Sorting method of high-quality rice husks for wine brewing

Abstract

The invention relates to a high-quality rice hull sorting method for wine brewing, which comprises the following steps: M1, in the process of conveying rice hulls subjected to impurity removal to a target container through a conveying belt, acquiring image data information of the rice hulls in real time based on a camera above the conveying belt, and acquiring volume weight data information of the rice hulls in real time based on a weighing sensor; and M2, based on the image data information of the rice husks, identifying and classifying the images of the rice husks by adopting a neural network model fused with a Viola-Jones algorithm to obtain the image data information of the classified rice husks. According to the rice hull sorting device, rice hulls can be accurately sorted, manual participation is not needed in the rice hull sorting process, the labor cost is reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of wine making, and in particular to a method for sorting high-quality rice husks for wine making. Background Art

[0002] With the continuous development of science and technology, it is driving the rapid development of various industries. Among them, the continuous optimization of machine learning, deep learning and other algorithms has enabled artificial intelligence to achieve remarkable results in image recognition, speech recognition, natural language processing and other fields. At the same time, artificial intelligence is also playing an increasingly important role in intelligent manufacturing, smart medical care, smart transportation and other fields.

[0003] Among them, rice husks are needed as auxiliary materials in the process of winemaking. Rice husks, as an indispensable solid filler and loosening agent in liquor brewing, have good looseness, air permeability and water absorption. After the rice husks are initially screened for dust, debris and other impurities, they are still required to be deeply screened. Traditional rice husk screening requires manual observation and feeling of the rice husks in the hands, so as to judge the quality of the rice husks. This screening of rice husk quality is not only inefficient, but also has low accuracy, which will lead to reduced quality of winemaking. Therefore, how to accurately sort rice husks has become a problem that we urgently need to solve. Summary of the invention

[0004] In view of the above problems, the present invention provides a method for sorting high-quality rice husks for brewing wine, which can not only accurately sort the rice husks, but also does not require manual participation in the rice husk sorting process, thereby reducing labor costs and improving production efficiency.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A method for sorting high-quality rice husks for brewing wine, the method comprising:

[0007] M1. In the process of conveying the rice husks after impurities removal to the target container through the conveyor belt, the image data information of the rice husks is obtained in real time based on the camera above the conveyor belt, and the bulk density data information of the rice husks is obtained in real time based on the weighing sensor;

[0008] M2. Based on the image data information of the rice husk, a neural network model integrating the Viola-Jones algorithm is used to identify and classify the image of the rice husk to obtain the classified image data information of the rice husk;

[0009] M3. Based on the image data information of the classified rice husk and the bulk density data information of the rice husk, the image and bulk density of the rice husk are fused using a production rule algorithm based on an adaptive adjustment factor to obtain the fused decision data information of the rice husk;

[0010] M4. Based on the decision data information of the fused rice husk, a quality evaluation function F of the rice husk is established to evaluate the quality of the rice husk and obtain quality evaluation data information of the rice husk.

[0011] Furthermore, the method further comprises:

[0012] M5. Based on the quality assessment data information of the rice husk, a preset threshold is set. If the quality assessment data information of the rice husk is greater than the preset threshold, the requirement is met, the rice husk is high-quality rice husk and is sorted. If the quality assessment data information of the rice husk is less than the preset threshold, the requirement is not met.

[0013] Furthermore, in step M2, the use of a neural network model integrated with the Viola-Jones algorithm to identify and classify the rice husk image includes:

[0014] M21. Based on the image data information of the rice husk, establish a rice husk image feature extraction function Q,

[0015]

[0016] Among them, x is the image data information of rice husk, α1, α2 and α3 are the feature extraction factors of rice husk image, and the feature extraction of rice husk image is performed to obtain the feature image data information of rice husk;

[0017] M22. Inputting the characteristic image data information of the rice husk into the neural network model for training and learning, determining the neuron function W,

[0018]

[0019] Among them, y is the characteristic image data information of rice husk, β1, β2 and β3 are weight coefficients, and the trained neural network model is obtained;

[0020] M23. Based on the trained neural network model, the image data information of the rice husk is input, the image of the rice husk is identified and classified, and the image data information of the classified rice husk is obtained.

[0021] Furthermore, in step M22, the constraints of the weight coefficients β1, β2 and β3 are:

[0022]

[0023] Among them, y is the characteristic image data information of rice husk.

[0024] Furthermore, the constraint function f of the feature extraction factors α1, α2 and α3 of the rice husk image is,

[0025]

[0026] The value range of f is (3,5).

[0027] Furthermore, in step M3, the step of fusing the rice husk image and bulk density using a production rule algorithm based on an adaptive adjustment factor includes:

[0028] M31. Based on the classified rice husk image data information, establish a production rule function R of the rice husk image,

[0029]

[0030] Among them, z is the image data information of the classified rice husk, δ1 and δ2 are the regular change factors of the rice husk image, which characterize the regular change of the rice husk image and obtain the regular change data information of the classified rice husk image;

[0031] M32. Based on the bulk density data information of the rice husk, a production rule function U of the bulk density of the rice husk is established.

[0032]

[0033] Among them, r is the bulk density data information of rice husk, γ1 and γ2 are the regular change factors of rice husk bulk density, which characterize the regular change of rice husk bulk density and obtain the regular change data information of rice husk bulk density;

[0034] M33. Based on the regular change data information of the rice husk bulk density and the regular change data information of the classified rice husk image, a fusion function P of the rice husk bulk density and the image is established.

[0035]

[0036] Among them, g1 is the regular change data information of rice husk bulk density, g2 is the regular change data information of the classified rice husk image, η1, η2 and η3 are adaptive adjustment factors, and the image and bulk density of rice husk are fused to obtain the determined data information of the fused rice husk.

[0037] Furthermore, the adaptive adjustment factors η1, η2 and η3 are:

[0038]

[0039] Among them, g1 is the regular change data information of rice husk bulk density, and g2 is the regular change data information of the classified rice husk image.

[0040] Furthermore, the constraints of the regular variation factors γ1 and γ2 of the rice husk bulk density are:

[0041] The constraints of the regular variation factors δ1 and δ2 of the rice husk image are:

[0042]

[0043] Further, in step M4, the rice husk quality assessment function F is,

[0044]

[0045] Among them, h is the decision data information of the fused rice husk, and ω1, ω2 and ω3 are the quality evaluation factors of rice husk.

[0046] Furthermore, the constraint function S of the rice husk quality assessment factors ω1, ω2 and ω3 is,

[0047]

[0048] The value range of the constraint function S is (1,2).

[0049] The present invention has the following positive effects:

[0050] 1. The present invention recognizes and classifies rice husk images by adopting a neural network model integrating the Viola-Jones algorithm, and fuses the rice husk image and bulk density by combining a production rule algorithm based on an adaptive adjustment factor, so as to obtain the decision data information of the fused rice husk. The rice husk can not only be sorted accurately, but also no manual participation is required in the process of rice husk sorting, thereby reducing labor costs and improving production efficiency.

[0051] 2. The present invention evaluates the quality of rice husks by establishing a quality evaluation function F of rice husks. It can not only accurately evaluate different batches of rice husks, thereby improving the quality of winemaking, but also save screening time during the rice husk sorting process, providing high-quality raw material supply for subsequent processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a structural schematic diagram of the rice husk sorting production line of the present invention;

[0053] Figure 2 It is a schematic diagram of the method flow of the present invention;

[0054] Figure 3 It is a flow chart of the neural network model integrating the Viola-Jones algorithm of the present invention;

[0055] Figure 4 The figure is a flow chart of the production rule algorithm based on the adaptive adjustment factor of the present invention.

[0056] Explanation of the numbers in the figure: 1-camera, 2-weighing sensor, 3-conveyor belt, 4-rice husk. DETAILED DESCRIPTION

[0057] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0058] Example 1: Figure 1 or Figure 2 As shown, a method for sorting high-quality rice husks for brewing wine comprises:

[0059] M1. In the process of conveying the rice husk 4 after impurities removal to the target container through the conveyor belt 3, the camera 1 above the conveyor belt 4 obtains the image data information of the rice husk in real time, and the weighing sensor 2 obtains the bulk density data information of the rice husk in real time;

[0060] M2. Based on the image data information of the rice husk, a neural network model integrating the Viola-Jones algorithm is used to identify and classify the image of the rice husk to obtain the classified image data information of the rice husk;

[0061] M3. Based on the image data information of the classified rice husk and the bulk density data information of the rice husk, the image and bulk density of the rice husk are fused using a production rule algorithm based on an adaptive adjustment factor to obtain the fused decision data information of the rice husk;

[0062] M4. Based on the decision data information of the fused rice husk, a quality evaluation function F of the rice husk is established to evaluate the quality of the rice husk and obtain quality evaluation data information of the rice husk.

[0063] In this embodiment, the method further includes:

[0064] M5. Based on the quality assessment data information of the rice husk, a preset threshold is set. If the quality assessment data information of the rice husk is greater than the preset threshold, the requirement is met, the rice husk is high-quality rice husk and is sorted. If the quality assessment data information of the rice husk is less than the preset threshold, the requirement is not met.

[0065] In this embodiment, if Figure 3 As shown, in step M2, the use of a neural network model integrating the Viola-Jones algorithm to identify and classify the rice husk image includes:

[0066] M21. Based on the image data information of the rice husk, establish a rice husk image feature extraction function Q,

[0067]

[0068] Among them, x is the image data information of rice husk, α1, α2 and α3 are the feature extraction factors of rice husk image, and the feature extraction of rice husk image is performed to obtain the feature image data information of rice husk;

[0069] M22. Inputting the characteristic image data information of the rice husk into the neural network model for training and learning, determining the neuron function W,

[0070]

[0071] Among them, y is the characteristic image data information of rice husk, β1, β2 and β3 are weight coefficients, and the trained neural network model is obtained;

[0072] M23. Based on the trained neural network model, the image data information of the rice husk is input, the image of the rice husk is identified and classified, and the image data information of the classified rice husk is obtained.

[0073] In this embodiment, in step M22, the constraints of the weight coefficients β1, β2 and β3 are:

[0074]

[0075]

[0076] Among them, y is the characteristic image data information of rice husk.

[0077] In this embodiment, the constraint function f of the feature extraction factors α1, α2 and α3 of the rice husk image is,

[0078]

[0079] The value range of f is (3,5).

[0080] Example 2: Based on the method for sorting high-quality rice husks for brewing wine in Example 1, the present invention is further illustrated and described below.

[0081] like Figure 1 or Figure 2 As shown, a method for sorting high-quality rice husks for brewing wine comprises:

[0082] M1. In the process of conveying the rice husk 4 after impurities removal to the target container through the conveyor belt 3, the camera 1 above the conveyor belt 3 obtains the image data information of the rice husk in real time, and the weighing sensor 2 obtains the bulk density data information of the rice husk in real time;

[0083] M2. Based on the image data information of the rice husk, a neural network model integrating the Viola-Jones algorithm is used to identify and classify the image of the rice husk to obtain the classified image data information of the rice husk;

[0084] M3. Based on the image data information of the classified rice husk and the bulk density data information of the rice husk, the image and bulk density of the rice husk are fused using a production rule algorithm based on an adaptive adjustment factor to obtain the fused decision data information of the rice husk;

[0085] M4. Based on the decision data information of the fused rice husk, a quality evaluation function F of the rice husk is established to evaluate the quality of the rice husk and obtain quality evaluation data information of the rice husk.

[0086] In this embodiment, if Figure 4 As shown, in step M3, the method of fusing the rice husk image and bulk density using a production rule algorithm based on an adaptive adjustment factor includes:

[0087] M31. Based on the classified rice husk image data information, establish a production rule function R of the rice husk image,

[0088]

[0089] Among them, z is the image data information of the classified rice husk, δ1 and δ2 are the regular change factors of the rice husk image, which characterize the regular change of the rice husk image and obtain the regular change data information of the classified rice husk image;

[0090] M32. Based on the bulk density data information of the rice husk, a production rule function U of the bulk density of the rice husk is established.

[0091]

[0092] Among them, r is the bulk density data information of rice husk, γ1 and γ2 are the regular change factors of rice husk bulk density, which characterize the regular change of rice husk bulk density and obtain the regular change data information of rice husk bulk density;

[0093] M33. Based on the regular change data information of the rice husk bulk density and the regular change data information of the classified rice husk image, a fusion function P of the rice husk bulk density and the image is established.

[0094]

[0095] Among them, g1 is the regular change data information of rice husk bulk density, g2 is the regular change data information of the classified rice husk image, η1, η2 and η3 are adaptive adjustment factors, and the image and bulk density of rice husk are fused to obtain the determined data information of the fused rice husk.

[0096] In this embodiment, the adaptive adjustment factors η1, η2 and η3 are:

[0097]

[0098] Among them, g1 is the regular change data information of rice husk bulk density, and g2 is the regular change data information of the classified rice husk image.

[0099] In this embodiment, the constraint conditions of the regular variation factors γ1 and γ2 of the rice husk bulk density are:

[0100]

[0101] The constraints of the regular variation factors δ1 and δ2 of the rice husk image are:

[0102]

[0103] In this embodiment, in step M4, the quality evaluation function F of the rice husk is,

[0104]

[0105] Among them, h is the decision data information of the fused rice husk, and ω1, ω2 and ω3 are the quality evaluation factors of rice husk.

[0106] In this embodiment, the constraint function S of the rice husk quality assessment factors ω1, ω2 and ω3 is,

[0107]

[0108] The value range of the constraint function S is (1,2).

[0109] In this embodiment, the present invention provides a high-quality rice husk sorting system for brewing wine, comprising a computer device programmed or configured to execute the steps of any one of the methods for sorting high-quality rice husk for brewing wine.

[0110] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the methods for sorting high-quality rice husks for brewing wine.

[0111] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0112] In summary, the present invention can not only accurately sort rice husks, but also does not require manual intervention during the rice husk sorting process, thereby reducing labor costs and improving production efficiency.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for sorting high-quality rice husks for brewing wine, characterized in that: The method comprises: M1. In the process of conveying the rice husks after impurities removal to the target container through the conveyor belt, the image data information of the rice husks is obtained in real time based on the camera above the conveyor belt, and the bulk density data information of the rice husks is obtained in real time based on the weighing sensor; M2. Based on the image data information of the rice husk, a neural network model integrating the Viola-Jones algorithm is used to identify and classify the image of the rice husk to obtain the classified image data information of the rice husk; M3. Based on the image data information of the classified rice husk and the bulk density data information of the rice husk, the image and bulk density of the rice husk are fused using a production rule algorithm based on an adaptive adjustment factor to obtain the fused decision data information of the rice husk; M4. Based on the decision data information of the fused rice husk, a quality evaluation function F of the rice husk is established to evaluate the quality of the rice husk and obtain quality evaluation data information of the rice husk.

2. The method for sorting high-quality rice husks for brewing wine according to claim 1, characterized in that: The method further comprises: M5. Based on the quality assessment data information of the rice husk, a preset threshold is set. If the quality assessment data information of the rice husk is greater than the preset threshold, the requirement is met, the rice husk is high-quality rice husk and is sorted. If the quality assessment data information of the rice husk is less than the preset threshold, the requirement is not met.

3. The method for sorting high-quality rice husks for brewing wine according to claim 1, characterized in that: In step M2, the use of a neural network model integrated with the Viola-Jones algorithm to identify and classify images of rice husks includes: M21. Based on the image data information of the rice husk, establish a rice husk image feature extraction function Q, Among them, x is the image data information of rice husk, α1, α2 and α3 are the feature extraction factors of rice husk image, and the feature extraction of rice husk image is performed to obtain the feature image data information of rice husk; M22. Inputting the characteristic image data information of the rice husk into the neural network model for training and learning, determining the neuron function W, Among them, y is the characteristic image data information of rice husk, β1, β2 and β3 are weight coefficients, and the trained neural network model is obtained; M23. Based on the trained neural network model, the image data information of the rice husk is input, the image of the rice husk is identified and classified, and the image data information of the classified rice husk is obtained.

4. The method for sorting high-quality rice husks for brewing wine according to claim 3, characterized in that: In step M22, the constraints of the weight coefficients β1, β2 and β3 are: Among them, y is the characteristic image data information of rice husk.

5. The method for sorting high-quality rice husks for brewing wine according to claim 3, characterized in that: The constraint function f of the feature extraction factors α1, α2 and α3 of the rice husk image is, The value range of f is (3,5).

6. The method for sorting high-quality rice husks for brewing wine according to claim 1, characterized in that: In step M3, the step of fusing the rice husk image and bulk density using a production rule algorithm based on an adaptive adjustment factor includes: M31. Based on the classified rice husk image data information, establish a production rule function R of the rice husk image, Among them, z is the image data information of the classified rice husk, δ1 and δ2 are the regular change factors of the rice husk image, which characterize the regular change of the rice husk image and obtain the regular change data information of the classified rice husk image; M32. Based on the bulk density data information of the rice husk, a production rule function U of the bulk density of the rice husk is established. Among them, r is the bulk density data information of rice husk, γ1 and γ2 are the regular change factors of rice husk bulk density, which characterize the regular change of rice husk bulk density and obtain the regular change data information of rice husk bulk density; M33. Based on the regular change data information of the rice husk bulk density and the regular change data information of the classified rice husk image, a fusion function P of the rice husk bulk density and the image is established. Among them, g1 is the regular change data information of rice husk bulk density, g2 is the regular change data information of the classified rice husk image, η1, η2 and η3 are adaptive adjustment factors, and the image and bulk density of rice husk are fused to obtain the determined data information of the fused rice husk.

7. The method for sorting high-quality rice husks for brewing wine according to claim 6, characterized in that: The adaptive adjustment factors η1, η2 and η3 are: Among them, g1 is the regular change data information of rice husk bulk density, and g2 is the regular change data information of the classified rice husk image.

8. The method for sorting high-quality rice husks for brewing wine according to claim 6, characterized in that: The constraints of the regular variation factors γ1 and γ2 of the rice husk bulk density are: The constraints of the regular variation factors δ1 and δ2 of the rice husk image are:

9. The method for sorting high-quality rice husks for brewing wine according to claim 1, characterized in that: In step M4, the rice husk quality assessment function F is, Among them, h is the decision data information of the fused rice husk, and ω1, ω2 and ω3 are the quality evaluation factors of rice husk.

10. The method for sorting high-quality rice husks for brewing wine according to claim 9, characterized in that: The constraint function S of the rice husk quality assessment factors ω1, ω2 and ω3 is, The value range of the constraint function S is (1,2).

Images