Detection method and process control system for rice processing targeted milling process

Abstract

The application discloses a rice processing targeted milling process detection method and a process control system thereof, and comprises the following steps: setting a detection sequence as (1st milling, final milling), (2nd milling, final milling),..., (n-1st milling, final milling); acquiring C values of each milling process, and arranging the C values according to the detection sequence as (C1, Cn), (C2, Cn),..., (Cn-1, Cn), wherein C1, C2,..., Cn are respectively C values of 1st milling, 2nd milling,..., nth milling obtained by current detection, and n is the number of the milling processes; and performing a modulation process according to a modulation rule once every round of detection is completed according to the set detection sequence. The application ensures that the final milling target is most effectively achieved through coordination between the milling processes by the front and rear milling processes, and realizes precise processing of targeted milling.

Description

Technical Field

[0001] This invention relates to rice processing and testing technology, and in particular to a method and system for detecting targeted milling processes in rice processing. Background Technology

[0002] Targeted milling in rice processing is an intelligent milling method that precisely removes the outer layer containing pesticide residues and coarse fiber, while completely preserving the target nutrient layer (i.e., the "target" of the milling process), based on the layered distribution characteristics of rice bran and nutrients. Under the condition of fine process detection that can accurately detect which rice layer is being milled, targeted milling is used to precisely remove the outer layer containing pesticide residues and coarse fiber.

[0003] 1. In traditional rice processing technology and processes, the degree of whitening is measured solely by whiteness value, and the processing precision is evaluated by the rate of husk retention, the rate of embryo retention, or the degree of husk retention. However, it is impossible to evaluate or detect the process status of targeted milling.

[0004] 2. Traditional rice processing relies solely on sensory evaluation of the final milling state to determine the processing technology. This evaluation is used as the only basis for adjusting the current rice milling machine based on experience or feel. The processing process cannot be scientifically adjusted according to a reasonable model, and therefore cannot meet the process requirements of targeted milling.

[0005] 3. How to achieve the final milling goal most effectively through coordination between different rice milling processes is a technical obstacle that traditional rice processing cannot overcome.

[0006] Therefore, traditional rice processing technology cannot achieve precise targeted milling. To achieve targeted milling, a complete overhaul of process detection, process flow, and control methods is necessary. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to provide a method and system for detecting targeted milling process in rice processing, in order to address the shortcomings of the existing technology and achieve precise processing through targeted milling.

[0008] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a method for detecting targeted milling process in rice processing, comprising the following steps:

[0009] S1. Set the detection order as (1st mill, final mill), (2nd mill, final mill), ..., (n-1th mill, final mill);

[0010] S2. Obtain the C value of each rice milling process, and arrange the C values ​​according to the detection order as follows: (C1, Cn), (C2, Cn), ..., (Cn-1, Cn), where C1, C2, ..., Cn are the C values ​​of the 1st, 2nd, ..., nth milling processes obtained in the current detection, and n is the number of rice milling processes.

[0011] S3. Following the set detection order, after each round of detection is completed, a modulation process is executed once according to the modulation rules, which are as follows:

[0012] ΔPi = (dPi / dCi) × ΔCi;

[0013] ΔPj= 1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dCj / dCn) × (dPj / dCj);

[0014] ΔPn=1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dPn / dCn);

[0015] Wherein, ΔPi is the rice milling pressure adjustment amount of the i-th rice milling process currently being detected, and ΔPj Let ΔCi be the rice milling pressure adjustment amount for the remaining undetected rice milling process j, ΔCi be the difference between the actual detected C value and the optimal C value for the currently detected rice milling process i, dPi / dCi be the rate of change of rice milling pressure and C value for the currently detected rice milling process i, ΔPn be the final rice milling pressure adjustment amount, ΔCn be the difference between the current actual C value and the target C value for the final milling, dPn / dCn be the rate of change of rice milling pressure and C value for the final milling, dPj / dCj be the rate of change of rice milling pressure and C value for the j-th rice milling process, dCn / dCi be the rate of change of C value for the currently detected rice milling process i and the final milling, and dCj / dCn be the rate of change of C value for the j-th rice milling process and the final milling, i=1,2,……,n-1; j=1,2,……,n-1; i≠j;

[0016] The formula for calculating the C value is: Ci = xH + yS + zV + kR + jG + gB; where H, S, V, R, G, and B correspond to the H, S, V, R, G, and B channel values ​​of the tested sample in machine vision, respectively, and x, y, z, k, j, and g are constant coefficients.

[0017] This invention utilizes the H, S, V, R, G, and B channel values ​​of the machine vision corresponding to the sample to be inspected to determine the C value of each level in each rice milling process. Based on the C value, the rice milling pressure adjustment amount of each rice milling process is determined, thereby realizing precise processing of targeted milling. This allows the rice milling process to achieve the final milling target most effectively through the coordination between the preceding and following processes.

[0018] In this invention, the process of determining the constant coefficient in the C-value calculation formula includes:

[0019] A set of samples of the same variety at multiple levels is randomly input into the machine vision system, and the H, S, V, R, G, and B channel values ​​of each independent sample are recorded.

[0020] Each independent sample was stained and sectioned. Samples with the same degree of grinding were grouped into the same group. The C-value of samples in the same group was defined to be equal. Six samples from the same group were randomly selected, and the H, S, V, R, G, and B channel values ​​of the six samples were substituted into the C-value calculation formula to determine x, y, z, k, j, and g.

[0021] In this invention, the layers include a full aleurone layer, an 80% aleurone layer, a 50% aleurone layer, a 30% aleurone layer, a 10% aleurone layer, a sub-aleurone layer, and endosperm.

[0022] In this invention, C1 < C2 < ... < Cn.

[0023] Furthermore, in this invention, 0 ≤ C1 < C2 < ... < Cn ≤ 100.

[0024] Furthermore, in each testing process, the present invention adjusts the rice milling pressure according to the rice milling pressure adjustment amount of each rice milling process.

[0025] As an inventive concept, the present invention also provides a targeted milling process detection system for rice processing, comprising:

[0026] One or more processors;

[0027] A memory having stored one or more programs that, when executed by one or more processors, cause the one or more processors to implement the steps of the method described above.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention ensures that the final milling target is achieved most effectively through the coordination between the successive milling processes, thereby realizing the precise processing of targeted milling. Attached Figure Description

[0029] Figure 1 This is a flowchart of a method according to an embodiment of the present invention;

[0030] Figure 2 This is a sample milled to a sub-aleurone layer according to an embodiment of the present invention;

[0031] Figure 3 Samples with intact aleurone layers preserved for embodiments of the present invention;

[0032] Figure 4 The sample retains 50% of the aleurone layer for the embodiments of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] Based on the stratification characteristics of rice, the characteristics of rice retaining the full aleurone layer, 80% aleurone layer, 50% aleurone layer, 30% aleurone layer, 10% aleurone layer, sub-aleurone layer, and endosperm are mapped to the comprehensive dimensions of color value, saturation, transparency, gray value, and brightness under machine vision. A mathematical model is established for this comprehensive dimension. Any rice sample being inspected can obtain an accurate value through this model after being input into machine vision, and this value is named the C value.

[0035] In actual production, once the final milling target is determined, the corresponding C value can be obtained. Then, using the final milling C value, the most reasonable C value for each rice milling process is found, and the most reasonable C values ​​for each rice milling process constitute the optimal process curve for that variety under the final milling target.

[0036] Based on the optimal process curve, an "optimal process curve regression algorithm" is constructed. This algorithm controls each rice milling process and its processing in real time online, ensuring that the final milled product matches the processing target to the highest degree.

[0037] The detection method of this invention is implemented as follows: Figure 1 As shown.

[0038] The specific implementation steps of this invention are described below.

[0039] 1. Determine the C-value model and parameters

[0040] The model for setting the value of C is: xH+yS+zV+kR+jG+gB.

[0041] H, S, V, R, G, and B correspond to the H, S, V, R, G, and B values ​​in machine vision, respectively. For any sample or set of samples, they become known values ​​after being input into the machine vision of the "Online Process Inspection System". x, y, z, k, j, and g are the coefficients of each value, and the theoretical maximum C value is defined as 100, and the minimum C value is defined as 0.

[0042] A set of samples from multiple levels of the same variety were randomly input and labeled with serial numbers. The H, S, V, R, G, and B values ​​of each independent sample were recorded.

[0043] Each individual sample in the group was sectioned and stained. Samples with the same degree of grinding were grouped into the same subgroup and labeled as follows: all samples with an intact aleurone layer were grouped into group A; all samples with 80% of the aleurone layer were grouped into group B; all samples with 50% of the aleurone layer were grouped into group C; all samples with 30% of the aleurone layer were grouped into group D; all samples with 10% of the aleurone layer were grouped into group E; all samples with only the sub-aleurone layer were grouped into group F; and all samples with only the endosperm were grouped into group G.

[0044] Define that the C-values ​​of samples in the same group are equal, and establish a system of equations to obtain the definite values ​​of the coefficients of x, y, z, k, j, and g in the C-value model.

[0045] After determining the coefficients of x, y, z, k, j, and g, input their specific values ​​into the C-value model.

[0046] 2. Create a C-value lookup table

[0047] Then, the C value of each milling degree of the variety is determined, including the C value of each milling degree such as retaining the complete aleurone layer, 80% aleurone layer, 50% aleurone layer, 30% aleurone layer, 10% aleurone layer, retaining only the sub-aleurone layer, and retaining only the endosperm.

[0048] Furthermore, this leads to the C values ​​corresponding to retaining 20%, 40%, 60%, 70%, and 90% of the aleurone layer.

[0049] Establish a lookup table for the different milling degrees of this variety and their corresponding C values.

[0050] 3. Establish an optimal process curve lookup table

[0051] An intelligent manufacturing system for targeted milling of rice is constructed by utilizing an online intelligent material handling system (CN201810734107.7), an online process detection system (CN201911406271.6), a rice milling pressure stabilization control system (CN202011103410.0), and an industrial internet based on edge computing (CN202210294938.3).

[0052] Based on the final milling target (i.e., milling target) of each batch of processing, query the C value corresponding to the milling target, select the C value as the final milling target value of the batch of processing, and let the value be a.

[0053] Let the C value of this variety of brown rice be b. Obviously, a is greater than b.

[0054] Let the number of rice milling stages in the production line be n. The optimal C value for the first milling stage is α1, the optimal C value for the second milling stage is α2, and so on, with the optimal C value for the i-th milling stage being αi... and the optimal C value for the final milling stage being αn.

[0055] Obviously αn=a, and α1<α2<α3...<αi... <a。

[0056] The goal is to find the optimal C values ​​for α1, α2, α3, ..., αi such that when the final C value of the multi-stage rice milling is a under this combination, the product has the highest degree of conformity with the final milling target.

[0057] The highest degree of product conformity to the final milling target means that when the final milling target (milling target) is determined, its corresponding C-value is also determined. However, in actual production, the fact that the final milling C-value matches the milling target C-value does not mean that every grain of rice in the final milling product is exactly milled on the target. Rather, it means that the average of the sum of the C-values ​​of all objects is equal to the C-value of the milling target. In other words, in actual production, it is not possible to truly achieve that every grain of rice is exactly kept on a certain milling layer. Some grains just reach the milling target, some are milled beyond the milling target, and some are milled below the milling target.

[0058] Therefore, when the final milling reaches the same C value, the percentage of the target milling product that just reaches the target milling point may still be large or small. Under this condition, it is necessary to find the synergistic method with the highest final milling product compliance rate among different combinations of milling processes. This combination of milling processes is the optimal process curve of the milling target on the production line: α1, α2, α3, ..., αi, ..., a.

[0059] The optimal process curve ensures the highest degree of conformity between the product and the final milling target, which means the highest compliance rate.

[0060] Using this method, we can find the optimal process curves for other grinding targets and establish a lookup table of the optimal process curves for this product on this production line.

[0061] The final milling compliance rate was determined by randomly selecting product samples, slicing them, and analyzing them under a 1000x microscope.

[0062] 4. Obtain the rate of change between milling pressure and C-value at each milling stage on the production line, as well as the rate of change between the C-value at each milling stage and the final milling C-value.

[0063] The variable rates of various parameters for this rice variety on the production line were obtained through the established intelligent system for targeted milling in rice processing, including:

[0064] The relationship (rate of change) between the rice milling pressure and the C value of each rice milling process, dCi / dPi;

[0065] The relationship (rate of change) between the C value of each sub-process and the final C value, dCn / dCi;

[0066] i = 1, 2, 3...n, where 1 represents the first milling of rice, 2 represents the second milling of rice, and so on, with n being the final milling.

[0067] 5. Constructing the optimal process curve regression algorithm

[0068] Adjust the detection rules of the online intelligent material handling system and the online process detection system so that they are executed in the detection sequence of (1st mill, final mill), (2nd mill, final mill)... (ith mill, final mill).

[0069] According to the detection rules, the system obtains the C values ​​of each rice milling process in the following order: (C1, Cn), (C2, Cn), (Ci, Cn)... (Cn-1, Cn), where C1, C2...Ci are the C values ​​of the current milling process (1st milling, 2nd milling, ..., ith milling), Cn-1 is the C value of the second-to-last milling process obtained by the detection system, and Cn is the C value of the final milling process obtained by the detection system.

[0070] Meanwhile, the current milling pressure of each milling stage in the rice milling pressure stabilization control system is denoted as P1, P2...P3...Pn, where P1 represents the milling pressure of the current 1st milling, P2 represents the milling pressure of the current 2nd milling, and so on, and Pn represents the final milling pressure.

[0071] After each round of testing is completed (C1 and Cn constitute one round, C2 and Cn constitute one round, Ci and Cn constitute one round, ... similarly, Cn-1 and Cn constitute one round), the system performs one rice milling pressure control modulation. The modulation rules are as follows:

[0072] ΔPi = (dPi / dCi) × ΔCi;

[0073] ΔPj= 1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dCj / dCn) × (dPj / dCj);

[0074] ΔPn=1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dPn / dCn);

[0075] In the formula, ΔPi is the rice milling pressure adjustment amount of the currently detected rice milling process, ΔCi is the difference between the actual detected C value and the optimal C value of the currently detected rice milling process, dPi / dCi is the relationship (rate of change) between the rice milling pressure and C value of the currently detected i-th rice milling process, ΔPn is the final rice milling pressure adjustment amount, ΔCn is the difference between the current actual C value and the target C value of the final milling, dPn / dCn is the relationship (rate of change) between the final rice milling pressure and its C value, dCn / dCi is the relationship (rate of change) between the currently detected rice milling process and the final rice milling C value, ΔPj is the rice milling pressure adjustment amount of the remaining undetected j-th rice milling process, dPj / dCj is the relationship (rate of change) between the rice milling pressure and its C value of the j-th rice milling process, and dPj / dCj is the rate of change between the rice milling pressure and its C value of the j-th rice milling process.

[0076] Taking the current inspection as the first round (C1, Cn) as an example, then i=1 at this time, and the remaining uninspected rice milling processes refer to sub-processes 2 to n-1. Similarly, if the current inspection is for the second round (C2, Cn), then i=2 at this time, and the remaining uninspected rice milling processes refer to the first rice milling process and sub-processes 3 to n-1.

[0077] The following uses four rice milling processes and yellow rice as an example to illustrate the specific implementation process of the present invention.

[0078] One hundred samples of *Huanghua* viscous grains with varying degrees of grinding were input into a machine vision system and labeled as 001, 002, 003, 004...098, 099, 100. The machine vision samples were saved, and their H, S, V, R, G, and B values ​​were recorded. Then, the actual samples (from 001 to 100) were sectioned, stained, and observed under a 1000x microscope. Examples are shown below. Figure 2 .

[0079] Samples with the same degree of milling are grouped into one class, and the C-values ​​of samples in the same class are defined as equal. By selecting any one class (here, the sample group whose milling degree retains 50% aleurone layer), only 6 samples of the same class are needed to obtain the 6 parameters in the C-value model:

[0080] Equation 1: x×H1 + y×S1 + z×V1 + k×R1 + j×G1 + g×B1 = C0;

[0081] Equation 2: x×H² + y×S² + z×V² + k×R² + j×G² + g×B² = C0;

[0082] Equation 3: x×H3 + y×S3 + z×V3 + k×R3 + j×G3 + g×B3 = C0;

[0083] Equation 4: x×H4 + y×S4 + z×V4 + k×R4 + j×G4 + g×B4 = C0;

[0084] Equation 5: x×H5 + y×S5 + z×V5 + k×R5 + j×G5 + g×B5 = C0;

[0085] Equation 6: x×H6 + y×S6 + z×V6 + k×R6 + j×G6 + g×B6 = C0.

[0086] Solving the system of equations, we get:

[0087] x=0.093 y=0.072 z=0.071;

[0088] k=0.063 j=0.061 g=0.059;

[0089] The C-value of Huang Huazhan, who retained 50% of the aleurone layer, was 26. Among them, H1, S1, V1, R1, G1, and B1 are the H, S, V, R, G, and B values ​​corresponding to six similar samples, respectively.

[0090] 2. The Huanghua aleurone layer was obtained sequentially while retaining its integrity. Figure 3 The C values ​​for rice with 80% aleurone layer, 30% aleurone layer, 10% aleurone layer, only sub-aleurone layer, only endosperm, and brown rice were 24, 24.5, 27.1, 28.3, 29, 31, and 13.9, respectively.

[0091] 3. The rice processing targeted milling intelligent manufacturing system was started, and the relationship between milling pressure and C value (rate of change), and the relationship between C value of each milling sub-process and final milling C value (rate of change) were obtained: dP1 / dC1 = 297; dP2 / dC2 = 231; dP3 / dC3 = 245; dP4 / dC4 = 156; dC4 / dC1 = 0.79; dC4 / dC2 = 0.86; dC4 / dC3 = 0.90.

[0092] 4. Activate the intelligent manufacturing system for targeted milling of rice. Based on the characteristics of multi-machine light milling process, when the final milling target is to retain 50% of the aleurone layer ( Figure 4 When the C value is 26, that is, the final rolling target C value is 26, the optimal process curve range can be predicted to be: C value of 18-20 for the first rolling; C value of 20-23 for the second rolling; C value of 23-25 ​​for the third rolling; and C value of 26 for the fourth rolling.

[0093] Within the C-value range of each rice milling process, different combinations were made. Then, 100 grains of the four-milling (final milling) products with a C-value of 26 obtained from different combinations were randomly sampled. The obtained samples were sliced, stained, and examined under a 1000x microscope to find the synergistic processing combination of milling processes 1, 2, 3, and 4 with the highest proportion of aleurone layer.

[0094] The optimal rice milling process for obtaining a final C value of 26 is as follows:

[0095] C value of 1 mill: 19.6; C value of 2 mills: 22.1; C value of 3 mills: 24.3; C value of 4 mills: 26.

[0096] Under this combination, the final milling compliance rate (the percentage of the final milled product that retains just 50% of the aleurone layer) is 87%, the percentage of samples with the aleurone layer completely milled is 1.5%, and the percentage of samples with the outer skin layer not completely removed is 0.5%. This is an extremely ideal result in actual production.

[0097] Similarly, the optimal combination of rice milling processes can be obtained for the final milling objectives of retaining the complete aleurone layer, 30% aleurone layer, 10% aleurone layer, and only retaining the sub-aleurone layer.

[0098] The detection and material handling rules of the online process detection system and the online intelligent material handling system of the rice processing targeted milling intelligent manufacturing system are set as follows: (1 milling, 4 milling); (2 milling, 4 milling); (3 milling, 4 milling).

[0099] The detection time for each round is set to 2 minutes, so a device modulation decision is generated after each round of online detection is completed.

[0100] When the detection process executes rounds (1st mill, 4th mill), the current processing status of mill 1 and mill 4, the C1 value and C4 value, and the production line adjustment actions and their magnitudes are obtained as follows:

[0101] ΔP1 = (dP1 / dC1)×ΔC1 = 297×(19.6-C1);

[0102] ΔP2 = 1 / (4-1)×(ΔC4 - ΔC1×dC4 / dC1)×(dC2 / dC4) × (dP2 / dC2)=(1 / 3)×[(C4-24 - (19.6-C1)×0.79]×(1 / 0.86)×231;

[0103] Similarly, according to the formula:

[0104] ΔP3 = (1 / 3) × [(C4-24 - (19.6-C1) × 0.79] × (1 / 0.90) × 245;

[0105] ΔP4 = (1 / 3) × [(C4-24 - (19.6-C1) × 0.79] × 156;

[0106] ΔP1, ΔP2, ΔP3, and ΔP4 represent the rice milling pressure adjustment for mills 1, 2, 3, and 4, respectively, in grams.

[0107] Another embodiment of the present invention provides a detection system corresponding to the above embodiments, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program in the memory to implement the steps of the method in the above embodiments.

[0108] In some implementations, the memory may be high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk storage device.

[0109] In other implementations, the processor can be any type of general-purpose processor, such as a central processing unit (CPU) or a digital signal processor (DSP), and there is no limitation here.

[0110] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0111] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for detecting targeted milling process in rice processing, characterized in that, Includes the following steps: S1. Set the detection order as (1st mill, final mill), (2nd mill, final mill), ..., (n-1th mill, final mill); S2. Obtain the C value of each rice milling process, and arrange the C values ​​according to the detection order as follows: (C1, Cn), (C2, Cn), ..., (Cn-1, Cn), where C1, C2, ..., Cn are the C values ​​of the 1st milling, 2nd milling, ..., nth milling processes obtained by the current detection, and n is the number of rice milling processes. S3. Following the set testing sequence, after each round of testing is completed, a modulation process is executed once according to the modulation rules. That is, during each testing process, the rice milling pressure is adjusted according to the rice milling pressure adjustment amount of each rice milling process. The modulation rules are as follows: ΔPi = (dPi / dCi) × ΔCi; ΔPj=1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dCj / dCn) × (dPj / dCj); ΔPn=1 / (n-1)×(ΔCn - ΔCi×dCn / dCi)×(dPn / dCn); Where ΔPi is the rice milling pressure adjustment amount of the i-th rice milling process currently being detected, and ΔPj Let ΔCi be the rice milling pressure adjustment amount for the remaining undetected rice milling process j, ΔCi be the difference between the actual detected C value and the optimal C value for the currently detected rice milling process i, dPi / dCi be the rate of change of rice milling pressure and C value for the currently detected rice milling process i, ΔPn be the final rice milling pressure adjustment amount, ΔCn be the difference between the current actual C value and the target C value for the final milling, dPn / dCn be the rate of change of rice milling pressure and C value for the final milling, dPj / dCj be the rate of change of rice milling pressure and C value for the j-th rice milling process, dCn / dCi be the rate of change of C value for the currently detected rice milling process i and the final milling, and dCj / dCn be the rate of change of C value for the j-th rice milling process and the final milling, i=1,2,……,n-1; j=1,2,……,n-1; i≠j; The formula for calculating the C value is: C = xH + yS + zV + kR + jG + gB; where H, S, V, R, G, and B correspond to the H, S, V, R, G, and B channel values ​​of the tested sample in machine vision, respectively, and x, y, z, k, j, and g are constant coefficients. The process of determining the constant coefficient in the formula for calculating the C value includes: A set of samples of the same variety at multiple levels is randomly input into the machine vision system, and the H, S, V, R, G, and B channel values ​​of each independent sample are recorded. Each independent sample was stained and sectioned. Samples with the same degree of grinding were grouped into the same group. The C-value of samples in the same group was defined to be equal. Six samples from the same group were randomly selected, and the H, S, V, R, G, and B channel values ​​of the six samples were substituted into the C-value calculation formula to determine x, y, z, k, j, and g.

2. The method for detecting targeted milling process in rice processing according to claim 1, characterized in that, The layers include a full aleurone layer, an 80% aleurone layer, a 50% aleurone layer, a 30% aleurone layer, a 10% aleurone layer, a sub-aleurone layer, and endosperm.

3. The method for detecting targeted milling process in rice processing according to claim 1, characterized in that, C1 < C2 < ... < Cn.

4. The method for detecting targeted milling process in rice processing according to claim 1, characterized in that, 0≤C1<C2<……<Cn≤100.

5. A targeted milling process detection system for rice processing, characterized in that, include: One or more processors; A memory having stored one or more programs thereon, which, when executed by the one or more processors, cause the one or more processors to perform the steps of the method according to any one of claims 1 to 4.

Images