hardness of the target soil by a hardness meter; and measuring the soil particle composition of the target soil by a Malvern laser particle size analyzer.

[0029] In this implementation, the soil subsurface layer is 10 cm to 20 cm from the ground, and the soil surface layer is 0 cm to 10 cm from the ground; the soil particle composition includes sand, silt and clay.

[0030] Specifically, the plot is evenly divided into n 10*50mm 2 The corresponding soil physical property parameters of cultivated land include soil bulk density, soil water content, clay content, soil surface hardness, soil subsurface hardness, powder content and sand content. X j It indicates that, j =1,2,3,4,5,6,7; X j It is expressed as: ; in, x j ( q ) is the q Sample data in the reference sequence, q =1,2,…, n .

[0031] In this embodiment, since there is no unified measurement unit between different cultivated land soil physical parameter indicators, each soil physical property parameter can be normalized to convert the evaluation index into a dimensionless number, which is then calculated and quantified.

[0032] For example, in this embodiment, a membership function may be used to normalize a plurality of soil physical property parameters; commonly used membership functions are divided into three types: S-type, inverse S-type, and parabolic.

[0033] In this embodiment, the cabbage mechanized transplanting quality evaluation indicators can be determined as transplanting depth qualified rate, seedling leakage rate, bare root rate and replanting rate in combination with cabbage transplanting agronomy with reference to dryland transplanting machinery operation standards.

[0034] Specifically, the qualified rate of transplant depth refers to the distance from the root of the main stem of the seedling to the surface soil; according to cabbage transplanting agronomy, the qualified transplant depth of transplanted seedlings (plug seedlings) is h Approx. : ; in, N h Indicates the total number of plants with qualified transplant depth (plants), N Indicates the total number of plants measured (plants).

[0035] Missing transplant seedlings refers to the situation where seedlings should be planted in theory but are not actually planted. In the mechanized transplanting process, there is a problem of missing seedlings due to the duckbill transplanter being blocked by the soil. The missing seedling rate is calculated as follows: ; in, N lz It is the number of missed seedlings in the total number of plants; the calculation methods of bare root rate L (%) and heavy planting rate C (%) are similar to those of missed seedling rate, namely, the bare root rate is the ratio of the number of bare root seedlings (i.e. not planted in the soil, with roots exposed on the ground) to the total number of plants measured; the heavy planting rate is the ratio of the number of heavy root seedlings (i.e. multiple seedlings planted in the same position) to the total number of plants measured.

[0036] In this embodiment, if the multiple transplanting quality evaluation indicators include the qualified rate of transplanting depth, the rate of missing seedlings, the rate of bare roots, and the rate of replanting, the multiple transplanting quality evaluation indicators can be expressed as a sequence: Y i : ; in, y i ( k ) is the sample data in each transplant quality sequence, i is the number of transplanting quality indicators, k is the number of samples, i =1,2,3,4, k =1,2,…, n .

[0037] In this embodiment, the measurement units of different transplanting quality evaluation indicators are also different. This embodiment normalizes each transplanting quality evaluation indicator to convert the evaluation indicator into a dimensionless number, which is then calculated and quantified.

[0038] Step 120: Analyze the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence to obtain the correlation between multiple soil characteristics and transplanting quality.

[0039] In this step, a system of evaluation indicators for mechanized transplanting quality and efficiency of plug seedlings was constructed by quantitatively analyzing the relationship between soil physical property parameters and transplanting quality evaluation indicators, combined with the characteristics of mechanized transplanting of plug seedlings.

[0040] In this embodiment, a duckbill transplanter can be installed on a leafy vegetable transplanter for seedling transplanting in trays, and a grey correlation analysis can be performed on the physical properties of cultivated soil and transplanting quality based on the mechanized transplanting working mechanism to study the adaptability of different physical properties of cultivated soil to mechanical transplanters.

[0041] In this implementation, the regression relationship between multiple soil physical property parameters and multiple transplanting quality evaluation indicators was constructed, which could quantify the relationship between the key soil physical properties affecting the mechanized transplanting quality of cabbage, the transplanting quality components and the transplanting efficiency. For example, the Spearman correlation coefficient could be used to evaluate the monotonic relationship between cultivated land soil physical parameters and transplanting quality, so as to explore the key soil properties in cultivated land that affect the yield and quality of cabbage transplanting, and thus provide a theoretical reference for the selection of high-quality and efficient mechanized production mode of cabbage plug seedlings.

[0042] Specifically, the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence is analyzed to obtain the correlation between multiple soil characteristics and transplanting quality, including: according to the rank obtained by sorting each element in the first dimensionless sequence and the rank obtained by sorting each element in the second dimensionless sequence, the rank difference and the sum of squares between multiple target sample pairs are obtained; each target sample pair includes a dimensionless number corresponding to a soil physical property parameter and a dimensionless number corresponding to a transplanting quality evaluation index; according to the rank difference and the sum of squares between each target sample pair, the Spearman correlation coefficient between soil health and transplanting quality in each target sample is calculated; the mean between the Spearman correlation coefficients corresponding to each target sample is calculated to obtain the correlation between multiple soil characteristics and transplanting quality.

[0043] The soil properties are calculated by the following steps: X j Transplant quality Y i The correlation between: (1) Sort the elements in the dimensionless sequence obtained above and assign them a rank.

[0044] For example, for the first dimensionless series , sort the data and assign a rank R ( x jq ); For the second dimensionless sequence Sort and assign ranks to the data after sorting R ( y ik ).

[0045] (2) For each set of sample pairs ( xjq , y ik ), calculate the rank difference and the sum of squares of the rank difference between two samples: ; ; in, is the rank difference, is the sum of squares of rank differences.

[0046] (3) For each pair X j and Y i , the Spearman correlation coefficient between the two is calculated by the following formula: ; in, is the Spearman correlation coefficient; ∑ represents the sum of samples, and 𝑛 is the number of samples.

[0047] (4) Calculate the mean of each Spearman correlation coefficient, and express the Spearman correlation between different cultivated soil physical parameters and transplanting quality indicators as follows:

[0048] in, For the degree of relevance.

[0049] Step 130: Perform regression analysis on multiple correlations based on the stepwise regression analysis algorithm of statistical quantiles and the significance test algorithm to obtain an empirical formula, and predict the transplanting quality of the transplanted seedlings based on the actual soil physical properties based on the empirical formula.

[0050] It should be noted that in the automated cabbage transplanting, the transplanting quality is greatly affected by the physical parameters of the cultivated soil; however, due to the large number of cultivated soil physical parameters and transplanting quality evaluation indicators, parameter processing is difficult; this embodiment uses a stepwise regression algorithm based on statistical quantiles to select a combination of cultivated soil parameters for transplanting quality prediction.

[0051] In this embodiment, multiple correlations are analyzed by regression analysis through the following steps: (1) Each transplanting quality index was used as the dependent variable and the soil physical property parameters were used as the independent variables. The Spearman correlation coefficient between each physical parameter and the dependent variable was calculated, and a suitable threshold T was automatically determined using the cross-validation method. (2) After selecting the threshold, the physical parameters with Spearman correlation higher than T are retained as the initial independent variables; (3) All initial independent variables are introduced into the model, and variables with small or insignificant effects are gradually eliminated; each time a variable is eliminated, the significance test is re-performed to ensure that the remaining variables have a significant effect on the dependent variable.

[0052] (4) In order to ensure that the independent variables in the regression equation have a significant impact on the dependent variable, an F test is performed at each step in the backward elimination process until only the physical parameters that have a significant impact on the transplanting quality are retained in the regression equation. The empirical formula for the influence of the significant physical indicators of cultivated land soil on each transplanting quality is calculated, thereby realizing the measurement of different transplanting qualities.

[0053] In this embodiment, after obtaining the above-mentioned empirical formula, the new transplant depth qualification rate, seedling leakage rate, bare root rate and replanting rate are calculated according to the empirical formula, and then the transplanting quality of the transplanted seedlings in mechanized operations is measured and evaluated according to the new transplanting quality evaluation index.

[0054] The mechanized transplant seedling quality analysis method provided by the embodiment of the present invention performs dimensionless processing on soil physical property parameters and transplant quality evaluation indicators respectively, and obtains the correlation between soil characteristics and transplant quality according to the correlation between each element in the corresponding dimensionless sequence. Finally, multiple correlations are screened based on the stepwise regression analysis algorithm of statistical quantiles and the significance test algorithm to obtain the target correlation. It can quantify the correlation between the physical properties of cultivated land soil and the mechanized transplanting of seedlings, realize the coordination of the mechanized transplanting characteristics of different leafy vegetable seedlings and the soil physical properties, improve the efficiency of mechanized transplanting of seedlings, and clarify the suitable trend of duckbill mechanized transplanting of plug seedlings under different soil environments.

[0055] Furthermore, in the above step 110, the multiple transplanting quality evaluation indicators include a transplanting depth qualified rate, a seedling leakage rate, a bare root rate, and a replanting rate; and dimensionless processing of the multiple transplanting quality evaluation indicators includes: performing dimensionless processing of Z-score standardization on the multiple transplanting quality evaluations using the following formula: ; in, yes The mean of is a collection of multiple transplanting quality evaluation indicators. yes The standard deviation of i is the number of transplanting quality evaluation indicators, k is the number of samples, For the i The first of the transplanting quality evaluation indicators k Sample values, for The dimensionless value of .

[0056] The mechanized transplanted seedling quality analysis method provided in an embodiment of the present invention converts different transplanting quality evaluation indicators into the same dimensionless representation through the above-mentioned Z-score standardized dimensionless processing method, realizes format alignment between the transplanting quality evaluation indicators and the soil physical property parameters, and improves the calculation and analysis efficiency of the transplanting quality evaluation indicators.

[0057] It should be noted that when the target soil physical property parameters including soil moisture content, soil bulk density, soil surface hardness, soil sub-surface hardness and soil particle composition, the content of these indicators is within a certain range, it can positively promote the mechanized transplanting of seedlings and the stable growth of crops; on the contrary, when the indicator content is higher or lower than a certain range, the effect on crop growth and mechanized transplanting will deteriorate.

[0058] Furthermore, in the above step 110, the multiple soil physical property parameters include soil bulk density, soil moisture content, soil surface hardness, soil subsurface hardness and soil particles; dimensionless processing of the multiple soil physical property parameters includes: dimensionless processing of the multiple soil physical property parameters using a membership function, and the membership function is shown in the following formula: ; in, X are multiple soil physical property parameters, F(X) for X The corresponding dimensionless number calculated by the membership function; X 1 , X 2 , X 3 and X 4 There are four different critical values.

[0059] In this embodiment, the relationship between the above four critical values ​​and the soil physical property parameters is shown in the following Table 1: Table 1: Relationship between four critical values ​​and eight different soil physical property parameters

[0060] The mechanized transplanted seedling quality analysis method provided in an embodiment of the present invention converts different soil physical property parameters into the same dimensionless representation through the above-mentioned membership function, achieves format alignment between transplanting quality evaluation indicators and soil physical property parameters, and improves the calculation and analysis efficiency of soil physical property parameters.

[0061] In some embodiments, the target soil includes brown soil, brown loam, sandy soil and yellow loam; the target soil is cultivated and prepared by the following steps: cultivating and preparing the brown soil, brown loam, sandy soil and yellow loam in the target soil, and collecting a full data set from the soil after the cultivation and preparation; performing data cleaning on each sample data in the full data set to obtain a new full data set.

[0062] In this embodiment, data cleaning includes removing outliers and missing values ​​and unifying data formats.

[0063] Taking the cabbage seedlings as an example, this embodiment selects the main soil types in the main cabbage producing areas, namely cinnamon soil, brown loam, sandy soil, and yellow loam, for mechanized transplanting of cabbage seedlings in plug trays; specifically, each test area is divided into 30 plots, each of which is 100m long and 5m wide. Before cabbage transplanting, the test area is cultivated and prepared. The plots in each test area adopt the orthogonal test method, and 5 treatments are set as shown in Table 2, with 6 repetitions: Table 2: Classification of cultivated land operation types in the experimental area

[0064] In this embodiment, after the tillage and land preparation operation is completed, three 5m×5m sample plots are set in each plot in the ridge direction, and surface soil samples (0-20 cm) are collected in each sample plot, and three replicates are collected at each sampling point; then, the cabbage seedlings are transplanted in the tray using a cabbage transplanter, and after transplanting, the number of missed plantings, the number of heavy plantings, and the number of bare roots in each sampling point are counted, and 45 transplanted seedlings are evenly selected in each soil sampling point to measure the transplanting depth, the number of missed plantings, the number of heavy roots, and the number of bare roots.

[0065] Figure 2 The diagram is a schematic diagram of the coupling relationship between the physical properties of cultivated soil and the quality and efficiency of cabbage transplantation provided by the present invention. Figure 2 In the illustrated embodiment, by subjecting the target soil to four different disturbance treatments, seven soil physical property parameters, namely, soil bulk density, soil moisture content, soil surface hardness, soil sub-surface hardness, sand content, silt content and clay content, are obtained respectively. Then, the Spearman correlation coefficient between the two types of indicators is calculated based on the seven soil physical property parameters and four different transplanting quality evaluation indicators (transplanting depth qualified rate, seedling leakage rate, replanting rate and bare root rate). The corresponding mean of the Spearman correlation coefficient is subjected to successive regression calculation to obtain an empirical formula for transplanting quality prediction. The empirical formula then calculates the transplanting depth qualified rate, seedling leakage rate, replanting rate and bare root rate based on the cultivated soil physical parameter data set that has a significant impact on the transplanting quality, thereby realizing the analysis and evaluation of the cabbage transplanting quality.

[0066] The mechanized transplant seedling quality analysis method provided in the embodiment of the present invention performs tillage operations on brown soil, brown loam, sandy soil and yellow loam in the target soil, collects the full data set from the soil after the tillage operations and performs data cleaning processing to obtain a new full data set, thereby providing reliable data for the subsequent calculation of transplant quality evaluation indicators.

[0067] Figure 3 This is the second flow chart of the mechanized transplant seedling quality analysis method provided by the present invention. Figure 3 In the illustrated embodiment, a mechanized transplant seedling quality analysis method is also implemented by the following steps: 1. Performing tillage and preparation operations in the test area, collecting soil samples of the cultivated land after the tillage and preparation operations for measurement, and establishing a full data set, each of which includes preliminary selected soil physical properties of the cultivated land and corresponding data, and performing data cleaning processing on a number of sample data; 2. After the tillage and preparation operations are completed in the test area, mechanized transplanting of cabbage seedlings in plug trays is performed, and the transplanter is equipped with a duckbill transplanter, and the total number of transplants, the transplanting depth of the seedlings after transplanting, the number of bare-root seedlings, the number of replanted seedlings, and the number of bare-root seedlings are collected. , establish a transplanting quality data set, and perform data cleaning on several sample data; 3. Use the membership function to normalize the correlation factors in the minimum data set, calculate the correlation coefficient between the cultivated land soil physical property data set and the transplanting quality data set by the Spearman correlation coefficient and the improved stepwise regression method, construct a cultivated land soil physical parameter data set that has a significant impact on transplanting quality, and construct a prediction empirical formula; 4. Calculate the transplanting depth qualified rate, missed planting rate, heavy root rate and bare root rate based on the cultivated land soil physical parameter data set that has a significant impact on transplanting quality.

[0068] The mechanized transplanted seedling quality analysis device provided by the present invention is described below. The mechanized transplanted seedling quality analysis device described below and the mechanized transplanted seedling quality analysis method described above can be referenced to each other.

[0069] Figure 4 Schematic diagram of the structure of the mechanized transplant seedling quality analysis device provided by the present invention. Figure 4 As shown, the mechanized transplanted seedling quality analysis device includes: a dimensionless calculation module 410, a correlation analysis module 420 and a regression analysis module 430.

[0070] The dimensionless calculation module 410 is used to perform dimensionless processing on multiple soil physical property parameters to obtain a first dimensionless sequence, and when mechanized transplanting of multiple transplanted seedlings is completed through the target soil, perform dimensionless processing on multiple transplanting quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to multiple soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to multiple transplanting quality evaluation indicators; A correlation analysis module 420 is used to analyze the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence to obtain the correlation between multiple soil characteristics and transplanting quality; The regression analysis module 430 is used to perform regression analysis on multiple correlations based on a stepwise regression analysis algorithm of statistical quantiles and a significance test algorithm to obtain an empirical formula, and predict the transplanting quality of transplanted seedlings based on the empirical formula according to actual soil physical properties.

[0071] The mechanized transplanted seedling quality analysis device provided by the embodiment of the present invention performs dimensionless processing on soil physical property parameters and transplanting quality evaluation indicators respectively, and obtains the correlation between soil characteristics and transplanting quality according to the correlation between each element in the corresponding dimensionless sequence. Finally, multiple correlations are screened based on the stepwise regression analysis algorithm and significance test algorithm of statistical quantiles to obtain the target correlation. It can quantify the correlation between the physical properties of cultivated land soil and the mechanized transplanting of seedlings, realize the coordination of the mechanized transplanting characteristics of different leafy vegetable seedlings and the soil physical properties, improve the efficiency of mechanized transplanting of seedlings, and clarify the suitable trend of duckbill mechanized transplanting of plug seedlings under different soil environments.

[0072] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5 As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the mechanized transplant seedling quality analysis method, which includes: performing dimensionless processing on multiple soil physical property parameters to obtain a first dimensionless sequence, and when completing the mechanized transplanting of multiple transplant seedlings through the target soil, performing dimensionless processing on multiple transplant quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to multiple soil physical property parameters; the second dimensionless sequence includes dimensionless numbers corresponding to multiple transplant quality evaluation indicators; analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, respectively, to obtain the correlation between multiple soil characteristics and transplant quality; performing regression analysis on multiple correlations based on the stepwise regression analysis algorithm of statistical quantiles and the significance test algorithm to obtain an empirical formula, and predicting the transplant quality of transplant seedlings based on the actual soil physical properties based on the empirical formula.

[0073] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0074] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the mechanized transplant seedling quality analysis method provided by the above-mentioned methods, the method including: dimensionlessly processing multiple soil physical property parameters to obtain a first dimensionless sequence, and when completing the mechanized transplanting of multiple transplant seedlings through the target soil, dimensionlessly processing multiple transplant quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to multiple soil physical property parameters; the second dimensionless sequence includes dimensionless numbers corresponding to multiple transplant quality evaluation indicators; analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, respectively, to obtain the correlation between multiple soil characteristics and transplant quality; performing regression analysis on multiple correlations based on the stepwise regression analysis algorithm and the significance test algorithm based on the statistical quantile to obtain an empirical formula, and predicting the transplant quality of transplant seedlings based on the actual soil physical properties based on the empirical formula.

[0075] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the mechanized transplant seedling quality analysis method provided by the above-mentioned methods, the method comprising: dimensionlessly processing a plurality of soil physical property parameters to obtain a first dimensionless sequence, and when mechanized transplanting of a plurality of transplant seedlings is completed through target soil, dimensionlessly processing a plurality of transplant quality evaluation indicators to obtain a second dimensionless sequence; wherein, the first dimensionless sequence includes dimensionless numbers corresponding to a plurality of soil physical property parameters; the second dimensionless sequence includes dimensionless numbers corresponding to a plurality of transplant quality evaluation indicators; analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, respectively, to obtain the correlation between multiple soil characteristics and transplant quality; performing regression analysis on multiple correlations based on a stepwise regression analysis algorithm based on statistical quantiles and a significance test algorithm, to obtain an empirical formula, and predicting the transplant quality of transplant seedlings based on actual soil physical properties based on the empirical formula.

[0076] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mechanized transplant seedling quality analysis method, characterized in that: include: A plurality of soil physical property parameters are dimensionally processed to obtain a first dimensionless sequence, and when a plurality of transplanted seedlings are mechanized transplanted through the target soil, a plurality of transplanting quality evaluation indicators are dimensionally processed to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to the plurality of soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to the plurality of transplanting quality evaluation indicators; Analyzing the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, and obtaining the correlation between multiple soil characteristics and transplanting quality; A stepwise regression analysis algorithm based on statistical quantiles and a significance test algorithm are used to perform regression analysis on multiple correlations to obtain an empirical formula, and the transplanting quality of the transplanted seedlings is predicted based on the empirical formula according to actual soil physical properties.

2. The mechanized transplant seedling quality analysis method according to claim 1, characterized in that: The correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence is analyzed to obtain the correlation between multiple soil characteristics and transplanting quality, including: According to the rank obtained by sorting each element in the first dimensionless sequence and the rank obtained by sorting each element in the second dimensionless sequence, the rank difference and the sum of squares between multiple target sample pairs are obtained; each target sample pair includes a dimensionless number corresponding to a soil physical property parameter and a dimensionless number corresponding to a transplanting quality evaluation index; The Spearman correlation coefficient between soil health and transplanting quality in each target sample was calculated based on the rank difference and sum of squares between each target sample pair; The mean values ​​of the Spearman correlation coefficients corresponding to the target samples are calculated to obtain the correlation between the multiple soil characteristics and the transplanting quality.

3. The mechanized transplant seedling quality analysis method according to claim 1, characterized in that: The multiple transplanting quality evaluation indicators include transplanting depth qualified rate, seedling leakage rate, bare root rate and replanting rate; The dimensionless processing of the plurality of transplanting quality evaluation indicators comprises: The following formula is used to perform dimensionless Z-score standardization on the multiple transplanting quality evaluations: ； in, yes The mean of is a collection of multiple transplanting quality evaluation indicators. yes The standard deviation of i is the number of transplanting quality evaluation indicators, k is the number of samples, For the i The first of the transplanting quality evaluation indicators k Sample values, for The dimensionless value of .

4. The mechanized transplant seedling quality analysis method according to claim 1, characterized in that: The plurality of soil physical property parameters include soil bulk density, soil moisture content, soil surface hardness, soil subsurface hardness and soil particles; The dimensionless processing of multiple soil physical property parameters includes: The plurality of soil physical property parameters are dimensionlessly processed using a membership function, and the membership function is shown in the following formula: ； in, X are multiple soil physical property parameters, F(X) for X The corresponding dimensionless number calculated by the membership function; X 1. X 2. X 3 and X 4 are four different critical values.

5. The mechanized transplant seedling quality analysis method according to claim 1, characterized in that: The plurality of soil physical property parameters also include soil moisture content, soil bulk density, soil surface hardness, sub-surface hardness and soil particle composition; The multiple soil physical property parameters are obtained by the following steps: The soil moisture content is obtained from the target soil by using a drying method; the target soil bulk density is obtained from the target soil by using a ring knife method; the soil surface hardness and sub-surface hardness of the target soil are measured by using a hardness meter; and the soil particle composition of the target soil is measured by using a Malvern laser particle size analyzer.

6. The mechanized transplant seedling quality analysis method according to claim 1, characterized in that: The target soil includes brown soil, brown loam, sandy soil and yellow soil; The target soil is cultivated and prepared by the following steps: performing tillage and land preparation operations on the target soil, the cinnamon soil, the brown loam soil, the sandy soil, and the yellow loam soil, and collecting a full data set from the soil after the tillage and land preparation operations; Data cleaning is performed on each sample data in the full data set to obtain a new full data set.

7. A mechanized transplant seedling quality analysis device, characterized in that: include: The dimensionless calculation module is used to perform dimensionless processing on multiple soil physical property parameters to obtain a first dimensionless sequence, and when mechanized transplanting of multiple transplanted seedlings is completed through the target soil, perform dimensionless processing on multiple transplanting quality evaluation indicators to obtain a second dimensionless sequence; wherein the first dimensionless sequence includes dimensionless numbers corresponding to multiple soil physical property parameters; and the second dimensionless sequence includes dimensionless numbers corresponding to multiple transplanting quality evaluation indicators; A correlation analysis module, used to analyze the correlation between each element in the first dimensionless sequence and each element in the second dimensionless sequence, and obtain the correlation between multiple soil characteristics and transplanting quality; The regression analysis module is used to perform regression analysis on multiple correlations based on a stepwise regression analysis algorithm of statistical quantiles and a significance test algorithm to obtain an empirical formula, and predict the transplanting quality of the transplanted seedlings based on the actual soil physical properties based on the empirical formula.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the mechanized transplanted seedling quality analysis method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the mechanized transplanted seedling quality analysis method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the mechanized transplanted seedling quality analysis method as described in any one of claims 1 to 6 is implemented.

Images