An intelligent, automated red pepper powder production system that combines ai quality analysis and esg factors

Abstract

An intelligent chili powder production automation system combining AI quality analysis and ESG elements according to an embodiment may include: an AI quality analysis module for analyzing the quality of chili raw materials; an intelligent drying control module that automatically controls drying conditions according to climate and environmental conditions; an integrated foreign substance removal module that removes foreign substances including insects, soil, metal fragments, and plastics in multiple ways; a blockchain-based history management module that records and tracks production history from raw material receipt to finished product shipment in a blockchain database; an ESG integrated management module that collects, analyzes, and visualizes ESG indicators in terms of energy, social responsibility, and governance in real time; and a process feedback control module that collects and integrally evaluates multiple production status information including at least one of AI quality analysis results, drying efficiency indicators, foreign substance removal rates, carbon emissions, and history data integrity status, and corrects overall process parameters according to the evaluation results.

Description

Technology Field

[0001] The present disclosure relates to the field of agricultural product processing machinery technology, and specifically, to an intelligent chili powder production automation system capable of automating the entire chili powder production process and intelligently managing quality by combining AI-based image recognition technology, IoT (Internet of Things)-based smart factory technology, blockchain-based traceability technology, and ESG (Environmental, Social, Governance) element integrated management technology. Background Technology

[0002] Unless otherwise indicated in this specification, the contents described in this section are not prior art for the claims of this application, and are not to be recognized as prior art simply because they are included in this section.

[0003] In the agricultural processing industry, particularly in the field of spices such as chili powder, many processes still rely on manual labor. This traditional production method faces challenges, such as difficulty in maintaining quality consistency and variations in product quality depending on the skill level of the workers. In particular, since the ripeness, damage status, and size of chili peppers rely on visual inspection, it is difficult to ensure quality standardization during mass production.

[0004] In addition, drying processes traditionally often utilize high-temperature blowers or fossil fuel-based heat sources, leading to problems such as excessive energy consumption and high carbon emissions. This energy waste not only increases production costs but also has a negative impact on ESG (Environmental, Social, Governance) aspects.

[0005] Furthermore, it is difficult to completely remove various types of foreign substances, such as insects, dirt, plastic, and metal fragments, using only existing mechanical sorting devices. This can cause food safety issues and lead to a decline in product credibility and a risk of recall.

[0006] Production history management is also one of the major issues. Existing systems often rely on manual recording of raw material receipt, processing, packaging, and shipment histories, or manual input into separate management systems, posing risks of forgery and traceability. In particular, while demands for food traceability are intensifying for chili powder intended for export, the technological infrastructure to meet these requirements is lacking.

[0007] Furthermore, due to the aging rural population, there are many cases where difficulties arise in handling complex machine control or quality management systems. There are limitations to improving production efficiency due to a lack of user-friendly interfaces and automation technology.

[0008] Therefore, there is an urgent need to introduce a quality control system capable of automatically determining the ripeness, damage level, and size of chili peppers in real time and automatically sorting them by quality using AI video analysis technology; smart drying technology that enables energy-saving production through intelligent drying control considering climate conditions; an integrated removal system that maximizes the foreign substance removal rate by combining multi-detection and removal technologies; a transparent production and distribution tracking system through a blockchain-based traceability module; and an integrated management platform that incorporates ESG elements. Prior art literature

[0009] 1. Korean Patent Publication No. 10-2004-0077433 (September 4, 2004) 2. Korean Patent Publication No. 10-2023-0121882 (August 21, 2023) The problem to be solved

[0010] The embodiments disclosed in this disclosure aim to provide an intelligent production automation system that overcomes the limitations of existing technology and automates the entire process of chili powder production, thereby simultaneously achieving quality standardization, ensuring food safety, maximizing energy efficiency, supporting ESG management, and transparency of production history.

[0011] In addition, the embodiments disclosed in this disclosure aim to ensure the standardization and uniformity of quality by determining the ripeness, damage, size, etc. of chili peppers in real time and automatically sorting them through an AI image recognition and deep learning-based quality analysis module.

[0012] In addition, the embodiments disclosed in this disclosure aim to reduce energy consumption, lower production costs, and achieve carbon reduction effects in terms of ESG (Environmental) by combining an AI-controlled intelligent drying system with solar heat collection and heat recovery technology.

[0013] In addition, the embodiments disclosed in this disclosure maximize food safety by securing a removal rate of over 99% through a multi-removal system that integrates AI vision inspection, magnetic separation, and pneumatic separation technologies.

[0014] In addition, the embodiments disclosed in this disclosure prevent tampering and enhance the reliability of consumers and business partners by transparently recording and sharing the entire process through a history management module that combines RFID, IoT sensors, and a blockchain DB.

[0015] Furthermore, the embodiments disclosed in this disclosure include an intuitive user interface (UI), automatic control functions, a HACCP compliance system, safety devices, etc., to enable easy access and operation by users, thereby providing a smart production environment that can be efficiently utilized even by elderly farmers.

[0016] In addition, the embodiments disclosed in this disclosure support ESG management and strengthen corporate sustainability through functions such as solar energy utilization, dust recycling, carbon emission monitoring, real-time quality data disclosure, and automatic quality assurance certificate issuance.

[0017] Furthermore, the embodiments disclosed in this disclosure aim to integrate AI, IoT, blockchain, and ESG technologies to automate the entire process of chili powder production and to innovatively overcome the limitations of existing technologies in all areas of quality, safety, efficiency, transparency, and sustainability.

[0018] Meanwhile, the technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0019] An intelligent chili powder production automation system combining AI quality analysis and ESG elements according to the present disclosure for achieving the aforementioned technical challenges may include: an AI quality analysis module for analyzing the quality of chili raw materials; an intelligent drying control module that automatically controls drying conditions according to climate and environmental conditions; an integrated foreign substance removal module that removes foreign substances including insects, soil, metal fragments, and plastics in multiple ways; a blockchain-based history management module that records and tracks production history from raw material receipt to finished product shipment in a blockchain database; an ESG integrated management module that collects, analyzes, and visualizes ESG indicators in terms of energy, social responsibility, and governance in real time; and a process feedback control module that collects and integrally evaluates a plurality of production status information including at least one of AI quality analysis results, drying efficiency indicators, foreign substance removal rates, carbon emissions, and history data integrity status, and corrects overall process parameters according to the evaluation results.

[0020] In addition, the AI ​​quality analysis module takes raw material images acquired through a high-resolution camera as input and simultaneously extracts information on maturity, damage, color, size, and surface defects using a deep learning-based multi-characteristic analysis network, automatically calculates a quality grade based on the extracted information, and can automatically sort raw materials classified by grade by transporting them along different paths.

[0021] In addition, the intelligent drying control module can automatically set a drying curve using an AI controller based on data collected from a temperature and humidity sensor, an ambient environment sensor, and a solar sensor, improve the energy efficiency of the drying process through a composite heat source control device including at least one of a solar collector, a heat pump, and a heat recovery heat exchanger, and control the drying process to automatically terminate when the moisture content of the raw material is measured in real time and reaches a target moisture level.

[0022] In addition, it may further include a self-learning foreign substance management algorithm that first determines the presence of foreign substances through the integrated foreign substance removal module AI vision inspection device, secondarily removes heterogeneous materials such as metal fragments, plastics, and mold through a magnetic separator and an air pressure separator, and automatically corrects the removal algorithm in the future by utilizing information on the type, frequency, and removal efficiency of the detected foreign substances as training data.

[0023] In addition, the blockchain-based traceability module generates unique identification information for each raw material unit through RFID tags, collects historical data generated throughout the entire process including the time of receipt, washing history, drying temperature and time, quality grade, and packaging date from IoT sensors, records it in a blockchain database, and provides the registered historical data in the form of an API (Application Programming Interface) that can be linked with external systems to perform verification in distribution, inspection, and certification procedures.

[0024] In addition, the above-mentioned ESG integrated management module collects and analyzes environmental (E) indicators such as energy consumption, carbon emissions, waste heat recovery rate, and dust recycling rate; social (S) indicators such as HACCP compliance status, worker safety records, and user interface accessibility; and governance (G) indicators such as data disclosure levels and automatic issuance of quality assurance certificates in real time, visualizes them on an ESG performance dashboard, and can output the analysis results in the form of an automatic report by linking with external ESG certification bodies.

[0025] In addition, the process feedback control module comprises a comprehensive quality index S including at least two of the quality analysis result (Q), foreign substance removal rate (M), energy consumption (E), carbon emissions (C), and historical data integrity index (I).

[0026] mathematical formula

[0027] It is calculated as follows, where α, β, γ, δ, and are weights in the above mathematical formula, and if the calculated S value is lower than the set quality standard, at least one of the AI ​​quality analysis algorithm, drying control parameter, foreign substance removal intensity, and blockchain recording cycle can be adjusted to improve the indicator. Effects of the invention

[0028] According to the means for solving the aforementioned problem of the present disclosure, an intelligent chili powder production automation system combining AI quality analysis and ESG elements innovatively improves the existing manual-centered and inefficient production method, thereby providing the following technical and industrial effects in various aspects such as quality, safety, efficiency, transparency, and sustainability.

[0029] In addition, according to the aforementioned means for solving the problem of the present disclosure, the degree of ripeness, damage, size, etc. of chili peppers are automatically determined and sorted through AI-based image recognition and deep learning analysis, thereby maintaining consistent quality standards regardless of worker skill level or environmental changes. Through this, the uniformity of product quality is improved to over 95%, thereby significantly strengthening consumer trust and market competitiveness.

[0030] In addition, according to the aforementioned means for solving the problem of the present disclosure, drying energy consumption can be reduced by more than 40% through the combination of intelligent drying control considering climate conditions and solar thermal and heat recovery technologies. This leads to a reduction in carbon emissions and energy costs, and realizes sustainable corporate management in terms of ESG (Environmental).

[0031] In addition, according to the aforementioned means for solving the problem of the present disclosure, by integrating multiple foreign substance removal methods such as AI vision inspection, magnetic separation, and pneumatic separation to secure a removal efficiency of 99% or more, consumer health and food safety are guaranteed.

[0032] Furthermore, according to the aforementioned means for solving the problem of the present disclosure, the automatic HACCP compliance function and quality control automation simultaneously enhance responsiveness to food hygiene regulations and export competitiveness.

[0033] In addition, according to the aforementioned means for solving the problem of the present disclosure, transparency of the distribution process is secured by utilizing RFID, IoT sensors, and blockchain technology to record and share the entire process history from raw material receipt to shipment in an untamper-proof form.

[0034] Furthermore, according to the aforementioned means for solving the problem of the present disclosure, production history information can be disclosed and verified in real time, thereby maximizing the trust of consumers, business partners, and supervisory authorities.

[0035] In addition, according to the aforementioned means for solving the problem of the present disclosure, by automating manual processes, the dependence on manpower is reduced by more than 70%, and production efficiency is dramatically improved. In particular, even elderly agricultural workers can easily operate the system through an intuitive user interface, thereby solving the labor problem in rural areas and ensuring production sustainability.

[0036] Furthermore, according to the aforementioned means for solving the problem of the present disclosure, an eco-friendly production system is implemented through solar energy utilization, energy saving, dust recycling, and carbon monitoring functions. In addition, social responsibility is fulfilled through HACCP compliance, user-friendly UI, safety devices, etc. Moreover, a transparent management system is secured through real-time data disclosure and automatic issuance of quality assurance certificates.

[0037] These factors have the effect of raising a company's ESG rating and increasing corporate value and brand credibility in the long term.

[0038] Furthermore, according to the aforementioned means for solving the problem disclosed herein, the added value of products can be increased and competitiveness secured in domestic and international markets through quality improvement, energy conservation, ensuring traceability transparency, and ESG responsiveness. This contributes not only to increasing the income of farm households but also to the advancement of the local agricultural processing industry and the expansion of the export base.

[0039] In addition, according to the aforementioned means for solving the problem of the present disclosure, by transforming the paradigm of the agricultural product processing industry, a next-generation smart production system that simultaneously satisfies high quality, low cost, eco-friendliness, high reliability, and sustainability is realized, and the effect of dramatically improving industrial competitiveness in the food processing sector is provided.

[0040] The effects obtainable from the exemplary embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by those skilled in the art to which the exemplary embodiments of the present disclosure belong from the description below. That is, unintended effects resulting from the implementation of the exemplary embodiments of the present disclosure can also be derived by those skilled in the art from the exemplary embodiments of the present disclosure. Brief explanation of the drawing

[0041] FIG. 1 is a drawing showing an intelligent chili powder production automation system combining AI quality analysis and ESG elements according to an embodiment. FIG. 2 is a drawing showing a transaction structure according to an embodiment. FIG. 3 is a drawing illustrating an intelligent chili powder production automation process combining AI quality analysis and ESG elements according to an embodiment. Specific details for implementing the invention

[0042] Hereinafter, various embodiments of the present disclosure are described in conjunction with the accompanying drawings. As various embodiments of the present disclosure may be subject to various modifications and may have various forms, specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the various embodiments of the present disclosure to specific forms, and it should be understood that they include all modifications and / or equivalents and substitutions that fall within the spirit and scope of the various embodiments of the present disclosure. In relation to the description of the drawings, similar reference numerals have been used for similar components.

[0043] In various embodiments of the present disclosure, terms such as “comprising” or “having” are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0044] In various embodiments of the present disclosure, expressions such as “or” include any and all combinations of the words listed together. For example, “A or B” may include A, may include B, or may include both A and B.

[0045] Expressions such as "first," "second," "first," or "second" used in various embodiments of the present disclosure may modify various components of the various embodiments, but do not limit such components. For example, such expressions do not limit the order and / or importance of such components and may be used to distinguish one component from another.

[0046] When it is mentioned that a component is "connected" or "joined" to another component, it should be understood that the component may be directly connected or joined to the other component, but that a new component may also exist between the component and the other component.

[0047] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or in a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0048] Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in the various embodiments of the present disclosure.

[0049] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0050] FIG. 1 is a diagram showing an intelligent chili powder production automation system that combines AI quality analysis and ESG elements according to an embodiment.

[0051] Referring to FIG. 1, an intelligent chili powder production automation system combining AI quality analysis and ESG elements according to an embodiment may be configured to include an AI quality analysis module (100), an intelligent drying control module (200), an integrated foreign substance removal module (300), a blockchain-based history management module (400), an ESG integrated management module (500), and a process feedback control module (600).

[0052] The AI ​​quality analysis module (100) analyzes the quality of the chili raw material. The AI ​​quality analysis module (100) is a core component for automatically analyzing the quality of the chili raw material and is an intelligent analysis system designed to overcome the quality deviation and efficiency limitations of existing visual inspection or simple mechanical sorting methods. The AI ​​quality analysis module (100) is composed of a high-resolution image acquisition unit, a preprocessing unit, an AI-based quality determination unit, a quality grade classification unit, and a control interface unit, and these components are organically linked to evaluate the condition of the chili raw material in real time and perform automatic classification. The AI ​​quality analysis module (100) photographs the chili raw material being transported through the production line from multiple angles using a high-resolution camera and simultaneously collects RGB and near-infrared (NIR) spectrum image data. In the embodiment, the RGB image is used to secure visual characteristics such as surface color, shape, and damage, while the NIR image complementarily provides intrinsic quality information such as moisture content, ripeness, and tissue density. The acquired raw material images are transmitted sequentially through an image buffer, and a preprocessing step is subsequently performed. In the embodiment, the preprocessing unit performs tasks such as noise removal, brightness and contrast correction, and background removal to normalize the image into a state suitable for AI analysis. The normalized image data calculates quality-related parameters, including a maturity index, a damage index, a size index, and a defect index, through a feature extraction engine. In the embodiment, the maturity index (R) is calculated through color spectrum distribution and color histogram analysis, and the damage index (D) is quantified by detecting surface texture non-uniformity, scratches, and mold traces. The size index (S) is an index obtained by analyzing object boundaries within the image to measure length, width, and volume. The defect index (F) is an index that determines quality abnormalities by detecting abnormal shapes or the attachment of foreign substances. In the embodiment, these indices are converted into vector-type quality characteristic data (QV) and provided to the AI ​​quality determination unit.

[0053] In the embodiment, the quality discrimination unit analyzes input quality characteristic data (QV) using a pre-trained deep learning model (e.g., a CNN-based multi-class quality discrimination network). This model is trained based on a large amount of quality labeling datasets to comprehensively determine the ripening stage, damage status, and size grade. In the embodiment, a probability-based quality score (Qscore) is calculated for each quality characteristic and is reflected in the determination of the overall quality grade.

[0054] The quality score can be calculated as follows:

[0055] Mathematical formula 1

[0056]

[0057] In mathematical formula 1, R is the maturity index, D is the damage index, S is the size index, and F is the defect index. α, β, γ, and δ are weights representing the quality influence. The quality score values ​​calculated in the examples are compared with predefined reference values ​​and classified into grades such as, for example, A (superior grade), B (goods), C (for processing).

[0058] Subsequently, the quality grading unit controls each raw material using automatic transfer and sorting devices based on AI analysis results, ensuring it is transported to the appropriate line for each grade. For instance, Grade A peppers are automatically branched to the packaging line, Grade B peppers to the additional drying line, and Grade C peppers to the pre-grinding line. Additionally, raw materials identified as being in an abnormal condition (such as mold growth or foreign matter attachment) are automatically discharged into a separate inspection tray, thereby preventing the mixing of defective products in advance.

[0059] In addition, in the embodiment, the AI ​​quality analysis module (100) can perform self-learning to periodically retrain the quality judgment model through the continuous accumulation of quality data and user feedback. In the embodiment, the accuracy of quality determination is continuously improved by reflecting seasonal crop conditions, differences in characteristics by variety, and changes in processing conditions during the self-learning process. Through this, quality consistency of 95% or higher can be maintained, and automation of the entire production process can be performed more precisely. According to the AI ​​quality analysis module (100) configured as above, it is possible to secure a quality judgment accuracy of 95% or higher compared to conventional visual sorting, improve production efficiency by performing the classification of raw materials by grade and automatic transfer processes in real time, and significantly enhance food safety by preventing the ingress of foreign substances and defective products in advance. Furthermore, the AI ​​quality analysis module (100) enables the quality analysis data to be linked with other processes (drying control, foreign substance removal, ESG management, etc.) so that it can also be utilized for overall process optimization.

[0060] In addition, in the embodiment, the intelligent drying control module (200) controls drying conditions according to climate and environmental conditions. The intelligent drying control module (200) is a component for automating the drying process, which is a key step in the red pepper powder production process, and for improving quality and maximizing energy efficiency by maintaining an optimal drying state by reflecting external climate and internal environmental conditions in real time. The intelligent drying control module (200) includes an environmental sensor unit, a data collection and analysis unit, an AI-based drying control unit, a heat source management unit, and a drying state feedback control unit, and these components interact with each other to intelligently control the entire drying process.

[0061] In the embodiment, the intelligent drying control module (200) includes a plurality of sensors to collect climate information inside and outside the drying chamber in real time. For example, a temperature and humidity sensor measures the temperature (T) and relative humidity (H) inside and outside the drying chamber, and a pressure and wind speed sensor detects external conditions to obtain airflow information that affects the drying process. In addition, a solar sensor determines the feasibility of utilizing natural heat sources and is linked with a solar thermal collector system. The collected data in the embodiment undergoes a preprocessing process and is transmitted to a data collection and analysis unit, and initial drying conditions (target temperature, target humidity, drying time, etc.) are set.

[0062] Subsequently, the data collection and analysis unit generates an optimal drying curve (D(t)) using an AI control algorithm (e.g., an LSTM-based time series prediction model or a reinforcement learning-based control policy) with real-time environmental conditions and historical production data as input values. This curve defines control variables (Target Parameters) such as drying temperature, relative humidity, and wind speed over time, and can be calculated through a multivariate optimization problem such as the following mathematical equation.

[0063] Mathematical formula 2

[0064]

[0065] Here, Pheat(t) is the instantaneous power consumption of the heater or heat pump, Pfan(t) is the power consumption of the blower, ηsolar(t) is the energy saved by solar heat collection, and tf is the drying end time.

[0066] In the example, the drying temperature T(t) and humidity H(t), which change over time, are set as control variables through Equation 2, and the total energy consumption Etotal can be minimized by adjusting them. The aforementioned optimization process is carried out by simultaneously considering quality requirements (target moisture content, color retention rate, etc.) and energy efficiency.

[0067] In addition, the intelligent drying control module (200) is an AI-based drying control unit that dynamically controls various heat source devices according to the generated drying curve (D(t)). For example, the solar heat supply can be automatically adjusted by detecting external solar radiation through solar collector control. In addition, through heat pump control, it can be operated as an auxiliary heat source when the external temperature is low or natural heat sources are insufficient. Furthermore, the thermal energy of the hot air discharged during the drying process can be recovered and recycled through a heat recovery device. In particular, the heat recovery device is utilized to gradually lower the internal temperature of the chamber at the end of the drying stage, thereby enabling a state close to natural cooling without deterioration of the raw material quality.

[0068] In the embodiment, during the drying process, the intelligent drying control module (200) continuously monitors quality-related indicators such as the real-time moisture content (W), drying speed (V), and surface color change (C) of the raw material. In the embodiment, the moisture sensor continuously measures changes in the internal moisture content of the chili raw material, and the image sensor analyzes changes in surface color and drying uniformity to quantify changes in quality. The measured information is input back into the AI ​​controller to dynamically adjust the drying curve (D(t)). For example, if the target moisture content is reached early, the energy supply is immediately cut off, and if the drying speed is slow, the airflow intensity is automatically increased.

[0069] In addition, in the embodiment, the intelligent drying control module (200) can perform self-learning to automatically improve drying strategies based on past production history and seasonal and regional climate data. For example, the control policy is adjusted to actively utilize high-temperature external conditions during the summer and to prioritize the use of a heat pump during the winter. Through this, annual energy consumption can be reduced by more than 40%, and drying time can be shortened without quality degradation. Furthermore, in the embodiment, the intelligent drying control module (200) automatically adjusts drying conditions in real time according to external climate conditions to prevent quality degradation issues such as excessive drying, color loss, and moisture non-uniformity. Additionally, energy consumption can be reduced by combining a solar heat recovery system with AI control. Moreover, overall process operating costs are reduced by minimizing heat source usage and optimizing drying time. Furthermore, ESG (Environmental) standards are met through carbon emission monitoring and the use of eco-friendly heat sources, an eco-friendly production system is implemented, and product consistency can be ensured by automatically optimizing the drying process through real-time control feedback based on changes in quality indicators. In the embodiment, the intelligent drying control module (200) can go beyond simple temperature and humidity control and implement climate-adaptive, quality-oriented, and energy-optimized drying technology, thereby dramatically improving productivity throughout the agricultural processing industry.

[0070] The integrated foreign substance removal module (300) removes foreign substances including insects, soil, metal fragments, and plastic in multiple ways. In the embodiment, the integrated foreign substance removal module (300) ensures food safety and improves quality reliability by removing various forms of foreign substances, such as insects, soil, metal fragments, and plastic, that may be contained in the raw materials during the red pepper powder production process, by combining multiple physical and intelligent methods. The integrated foreign substance removal module (300) includes an AI vision inspection unit, a magnetic separation unit, an air pressure separation unit, a precision filtering unit, and a self-learning-based foreign substance identification algorithm, and these components are linked to remove foreign substances step by step from pretreatment to final separation.

[0071] In the embodiment, the integrated foreign substance removal module (300) photographs the chili raw material moving along the conveyor from multiple angles using high-resolution RGB and near-infrared (NIR) cameras.

[0072] For example, the integrated foreign substance removal module (300) analyzes color and shape information through RGB images to detect visual foreign substances such as insects, mold traces, and plastic pieces attached to the surface.

[0073] In addition, the presence of soil or residual foreign substances is detected based on differences in density and moisture content through NIR imaging.

[0074] AI-based object detection algorithms (e.g., YOLO, Mask R-CNN, etc.) are applied to determine the location, size, shape, and type of each foreign substance in real time, and the detected coordinate information is transmitted to the subsequent removal stage. Through this process, approximately 60–70% of the total foreign substances are sorted out in this stage, and the remaining foreign substances are processed through a subsequent physical removal process. Subsequently, metallic foreign substances not identified by the AI ​​vision inspection unit are removed through the magnetic separation unit. In the embodiment, the magnetic separation unit uses high-performance neodymium magnets or electromagnets to strongly adsorb and separate metal fragments (iron, iron powder, wire mesh debris, etc.) inserted into the conveyor line. By adjusting the magnetic flux density in real time through a sensor feedback loop, stable removal efficiency is maintained even with changes in the size and concentration of metallic foreign substances. In the embodiment, through this process, the removal rate of metallic foreign substances reaches over 99%, reducing the possibility of metal contamination to a level that meets food safety standards. Subsequently, non-magnetic foreign substances that do not respond to magnetism, such as plastic fragments, light insect debris, and paper fibers, are removed in the pneumatic separation unit. In this step, a high-speed air jet nozzle and a separation chamber are used to utilize the difference in density and inertia between the raw material and the foreign substances. Additionally, in the embodiment, based on position information extracted during the AI ​​vision inspection step, high-pressure air is injected at precise timings aligned with the movement trajectory of the target foreign substances to separate only the foreign substances from the raw material flow. Through this, impurities can be removed without damaging the raw material as the system operates quickly and accurately without physical contact.

[0075] In addition, in the embodiment, the integrated foreign substance removal module (300) removes fine foreign substances (e.g., fine soil particles, mold spores, etc.) that may remain even after the first to third removal in the precision filtering unit. For example, the integrated foreign substance removal module (300) further removes residual foreign substances according to particle size, mass, and electrical characteristics through a composite filtering device such as a vibrating sieve, a cyclone dust collector, or an electrostatic dust collector filter. This step is designed to meet HACCP standards and serves as the final defense for ensuring food safety.

[0076] In addition, the integrated foreign substance removal module (300) can continuously improve the self-learning removal algorithm by learning foreign substance characteristic data collected during the detection and removal process. For example, if there are changes in foreign substance characteristics due to the season, region, or cultivation environment, or if a new type of contaminant appears, the AI ​​model automatically corrects the detection sensitivity and separation efficiency by reflecting this. This function is implemented through the following iterative learning loop.

[0077] Mathematical formula 3

[0078]

[0079] Here, Mnew is the updated discrimination model, and Mprev is the existing discrimination model. ΔD is the newly collected foreign substance characteristic data, and η is the learning rate.

[0080] In the embodiment, an integrated foreign substance removal module (300) achieves a removal efficiency of over 99% by combining image-based detection, magnetic separation, air pressure separation, and precision filtering. Additionally, it significantly reduces the possibility of foreign substance contamination, thereby ensuring consumer safety and product reliability. Furthermore, through air pressure and non-contact separation technologies, it prevents damage to raw materials and prevents quality degradation. Moreover, by continuously learning foreign substance characteristic data, it maintains high removal performance even with seasonal and variety-specific environmental changes, satisfies food safety regulations such as metal detection and residual foreign substance removal, and guarantees food hygiene and safety required by ESG (Environmental, Social, Governance) standards. The integrated foreign substance removal module (300) according to the embodiment goes beyond a simple mechanical separation device and serves as an AI-based intelligent foreign substance removal platform, enabling significantly higher food safety, removal efficiency, and reliability compared to existing methods.

[0081] The blockchain-based history management module (400) records the production history from the receipt of raw materials to the shipment of finished products in a blockchain database and tracks the said production history. In the embodiment, the blockchain-based history management module (400) safely and transparently records and manages all history data generated throughout the entire process of chili powder production, thereby enabling tracking of production stages and prevention of tampering. The blockchain-based history management module (400) includes a data collection unit, an identification information management unit, a blockchain data recording unit, a history tracking unit, and an external linkage interface unit, digitizes the entire process from the receipt of raw materials to the shipment of finished products, and records it in an immutable distributed ledger. To this end, when chili raw materials are received in the initial stage of production, the blockchain-based history management module (400) assigns a unique identifier (UID) to each raw material unit (lot, batch, etc.). In the embodiment, the unique identifier UID is assigned through one or more of an RFID tag, a QR code, or a barcode, and the tag includes the raw material's place of production, harvest date, variety, supplier information, etc. In addition, initial historical data, such as the time of receipt, storage temperature, and transportation route, is automatically collected through IoT sensors or an ERP-linked system. In the embodiment, the UID generated according to the aforementioned process is registered as the first transaction recorded on the blockchain and is subsequently used as reference information linked to all process histories. Subsequently, as the raw material moves along the processing line, various process histories are automatically collected. For example, the process history may include washing and drying information, quality analysis results, foreign substance removal history, packaging and shipment information, etc. Specifically, washing and drying information may include temperature, humidity, time, heat source usage, energy consumption, etc. Quality analysis results may include AI judgment grades, damage rates, and size classification results. Foreign substance removal history may include the types of substances to be removed, removal rates, and detection history.In addition, packaging and shipping information may include the packaging date, packaging line number, and scheduled shipping date. Data collected at each stage in the embodiment is recorded on the blockchain in the transaction structure shown in FIG. 2.

[0082] Each transaction is linked to the previous block via a hash value and stored in a chain format, ensuring immutability so that no data can be changed subsequently. Furthermore, in the embodiment, users, administrators, and consumers can view the entire history recorded on the blockchain in real time based on a UID. Administrators can check all processes, from washing and drying to quality inspection, packaging, and shipment of a specific route, in chronological order on a web dashboard or ERP integration screen. Consumers can scan a QR code attached to the packaging to view information such as the production farm, processing history, quality certification details, and carbon emission data at a glance. The traceability function provided in the embodiment enables rapid cause analysis in the event of product recalls or quality claims, and supports easy compliance with food safety management standards (HACCP, ISO22000, etc.).

[0083] Additionally, the blockchain-based history management module (400) operates through a public or private blockchain network and verifies the validity of data according to a consensus algorithm (e.g., PBFT, PoA, etc.) in which multiple nodes participate. Each node verifies the collected process data through a hash value and a signature, and a block is created only when consensus is complete.

[0084] This structure fundamentally prevents administrators or third parties from altering or deleting data, thereby ensuring the integrity and reliability of the history.

[0085] In addition, the blockchain-based history management module (400) can be linked via API with government certification systems, export traceability platforms, ESG reporting systems, etc. For example, quality assurance certificates, production history certificates, carbon emission certificates, etc., based on blockchain data can be automatically generated and transmitted to external organizations or trading partners. Through this, data transparency between producers, distributors, and consumers can be secured, and compliance with international regulations or export certification standards can be achieved. The blockchain-based history management module (400) according to the embodiment provides tamper-proof production history management: by recording all production processes on a hash-based blockchain, data tampering is prevented at the source, and legal probative value and reliability are secured. In addition, the entire process from raw material receipt to finished product shipment can be tracked in real-time through a UID, enabling rapid response to quality claims and recall management. Furthermore, through automatic certificate issuance and ESG reporting functions, it is possible to effectively respond to export regulations, sustainability assessments, government certifications, etc. In addition, it establishes a high-value-added agri-food supply chain by connecting suppliers, manufacturers, distributors, and consumers into a single data system.

[0086] The ESG integrated management module (500) collects, analyzes, and visualizes ESG indicators in terms of energy, social responsibility, and governance in real time. In the embodiment, the ESG integrated management module (500) is a core component for implementing a sustainable management system and maximizing ESG response capabilities by collecting, analyzing, and visualizing key indicators in terms of environment, social, and governance in real time throughout the entire chili powder production process. This module (500) is composed of a data collection unit, an ESG indicator analysis unit, an evaluation index calculation unit, a visualization and reporting unit, and an external linkage unit, and is linked with production facilities, IoT sensors, ERP systems, quality control devices, etc. to automatically collect and manage ESG data. To this end, the ESG integrated management module (500) collects environmental data, social data, and governance data generated throughout the entire production process in real time. In the embodiment, environmental (E) data may include energy consumption, heat recovery rate, solar power generation, carbon emissions, waste recycling rate, dust emissions, etc.

[0087] Social (S) data may include HACCP compliance status, occurrence of worker safety accidents, equipment emergency stop records, user interface accessibility, worker feedback logs, etc. Governance (G) data may include whether a quality assurance certificate has been issued, the level of real-time quality data disclosure, external audit logs, regulatory compliance history, etc. This data is automatically collected by linking with IoT sensors, AI controllers, ERP servers, blockchain history management modules (400), etc., and is stored in a standardized ESG data format. Subsequently, the collected raw ESG data is refined and analyzed by an AI-based data analysis engine. For example, through environmental analysis, an energy efficiency index is calculated by comparing hourly energy consumption and production, and the degree of achievement is evaluated by comparing carbon emissions and reduction targets. In addition, through social analysis, the level of social responsibility fulfillment is evaluated by synthesizing the frequency of safety accidents, equipment emergency stop rates, and UI accessibility scores. Furthermore, through governance analysis, a transparency index is calculated based on the speed of quality assurance certificate issuance, history disclosure rate, and external certification status. In addition, the AI ​​model detects abnormal patterns (e.g., rapid increase in carbon emissions, occurrence of HACCP non-compliance, etc.) through time series analysis and anomaly detection algorithms and sends alerts to managers.

[0088] In addition, the ESG integrated management module (500) synthesizes the analysis results and quantifies ESG performance into a single integrated indicator. The ESG integrated score (S_ESG) can be defined as follows:

[0089] Mathematical formula 4

[0090]

[0091] Here, E represents environmental indicators (e.g., energy efficiency, carbon reduction rate, recycling rate), S represents social indicators (e.g., safety index, UI accessibility, regulatory compliance rate), and G represents governance indicators (e.g., data transparency, quality assurance certificate issuance rate). α, β, and γ are coefficients determined based on corporate policies or certification body weights. The calculated integrated ESG score is compared with target values ​​to grade ESG performance levels (grades A–E) or used to derive long-term and short-term improvement strategies.

[0092] Subsequently, the ESG integrated management module (500) visualizes the analyzed and calculated ESG data in the form of a real-time dashboard that is easy for managers and external stakeholders to understand. In the embodiment, data such as energy consumption trends, carbon emissions, and recycling rates are displayed as graphs and color maps. Additionally, the status of safety accidents and HACCP compliance is visualized as warning icons and timelines. Furthermore, the history of automatic quality assurance certificate issuance and data disclosure is displayed in the form of tables and indicators. Additionally, ESG reports can be automatically generated periodically and output in PDF, CSV, or API formats, and support is also available for submission to certification bodies.

[0093] The ESG integrated management module (500) can be linked via API with ESG certification bodies, government reporting systems, carbon emission allowance management platforms, ESG evaluation systems for investors, etc. It automatically transmits data such as ESG scores, carbon reduction performance, and social responsibility fulfillment rates to the linked platforms, receives feedback results from external organizations to correct the ESG evaluation model, and utilizes it for establishing future management strategies. Through this, ESG data generated in the production process is collected and analyzed in real time, enabling immediate response and improvement measures.

[0094] In addition, indicators across the entire spectrum of Environment, Society, and Governance can be quantified and utilized for establishing sustainable production and ESG strategies.

[0095] In addition, the process feedback control module (600) collects and comprehensively evaluates multiple production status information, including at least one of the AI ​​quality analysis results, drying efficiency indicator, foreign substance removal rate, carbon emissions, and history data integrity status, and automatically corrects all process parameters according to the evaluation results. To this end, the process feedback control module (600) collects key status information, such as AI quality analysis results (Q), drying efficiency indicator, foreign substance removal rate, carbon emissions, and history data integrity, in real time throughout the production process. In the embodiment, the AI ​​quality analysis results (Q) include ripeness, damage, quality grade, and discrimination accuracy, and the drying efficiency indicator (D) may include energy consumption, drying speed, moisture removal rate, and time to reach target moisture. The foreign substance removal rate (M) may include detection rate, removal success rate, and residue rate, and the carbon emissions (C) may include CO₂ emissions relative to energy consumption, reduction rate, emission intensity index, etc. History data integrity (I) may include blockchain transaction error rate, data omission rate, and authentication log normality status, etc. The collected data is transmitted to the evaluation department after undergoing time synchronization and standardization, during which diversified data such as real-time sensor data, AI analysis results, ERP logs, and blockchain logs are fused.

[0096] Subsequently, the integrated evaluation department calculates a single comprehensive performance index (S) from the collected status data using a weighted sum-based evaluation algorithm. In this case, S represents the total performance of the production status, reflecting quality, efficiency, safety, sustainability, etc.

[0097] Mathematical formula 5

[0098]

[0099] In mathematical formula 5, Q is the quality score (0~1), D is the drying efficiency score (0~1), M is the foreign matter removal rate score (0~1), C is the carbon emission fraud score (0~1), and I is the data integrity score (0~1). α, β, γ, δ, and are weights based on importance (adjustable according to corporate policy or product specifications). The calculated overall quality index S is compared with a reference threshold Sref to classify the process state as follows. In the embodiment, the process feedback control module (600) compares the calculated overall quality index S with the reference threshold to classify the state of the entire system into three stages and performs different control strategies according to each state. If the overall quality index S is greater than or equal to the reference threshold Sref, the current process is determined to be in a steady state satisfying the target quality and efficiency conditions, and the current state is maintained without separate correction. In addition, if the overall quality index S is lower than the reference threshold Sref but greater than the minimum allowable value Smin, it is determined that the process is exhibiting partial performance degradation within the allowable range, and certain control variables affecting it (e.g., drying temperature, foreign substance removal sensitivity, quality analysis threshold, etc.) are automatically adjusted to improve performance.

[0100] In addition, if the overall quality index S is below the minimum allowable value Smin, it is determined that the process has deviated from the normal operating range, and a comprehensive readjustment procedure is performed covering the entire process, including quality, drying, removal, history management, and ESG control, to restore the system to a normal state. In the embodiment, the quality, efficiency, and stability of the entire production process are dynamically maintained through a stepwise feedback control logic that proceeds from process maintenance to partial correction to full readjustment depending on the quality index level.

[0101] In the embodiment, if the integrated evaluation result falls below the reference value, the process feedback control module (600) determines the correction target by reverse tracing the influencing factor. For example, if the quality score Q decreases, the threshold of the AI ​​quality analysis algorithm may be reset or camera lighting correction may be performed, and if the drying efficiency D decreases, the drying temperature and humidity control curve may be readjusted or the heat source supply speed may be changed. In addition, if the foreign matter removal rate M decreases, the vision inspection sensitivity may be adjusted or the air pressure injection timing may be changed. In addition,

[0102] When carbon emissions C increase, the usage priority of heat pumps can be adjusted and the operating rate of heat recovery units increased. Additionally, if integrity I degrades, blockchain node resynchronization and the RFID re-verification cycle can be shortened. Such control is performed automatically by a central control processor, and parameter change details are recorded in a blockchain-based log for future verification and analysis.

[0103] In addition, the process feedback control module (600) performs mutual optimization between modules, going beyond independent control of individual modules. For example, if a decrease in the foreign substance removal rate leads to a decrease in the quality score, it simultaneously performs sensitivity adjustment of the foreign substance removal algorithm and threshold correction of the quality analysis model. Furthermore, in situations where drying efficiency is low and carbon emissions increase, it coordinates the heat source supply strategy and the reduction policy of the ESG module in a complex manner. This cooperative control contributes to optimizing the efficiency and quality of the entire production chain, going beyond the improvement of a single indicator.

[0104] In addition, the process feedback control module (600) can predict future process changes and perform pre-control by accumulating and learning past correction history and production status data. For example, if it learns a pattern in which drying efficiency declines repeatedly under specific seasonal conditions, it preemptively adjusts the drying curve before the process starts. This learning function can be implemented through reinforcement learning (RL) or time series forecasting (LSTM) algorithms. Through this, the real-time production status is evaluated, and control parameters of each process are automatically adjusted based on this, thereby ensuring quality, efficiency, and safety simultaneously. Furthermore, by detecting abnormal signs early and performing immediate feedback control, it prevents quality degradation, energy waste, and pollution risks in advance.

[0105] Below, we will look at Fig. 3. The intelligent chili powder production automation method combining AI quality analysis and ESG elements illustrated in Fig. 3 can be performed by an intelligent chili powder production automation system combining AI quality analysis and ESG elements that includes a processor.

[0106] Meanwhile, FIG. 3 is merely illustrative, and the concept of the present invention is not to be interpreted as being limited to that shown in FIG. 3. For example, each step may be configured in a different order than that shown in FIG. 3, at least one of the steps shown in FIG. 3 may not be performed, or one or more steps not shown in FIG. 3 may be additionally performed.

[0107] Figure 3 is a diagram showing an intelligent chili powder production automation process that combines AI quality analysis and ESG elements according to an embodiment.

[0108] Referring to FIG. 3, in step S110, the drying conditions are automatically controlled by an intelligent drying control module according to climate and environmental conditions. In step S120, foreign substances including insects, dirt, metal fragments, and plastics are removed in multiple ways. In step S130, the production history from the receipt of raw materials to the shipment of finished products is recorded and tracked in a blockchain database. In step S140, ESG indicators regarding energy, social responsibility, and governance are collected, analyzed, and visualized in real time. In step S150, multiple production status information, including at least one of AI quality analysis results, drying efficiency indicators, foreign substance removal rate, carbon emissions, and historical data integrity status, is collected and evaluated integrally, and the entire process parameters are automatically corrected according to the evaluation results.

[0109] FIG. 4 illustrates an example of the internal configuration of a system and device for performing intelligent chili powder production automation by combining AI quality analysis and ESG elements in an embodiment of the present invention. In the following description, descriptions of unnecessary embodiments that overlap with the descriptions of FIG. 1 to 3 described above will be omitted.

[0110] As illustrated in FIG. 4, the hardware capable of implementing the intelligent chili powder production automation system (100) combining AI quality analysis and ESG elements according to the embodiment is a computing device, and the computing device (10000) may include at least one processor (11100), memory (11200), peripheral interface (11300), input / output subsystem (I / O subsystem) (11400), power circuit (11500), and communication circuit (11600). At this time, the computing device (10000) may correspond to a user terminal (A) connected to a tactile interface device or the aforementioned computing device (B).

[0111] The memory (11200) may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. The memory (11200) may include software modules, instruction sets, or various other data required for the operation of the computing device (10000).

[0112] At this time, access to memory (11200) from other components, such as the processor (11100) or peripheral device interface (11300), can be controlled by the processor (11100).

[0113] The peripheral device interface (11300) can connect input and / or output peripheral devices of the computing device (10000) to the processor (11100) and memory (11200). The processor (11100) can perform various functions for the computing device (10000) and process data by executing software modules or instruction sets stored in the memory (11200).

[0114] The input / output subsystem (11400) can connect various input / output peripherals to the peripheral interface (11300). For example, the input / output subsystem (11400) may include a controller for connecting peripherals such as a monitor, keyboard, mouse, printer, or, if necessary, a touchscreen or sensor to the peripheral interface (11300). According to another aspect, input / output peripherals may be connected to the peripheral interface (11300) without passing through the input / output subsystem (11400).

[0115] The power circuit (11500) can supply power to all or part of the components of the terminal. For example, the power circuit (11500) may include one or more power sources such as a power management system, a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or any other components for power generation, management, and distribution.

[0116] The communication circuit (11600) can enable communication with another computing device using at least one external port.

[0117] Alternatively, as described above, the communication circuit (11600) may enable communication with other computing devices by including an RF circuit and transmitting and receiving an RF signal, also known as an electromagnetic signal.

[0118] The embodiment of FIG. 4 is merely an example of a computing system or device (10000), and the computing device (11000) may have some components shown in FIG. 4 omitted, additional components not shown in FIG. 4 added, or a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may include, in addition to the components shown in FIG. 4, a touchscreen or sensor, etc., and the communication circuit (1160) may include a circuit for RF communication of various communication methods (WiFi, 3G, LTE, Bluetooth, NFC, Zigbee, etc.). The components that can be included in the computing device (10000) may be implemented as hardware, software, or a combination of both hardware and software, including one or more integrated circuits specialized for signal processing or applications.

[0119] Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded on a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. An application to which the present invention is applied may be installed on a user terminal through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file upon a request from the user terminal.

[0120] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include a plurality of processing elements and / or a plurality of types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0121] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed across networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0122] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0123] Although the embodiments have been described above with reference to limited embodiments and drawings, those skilled in the art can make various modifications and variations from the description above. For example, appropriate results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents. Therefore, other implementations, other embodiments, and equivalents to the claims below also fall within the scope of the claims.

Claims

Claim 1 An intelligent red pepper powder production automation system combining AI quality analysis and ESG elements, comprising: an AI quality analysis module for analyzing the quality of red pepper raw materials; an intelligent drying control module for automatically controlling drying conditions according to climate and environmental conditions; an integrated foreign substance removal module for removing foreign substances including insects, soil, metal fragments, and plastics in multiple ways; a blockchain-based history management module for recording and tracking production history from raw material receipt to finished product shipment in a blockchain database; an ESG integrated management module for collecting, analyzing, and visualizing ESG indicators in terms of energy, social responsibility, and governance in real time; and a process feedback control module for collecting and integrally evaluating multiple production status information including at least one of AI quality analysis results, drying efficiency indicators, foreign substance removal rates, carbon emissions, and history data integrity status, and correcting overall process parameters according to the evaluation results. Claim 2 An intelligent red pepper powder production automation system according to claim 1, wherein the AI ​​quality analysis module takes raw material images acquired through a high-resolution camera as input, simultaneously extracts information on ripeness, damage, color, size, and surface defects using a deep learning-based multi-feature analysis network, automatically calculates a quality grade based on the extracted information, and automatically sorts raw materials classified by grade by different transport paths. Claim 3 An intelligent chili powder production automation system according to claim 1, wherein the intelligent drying control module automatically sets a drying curve using an AI controller based on data collected from a temperature and humidity sensor, an external environment sensor, and a solar sensor, improves the energy efficiency of the drying process through a composite heat source control device including at least one of a solar collector, a heat pump, and a heat recovery heat exchanger, and controls the drying process to automatically terminate when the moisture content of the raw material is measured in real time and reaches a target moisture level. Claim 4 delete Claim 5 An intelligent red pepper powder production automation system according to claim 1, wherein the blockchain-based traceability management module generates unique identification information for each raw material unit through an RFID tag, collects traceability data generated throughout the entire process including the time of receipt, washing history, drying temperature and time, quality grade, and packaging date from an IoT sensor and records it in a blockchain database, and provides the registered traceability data in the form of an API (Application Programming Interface) capable of linking with external systems to perform verification in distribution, inspection, and certification procedures. Claim 6 delete

Images