Quality monitoring method and device for rice flour prepared by semi-dry method

Abstract

The invention provides a quality monitoring method and device for rice flour prepared by a semi-dry method, and relates to the technical field of rice flour quality monitoring, and the method specifically comprises the following steps: collecting spectral data of the rice flour in real time, collecting physical parameters of the rice flour, and generating a physical evaluation index; calculating the content of the to-be-detected component, and generating a chemical evaluation index; combining the evaluation indexes to generate a rice flour quality evaluation index, and comparing the rice flour quality evaluation index with a preset threshold value to obtain the quality condition of the current rice flour. The comprehensive rice flour quality evaluation method is provided by collecting the spectral data of the rice flour in real time and combining physical parameters such as the particle size, the density, the moisture content and the moisture activity to form effective combination of a chemical evaluation index and a physical evaluation index. According to the method, quality problems possibly existing in the production process can be fed back in time, a basis for adjusting production parameters in real time can be provided for an operator by comparing the quality problems with the preset evaluation threshold value, and the production efficiency and the stability of product quality are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of rice noodle quality monitoring, in particular to a quality monitoring method and device for rice noodle prepared by a semi-dry method. Background Art

[0002] As an important food raw material, rice noodles are widely used in the global catering culture, and their quality directly affects the taste and nutritional value of the finished product. In the traditional rice noodle production process, quality monitoring methods usually rely on laboratory analysis, which is not only time-consuming, but also often cannot meet the requirements of real-time and flexibility in the production process. In actual production, if the quality data of rice noodles cannot be obtained in time, it may lead to unqualified products in the production process, resulting in waste of resources and economic losses. In addition, existing monitoring technologies are often limited to a single physical or chemical parameter, lack a comprehensive evaluation of the comprehensive quality characteristics of rice noodles, and fail to fully consider the relationship between the chemical composition (such as protein, starch, fat, etc.) and physical properties (such as particle size, moisture content, etc.) of rice noodles. This deficiency makes it difficult to detect and correct problems in the production process in a timely manner, affecting the overall quality and production efficiency of rice noodles.

[0003] In recent years, with the continuous development of near-infrared spectroscopy technology, its application in the field of food quality control has gradually attracted attention. This technology can quickly and non-destructively obtain information on the chemical composition of food with high sensitivity and accuracy. However, current research focuses on the application of spectral data alone, and fails to effectively compare and comprehensively analyze it with the physical parameters of rice noodles in real time, which is somewhat one-sided.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The object of the present invention is to provide a method and device for monitoring the quality of rice noodles prepared by a semi-dry method, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for monitoring the quality of rice noodles prepared by a semi-dry method, comprising the following specific steps:

[0008] Step 1: In the key link of preparing rice noodles, a near-infrared spectroscopy device is used to collect spectral data of the rice noodles in real time, and the sampling frequency is set to collect data once every five minutes. The key links include rice slurry preparation, drying and finished product packaging; while collecting spectral data each time, the particle size, density, moisture content and water activity of the rice noodles are collected to constitute the physical parameters of the rice noodles;

[0009] Step 2: Calculate the content of the components to be measured based on the collected spectral data, wherein the components to be measured include protein content, starch content, fat content, ash content, sugar content and cellulose content, and perform dimensionless processing on the content of the components to be measured to generate a chemical evaluation index; perform dimensionless processing on the physical parameters of the rice noodles collected at the same time to generate a physical evaluation index;

[0010] Step 3: combining the obtained chemical evaluation index and physical evaluation index of the rice noodles to generate a rice noodles quality evaluation index;

[0011] Step 4: Compare the rice noodle quality evaluation index with the preset evaluation threshold. When it exceeds the preset threshold, notify the operator and adjust the production parameters according to the real-time monitoring results.

[0012] Furthermore, the process of collecting the particle size of the rice noodles is specifically as follows: 5 kg of rice noodles are collected as a sample in real time, and the rice noodles are divided into different particle size levels by vibration screening using a standard sieve, and the weight proportion of each level is recorded, which represents the particle size distribution of the current whole rice noodles; the particle size of the sieved rice noodles is compared with a preset particle size threshold, and the proportion of rice noodles exceeding the preset threshold is recorded, which is recorded as D exceed ;

[0013] The process of collecting rice noodle density is as follows: 5 kg of rice noodles are collected as samples in real time, the rice noodles are put into water, the water displacement is measured, the current rice noodle density is calculated according to the Archimedean principle, and the current rice noodle density is compared with the preset rice noodle density threshold. If it exceeds the threshold range, the difference between the current rice noodle density and the preset threshold is calculated and recorded as Δρ; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index;

[0014] The process of collecting the moisture content MC of rice flour is as follows: collecting GCkg of rice flour as a sample in real time, using the drying method to heat the rice flour sample to a certain temperature in a constant temperature oven until it reaches a constant weight NCkg, and calculating the moisture loss to determine the moisture content:

[0015]

[0016] Wherein, MC is the moisture content of rice noodles, GC is the initial weight of the sample, and NC is the dry weight of the sample; the current moisture content of rice noodles is compared with the preset moisture content threshold. If it exceeds the threshold range, the difference between the current moisture content of rice noodles and the preset threshold is calculated and recorded as ΔMC; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index;

[0017] Collect rice flour water activity a wThe process is as follows: Use a water activity measuring instrument to measure the current water activity of rice flour, recorded as a w .

[0018] Furthermore, the process of estimating the content of the component to be measured based on the collected spectral data is specifically: using the following formula to perform component estimation on the collected spectral data:

[0019]

[0020] Wherein, Y is the content of the component to be tested, and the component to be tested is protein, starch, fat, ash, sugar or cellulose, and X i is the spectral absorption value of the i-th wavelength, a i is the regression coefficient of the ith wavelength, and b is the constant term.

[0021] Furthermore, the regression coefficient a i The determination process of the constant term b specifically includes:

[0022] A group of rice noodle samples with known ingredient contents are collected, and the ingredient contents of these samples are different from each other; spectral measurements are performed on these samples, and the absorption value of each sample at different wavelengths is recorded to form a spectral data set;

[0023] The standard sample data with known component content is combined with the corresponding spectral data to form a data matrix; the rows represent the samples and the columns represent the spectral features, i.e., the absorption values ​​at different wavelengths;

[0024] The target variable was set as the component content of the sample, including protein content, starch content, fat content, ash content, sugar content, and cellulose content, and the spectral data was used as the independent variable;

[0025] Select the linear regression model for modeling. The regression model is expressed as:

[0026] Y=a1X1+a2X2+…+a n X n +b

[0027] Among them, Y is the target variable, X1, X2, …, X n are the spectral absorption values ​​at different wavelengths, a1, a2, …, a n is the regression coefficient to be obtained;

[0028] The model is fitted by the least squares method to minimize the square error between the predicted value and the actual value. The minimized objective function is as follows:

[0029]

[0030] Among them, Y jis the actual component content of the jth sample, is the component content predicted by the model, and m is the total number of samples;

[0031] Through linear regression analysis, the regression coefficient a of each wavelength is calculated. i and constant term b, you can use Python to directly execute this process and return these parameters.

[0032] Furthermore, protein, starch, fat, ash, sugar and cellulose are numbered 1, 2, ... 6 respectively, and the content of the kth component to be tested is calibrated as Y k , k∈[1,6], based on the content of the component to be tested, it is compared with the corresponding preset threshold value. When the threshold value is exceeded, the difference between the component content and the preset threshold value is recorded, which is recorded as ΔY k If the content of the ingredient is within the threshold range, it is not included in the calculation. The formula based on the chemical evaluation index CHE of the generated rice flour is as follows:

[0033]

[0034] Wherein, CHE is the chemical evaluation index of rice noodles, α is a preset proportional coefficient, and α is not zero, and C1 is a constant correction index.

[0035] Furthermore, the formula for the physical evaluation index PHY of the generated rice noodles is as follows:

[0036]

[0037] Among them, PHY is the physical evaluation index of rice noodles, D exceed is the proportion of rice flour particle sizes that currently exceed the preset threshold, Δρ is the difference between the current rice flour density and the preset threshold, ΔMC is the difference between the current rice flour moisture content and the preset threshold, and a w is the current water activity of rice noodles, m, n, c are the denominator adjustment index, and m, n, c are not zero, C2 is the constant correction index.

[0038] Furthermore, the process of combining the chemical evaluation index and the physical evaluation index of the obtained rice noodles to generate the rice noodles quality evaluation index QS is specifically as follows:

[0039]

[0040] Among them, QS is the quality evaluation index of the current rice noodles, PHY is the physical evaluation index, β is its preset proportional coefficient, CHE is the chemical evaluation index, γ is its preset proportional coefficient, and γ>β>0, C3 is the constant correction index.

[0041] Further, the process of comparing the rice noodle quality evaluation index QS with a preset evaluation threshold QY specifically includes:

[0042] When QS < QY, it is determined that the quality of the current rice noodle sample is unqualified, the operator is notified, and the production parameters are adjusted according to the real-time monitoring results;

[0043] When QS ≥ QY, it is determined that the quality of the current rice noodle sample is qualified, and the preparation process of the rice noodles is continuously monitored;

[0044] Among them, QS is the quality evaluation index of the current rice noodles, and QY is the rice noodle evaluation threshold.

[0045] The present invention also provides a quality monitoring device for preparing rice noodles by the semi-dry method. The quality monitoring device for preparing rice noodles by the semi-dry method is used to execute the above-mentioned quality monitoring method for preparing rice noodles by the semi-dry method, and includes:

[0046] A data acquisition module, which is used to collect the spectral data of rice noodles in real time using a near-infrared spectroscopy device at the key links of preparing rice noodles, and set the sampling frequency to collect data every five minutes. The key links include rice milk preparation, drying, and finished product packaging; while collecting the spectral data each time, collect the particle size, density, moisture content, and water activity of the rice noodles to form the physical parameters of the rice noodles;

[0047] A data analysis module, which calculates the content of the components to be measured based on the collected spectral data. The components to be measured include protein content, starch content, fat content, ash content, sugar content, and cellulose content. After dimensionless processing of the above-mentioned contents of the components to be measured, a chemical evaluation index is generated; the physical parameters of the rice noodles collected at the same time are dimensionless processed to generate a physical evaluation index;

[0048] An evaluation index generation module, which is used to combine the obtained chemical evaluation index and physical evaluation index of the rice noodles to generate a rice noodle quality evaluation index;

[0049] An intelligent decision-making module, which is used to compare the rice noodle quality evaluation index with a preset evaluation threshold. When it exceeds the preset threshold, the operator is notified, and the production parameters are adjusted according to the real-time monitoring results.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] The present invention collects rice flour spectrum data in real time, and combines physical parameters such as particle size, density, moisture content and water activity to form an effective combination of chemical evaluation index and physical evaluation index, thereby providing a comprehensive rice flour quality evaluation method. This method can not only timely feedback possible quality problems in the production process, but also provide operators with a basis for adjusting production parameters in real time by comparing with preset evaluation thresholds, thereby significantly improving production efficiency and product quality stability. In addition, the use of dimensionless chemical and physical evaluation indexes makes the comparison between different indicators more intuitive, enhances the controllability and intelligent management level of the production process, and helps promote the modernization of rice flour production. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0053] Figure 2 It is a schematic diagram of the overall device module of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0056] Example:

[0057] See also Figure 1 , the present invention provides a technical solution:

[0058] A method for monitoring the quality of rice noodles prepared by a semi-dry method, comprising the following specific steps:

[0059] Step 1: In the key link of preparing rice noodles, a near-infrared spectroscopy device is used to collect spectral data of the rice noodles in real time, and the sampling frequency is set to collect data once every five minutes. The key links include rice slurry preparation, drying and finished product packaging; while collecting spectral data each time, the particle size, density, moisture content and water activity of the rice noodles are collected to constitute the physical parameters of the rice noodles;

[0060] In this embodiment, the process of collecting the particle size of rice noodles is specifically as follows: 5 kg of rice noodles are collected as a sample in real time, and the rice noodles are divided into different particle size levels by vibration screening using a standard sieve, and the weight proportion of each level is recorded, which represents the particle size distribution of the current whole rice noodles; the particle size of the sieved rice noodles is compared with a preset particle size threshold, and the proportion of rice noodles exceeding the preset threshold is recorded, which is recorded as D exceed ;

[0061] The process of collecting rice noodle density is as follows: 5 kg of rice noodles are collected as samples in real time, the rice noodles are put into water, the water displacement is measured, the current rice noodle density is calculated according to the Archimedean principle, and the current rice noodle density is compared with the preset rice noodle density threshold. If it exceeds the threshold range, the difference between the current rice noodle density and the preset threshold is calculated and recorded as Δρ; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index;

[0062] The process of collecting the moisture content MC of rice flour is as follows: collecting GCkg of rice flour as a sample in real time, using the drying method to heat the rice flour sample to a certain temperature in a constant temperature oven until it reaches a constant weight NCkg, and calculating the moisture loss to determine the moisture content:

[0063]

[0064] Wherein, MC is the moisture content of rice noodles, GC is the initial weight of the sample, and NC is the dry weight of the sample; the current moisture content of rice noodles is compared with the preset moisture content threshold. If it exceeds the threshold range, the difference between the current moisture content of rice noodles and the preset threshold is calculated and recorded as ΔMC; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index;

[0065] Collect rice flour water activity a w The process is as follows: Use a water activity measuring instrument to measure the current water activity of rice flour, recorded as a w .

[0066] Step 2: Calculate the content of the components to be measured based on the collected spectral data, wherein the components to be measured include protein content, starch content, fat content, ash content, sugar content and cellulose content, and perform dimensionless processing on the content of the components to be measured to generate a chemical evaluation index; perform dimensionless processing on the physical parameters of the rice noodles collected at the same time to generate a physical evaluation index;

[0067] In this embodiment, the process of estimating the content of the component to be measured based on the collected spectral data is specifically: using the following formula to estimate the component of the collected spectral data:

[0068]

[0069] Wherein, Y is the content of the component to be tested, and the component to be tested is protein, starch, fat, ash, sugar or cellulose, and X i is the spectral absorption value of the i-th wavelength, a i is the regression coefficient of the ith wavelength, and b is a constant term. i The determination process of the constant term b specifically includes:

[0070] A group of rice noodle samples with known ingredient contents are collected, and the ingredient contents of these samples are different from each other; spectral measurements are performed on these samples, and the absorption value of each sample at different wavelengths is recorded to form a spectral data set;

[0071] The standard sample data with known component content is combined with the corresponding spectral data to form a data matrix; the rows represent the samples and the columns represent the spectral features, i.e., the absorption values ​​at different wavelengths;

[0072] The target variable was set as the component content of the sample, including protein content, starch content, fat content, ash content, sugar content, and cellulose content, and the spectral data was used as the independent variable;

[0073] Select the linear regression model for modeling. The regression model is expressed as:

[0074] Y=a1X1+a2X2+…+a n X n +b

[0075] Among them, Y is the target variable, X1, X2, …, X n are the spectral absorption values ​​at different wavelengths, a1, a2, …, a n is the regression coefficient to be obtained;

[0076] The model is fitted by the least squares method to minimize the square error between the predicted value and the actual value. The minimized objective function is as follows:

[0077]

[0078] Among them, Y j is the actual component content of the jth sample, is the component content predicted by the model, and m is the total number of samples;

[0079] Through linear regression analysis, the regression coefficient a of each wavelength is calculated. i and constant term b, you can use Python to directly execute this process and return these parameters.

[0080] Number protein, starch, fat, ash, sugar and cellulose as 1, 2, ... 6 respectively, and mark the content of the kth component to be tested as Y k , k∈[1,6], based on the content of the component to be tested, it is compared with the corresponding preset threshold value. When the threshold value is exceeded, the difference between the component content and the preset threshold value is recorded, which is recorded as ΔY k If the content of the ingredient is within the threshold range, it is not included in the calculation. The formula based on the chemical evaluation index CHE of the generated rice flour is as follows:

[0081]

[0082] Wherein, CHE is the chemical evaluation index of rice noodles, α is a preset proportional coefficient, and α is not zero, and C1 is a constant correction index.

[0083] When ΔY k When it increases, it means that the difference between the chemical content in the rice noodles and the preset threshold value increases, resulting in an increase in the chemical evaluation index, which means that ΔY k It is positively correlated with the chemical evaluation index CHE.

[0084] The formula for the physical evaluation index PHY of the generated rice flour is as follows:

[0085]

[0086] Among them, PHY is the physical evaluation index of rice noodles, D exceed is the proportion of rice flour particle sizes that currently exceed the preset threshold, Δρ is the difference between the current rice flour density and the preset threshold, ΔMC is the difference between the current rice flour moisture content and the preset threshold, and a w is the current water activity of rice noodles, m, n, c are the denominator adjustment index, and m, n, c are not zero, C2 is the constant correction index; when D exceedWhen Δρ increases, it means that the proportion of rice noodle particles exceeding the preset threshold value increases, which will directly affect the solubility, taste and cooking performance of the rice noodles, so the physical evaluation index PHY decreases; when Δρ increases, it means that the difference between the current rice noodle density and the preset threshold value increases. Too high a density may make it difficult for the rice noodles to fully absorb water during cooking, resulting in a hard taste and difficulty in tasting the rice noodles. Low-density rice noodles may cause poor fluidity during the production process, affecting processing efficiency, so the physical evaluation index PHY decreases; when ΔMC increases, it means that the difference between the current moisture content of the rice noodles and the preset threshold value increases. Too high a moisture content may cause the rice noodles to become sticky during cooking, affecting the taste. Rice noodles with too low a moisture content may cause dryness, a rough taste and be fragile, so the physical evaluation index PHY decreases; when a w When the water activity increases, it means that the water activity of the current rice noodles increases. When the water activity is high, the water in the rice noodles is more easily utilized by microorganisms, which may lead to the rapid growth of microorganisms such as bacteria, yeast and mold, affecting its safety and palatability. Therefore, the physical evaluation index PHY decreases; that is, D exceed , Δρ, ΔMC, a w It is negatively correlated with the physical evaluation index PHY.

[0087] By estimating the content of components such as protein, starch, fat, ash, sugar and cellulose through near-infrared spectral data, efficient and non-destructive real-time monitoring can be achieved; compared with traditional chemical analysis methods, this method reduces sample processing time and cost, and improves the frequency and efficiency of monitoring.

[0088] Step 3: combining the obtained chemical evaluation index and physical evaluation index of the rice noodles to generate a rice noodles quality evaluation index;

[0089] In this embodiment, the process of combining the chemical evaluation index and the physical evaluation index of the obtained rice noodles to generate the rice noodles quality evaluation index QS is specifically as follows:

[0090]

[0091] Among them, QS is the quality evaluation index of the current rice noodles, PHY is the physical evaluation index, β is its preset proportional coefficient, CHE is the chemical evaluation index, γ is its preset proportional coefficient, and γ>β>0. The weight of the chemical evaluation index will be slightly higher than the physical evaluation index because in the semi-dry preparation process of rice noodles, the chemical properties of rice noodles directly affect its processing performance and the final user experience. C3 is a constant correction index; when the physical evaluation index PHY increases, the quality evaluation index QS increases; when the chemical evaluation index CHE increases, the quality evaluation index QS decreases; that is, CHE is negatively correlated with the quality evaluation index QS, and PHY is positively correlated with the quality evaluation index QS.

[0092] In this step, by combining the chemical evaluation index and the physical evaluation index to generate a comprehensive rice noodle quality evaluation index, a more comprehensive quality evaluation is provided. Compared with evaluating the quality of rice noodles relying only on a single index, the comprehensive evaluation can more comprehensively reflect the influence of various parameters in the production process on the quality of the final product, reducing potential biases.

[0093] Step 4: Compare the rice noodle quality evaluation index with a preset evaluation threshold. When it exceeds the preset threshold, notify the operator and adjust the production parameters according to the real-time monitoring results.

[0094] In this embodiment, the process of comparing the rice noodle quality evaluation index QS with the preset evaluation threshold QY specifically includes:

[0095] When QS < QY, it is determined that the quality of the current rice noodle sample is unqualified, notify the operator, and adjust the production parameters according to the real-time monitoring results.

[0096] When QS ≥ QY, it is determined that the quality of the current rice noodle sample is qualified, and continuously monitor the preparation process of the rice noodles.

[0097] Among them, QS is the quality evaluation index of the current rice noodles, and QY is the rice noodle evaluation threshold.

[0098] In this step, by comparing the rice noodle quality evaluation index with the preset evaluation threshold, a real-time feedback mechanism is achieved. When the rice noodle quality index exceeds the set threshold, the system can immediately notify the operator to make adjustments. Compared with the traditional production monitoring method, it can identify quality problems more quickly and accurately, reduce quality defects caused by improper production parameters, and ensure the consistency and stability of the rice noodles.

[0099] A quality monitoring device for preparing rice noodles by the semi-dry method, comprising:

[0100] A data analysis module, which calculates the content of the components to be measured based on the collected spectral data. The components to be measured include protein content, starch content, fat content, ash content, sugar content, and cellulose content. After dimensionless processing of the above contents of the components to be measured, a chemical evaluation index is generated; the physical parameters of the rice noodles collected at the same time are dimensionless processed to generate a physical evaluation index.

[0101] An evaluation index generation module, which combines the obtained chemical evaluation index and physical evaluation index of the rice noodles to generate a rice noodle quality evaluation index.

[0102] An intelligent decision-making module, which is used to compare the rice noodle quality evaluation index with a preset evaluation threshold. When it exceeds the preset threshold, notify the operator and adjust the production parameters according to the real-time monitoring results.

[0103] The specific values ​​of m, n, c, d, α, β, and γ in the formula are generally determined by technical personnel in this field according to actual conditions. The technical personnel in this field collect multiple groups of sample data, and set corresponding preset proportional coefficients for each group of sample data. The preset proportional coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these factor coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination, and the calculated factor coefficients are screened and averaged to obtain the values ​​of m, n, c, d, α, β, and γ.

[0104] In addition, the size of the preset factor coefficient is to quantify each parameter to obtain a specific value. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preset proportional coefficient initially set by technical personnel in this field for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0105] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0106] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A quality monitoring method for preparing rice noodles by a semi-dry method, characterized in that: The specific steps include: Step 1: In the key link of preparing rice noodles, a near-infrared spectroscopy device is used to collect spectral data of the rice noodles in real time, and the sampling frequency is set to collect data once every five minutes. The key links include rice slurry preparation, drying and finished product packaging; while collecting spectral data each time, the particle size, density, moisture content and water activity of the rice noodles are collected to constitute the physical parameters of the rice noodles; Step 2: Calculate the content of the components to be measured based on the collected spectral data, wherein the components to be measured include protein content, starch content, fat content, ash content, sugar content and cellulose content, and perform dimensionless processing on the content of the components to be measured to generate a chemical evaluation index; perform dimensionless processing on the physical parameters of the rice noodles collected at the same time to generate a physical evaluation index; Step 3: combining the obtained chemical evaluation index and physical evaluation index of the rice noodles to generate a rice noodles quality evaluation index; Step 4: Compare the rice noodle quality evaluation index with the preset evaluation threshold. When it exceeds the preset threshold, notify the operator and adjust the production parameters according to the real-time monitoring results.

2. The method for monitoring the quality of rice flour prepared by a semi-dry method according to claim 1, wherein: The process of collecting the particle size of rice noodles is specifically as follows: 5 kg of rice noodles are collected as samples in real time, and the rice noodles are divided into different particle size levels by vibration screening using a standard sieve, and the weight proportion of each level is recorded, which represents the particle size distribution of the current whole rice noodles; the particle size of the sieved rice noodles is compared with a preset particle size threshold, and the proportion of rice noodles exceeding the preset threshold is recorded, which is recorded as D exced ; The process of collecting rice noodle density is as follows: 5 kg of rice noodles are collected as samples in real time, the rice noodles are put into water, the water displacement is measured, the current rice noodle density is calculated according to the Archimedean principle, and the current rice noodle density is compared with the preset rice noodle density threshold. If it exceeds the threshold range, the difference between the current rice noodle density and the preset threshold is calculated and recorded as Δρ; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index; The process of collecting the moisture content MC of rice flour is as follows: collecting GCkg of rice flour as a sample in real time, using the drying method to heat the rice flour sample to a certain temperature in a constant temperature oven until it reaches a constant weight NCkg, and calculating the moisture loss to determine the moisture content: Wherein, MC is the moisture content of rice noodles, GC is the initial weight of the sample, and NC is the dry weight of the sample; the current moisture content of rice noodles is compared with the preset moisture content threshold. If it exceeds the threshold range, the difference between the current moisture content of rice noodles and the preset threshold is calculated and recorded as ΔMC; if it does not exceed the threshold range, it will not be included in the subsequent calculation of the physical evaluation index; Collect rice flour water activity a w The process is as follows: Use a water activity measuring instrument to measure the current water activity of rice flour, recorded as a w .

3. The method for monitoring the quality of rice flour prepared by a semi-dry method according to claim 2, wherein: The process of estimating the content of the component to be measured based on the collected spectral data is specifically: using the following formula to estimate the component of the collected spectral data: Wherein, Y is the content of the component to be tested, and the component to be tested is protein, starch, fat, ash, sugar or cellulose, and X i is the spectral absorption value of the i-th wavelength, a i is the regression coefficient of the Ith wavelength, and b is the constant term.

4. The method for monitoring the quality of rice flour prepared by a semi-dry method according to claim 3, wherein: The regression coefficient a i The determination process of the constant term b specifically includes: A group of rice noodle samples with known ingredient contents are collected, and the ingredient contents of these samples are different from each other; spectral measurements are performed on these samples, and the absorption value of each sample at different wavelengths is recorded to form a spectral data set; The standard sample data with known component content is combined with the corresponding spectral data to form a data matrix; the rows represent the samples and the columns represent the spectral features, i.e., the absorption values ​​at different wavelengths; The target variable was set as the component content of the sample, including protein content, starch content, fat content, ash content, sugar content, and cellulose content, and the spectral data was used as the independent variable; Select the linear regression model for modeling. The regression model is expressed as: Y=a1X1+a2X2+…+a n X n +b Among them, Y is the target variable, X1, X2, …, X n are the spectral absorption values ​​at different wavelengths, a1, a2, …, a n is the regression coefficient to be obtained; The model is fitted by the least squares method to minimize the square error between the predicted value and the actual value. The minimized objective function is as follows: Among them, Y j is the actual component content of the jth sample, is the component content predicted by the model, and m is the total number of samples; Through linear regression analysis, the regression coefficient a of each wavelength is calculated. i and constant term b, using Python to directly execute this process and return these parameters.

5. The quality monitoring method for preparing rice flour by a semi-dry method according to claim 3, wherein: Number protein, starch, fat, ash, sugar and cellulose as 1, 2, ... 6 respectively, and mark the content of the kth component to be tested as Y k , k∈[1,6], based on the content of the component to be tested, it is compared with the corresponding preset threshold value. When the threshold value is exceeded, the difference between the component content and the preset threshold value is recorded, which is recorded as ΔY k If the content of the ingredient is within the threshold range, it is not included in the calculation. The formula based on the chemical evaluation index CHE of the generated rice flour is as follows: Among them, CHE is the chemical evaluation index of rice noodles, α is a preset proportionality coefficient and α is not zero, and C1 is a constant correction index.

6. The method for monitoring the quality of rice flour prepared by a semi-dry method according to claim 2, wherein: The formula for generating the physical evaluation index PHY of the rice noodles is as follows: Among them, PHY is the physical evaluation index of rice noodles, D exceed is the proportion of rice flour particle sizes that currently exceed the preset threshold, Δρ is the difference between the current rice flour density and the preset threshold, ΔMC is the difference between the current rice flour moisture content and the preset threshold, and a w is the current water activity of rice noodles, m, n, c are the denominator adjustment index, and m, n, c are not zero, C2 is the constant correction index.

7. The quality monitoring method for preparing rice flour by a semi-dry method according to claim 1, characterized in that: The process of combining the chemical evaluation index and the physical evaluation index of the obtained rice noodles to generate the quality evaluation index QS of the rice noodles is specifically as follows: Among them, QS is the quality evaluation index of the current rice noodles, PHY is the physical evaluation index, β is its preset proportionality coefficient, CHE is the chemical evaluation index, γ is its preset proportionality coefficient, and γ>β>0, C3 is a constant correction index.

8. The quality monitoring method for preparing rice flour by a semi-dry method according to claim 1, characterized in that: The process of comparing the rice noodle quality evaluation index QS with the preset evaluation threshold QY specifically includes: When QS < QY, it is determined that the quality of the current rice noodle sample is unqualified, the operator is notified, and the production parameters are adjusted according to the real-time monitoring results; When QS ≥ QY, it is determined that the quality of the current rice noodle sample is qualified, and the preparation process of the rice noodles is continuously monitored; Among them, QS is the quality evaluation index of the current rice noodles, and QY is the rice noodle evaluation threshold.

9. A quality monitoring device for preparing rice noodles by a semi-dry method, characterized in that: The quality monitoring device for preparing rice noodles by the semi-dry method is used to execute the quality monitoring method for preparing rice noodles by the semi-dry method according to any one of claims 1-8, including: A data acquisition module, which is used to use a near-infrared spectroscopy device to collect the spectral data of rice noodles in real time at the key links of preparing rice noodles, and set the sampling frequency to collect data every five minutes. The key links include rice milk preparation, drying and finished product packaging; at the same time of collecting spectral data each time, collect the particle size, density, moisture content and water activity of the rice noodles to form the physical parameters of the rice noodles; A data analysis module, which calculates the content of the components to be measured based on the collected spectral data. The components to be measured include protein content, starch content, fat content, ash content, sugar content and cellulose content. After dimensionless processing of the above-mentioned content of the components to be measured, a chemical evaluation index is generated; the physical parameters of the rice noodles collected at the same time are dimensionless processed to generate a physical evaluation index; An evaluation index generation module, which is used to combine the chemical evaluation index and the physical evaluation index of the obtained rice noodles to generate a rice noodle quality evaluation index; An intelligent decision-making module, which is used to compare the rice noodle quality evaluation index with the preset evaluation threshold. When it exceeds the preset threshold, the operator is notified, and the production parameters are adjusted according to the real-time monitoring results.

Images