Non-contact component estimation system

Abstract

This invention provides a non-contact component estimation system using near-infrared spectroscopy that can estimate various components of grains, such as moisture content, with high accuracy. [Solution] The system comprises an absorption spectrum acquisition device 1 that acquires and outputs the near-infrared absorption spectrum of grains in the manufacturing process over time; a differential processing unit 21 that performs second derivative processing on the spectral data from the absorption spectrum acquisition device 1 and outputs second derivative data; a feature data generation unit 22 that generates feature data from the second derivative data; a machine learning model 4 that takes the feature data as input and outputs grain component data; and a component information notification unit 5 that generates and notifies grain component notification information in the manufacturing process from the grain component data output from the machine learning model and stored over time.

Description

Technical Field

[0004] , , , , , , , ,

[0005] , , ,

[0003] , , , ,

[0001] The present invention relates to a non-contact component estimation system that estimates various components such as moisture contained in grains in a manufacturing process of manufacturing products from grains over time.

Background Art

[0002] Patent Document 1 discloses a non-destructive moisture measurement device that measures the moisture state in a plant body non-destructively by near-infrared spectroscopy. This non-destructive moisture measurement device includes a near-infrared spectroscopy sensor that irradiates a cultivated plant, which is a measurement object, with near-infrared light and non-destructively measures the absorbance (reflectance) of the near-infrared light of this cultivated plant, and a calibration curve showing the correspondence between the moisture content (water content rate) of the cultivated plant and the absorbance. The non-destructive moisture measurement device calculates the moisture content (water content rate) of the living cultivated plant using the absorbance measured by the near-infrared spectroscopy sensor and the data of the calibration curve.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the non-destructive moisture measurement device disclosed in Patent Document 1, it is necessary to create in advance a calibration curve showing the correspondence between the moisture content and the absorbance of the measurement object, and the accuracy of this calibration curve affects the measurement accuracy. Furthermore, when states other than the moisture of the measurement object, for example, the surface state, etc. vary in each manufacturing process, there also arises a problem that the measurement accuracy deteriorates.

[0005] In view of the above circumstances, an object of the present invention is to provide a non-contact moisture estimation system using near-infrared spectroscopy that can estimate various components such as the moisture of grains with high accuracy.

Means for Solving the Problems

[0006] The present invention provides a non-contact component estimation system for successively estimating various components, such as moisture content, contained in grains during a manufacturing process for producing products from grains. The system comprises: an absorption spectrum acquisition device that successively acquires and outputs the near-infrared absorption spectrum of the grains during the manufacturing process; a differential processing unit that performs second-order differential processing on the spectral data from the absorption spectrum acquisition device and outputs second-order differential data; a feature data generation unit that generates feature data from the second-order differential data; a machine learning model that inputs the feature data and outputs component data of the grains; and a component information notification unit that generates and notifies component notification information of the grains during the manufacturing process from the component data of the grains output from the machine learning model and stored successively.

[0007] In this configuration, feature data generated from second derivative data obtained by applying second derivative processing to spectral data from an absorption spectrum acquisition device becomes input data for a machine learning model, and component data of grains (e.g., moisture content data) is generated from the output data of this machine learning model. Since the spectral data output from the absorption spectrum acquisition device shows complex curves, applying second derivative processing makes each feature data obtained over time in the manufacturing process comparable data, i.e., normalized and easily comparable data, and the output data from the machine learning model becomes highly reliable. Furthermore, the component information notification unit generates time-series component notification information of grains in the manufacturing process from the grain component data that is stored over time, so that the manufacturing process of producing products from grains can be appropriately managed based on this component notification information.

[0008] The near-infrared absorption spectrum, which can show various components such as moisture content in grains, exhibits significant intensity fluctuations (repeating extreme values) in various specific wavelength regions. To more accurately represent such characteristics (spectral shape), second derivative data obtained by applying second derivatives to specific wavelength regions is suitable. By using such second derivative data as characteristic data for grain components, the accuracy of component data output from machine learning models is improved. Therefore, in this invention, it is proposed that the differential processing unit obtains the second derivative data by applying second derivatives to the spectral data for each of multiple wavelength regions.

[0009] To estimate the composition of grains in each manufacturing process, an absorption spectrum acquisition device is placed at each manufacturing process; therefore, it is advantageous for the absorption spectrum acquisition device to have a compact configuration. For this reason, in the present invention, the absorption spectrum acquisition device is placed at multiple manufacturing process sites, and the absorption spectrum acquisition device has an infrared light sensor unit consisting of a light irradiation unit that irradiates the grains with infrared light and a light receiving unit that receives reflected light from the grains, and a spectroscopic unit that generates the near-infrared absorption spectrum from the reflected light. In this case, if the infrared light sensor unit and the spectroscopic unit are connected by a branch signal line, the spectroscopic unit can be used in common by multiple infrared light sensor units.

[0010] Examples of manufacturing plants that produce products from grains include rice processing plants that produce cooked rice from rice, sake processing plants that produce sake from rice, soy sauce processing plants that produce soy sauce from soybeans or wheat, and shochu processing plants that produce shochu from sweet potatoes or potatoes. In all of these cases, it is important to understand the grain components in the manufacturing process, that is, the grain components over time, in order to produce good products, and the non-contact component estimation system according to the present invention is suitably applied. Therefore, in the present invention, when the grain is rice, the manufacturing process is a cooked rice processing process or a sake processing process; when the grain is soybeans or soybeans and wheat, the manufacturing process is a soy sauce processing process; and when the grain is sweet potatoes or potatoes, the manufacturing process is a shochu processing process.

[0011] For a manufacturing manager to understand the grain composition over time in the manufacturing process, estimated grain composition data at multiple manufacturing times is necessary. Furthermore, to understand the state of the grain at each manufacturing stage, it is also important to understand the absorbance or water absorption at wavelengths. Therefore, in this invention, it is proposed that the component notification information includes the estimated component data at multiple manufacturing times in the manufacturing process.

[0012] In large-scale manufacturing plants that produce products from grains, the locations where each manufacturing process takes place are often geographically separated. To overcome these geographical problems in the manufacturing process, the present invention proposes that the absorption spectrum acquisition device and the differential processing unit be located at the manufacturing process sites of various manufacturing facilities, while the machine learning model and the component information notification unit are located at service providers that can communicate with each of the manufacturing facilities.

[0013] Other features, functions, and effects of the present invention will be revealed by the following description of the invention with reference to the drawings. [Brief explanation of the drawing]

[0014] [Figure 1] This is a schematic diagram of a non-contact component estimation system. [Figure 2] This is a schematic diagram of an infrared light sensor unit. [Figure 3] This is a schematic spectral diagram showing an example of the near-infrared absorption spectrum of an object being examined. [Figure 4] This graph schematically shows the second derivative data of the near-infrared absorption spectrum. [Figure 5] This is a schematic diagram showing a graph illustrating the change in moisture content during the sake brewing process, which is an example of component information. [Figure 6] This is a schematic diagram illustrating the process of generating training data for building a learning model. [Figure 7]It is a table showing the evaluation results of a learning model learned using combinations of learning data obtained from each of polished rice, sake rice koji rice in a dried state, and sake rice steamed rice. [Figure 8] It is a table showing the evaluation results of a learning model learned using combinations of learning data obtained from each of Koshihikari, sake rice koji rice in a dried state, sake rice steamed rice, and cooked rice. [Figure 9] It is a table showing the evaluation results of a learning model learned using combinations of learning data obtained from each of Koshihikari, sake rice koji rice in a dried state, sake rice steamed rice, and sweet potatoes. [Figure 10] It is a schematic diagram showing a distributed non-contact component estimation system using a data communication network.

Embodiments for Carrying Out the Invention

[0015] In the following embodiments, the non-contact component estimation system according to the present invention is configured as a non-contact moisture estimation system. In a system for estimating various components other than moisture (such as lipids and proteins), in the following description, "moisture" is replaced with "component to be estimated (such as lipids and proteins)". The schematic configuration of this non-contact moisture estimation system will be described using FIG. 1. This non-contact moisture estimation system continuously estimates the moisture contained in the grains in the manufacturing process of manufacturing products from grains. Grains include rice, wheat, soybeans, tubers, etc. The manufacturing processes for manufacturing products from grains include a cooked rice manufacturing process, a sake manufacturing process, a soy sauce manufacturing process, a shochu manufacturing process, a miso manufacturing process, etc. Furthermore, each manufacturing process includes a washing process, a steaming process, a boiling process, a fermentation process, etc.

[0016] The non-contact moisture estimation system is composed of an absorption spectrum acquisition device 1, a data preprocessing unit 2, a learning model unit 4, a moisture information notification unit 5 as a component information notification unit, and a learning model management unit 6.

[0017] The absorption spectrum acquisition device 1, which generates and outputs near-infrared absorption spectra of a material, comprises an infrared light sensor unit 11 and a spectroscopic unit 12. As shown in Figure 2, the infrared light sensor unit 11 has a light irradiation unit 11a that irradiates the material with infrared light (near-infrared light or infrared light including near-infrared light) and a light receiving unit 11b that receives the reflected light that returns after the infrared light irradiated onto the material has been reflected by the material. The spectroscopic unit 12 spectrally analyzes the reflected light sent from the light receiving unit 11b via an optical fiber to generate a near-infrared absorption spectrum of the object being inspected. Figure 3 shows rice as an example of grain, illustrating the near-infrared absorption spectra of rice in different states over time during the sake brewing process (soaked rice, steamed rice, cooled rice). In this near-infrared absorption spectrum, the horizontal axis represents wavelength, and the vertical axis represents absorbance (corresponding to moisture content). In other words, the absorbance or water absorption in wavelength units can be determined from this near-infrared absorption spectrum. In Figure 2, the absorption spectrum acquisition device 1 is shown schematically for illustrative purposes, but it can be configured in various forms depending on its application. For example, when the absorption spectrum acquisition device 1 is incorporated inside a rice cooker or the like, it is used in a form housed in a heat-resistant box. Also, if an infrared light transmission window is formed, a configuration is adopted in which infrared light is passed through the infrared light transmission window to perform infrared light measurements.

[0018] The data preprocessing unit 2 generates feature data from the spectral data obtained from the absorption spectrum acquisition device 1. In this embodiment, the data preprocessing unit 2 is equipped with a feature data generation unit 22 that generates feature data that represents the characteristics of the spectral data. The absorption spectrum represented by the spectral data is a wave curve in a coordinate system where the vertical axis is absorbance and the horizontal axis is wavelength (or wave number), as shown in Figure 3, and the feature data generation unit 22 converts the shape features of such a wave curve into feature data. An effective conversion technique for characterizing the shape of a wave curve is to perform a second derivative on the wave curve. Since the absorption spectrum has extrema in multiple specific frequency bands, feature data is calculated from the second derivative values ​​in multiple specific frequency bands that show extrema. For this reason, the data preprocessing unit 2 is equipped with a differential processing unit 21 that performs a second derivative on the spectral data, and a feature data generation unit 22 that converts the second derivative data from the differential processing unit 21 into feature data. The differential processing unit 21 performs a second derivative on the spectral data for each of multiple predetermined wavelength range units. In the feature data generation from differential data by the feature data generation unit 22, the second derivative values ​​in each specific frequency band may be used directly as feature data, but it is also possible to use vector data as feature data, in which the second derivative values ​​in each specific frequency band and preferably the group of second derivative values ​​over time are also vector elements. Figure 4 shows a schematic graph of second derivative data, which is the result of second derivative processing of the near-infrared absorption spectra of rice in its state over time (soaked rice, steamed rice, cooled rice) as shown in Figure 3. In this graph, the horizontal axis is wavelength and the vertical axis is second derivative absorbance.

[0019] The learning model unit 4 shown in FIG. 1 can be constructed as a linear regression model using partial least squares regression (PLS regression). However, in this embodiment, it is constructed as a non-linear regression model such as a neural network or a random forest model. In any case, the learning model unit 4 includes a machine learning model 40 (hereinafter simply referred to as the learning model 40), and an input data creation unit 41 that creates input data to be input to the learning model 40 from feature data. Further, the learning model unit 4 also includes a moisture content determination unit 42 that determines the moisture content of the test object from the output data as the estimation result output from the learning model 40. The moisture content determination unit 42 uses, as input data, the feature data of the spectral data obtained from measurements in each manufacturing process for the test object and time-dependent measurements performed in a specific manufacturing process (for example, measurements for the steamed rice continuously discharged in the steamed rice process, or measurements for each unit steaming time in the steamed rice process). It is also possible to determine the time-dependent moisture content of the test object in each manufacturing process from the output time-dependent output data and output the moisture content in the form of time-series data.

[0020] The moisture content output from the moisture content determination unit 42 is converted into notification data by the moisture information notification unit 5 and transmitted as moisture information to the required department, for example, a computer installed at the manufacturing site (an example of the on-site management computer ********), or a mobile terminal (an example of the on-site management computer ********) carried by the manufacturing manager at the manufacturing site. In order for the manufacturing manager to grasp the time-dependent grain moisture content in the manufacturing process, moisture data as component data estimated at a plurality of manufacturing times in the manufacturing process is required. Therefore, the manufacturing time is given as attribute information together with the data related to the manufacturing process in the moisture data. FIG. 5 shows an example of the moisture information. The moisture information exemplified here is a graph showing the moisture content (moisture rate) estimated using the near-infrared absorption spectrum in each process of sake manufacturing consisting of brown rice, polished rice, immersion, steamed rice, aging, koji making, and fermentation.

[0021] The learning model unit 4, particularly the learning model 40, is substantially composed of a computer program. By installing the trained learning model data, which is a computer program, into the computer, or by providing various coefficients to the learning model program, the computer functions as the learning model 40, and consequently as the learning model unit 4. Of course, at least a part of the learning model unit 4 may be constructed from hardware. The management of such a learning model unit 4, particularly the learning model 40, is performed by the learning model management unit 6.

[0022] In this embodiment, the learning model management unit 6 generates a learning model 40 by performing supervised machine learning on mixed feature data, which is a mixture of feature data containing at least two or more types of grains (such as rice, wheat, and potatoes) with different absorption spectral characteristics, their varieties, and feature data in various states thereof.

[0023] The specific method for generating the learning model 40 by the learning model management unit 6 will be explained below using Figure 6. In this embodiment, the learning model 40 outputs moisture data from feature data generated based on the near-infrared absorption spectrum of a specific grain (tested material: for example, rice). The learning data used to construct this learning model 40 is mixed feature data that includes feature data obtained from the substance to be estimated (specific grain) and feature data obtained from grains other than the specific grain or by-grains that are in a state other than the specific state of the specific grain.

[0024] Figure 6 schematically shows the process of generating mixed training data for constructing the learning model 40. Here, as mixed training data, in addition to feature data obtained by performing second-order differential processing on spectral data, which is the near-infrared absorption spectrum for rice used as a specific grain (referred to here as principal feature data to distinguish it from other feature data), feature data obtained by performing differential processing on spectral data, which is the near-infrared absorption spectrum for dried sake rice koji rice (first secondary grain), which is a rice state other than rice used as a grain (first secondary feature data), and feature data obtained by performing differential processing on spectral data, which is the near-infrared absorption spectrum for steamed sake rice (second secondary grain), are used (second secondary feature data). Of course, third secondary feature data, fourth secondary feature data, ... may also be used.

[0025] The training data creation unit 61 creates primary training data from primary feature data, primary secondary training data from primary secondary feature data, and secondary secondary training data from secondary secondary feature data. The total number of training data points can be around one thousand. Although not shown in the diagram, this machine learning is supervised machine learning, so the measured water content of each substance from which the feature data was obtained is added to the training data as training data.

[0026] The learning model 40a is trained using mixed learning data, which contains a mixture of primary learning data, first secondary learning data, and second secondary feature data. Once training is complete, the learning model management unit 6 outputs the trained learning model data and provides it to the learning model 40 of the learning model unit 4 (see Figure 1).

[0027] Figure 7 shows the model evaluation of moisture estimation in a learning model 40 trained using only training data obtained from rice (Koshihikari), a learning model 40 trained using only training data obtained from sake rice koji rice, a learning model 40 trained using only training data obtained from sake rice steamed rice, and a learning model 40 trained using mixed training data in which the above training data are mixed as primary training data, first secondary training data, and second secondary training data. This model evaluation is expressed as the mean absolute error (MAE). In the example in Figure 7, the number of data points used is the number of actual data points and the number of data points obtained by copying the actual data and amplifying it to more than 1000, with the number of actual data points indicated in parentheses. The model evaluation for each number of data points is also shown, with the model evaluation for the number of actual data points indicated in parentheses. What can be understood from Figure 7 is that the model evaluation with the number of copied and amplified data points is the same as or slightly better than the model evaluation with the number of actual data points. Furthermore, the learning model 40 trained using mixed learning data, which includes learning data for sake rice koji rice and sake rice steamed rice mixed with the learning data for rice cooked for drinking, yielded better or nearly the same model evaluation as the learning model 40 trained using only single-type learning data of rice cooked for drinking, which is the grain targeted for moisture estimation.

[0028] Figure 8 shows the model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from rice (Koshihikari), the model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from sake rice koji rice, the model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from sake rice steamed rice, the model evaluation of each moisture estimation in the learning model 40 trained using integrated mixed training data which combines training data obtained from rice, sake rice koji rice, and sake rice steamed rice, the model evaluation of moisture estimation in the learning model 40 trained using only training data obtained from cooked rice, and the model evaluation of moisture estimation in the learning model 40 trained using integrated mixed training data which adds training data obtained from cooked rice instead of rice training data. Here again, the model evaluation is the mean absolute error (MAE). The model evaluation of moisture estimation in the learning model 40 trained using only single-type training data is shown in parentheses. Figure 8 shows that the model evaluation of the learning model 40 trained using integrated mixed learning data, which includes learning data obtained from cooked rice instead of learning data from raw rice, is superior to the model evaluation of the other learning models 40.

[0029] Figure 9 shows the evaluation results of the learning model 40, which was trained using combinations of training data obtained from table rice (Koshihikari), sake rice koji, sake rice steamed rice, and sweet potato. The model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from table rice (Koshihikari), the model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from sake rice koji, the model evaluation of moisture estimation in the learning model 40 trained using only single-type training data obtained from sake rice steamed rice, and the model evaluation of moisture estimation in the learning model 40 trained using integrated mixed training data that combines training data obtained from table rice, sake rice koji, and sake rice steamed rice are the same as in Figure 8. The model evaluation of moisture estimation for sweet potato in the learning model 40 trained using only training data obtained from sweet potato is not good. However, in the integrated mixed training data, the model evaluation of sweet potato moisture estimation in the training model 40 trained using integrated mixed training data, which includes training data obtained from sweet potatoes instead of training data obtained from sake rice koji rice, is improved compared to the model evaluation of the training model 40 trained using only training data obtained from sweet potatoes.

[0030] Furthermore, one of the following grains—rice for eating, rice for sake, sweet potato, soybean, or wheat—is selected as the grain for moisture estimation, at least one of the other grains is selected as the reference grain, and a substance other than a grain (such as clay) may also be selected as the reference substance. In this case, the mixed feature data includes feature data obtained from the grain for moisture estimation (primary feature data), feature data obtained from the reference grain (first secondary feature data), and feature data obtained from the substance other than a grain (such as clay) (second secondary feature data).

[0031] Next, we will describe some specific embodiments. (Generation of general-purpose learning models) For rice with varying moisture content, the second derivative data (relationship between wavelength and second derivative absorbance) of the near-infrared absorption spectrum (showing the relationship between wavelength and absorbance) is obtained. Feature data generated from each second derivative data set is used to create training data, and this training data is used to generate a general-purpose learning model for moisture estimation.

[0032] (Application to the sake brewing process) A general-purpose learning model is further trained using training data created from feature data generated from the second derivative data (relationship between wavelength and second derivative absorbance) of near-infrared absorption spectra (showing the relationship between wavelength and absorbance) in the raw rice processing process, which consists of milling, soaking, steaming, aging, koji making, and fermentation, thereby generating a learning model for sake brewing. The generated learning model for sake brewing can estimate the moisture content based on the near-infrared absorption spectra from absorption spectrum acquisition devices 1 placed at each process.

[0033] (Application to the rice manufacturing process) A general-purpose learning model is further trained using training data created from feature data generated from the second derivative data (relationship between wavelength and second derivative absorbance) of near-infrared absorption spectra (showing the relationship between wavelength and absorbance) in the rice manufacturing process, which consists of milling, soaking, steaming (cooking), and molding, thereby generating a learning model for rice manufacturing.

[0034] (Application to the soy sauce manufacturing process) A general-purpose learning model is further trained using training data created from feature data generated from the second derivative data (relationship between wavelength and second derivative absorbance) of near-infrared absorption spectra (showing the relationship between wavelength and absorbance) in the soy sauce manufacturing process, which consists of processes such as milling, soaking, steaming, roasting, koji making, and fermentation, using soybeans alone or soybeans and wheat as raw materials, to generate a learning model for soy sauce manufacturing.

[0035] (Application to the shochu manufacturing process) A general-purpose learning model is further trained using feature data generated from the second derivative data (relationship between wavelength and second derivative absorbance) of the near-infrared absorption spectrum (showing the relationship between wavelength and absorbance) at each stage of the shochu manufacturing process, which consists of steaming, drying, and roasting, using sweet potatoes, potatoes, or rice as raw materials. This training data is then used to generate a learning model for shochu manufacturing.

[0036] As described above, when estimating the water content of a new substance, it is possible to estimate the water content of the new substance by further training a general-purpose learning model using training data created from the characteristic data of the new substance. Since this only involves further training of a general-purpose learning model, it has the advantage of requiring less training data compared to generating training model data for estimating the water content of a new substance from scratch. Furthermore, if a general-purpose learning model is not available, the learning model 40a can be trained using training data created from the characteristic data of multiple substances, and even in this case, satisfactory training model data can be generated with a small amount of training data.

[0037] Next, a distributed non-contact moisture estimation system will be explained using Figure 10. In this non-contact moisture estimation system, multiple manufacturing sites or processes, a first service provider SP1, and a second service provider SP2 are interconnected by data communication lines such as the Internet, public data communication lines, or private data communication lines. Each manufacturing site or process is equipped with a site management computer 7, an absorption spectrum acquisition device 1, and a data preprocessing unit 2. The first service provider SP1 is equipped with a learning model unit 4 and a moisture information notification unit 5. The second service provider SP2 is equipped with a learning model management unit 6. In this distributed non-contact moisture estimation system, the learning model management unit 6 of the second service provider SP2 generates trained learning model data for the learning model 40 based on the feature data (first feature data, second feature data, third feature data, ...) sent from each manufacturing site or process and their respective training data (actually measured moisture content). The learning model 40 used in practice is provided in the learning model unit 4 of the first service provider SP1 and is constructed based on the trained learning model data sent from the learning model management unit 6. The learning model unit 4 constructed in the first service provider SP1 estimates the moisture content of the grain to be estimated based on the feature data (first feature data, second feature data, third feature data, ...) sent from each manufacturing site or each manufacturing process.

[0038] [Another embodiment] (1) In the embodiments described above, it was assumed that the same learning model 40 would be used for various test objects, but different learning models 40 may be used depending on the test object. For example, depending on the test object, an appropriate one can be selected from linear regression, decision trees, random forests, neural networks, support vector machines, etc. In this case, appropriate training data will be created from the same feature data.

[0039] (2) In the embodiment described above, the data preprocessing unit 2, the learning model unit 4, the moisture information notification unit 5, and the learning model management unit 6 were each constructed as separate units (computers). However, in small-scale manufacturing facilities, all of these may be constructed as a single computer. In this case, the reception of spectral data from the absorption spectrum acquisition device 1 may be done online or by batch processing using a memory device.

[0040] (3) In the embodiments described above, the non-contact component estimation system was configured as a non-contact moisture estimation system. However, it can be configured as a non-contact component estimation system that measures lipids, proteins, and various other components that have absorption in the near-infrared region, and in that case, the components and measurement methods described in the embodiments described above can be applied.

[0041] Furthermore, the configurations disclosed in the above embodiments (including other embodiments, the same applies hereinafter) can be applied in combination with configurations disclosed in other embodiments, as long as no inconsistencies arise. Moreover, the embodiments disclosed herein are illustrative, and the embodiments of the present invention are not limited thereto, and can be modified as appropriate without departing from the object of the present invention. [Industrial applicability]

[0042] This invention applies to a non-contact moisture estimation system that estimates various components, such as moisture content, contained in grains during the manufacturing process of producing products from grains, using near-infrared absorption spectroscopy. [Explanation of symbols]

[0043] 1: Absorption spectrum acquisition device 2: Data preprocessing unit 4: Learning Model Unit 5: Moisture Information Notification Unit (Component Information Notification Unit) 6: Learning Model Management Department 7: Site Management Computer 11: Infrared light sensor unit 11a: Light irradiation part 11b: Light receiving part 12: Spectroscopic Unit 21: Differential Calculus Section 22: Feature Data Generation Unit 40: Learning Model (Machine Learning Model) 40a: Learning model for training 41: Input Data Creation Section 42: Moisture content determination unit 61: Training Data Creation Department SP1: First Service Provider SP2: Second Service Provider

Claims

1. A non-contact component estimation system for successively estimating various components, such as moisture content, contained in grains during a manufacturing process for producing products from grains, An absorption spectrum acquisition device that acquires and outputs the near-infrared absorption spectrum of the grain in the manufacturing process over time, A differential processing unit that performs second derivative processing on spectral data from the absorption spectrum acquisition device and outputs second derivative data, A feature data generation unit that generates feature data from the aforementioned second derivative data, A machine learning model that takes the aforementioned feature data as input and outputs the aforementioned grain component data, A component information notification unit generates and notifies component notification information for the grain in the manufacturing process from the component data of the grain output from the machine learning model and stored over time, A non-contact component estimation system equipped with the following features.

2. The non-contact component estimation system according to claim 1, wherein the differential processing unit performs a second derivative on the spectral data for each of the multiple wavelength regions to obtain the second derivative data.

3. The absorption spectrum acquisition device is placed at multiple locations in the manufacturing process. The non-contact component estimation system according to claim 1, wherein the absorption spectrum acquisition device comprises an infrared light sensor unit consisting of a light irradiation unit that irradiates the grain with infrared light and a light receiving unit that receives reflected light from the grain, and a spectroscopic unit that generates the near-infrared absorption spectrum from the reflected light.

4. The non-contact component estimation system according to claim 1, wherein if the grain is rice, the manufacturing process is a rice cooking process or a sake brewing process; if the grain is soybeans or soybeans and wheat, the manufacturing process is a soy sauce brewing process; and if the grain is sweet potatoes or potatoes, the manufacturing process is a shochu brewing process.

5. The non-contact component estimation system according to claim 1, wherein the component notification information includes the component data estimated at multiple manufacturing times in the manufacturing process.

6. The non-contact component estimation system according to any one of claims 1 to 5, wherein the absorption spectrum acquisition device and the differential processing unit are located at the manufacturing process sites of various manufacturing facilities, and the machine learning model and the component information notification unit are located at a service provider capable of data communication with each of the manufacturing facilities.

Images