Method, device and storage medium for evaluating easy shelling based on pod physical characteristics
Through multiple rounds of analysis of the experimental data of pods, core physical characteristics were extracted and evaluation models were constructed, and the problem of low evaluation efficiency of pods' prone to shelling in the existing technology was solved, and rapid and accurate evaluation and convenience of new varieties were achieved. .
Patent Information
- Application Number
- CN202410258134.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-06
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-03-06
AI Technical Summary
In the prior art, the efficiency of evaluating pods is low when evaluating the shellability, requiring a large number of samples and repeated process parameter adjustments, and lacking a quantifiable difficulty evaluation method.
By obtaining experimental data of pods, multiple rounds of data analysis are carried out to extract core physical features, and evaluation models are constructed. Grading pods are prone to shelling. Using frequency statistics and factor analysis to simplify physical features and reduce model complexity.
The rapid and accurate assessment of the pod's prone to shelling is achieved, reducing the number of physical characteristics required for testing, and improving the convenience of new varieties development.
Smart Images

Figure CN118155758B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of property evaluation of agricultural materials, and in particular to a method, device and storage medium for evaluating the ease of shelling based on the physical characteristics of pods. Background Art
[0002] Peanuts, walnuts and other pods can not only be used as food, but also important oil raw materials. When the pods are processed for oil extraction, the shells of the pods need to be removed to obtain the kernels for subsequent processing. Therefore, easy shelling is an important characteristic of the pods. In the selection of oil raw materials and agricultural cultivation, the easy shelling of the pods needs to be fully considered.
[0003] In the prior art, when evaluating pods of unknown shelling ease, shelling is mainly measured experimentally, and the evaluation is performed based on the results of the shelling experiment. In this method, a sufficient number of samples are required for testing, and during the test, the process parameters of the shelling machine need to be repeatedly adjusted to achieve the best shelling effect (for example, the applicant's prior application CN115318633A discloses real-time process parameter adjustment based on the shelling effect). The results obtained in this way can only be used as a reference, and the efficiency is very low.
[0004] In terms of theoretical research, the study of shelling ease is generally focused on biological perspectives such as genetics, and there is still a lack of knowledge on how to conduct a quantifiable difficulty evaluation of pods with unknown shelling ease. Summary of the invention
[0005] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a method, device and storage medium for evaluating the ease of shelling based on the physical characteristics of pods, which can extract core physical characteristics and construct an evaluation model based on the core physical characteristics to facilitate quantitative evaluation of pods.
[0006] Technical solution: To achieve the above purpose, the method for evaluating the ease of shelling of pods based on the physical characteristics of the present invention comprises:
[0007] Acquire a database containing experimental data of pods of multiple varieties, wherein the experimental data includes variety information, measured data of multiple physical characteristics, and measured data of quality indicators;
[0008] Performing a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature;
[0009] Performing a second round of data analysis on the measured data of the first physical features based on the measured data of the quality indicators in the database to divide all the first physical features into N groups, where N is an integer greater than 1;
[0010] Selecting at least one representative physical feature from each group of the first physical features, referred to as the second physical feature;
[0011] An evaluation model is constructed based on the second physical feature.
[0012] Preferably, the first round of data analysis is performed based on correlation analysis, specifically including:
[0013] Performing frequency statistics on all the physical features in the database according to measured data;
[0014] The first physical feature is determined according to the result of frequency statistics and the measured data of the quality index based on correlation analysis.
[0015] Preferably, the second round of data analysis of the measured data of the first physical characteristics based on the measured data of the quality indicators in the database to divide all the first physical characteristics into N groups includes:
[0016] Performing a second round of data analysis on the measured data of the first physical feature based on a factor analysis method to form N influencing factors and a first physical feature corresponding to each influencing factor;
[0017] The first physical feature corresponding to each of the influencing factors is taken as a group to obtain N groups.
[0018] Preferably, the at least one representative physical feature selected from each group of the first physical features, referred to as the second physical feature, includes:
[0019] The first physical feature with the largest factor weight in each group is selected as the representative physical feature, namely the second physical feature.
[0020] Preferably, constructing an evaluation model based on the second physical feature includes:
[0021] Assigning a weight to each of the second physical characteristics, and calculating a comprehensive score of each variety of pods according to the weight and a specific value of the second physical characteristic corresponding to each variety of pods;
[0022] Based on the comprehensive scores, all varieties of peanuts are classified into three levels, namely, easy to shell, medium difficulty and difficult to shell;
[0023] The measured data of the second physical characteristic of the variety corresponding to each grade is used to construct a grading function corresponding to the grade, and all the grading functions obtained are integrated to form the evaluation model.
[0024] The device for evaluating the ease of shelling of pods based on the physical characteristics of pods comprises:
[0025] An acquisition module, which is used to acquire a database containing experimental data of pods of multiple varieties, wherein the experimental data includes variety information, measured data of multiple physical characteristics, and measured data of quality indicators;
[0026] A first analysis module, which is used to perform a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index, to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature;
[0027] A second analysis module, configured to perform a second round of data analysis on the measured data of the first physical characteristics based on the measured data of the quality indicators in the database, so as to divide all the first physical characteristics into N groups, where N is an integer greater than 1;
[0028] A selection module, which is used to select at least one representative physical feature from each group of the first physical features, referred to as a second physical feature;
[0029] A model building module is used to build an evaluation model based on the second physical feature.
[0030] The storage medium stores a computer executable program, and when the computer executable program is executed by a processor, the method for evaluating the ease of shelling based on the physical characteristics of pods is implemented.
[0031] Beneficial effects: The method, device and storage medium for evaluating the ease of shelling based on the physical characteristics of pods of the present invention have the following beneficial effects:
[0032] (1) The present invention first performs a first round of screening based on the correlation between physical characteristics and quality indicators, and then groups the physical characteristics with overlapping information into the same group, and selects representative physical characteristics for each group, so that a large number of physical characteristics can be screened to obtain a small number of the most representative physical characteristics, that is, the second physical characteristics. In this way, the evaluation model constructed based on the obtained second physical characteristics can fully estimate the ease of shelling of the pods, and the complexity of the model is low. The user can estimate the ease of shelling of the pods by testing a limited number of physical characteristics of the pods to be evaluated, which can facilitate research such as the development of new varieties.
[0033] (2) The idea of factor analysis is to reduce the dimensionality of many influencing factors to form a few influencing factors, group the first physical characteristics, and effectively make the first physical characteristics in the same group have information overlap, providing a basis for further simplification.
[0034] (3) The pods of each variety are scored based on the second physical characteristic, and the varieties are graded based on the comprehensive score obtained. Finally, a grading function is obtained based on the second physical characteristic data of varieties of each grade. Based on the obtained evaluation model, the shelling ease of pod varieties whose shelling ease is unknown can be effectively predicted. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 The figure is a flow chart of the method for evaluating the ease of shelling based on the physical characteristics of pods;
[0036] Figure 2 The figure is a schematic diagram of the structure of the device for evaluating the ease of shelling based on the physical characteristics of pods. DETAILED DESCRIPTION
[0037] The present invention will be further described below in conjunction with the accompanying drawings.
[0038] In this embodiment, peanuts are taken as an example for description.
[0039] like Figure 1 The method for evaluating the ease of shelling of pods based on the physical characteristics of pods shown in the figure comprises the following steps S101-S105:
[0040] Step S101, obtaining a database containing experimental data of pods of multiple varieties, wherein the experimental data includes variety information, measured data of multiple physical characteristics, and measured data of quality indicators;
[0041] In this step, this embodiment selected 29 varieties of peanuts for data collection, and obtained the above database. The statistical physical characteristics include pod sphericity, pod uniformity, pod mechanical properties, pod average geometric diameter, kernel sphericity, kernel uniformity, kernel mechanical properties, kernel average diameter, pod mouth and other physical characteristics. All data that may affect the quality index should be counted in the database for screening. The measured data of physical characteristics can be numerical values or text descriptions; for example: the measured data of the average geometric diameter of pods, kernel mechanical properties, kernel average diameter, and kernel mechanical properties are specific numerical values; the physical characteristics such as kernel shape and pod mouth are text descriptions. The shape of the pod mouth, if the kernel shape includes cylindrical, conical, elliptical and triangular four types, the pod mouth includes four types: none, short, medium, and sharp. The above-mentioned quality indicators include the breakage rate and the shelling rate. The measured data of the breakage rate and the shelling rate of each variety of peanuts are the optimized results obtained from the shelling test of the variety of peanuts, which makes the measured data of the quality indicators fully credible.
[0042] Step S102, performing a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index, to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature;
[0043] Step S103, performing a second round of data analysis on the measured data of the first physical characteristics based on the measured data of the quality indicators in the database, so as to divide all the first physical characteristics into N groups, where N is an integer greater than 1;
[0044] Step S104, selecting at least one representative physical feature from each group of the first physical features, referred to as a second physical feature;
[0045] Step S105: constructing an evaluation model based on the second physical feature.
[0046] In the above step S103, if there is information overlap between the first physical features contained in the same group, the representative first physical features in each group are selected in step S104, so as to further screen out the physical features that best represent the ease of shelling of peanuts.
[0047] The method in the above steps S101-S105 first performs a first round of screening based on the correlation between physical characteristics and quality indicators, and then classifies physical characteristics with overlapping information into the same group, and selects representative physical characteristics for each group, so that a large number of physical characteristics can be screened to obtain a small number of the most representative physical characteristics, that is, the second physical characteristics. In this way, the evaluation model constructed based on the obtained second physical characteristics can fully estimate the ease of shelling of pods, and the complexity of the model is low. The user can estimate the ease of shelling of pods by testing a limited number of physical characteristics of the pods to be evaluated, which can facilitate research such as the development of new varieties.
[0048] Preferably, in the above step S102, the first round of data analysis is performed based on correlation analysis, and specifically includes the following steps S201-S202:
[0049] Step S201, performing frequency statistics on all the physical features in the database according to measured data;
[0050] In this step, for physical characteristics with specific values, frequency statistics are performed according to their value intervals. For example, multiple data intervals can be determined for the mechanical properties of the kernel, and the number of specific values falling into each data interval in the database is counted, and the ratio of the number of specific values corresponding to each data interval to the total number is calculated; for physical characteristics whose measured data are text descriptions, frequency statistics and ratio calculations are performed according to each text description. For example, for the shape of the kernel, the frequencies of the four shapes of cylinder, cone, ellipse and triangle are counted and the ratios are calculated.
[0051] Step S202: determining the first physical feature according to the result of frequency statistics and the measured data of the quality index by correlation analysis.
[0052] In this embodiment, through correlation analysis, physical characteristics related to the breakage rate and the removal rate can be obtained, including pod sphericity, pod uniformity, pod mechanical properties, constriction, pod fullness, geometric mean diameter, pod reticulation, pod shape, pod mouth, seed kernel sphericity, seed kernel uniformity, seed kernel mechanical characteristics and seed kernel shape.
[0053] Preferably, in the above step S103, the second round of data analysis is performed on the measured data of the first physical characteristics based on the measured data of the quality indicators in the database to divide all the first physical characteristics into N groups, including the following steps S301-S302:
[0054] Step S301, performing a second round of data analysis on the measured data of the first physical feature based on a factor analysis method to form N influencing factors and a first physical feature corresponding to each influencing factor;
[0055] Step S302: taking the first physical feature corresponding to each of the influencing factors as a group to obtain N groups.
[0056] In the above steps S301-S302, the idea of factor analysis is fully utilized to reduce the dimensions of many influencing factors to form a few influencing factors, and the first physical features are grouped, so that the first physical features in the same group have information overlap, providing a basis for further simplification.
[0057] In this embodiment, five influencing factors were obtained through factor analysis, and the first physical characteristics corresponding to the five influencing factors were as follows: the first influencing factor corresponds to pod sphericity, pod uniformity, pod mechanical properties and constriction, and the factor weights of the four are 0.952, 0.913, -0.852 and -0.775, respectively; the second influencing factor corresponds to pod fullness and pod average geometric diameter, and the factor weights of the two are 0.806 and -0.793, respectively; the third influencing factor corresponds to pod reticulation and pod shape, and the factor weights of the two are 0.784 and 0.704, respectively; the fourth influencing factor corresponds to pod mouth, and its factor weight is 0.974; the fifth influencing factor corresponds to seed kernel sphericity, seed kernel uniformity, seed kernel mechanical properties and seed kernel shape, and the factor weights of the four are 0.949, 0.979, 0.976 and -0.691, respectively. Correspondingly, all the above first physical characteristics are divided into 5 groups, and the first physical characteristics corresponding to each of the above influencing factors are separately divided into a group.
[0058] Preferably, in the above step S104, at least one representative physical feature is selected from each group of the first physical features, referred to as the second physical feature, including:
[0059] The first physical feature with the largest factor weight in each group is selected as the representative physical feature, namely the second physical feature.
[0060] In this embodiment, the five second physical characteristics obtained are pod sphericity, pod fullness, pod texture, pod mouth and seed kernel sphericity.
[0061] Preferably, the step S105 of constructing an evaluation model based on the second physical feature comprises the following steps S401-S403:
[0062] Step S401, assigning a weight to each of the second physical characteristics, and calculating a comprehensive score of each variety of pods according to the weight and a specific value of the second physical characteristic corresponding to each variety of pods;
[0063] Step S402, classifying all varieties of peanuts based on the comprehensive scores to obtain three grades of varieties, namely easy to shell, medium difficulty and difficult to shell;
[0064] Step S403, using the measured data of the second physical characteristic of the variety corresponding to each grade to construct a grading function corresponding to the grade, and integrating all the grading functions obtained to form the evaluation model.
[0065] In the above steps S401-S403, the pods of each variety are first scored based on the second physical characteristic, and then the varieties are graded based on the comprehensive score obtained by scoring. Finally, a grading function is obtained based on the second physical characteristic data of varieties of each grade. Based on the obtained evaluation model, the hulling ease of pod varieties with unknown hulling ease can be effectively predicted.
[0066] The above classification function has the form:
[0067] Y m =A m0 +A m1 X 1 +A m2 X 2 +A m3 X 3 +A m4 X 4 +A m5 X 5 , where m = 1, 2, 3; A m0 is the coefficient of the 0th term in the mth level, A m1 is the coefficient of the first item in the mth level, and so on; X1 -X 5 are the measured values of the second physical characteristic, namely, the measured values of pod sphericity, pod fullness, pod texture, pod mouth and seed kernel sphericity.
[0068] It can be seen that the evaluation model includes three grading functions. When the evaluation model is actually used to predict the shelling ease of peanut varieties with unknown shelling properties, the five values of peanut pod sphericity, pod fullness, pod texture, pod mouth and seed kernel sphericity are measured and substituted into each grading function to obtain Y 1 , Y 2 , Y 3 , and then compare which value is the largest among the three. 1 When it is the largest, it represents the level of easy shelling, Y 2 When it is at the maximum, it represents the level of medium difficulty, Y 3 When it is at the maximum, it means that the level is difficult to shed.
[0069] The present invention also provides a device 500 for evaluating the ease of shelling based on the physical characteristics of pods. The device 500 for evaluating the ease of shelling may include or be divided into one or more program modules. The one or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention and implement the above-mentioned method for evaluating the ease of shelling based on the physical characteristics of pods. The program module referred to in the embodiment of the present invention refers to a series of computer program instruction segments that can perform specific functions, and is more suitable for describing the execution process of the method for evaluating the ease of shelling based on the physical characteristics of pods in a storage medium than the program itself. The following description will specifically introduce the functions of each program module of this embodiment, such as Figure 2 As shown, the shelling ease evaluation device 500 includes:
[0070] An acquisition module 501 is used to acquire a database containing experimental data of pods of multiple varieties, wherein the experimental data includes variety information, measured data of multiple physical characteristics, and measured data of quality indicators;
[0071] A first analysis module 502, which is used to perform a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index, to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature;
[0072] A second analysis module 503, which is used to perform a second round of data analysis on the measured data of the first physical characteristics based on the measured data of the quality indicators in the database, so as to divide all the first physical characteristics into N groups, where N is an integer greater than 1;
[0073] A selection module 504, which is used to select at least one representative physical feature from each group of the first physical features, referred to as a second physical feature;
[0074] The model building module 505 is used to build an evaluation model based on the second physical feature.
[0075] Other contents of the method for evaluating the easy shelling of pods based on the physical characteristics of pods implemented by the easy shelling evaluation device 500 have been described in detail in the previous embodiments, and the corresponding contents in the previous embodiments may be referred to, and will not be repeated here.
[0076] The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, etc., on which a computer program is stored, and when the program is executed by a processor, a corresponding function is realized. The computer-readable storage medium of the present embodiment is used to store the easy shelling evaluation device 500, and when executed by the processor, the easy shelling evaluation method based on the physical characteristics of pods of the present invention is realized.
[0077] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for evaluating the ease of shelling of pods based on the physical characteristics of pods, characterized in that: The method comprises: Acquire a database containing experimental data of pods of multiple varieties, wherein the experimental data include variety information, measured data of multiple physical characteristics, and measured data of quality indicators; the physical characteristics include pod sphericity, pod uniformity, pod mechanical properties, pod average geometric diameter, seed kernel sphericity, seed kernel uniformity, seed kernel mechanical properties, seed kernel average diameter, and pod mouth; Performing a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature; Performing a second round of data analysis on the measured data of the first physical features based on the measured data of the quality indicators in the database to divide all the first physical features into N groups, where N is an integer greater than 1; Selecting at least one representative physical feature from each group of the first physical features, referred to as the second physical feature; An evaluation model is constructed based on the second physical feature.
2. The method for evaluating the ease of shelling based on the physical characteristics of pods according to claim 1, characterized in that: The first round of data analysis is based on correlation analysis, including: Performing frequency statistics on all the physical features in the database according to measured data; The first physical feature is determined according to the result of frequency statistics and the measured data of the quality index based on correlation analysis.
3. The method for evaluating the ease of shelling based on the physical characteristics of pods according to claim 1, characterized in that: The performing a second round of data analysis on the measured data of the first physical features based on the measured data of the quality indicators in the database to divide all the first physical features into N groups includes: Performing a second round of data analysis on the measured data of the first physical feature based on a factor analysis method to form N influencing factors and a first physical feature corresponding to each influencing factor; The first physical feature corresponding to each of the influencing factors is taken as a group to obtain N groups.
4. The method for evaluating the ease of shelling based on the physical characteristics of pods according to claim 3, characterized in that: The at least one representative physical feature selected from each group of the first physical features is called a second physical feature, including: The first physical feature with the largest factor weight in each group is selected as the representative physical feature, namely the second physical feature.
5. The method for evaluating the ease of shelling based on the physical characteristics of pods according to claim 1, characterized in that: The constructing of the evaluation model based on the second physical feature comprises: Assigning a weight to each of the second physical characteristics, and calculating a comprehensive score of each variety of pods according to the weight and a specific value of the second physical characteristic corresponding to each variety of pods; Based on the comprehensive scores, all varieties of peanuts are classified into three levels, namely, easy to shell, medium difficulty and difficult to shell; The measured data of the second physical characteristic of the variety corresponding to each grade is used to construct a grading function corresponding to the grade, and all the grading functions obtained by integration are used to obtain the evaluation model.
6. A device for evaluating the ease of shelling based on the physical characteristics of pods, characterized in that: It includes: An acquisition module, which is used to acquire a database containing experimental data of pods of multiple varieties, wherein the experimental data includes variety information, measured data of multiple physical characteristics, and measured data of quality indicators; A first analysis module, which is used to perform a first round of data analysis on the measured data of the physical feature based on the measured data of the quality index, to obtain the physical feature that is strongly correlated with the quality index, referred to as the first physical feature; A second analysis module, configured to perform a second round of data analysis on the measured data of the first physical characteristics based on the measured data of the quality indicators in the database, so as to divide all the first physical characteristics into N groups, where N is an integer greater than 1; A selection module, which is used to select at least one representative physical feature from each group of the first physical features, referred to as a second physical feature; A model building module is used to build an evaluation model based on the second physical feature.
7. A storage medium, characterized in that A computer executable program is stored therein, and when the computer executable program is executed by a processor, the method for evaluating the ease of shelling based on the physical characteristics of pods according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Nut grading method
CN115318633A
Integrated Quality Evaluation Method for Huangguogan
AU2020103500A4
Weight factor grade evaluation method and system
CN108053094A
Method, system and equipment for screening cadmium-tolerant varieties of crops and storage medium
CN115577981A
