Fully automated management system for kelp drying production process based on artificial intelligence

Abstract

The present invention relates to the technical field of intelligent management of kelp production, and in particular to a fully automated management system for kelp drying production process based on artificial intelligence. The system includes the following modules: a kelp characteristic perception module, a drying parameter planning module, an intelligent intervention and adjustment module, a production parameter intelligent optimization module, and a production visualization management module. It adopts a double-line hanging multi-temperature zone double-layer tunnel drying structure, divides the drying tunnel into multiple temperature zones, and each temperature zone can be set with a different temperature according to the drying requirements of the kelp. The temperature, humidity and drying status of each temperature zone are monitored in real time, and dynamic zoning and stage-by-stage regulation is performed according to preset drying parameters. The automated production operation parameters of the kelp are intelligently learned, and automated production parameter feedback is performed to realize automated control of the kelp drying production and management of the kelp drying production process. The present invention realizes fully automated management of the kelp drying production process through dynamic zoning and stage-by-stage regulation.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management of kelp production, and in particular to a fully automated management system for a kelp drying production process based on artificial intelligence. Background Art

[0002] Because fresh kelp contains approximately 90% water and is prone to spoilage, it has traditionally been processed into dried kelp for long-term storage and long-distance transportation. However, traditional kelp drying methods are no longer able to meet the demands of modern production and market demand. This is primarily due to the following issues: 1. Traditional kelp drying methods rely primarily on sun drying or simple drying equipment, which are severely limited by weather conditions and result in long and unstable processing cycles. In rainy weather or high humidity seasons, kelp is prone to mold and spoilage, causing significant economic losses. Furthermore, open-air drying is susceptible to contamination from external factors such as dust and insect pests, making it difficult to ensure the hygienic quality and safety of the product. 2. Traditional drying equipment suffers from low energy efficiency, resulting in significant energy waste. Most drying equipment uses a single heating method, which is unable to precisely control the temperature according to the requirements of different stages of the kelp drying process. This results in uneven kelp quality, with some areas over-drying while others retain excess moisture, which not only affects product quality but also increases energy consumption. Heat energy is often not effectively recycled during the drying process, further reducing energy efficiency. 3. Existing processing equipment has a low level of automation, resulting in low production efficiency and heavy reliance on manual operation. From cleaning and hanging to drying, sorting, and packaging, kelp production often requires extensive manual labor. This not only increases labor costs but also easily leads to fluctuations in product quality due to human factors. Therefore, there is an urgent need for an AI-based, fully automated management system for the kelp drying process. Through intelligent control and precise energy supply, this system could achieve efficient, energy-saving, environmentally friendly kelp drying, and consistently improve product quality. Summary of the Invention

[0003] Based on this, the present invention provides a fully automated management system for the kelp drying production process based on artificial intelligence to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a fully automated management system for the kelp drying production process based on artificial intelligence is proposed. The fully automated management system for the kelp drying production process based on artificial intelligence adopts a double-line hanging multi-temperature zone double-layer tunnel drying structure, including the following modules:

[0005] The kelp characteristic perception module is used to analyze the kelp monitoring characteristics of single pieces / clusters of fresh kelp units to obtain target kelp monitoring characteristic data; based on the target kelp monitoring characteristic data, a hanging queue layout is performed to generate queue data for kelp to be dried;

[0006] The drying parameter planning module is used to automatically clean and pre-dry single pieces or clusters of fresh kelp using the queue data of the kelp to be dried, and to set the multi-temperature zone production parameters based on the monitoring characteristic data of the target kelp to obtain the automated production parameters of the kelp.

[0007] An intelligent intervention and adjustment module is used to optimize multi-temperature zone kelp drying production based on automated kelp production parameters, classify the finished kelp products, and generate grading data for the dried kelp products. Multi-temperature zone kelp drying optimization includes preheating and sweating optimization, balanced dehumidification optimization, heating and drying optimization, and cooling and shaping optimization.

[0008] The production parameter intelligent optimization module uses a preset convolutional neural network model to perform transfer learning through kelp drying product grading data and kelp automated production operation parameters, and provides automated production parameter feedback to obtain intelligent production operation parameters;

[0009] The production visualization management module is used to monitor the kelp drying process in real time to achieve comprehensive and transparent management of the kelp drying production process.

[0010] The present invention's fully automated management system for the artificial intelligence-based kelp drying production process, through the synergistic effect of multiple modules, has achieved a revolutionary improvement in kelp drying processing. The system's precise perception and analysis of kelp characteristics enables equipment to customize processing based on the actual characteristics of different kelp batches, completely resolving the problem of traditional drying methods being unable to cope with the variability of kelp materials and significantly improving the uniformity and stability of product quality. The combination of a multi-temperature zone intelligent design and precise temperature control technology eliminates weather dependence in the drying process, shortening the traditional processing cycle of several days to just a few hours, significantly improving production efficiency and capacity. The system's precise, staged control of multiple temperature zones, based on the moisture migration patterns of the kelp drying process, provides the optimal temperature and humidity environment for each drying stage, significantly improving the product's rehydration and taste, while shortening the drying cycle and reducing energy consumption. In particular, intelligent intervention and regulation during the four key stages of preheating and sweating, balanced dehumidification, heating and drying, and cooling and setting ensures balanced evaporation of moisture from the inside and outside of the kelp, preventing surface filming and forming microchannels that facilitate moisture drainage, resulting in a more uniform product texture. The implementation of a waste heat recycling strategy significantly reduces system energy consumption. Through intelligent heat allocation, waste heat from high-temperature areas is precisely distributed to low-temperature areas, improving energy efficiency by approximately 30% and achieving energy conservation and environmental protection. The dual-line suspended, multi-temperature zone, double-layer tunnel structure increases production capacity by over 50% within the same footprint, achieving efficient utilization of space resources. The production parameter optimization module, based on a convolutional neural network, features self-learning capabilities, continuously adjusting and refining process parameters based on historical production data. As production experience accumulates, system performance and adaptability continue to improve. The system intelligently grades dried finished products, ensuring standardized quality for market supply and enhancing their market competitiveness and added value. A real-time visual management platform provides transparency throughout the production process, allowing managers to remotely monitor the status of each temperature zone, production progress, and energy consumption, promptly identifying and addressing anomalies and reducing operational risks. The entire system minimizes manual operations, automating the entire process from kelp cleaning to packaging, reducing labor costs by 30%-50% and eliminating quality fluctuations caused by human factors. This system is not only suitable for large-scale kelp processing enterprises, but its modular design and mobility also enable it to meet the needs of small and medium-sized production, improve the applicability and promotion value of the equipment, and promote the intelligent transformation of the kelp processing industry. Therefore, the present invention is a fully automated management system for the kelp drying production process based on artificial intelligence. Through accurate identification and analysis of kelp characteristics, combined with a convolutional neural network model to achieve parameter self-optimization, it adopts a double-line hanging multi-temperature zone double-layer tunnel structure design, and performs staged precise control of the kelp drying process for preheating and sweating, balanced dehumidification, heating and drying, and cooling and shaping, realizing waste heat circulation exchange and heat compensation between temperature zones, integrating real-time monitoring and visual management platforms, and realizing intelligent control of the entire process from raw material processing to finished product grading. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a schematic diagram of the module flow of the fully automated management system for the kelp drying production process based on artificial intelligence of the present invention;

[0012] Figure 2 for Figure 1 Schematic diagram of the detailed implementation process of the kelp characteristic perception module;

[0013] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0014] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0015] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0016] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0017] To achieve this, please refer to Figures 1 to 2 The present invention provides a fully automated management system for the kelp drying production process based on artificial intelligence. The fully automated management system for the kelp drying production process based on artificial intelligence adopts a double-line hanging multi-temperature zone double-layer tunnel drying structure, including the following modules:

[0018] The kelp characteristic perception module is used to analyze the kelp monitoring characteristics of single pieces / clusters of fresh kelp units to obtain target kelp monitoring characteristic data; based on the target kelp monitoring characteristic data, a hanging queue layout is performed to generate queue data for kelp to be dried;

[0019] The drying parameter planning module is used to automatically clean and pre-dry single pieces or clusters of fresh kelp using the queue data of the kelp to be dried, and to set the multi-temperature zone production parameters based on the monitoring characteristic data of the target kelp to obtain the automated production parameters of the kelp.

[0020] An intelligent intervention and adjustment module is used to optimize multi-temperature zone kelp drying production based on automated kelp production parameters, classify the finished kelp products, and generate grading data for the dried kelp products. Multi-temperature zone kelp drying optimization includes preheating and sweating optimization, balanced dehumidification optimization, heating and drying optimization, and cooling and shaping optimization.

[0021] The production parameter intelligent optimization module uses a preset convolutional neural network model to perform transfer learning through kelp drying product grading data and kelp automated production operation parameters, and provides automated production parameter feedback to obtain intelligent production operation parameters;

[0022] The production visualization management module is used to monitor the kelp drying process in real time to achieve comprehensive and transparent management of the kelp drying production process.

[0023] In an embodiment of the present invention, the fully automated management system for the kelp drying production process based on artificial intelligence includes the following modules:

[0024] S1: Kelp characteristic perception module, used to analyze the kelp monitoring characteristics of single pieces / clusters of fresh kelp units to obtain target kelp monitoring characteristic data; based on the target kelp monitoring characteristic data, it arranges the hanging queue and generates the queue data of kelp to be dried;

[0025] In an embodiment of the present invention, before the kelp enters the drying production line, each piece or cluster of fresh kelp is first photographed at high resolution by an image recognition unit. The image is enhanced with surface texture and color difference information by a multi-channel light source, and then sent to a deep convolution recognition model for feature extraction. The monitoring features extracted by the system include kelp length, width, thickness, color distribution, surface adhesion distribution, water-containing area distribution, etc. The thickness is scanned non-contactly by a laser displacement sensor, and the surface humidity is regionally analyzed by a near-infrared reflectance spectroscopy device. After all feature data are fused and processed by the main control system, target kelp monitoring feature data is generated. Based on the feature data, the hanging layout scheduling system performs task planning, automatically controls the sorting unit on the hanging track, and automatically distributes the kelp to different hanging points according to length and thickness. The spacing control range is 100 to 300 mm, generating structured kelp queue data to be dried.

[0026] S2: Drying parameter planning module, used to perform automated cleaning and blowing treatment production operations on single pieces / clusters of fresh kelp units based on the queue data of kelp to be dried, and to set multi-temperature zone production operation parameters based on the monitoring characteristic data of the target kelp to obtain the kelp automated production operation parameters;

[0027] In this embodiment of the present invention, the drying parameter planning module first implements an automated kelp washing and drying process. The washing system utilizes a three-stage design: the first stage involves a high-pressure spray (0.8 MPa, fresh water) to remove surface impurities; the second stage involves an ozone water spray (0.5 ppm concentration) for disinfection; and the third stage involves a clean water rinse (0.5 MPa) to remove residues. The conveyor speed is controlled at 0.3 m / s to ensure that each piece of kelp is washed for at least 45 seconds. The drying system consists of 12 centrifugal blowers, operating at a pressure of 2000 Pa, a temperature of 35°C, and a speed of 15 m / s. These blowers are evenly distributed on both sides of the conveyor, providing a 360-degree, seamless drying process. Subsequently, the multi-temperature zone production operation parameter setting unit receives the target kelp monitoring characteristic data and initiates a four-stage parameter planning process. The preheating stage parameters are set based on the average kelp thickness and initial moisture content: a preheating temperature of 57°C, a humidity of 65%, a circulating fan speed of 1300 rpm, and a preheating time of 180 seconds. The dehumidification stage parameters are based on the surface moisture distribution of the kelp, setting the dehumidification temperature at 50°C, the initial damper opening of the dehumidification fan at 40%, the fresh air supply at 25 cubic meters per minute, and the dehumidification time at 300 seconds. The drying stage parameters are determined based on the wet weight and moisture content gradient of the kelp, with a target drying temperature of 85°C, a main air duct speed of 9.5 meters per second for the powerful dehumidification fan, and a drying time of 480 seconds. The shaping stage parameters are set based on the expected state after drying, with a cooling temperature of 25°C, a cooling fan air supply speed of 4.5 meters per second, and a conveyor belt speed of 3.2 meters per minute. The system integrates the parameters of the four stages to generate a complete data set of automated kelp production operation parameters, which are distributed to the control units of each temperature zone via the fieldbus network.

[0028] S3: An intelligent intervention and adjustment module, used to optimize multi-temperature zone kelp drying production based on automated kelp production parameters, classify kelp dried products, and generate kelp dried product grading data. It also performs heat compensation for waste heat exchange in temperature zones based on automated kelp production parameters, and establishes a waste heat recycling strategy. The multi-temperature zone kelp drying production optimization process includes preheating and sweating optimization, balanced dehumidification optimization, heating and drying optimization, and cooling and shaping optimization.

[0029] In this embodiment of the present invention, an intelligent intervention and adjustment module dynamically optimizes the drying process throughout the entire process, utilizing four stages of coordinated control. The preheating and sweating production optimization system uses 16 PT100 temperature sensors and 12 humidity sensors to construct an environmental field in the first temperature zone, monitoring the surface temperature distribution and local humidity changes of the kelp. If uneven surface temperature is detected, with a temperature gradient exceeding 3°C / cm, the system precisely adjusts the angles of 36 micro-air vents and the power of 24 infrared heating units to achieve precise sweating control. The balanced dehumidification production optimization system deploys eight high-precision load cells and 16 near-infrared moisture sensors in the second temperature zone to continuously monitor the water loss rate. Combined with a microenvironmental model constructed using 24 humidity sensors and 16 wind speed sensors, it detects dehumidification anomalies in real time. If a moisture accumulation anomaly (local humidity exceeding 70%) is detected, the system immediately increases the air valve opening by 25% and reduces the temperature by 3°C. The heating and drying production optimization system calculates the drying uniformity index based on the three-dimensional temperature and wind speed fields constructed by 56 temperature sensors and 32 wind speed sensors in the third temperature zone. When the index falls below the preset threshold of 75, the system adjusts the kelp hanging height using 16 sets of chain lifts, shifting the drying lag zone upward by 100-150 mm to optimize thermal energy utilization. The cooling and shaping production optimization system precisely controls the cooling curve in the fourth temperature zone, creating a stable cooling environment through a water-cooled heat sink and 16 centrifugal fans. A high-precision sensor array is deployed at the discharge end to measure the final moisture content, appearance, morphology, and texture characteristics. The system then categorizes the kelp into four grades: special, first, second, and third, based on a weighted scoring system. This generates complete grading data for the finished dried kelp product.

[0030] S4: Production parameter intelligent optimization module, which is used to perform transfer learning based on the preset convolutional neural network model through the kelp drying finished product grading data and kelp automated production operation parameters, and provide automated production parameter feedback to obtain intelligent production operation parameters;

[0031] In this embodiment of the present invention, the core of the system is a pre-set, improved ResNet-50 convolutional neural network model. The initial model is pre-trained using 5,000 batches of historical production data, containing complete production parameters and finished product quality data for each grade of kelp. The transfer learning unit receives the current kelp drying product grade data and the corresponding kelp automated production operation parameters, constructing an input tensor containing 245 feature dimensions. These feature dimensions include production parameters such as temperature curves for four temperature zones, humidity changes, wind speed adjustment, and conveyor speed, as well as quality indicators such as finished product moisture content, hardness, rehydration, and color. The learning process uses a small-batch learning method with a batch size of 32 and a learning rate of 0.001, with the model updated every 50 batches of new data. The optimization objective is to maximize the sum of the premium and first-grade product rates while minimizing energy consumption. Based on the updated model, the parameter optimization engine generates differentiated production parameter recommendations for kelp raw materials with different characteristics, focusing on optimizing sensitive parameters such as preheating temperature, dehumidification wind speed, and drying time. The system compares production data from 30 consecutive batches. If it detects an increase of more than 2.5 percentage points in the premium product rate or a reduction of more than 5% in energy consumption, it locks the optimized parameters into the new standard process parameters. After the optimization results are verified by the quality inspection unit, an intelligent production operation parameter package containing temperature adjustment values ​​for each temperature zone, wind speed correction coefficients, and optimized duration ratios is generated. This package is then distributed to each execution unit via Industrial Ethernet, achieving closed-loop continuous optimization.

[0032] S5: Production visualization management module, used to monitor in real time the operating status of each temperature zone in the dual-line hanging multi-temperature zone double-layer tunnel drying structure, the processing progress of the kelp drying unit, and the system energy consumption, so as to achieve comprehensive and transparent management of the kelp drying production process.

[0033] In this embodiment of the present invention, the production visualization management module achieves comprehensive monitoring through a distributed data acquisition system. The system deploys 198 sensor nodes (96 for temperature, 48 for humidity, 32 for wind speed, and 22 for weight), with sampling periods ranging from 1 to 60 seconds. Data is transmitted to a central server via the Industrial Internet of Things (IIoT) protocol. The monitoring interface utilizes a 43-inch industrial touchscreen with a resolution of 3840×2160 and a refresh rate of 60 Hz. The main interface displays a 3D model of the dual-hanging, multi-temperature-zone, double-layer tunnel drying structure, with color coding indicating temperature distribution (blue, yellow, and red correspond to 20-65°C). The system updates 46 key process parameters for each temperature zone in real time, including temperature and humidity curves, energy consumption data, and abnormality alerts. The kelp drying unit's processing progress is intuitively displayed via a Gantt chart, including information such as ID, moisture content trends, estimated completion time, and quality forecasts. System energy consumption monitoring utilizes multi-level statistical analysis, calculating energy consumption per product, from individual heating elements (with an accuracy of 0.1 kWh) to the overall system energy consumption, and generating hourly, daily, and weekly energy consumption reports. The management module integrates 10 abnormal state recognition algorithms to provide early warning of equipment failure or parameter deviation, and provides historical data query function, supporting multi-dimensional screening by time, batch, variety, etc.

[0034] Preferably, the double-line hanging multi-temperature zone double-layer tunnel drying structure includes:

[0035] Two independently operated drying lines are set up, each drying line is provided with a hanging conveyor belt, and a plurality of hanging units are installed on the hanging conveyor belt to obtain a double-line hanging conveying mechanism;

[0036] Each hanging unit is equipped with a weighing sensor and a near-infrared moisture content sensor, and a three-dimensional laser scanner is deployed at the entrance of the double-line hanging transmission mechanism;

[0037] The double-line hanging transmission mechanism is set to a tunnel structure, including upper and lower layers, and both the upper and lower layers can be used for the kelp carried by the hanging unit to pass through for drying, thereby obtaining a double-layer reuse tunnel structure;

[0038] Along the length of the double-layer reuse tunnel structure, the multiple independent temperature zones within the tunnel are divided into at least four physically isolated temperature zones, resulting in multiple drying function temperature zones. The multiple independent temperature zones include a first temperature zone for preheating and sweating the kelp, a second temperature zone for balanced dehumidification, a third temperature zone for heating and drying, and a fourth temperature zone for cooling and setting.

[0039] Independently adjustable temperature sensors, humidity sensors, and wind speed sensors are arranged on the inner walls and top partitions of the multi-section drying function temperature zones to build a drying temperature zone monitoring network.

[0040] In an embodiment of the present invention, a dual-line hanging transmission mechanism is made of 304 stainless steel and is equipped with two independent parallel drying lines with a spacing of 1.5 meters, each drying line is 20 meters long. A chain hanging conveyor belt is installed on each drying line. The conveyor belt is driven by a 22-kilowatt variable-frequency motor with a speed range of 0.5-3 meters per minute and an accuracy of ±0.05 meters per minute. A hanging unit connection point is set every 0.8 meters on the conveyor belt, for a total of 25 hanging points. The hanging unit adopts a quick-release stainless steel hook structure with a load-bearing capacity of 15 kilograms per unit. It is fixed to the conveyor belt with a special lock to ensure that it will not fall off in high-temperature environments. The dual-line transmission system is controlled by a central PLC controller to achieve independent or synchronous operation, and the operating status is displayed in real time on the control panel. The bottom of each hanging unit is integrated with a DS-1 high-precision weighing sensor with a measuring range of 0-20 kilograms and an accuracy of ±5 grams. It adopts a waterproof and dustproof design with an IP67 level. An NIR-100 near-infrared moisture sensor with a spectral range of 900-1700 nm, a sampling frequency of 10 times / second, and a moisture content accuracy of ±0.5% is installed on the side of the unit. An LT-300 3D laser scanner with a scanning accuracy of 0.1 mm, a scanning frequency of 60 Hz, and a field of view of 120° × 90° is fixed at the entrance of the dual-line hanging conveyor mechanism. It uses a 3D point cloud image processing algorithm to calculate the size and volume of the kelp in real time. All sensor data is transmitted to the data acquisition unit via an RS485 bus with a sampling period of 1 second. The double-layer multiplexing tunnel structure is constructed from 100 mm thick polyurethane sandwich insulation panels and measures 22 meters long, 4 meters wide, and 3 meters high. The tunnel interior is divided into two levels, each 1.4 meters high with a 0.2 meter gap between them. Both levels are equipped with a rail system for the hanging units carrying the kelp to pass through. Automatic rolling shutter doors measuring 2 meters × 2 meters are installed at the tunnel entrance and exit, opening and closing at a speed of 0.5 meters / second. The tunnel's interior walls are clad in high-temperature-resistant, reflective aluminum panels to enhance thermal efficiency. Each floor is designed with a 5° slope to ensure automatic drainage of condensed water. Maintenance doors measuring 1 meter by 2 meters are installed on both sides of the tunnel, spaced 5 meters apart. The 22-meter-long double-layered, reused tunnel is divided into four physically isolated temperature zones, separated by 30mm-thick silicone curtains with an adjustable opening height of 1.2-1.5 meters. The first temperature zone is 5 meters long, maintained at 36-40°C and a relative humidity of 75-85%, for preheating and sweating the kelp. The second temperature zone is 5 meters long, maintained at 42-46°C and a relative humidity of 55-65%, for balanced dehumidification. The third temperature zone is 7 meters long, maintained at 50-65°C and a relative humidity of 35-45%, for heating and drying. The fourth temperature zone is 5 meters long, with a gradually decreasing temperature to 28-32°C and a relative humidity of 30-40%, for cooling and setting. Each temperature zone is equipped with an independent hot air circulation system, and the heat source uses electric heating tubes with powers of 12 kW, 15 kW, 25 kW and 10 kW respectively.The drying zone monitoring network features sensor nodes evenly distributed around the inner walls and ceiling of each zone. Eight PT100 temperature sensors are installed around the inner walls of each zone, with a measurement range of 0-150°C and an accuracy of ±0.1°C. Four SHT85 high-precision humidity sensors are installed on the ceiling of each zone, with a measurement range of 0-100%RH and an accuracy of ±1.5%RH. Two FS450 thermal wind speed sensors are installed at the entrance and exit of each zone, with a measurement range of 0-30 m / s and an accuracy of ±0.1 m / s. All sensor data is collected every two seconds by an industrial IoT module, processed by a data pre-processing algorithm, and transmitted to the central control system. Micro-air vents with a diameter of 5 cm are installed every 30 cm on the inner walls of the tunnels in the first and third zones, along both sides of the conveyor track along the coastal belt. Each vent is equipped with a 15-watt servo motor-driven air deflector with precise adjustment from 0 to 90 degrees. The air outlet array automatically adjusts the angle of the air deflectors using a PID control algorithm based on real-time kelp moisture data detected by infrared sensors, directing the hot air toward areas with higher moisture content. Twenty-four power-adjustable infrared radiation heating units are installed on the top and sides of the tunnel's inner wall in the first temperature zone, spaced evenly across the width of the kelp conveyor belt. Each unit consists of a ceramic heating element and a focusing reflector. The power of each heating unit ranges from 100 to 500 watts, with power adjustment achieved with a precision of 0.1 watt using a silicon-controlled rectifier. Each temperature zone is equipped with a DN200 main air valve driven by a precision stepper motor, offering a valve opening adjustment accuracy of 0.5% and a maximum air flow of 2,000 cubic meters per hour. The second temperature zone is equipped with a 5-kilowatt centrifugal dehumidification fan with a speed range of 800-3,000 rpm, precisely controlled by a frequency converter. The third temperature zone is equipped with a 7.5-kilowatt high-temperature fan, achieving a maximum air temperature of 80°C. The fourth temperature zone uses a 3-kilowatt low-temperature fan, maintaining an air temperature of 30-35°C. A plate heat exchanger, with a heat exchange area of ​​25 square meters, is installed between the exhaust port of the third temperature zone and the air inlet of the first temperature zone. Made of SUS316L stainless steel for high corrosion resistance, the heat exchanger features a staggered flow channel structure, with hot and cold channels alternately arranged, and a single channel width of 8 mm. Exhaust hot air (approximately 70°C) exchanges heat with fresh intake air (at ambient temperature) without mixing, achieving a heat recovery efficiency of 75%. A temperature sensor monitors the inlet and outlet temperature differential and automatically adjusts the bypass valve opening accordingly, maintaining a stable inlet temperature of 40-45°C for the first temperature zone. The central control unit utilizes a redundant industrial controller. The main controller is equipped with a quad-core processor operating at 3.2 GHz and 32GB of memory. EtherCAT fieldbus technology connects all actuators. Each actuator is equipped with an independent microcontroller, forming a three-level control network: central controller, regional controller, and terminal actuator. System response time is less than 20 milliseconds, and control accuracy reaches ±0.5% of the set value.The system automatically generates the optimal drying curve based on factors such as product batch characteristics, ambient humidity, and the initial moisture content of the kelp. The actuator group works together to accurately track this curve.

[0041] Preferably, the kelp characteristic perception module is specifically:

[0042] S21: Using a 3D laser scanner to perform non-contact contour scanning on a single piece / cluster of fresh kelp entering the automatic hanging station to obtain 3D morphological data of the kelp;

[0043] S22: Perform 3D surface reconstruction based on kelp 3D morphology data and estimate the kelp macroscopic surface area;

[0044] S23: Analyze kelp monitoring characteristics based on the macroscopic surface area of ​​the kelp to obtain target kelp monitoring characteristic data; wherein the target kelp monitoring characteristic data includes kelp wet weight data, target kelp average thickness data, and kelp surface moisture content at multiple points;

[0045] S24: Evaluate the hanging distance between the front and rear hanging units according to the macroscopic surface area of ​​the kelp to obtain a target kelp hanging distance value;

[0046] S25: Controlling the hanging unit to adjust the spacing on the conveyor chain according to the target kelp hanging spacing value to obtain real-time hanging queue layout data;

[0047] S26: Matching the spraying pressure and the spraying time according to the average thickness data of the target kelp and the macroscopic surface area of ​​the kelp to obtain a spraying instruction for the cleaning area;

[0048] S27: Setting air knife drying parameters according to the target kelp monitoring characteristic data and the kelp macroscopic surface area, and obtaining a kelp air knife drying control instruction;

[0049] S28: The real-time hanging queue layout data is used to associate the cleaning area spraying instruction and the kelp air knife drying control instruction with production instructions to obtain the kelp queue data to be dried.

[0050] In an embodiment of the present invention, before the kelp enters the automatic hanging station, a non-contact contour scan is performed using an LT-500 high-precision laser 3D scanner. The scanner is positioned 1.2 meters in front of the hanging station and has a spatial resolution of 0.1 mm, a 120° × 90° field of view, and a sampling frequency of 120 Hz. The scan uses a 180° rotational scanning method, with the motor driving the scanning head to rotate at a speed of 15 rpm to acquire omnidirectional point cloud data. The scanning process lasts 3 seconds, and a single scan acquires 3.6 million points of point cloud data. The point cloud data is transmitted to the processing unit in real time via industrial Ethernet. After processing using a point cloud registration algorithm and removing environmental noise, complete kelp 3D topography data is generated. The data is saved in a 3D matrix format with a matrix size of 1024 × 1024 × 3, achieving millimeter-level accuracy. The acquired kelp 3D topography point cloud data is processed using a Poisson surface reconstruction algorithm, with a reconstruction accuracy set to 0.5 mm. First, the point cloud data is subjected to noise reduction. The statistical analysis method within a spherical neighborhood with a radius of 2 mm is used to remove outliers and retain connected points with a degree of not less than 8. Then, a triangular mesh is constructed using an octree space partitioning method with a depth of 10 to generate a complete kelp surface model. The surface model is calculated using the discrete differential geometry method. The specific calculation formula is: , where S is the macroscopic surface area of ​​kelp, is the area of ​​the i-th triangle, and the unit of area is square centimeters. The accuracy of the calculation results is controlled within the range of ±1%, and the maximum length, maximum width and surface undulation data of the kelp are recorded at the same time. The wet weight data of the kelp is measured by a high-precision XS-500 electronic scale with an accuracy of ±0.5 grams, and the measured values ​​are transmitted to the database in real time. The average thickness of the kelp is obtained by measuring at 25 sampling points evenly divided by a grid on the kelp surface using an LDM-150 laser rangefinder. The measurement accuracy is 0.01 mm, and the arithmetic mean of the thickness of the sampling points is taken. The calculation formula is , where H is the average thickness of kelp, is the thickness at the i-th measurement point, and n is the number of measurement points (25). The surface moisture content of kelp was measured at five key points using an NIR-200 near-infrared spectrometer, with a wavelength range of 900-1700 nm, a sampling depth of 0.5-3 mm, and a measurement accuracy of ±0.5%. The average moisture content and standard deviation were calculated. The system sets the base spacing value to 25 cm. The target kelp hanging spacing value is calculated as follows: Dspacing = Dbase + k × (Smeasured - Sstandard), where Dspacing is the target hanging spacing value (cm), Dbase is the base spacing value (25 cm), Smeasured is the measured kelp macroscopic surface area (square centimeters), Sstandard is the standard kelp surface area (400 square centimeters), and k is the proportionality factor (0.05 cm / square centimeter). When the measured S is less than 200 square centimeters, the spacing factor is adjusted to 0.025. When 200 ≤ S < 600 square centimeters, the spacing factor remains unchanged at 0.05. When S is ≥ 600 square centimeters, the spacing factor is increased to 0.075. To account for air circulation requirements, the system sets a minimum hanging spacing of 15 cm and a maximum of 45 cm. If the calculated result exceeds the range, the system automatically limits it to within the valid range. Spacing assessment considers the surface area difference between the front and rear kelp units, taking the arithmetic average of the two spacing values ​​as the final adjustment to ensure balanced spacing across the entire hanging queue. The system converts the target kelp hanging spacing value into the number of pulses for the conveyor chain's stepper motor using the following formula: N pulses = D spacing × P, where N pulses is the number of stepper motor pulses, D spacing is the target hanging spacing value (cm), and P is the transmission ratio (200 pulses / cm). The system sends positioning commands to the stepper motor controller via the RS485 bus, controlling the conveyor chain to precisely move to the target position with positioning accuracy within ±1 mm. During the positioning process, Hall sensors monitor the actual chain displacement in real time, forming a closed-loop feedback loop to correct accumulated errors. After positioning is complete, the system records the absolute position coordinates of the hanging unit on the conveyor chain (the chain starting point is 0) and generates real-time hanging queue layout data including position, spacing, and timestamps. Simultaneously, an encoder continuously monitors the conveyor chain speed and automatically compensates for speed fluctuations exceeding ±2%, ensuring uniform speed operation across the entire hanging queue. The spray pressure calculation formula is: Pspray = Pbase × (daverage / dstandard) × (Smeasured / Sstandard)^0.5, where Pspray is the spray pressure (MPa), Pbase is the base spray pressure (0.25 MPa), daverage is the average kelp thickness (mm), dstandard is the standard thickness (2 mm), Smeasured is the measured surface area (square centimeters), and Sstandard is the standard surface area (400 square centimeters). The calculation formula for the spray action time is: Tspray = Tbase × (daverage / dstandard)^1.5 × (Smeasured / Sstandard)^0.3, where Tspray is the spray action time (seconds) and Tbase is the basic spray time (3 seconds).Based on the calculated results, the system sets the variable-frequency pump output pressure (range: 0.1-0.5 MPa, adjustment steps: 0.05 MPa) and the solenoid valve opening time (range: 1-6 seconds, accuracy: 0.1 second). The cleaning area is equipped with six rotating nozzles with a nozzle diameter of 1.2 mm and installed 10 cm apart, forming a cross-spray network. The system precisely controls the nozzle start and stop times based on kelp location information, minimizing cleaning solution loss while ensuring cleaning uniformity exceeding 95%. The air knife speed parameter setting formula is: V Speed ​​= V Base × (W Average / W Standard) ^ 0.7 × (S Measured / S Standard) ^ 0.4, where V Speed ​​is the air knife speed (m / s), V Base is the base speed (25 m / s), W Average is the average moisture content (%), W Standard is the standard moisture content (85%), S Measured is the measured surface area (square centimeters), and S Standard is the standard surface area (400 square centimeters). The air knife action distance parameter setting formula is: L distance = L base × (d average / d standard) ^ 0.5, where L distance is the distance between the air knife and the kelp surface (cm), L base is the base distance (8 cm), d average is the average kelp thickness (mm), and d standard is the standard thickness (2 mm). Based on the calculated results, the system adjusts the fan speed (range: 1000-3000 rpm, in 50 rpm increments) via a frequency converter and the air knife height (range: 5-15 cm, with 0.5 cm accuracy) via a servo mechanism. The air knife system utilizes a dual-layer design, with five sets of linear air knives on each layer. Each layer has a 50 cm blade length and a 1.5 mm air outlet width, creating a uniform airflow field across the entire width of the conveyor belt. The generated air knife drying control instructions contain three core parameters: wind speed, distance, and action time, precisely matching the drying requirements of kelp with different characteristics. The system utilizes a dual-buffered queue structure: the main queue stores kelp location information, and the sub-queue stores the corresponding processing instructions. The association algorithm uses the kelp ID as an index key to bind all processing instructions for the same kelp unit, forming a command chain. The system updates the queue status every 100 milliseconds, calculates the estimated time for each kelp unit to arrive at each workstation based on the actual speed of the conveyor chain, and sends control instructions to the target workstation 5 seconds in advance.

[0051] Preferably, the kelp monitoring characteristic analysis based on the kelp macroscopic surface area includes:

[0052] Use a weighing sensor to weigh a single piece or cluster of fresh kelp to generate kelp wet weight data;

[0053] The average thickness of kelp is evaluated based on the wet weight data of kelp and the macroscopic surface area of ​​kelp to obtain the target average thickness data of kelp;

[0054] A near-infrared moisture content sensor is used to perform multi-point near-infrared spectral rapid scanning of a single piece or cluster of fresh kelp to generate kelp surface spectrum data.

[0055] Performing baseline drift correction and filtering on the kelp surface spectrum data to generate kelp surface corrected spectrum data;

[0056] The characteristic bands of the kelp surface corrected spectral data were identified using the preset kelp spectral calibration information library, and the average initial moisture content of the kelp surface was evaluated to obtain the multi-point moisture content of the kelp surface.

[0057] In an embodiment of the present invention, a single piece or cluster of fresh kelp is weighed using an HS-3000 high-precision load cell when the kelp is transported to the automatic hanging station. This sensor has a range of 0-5 kg, an accuracy of ±0.5 g, a sensitivity of 2 mV / V, and a response time of less than 100 milliseconds. The load cell is mounted at the bottom of the hanging unit, employing a four-point support structure and measuring weight using the Stern-Wheatstone bridge principle. During the weighing process, the system collects 300 data points at a sampling frequency of 100 Hz for 3 seconds. After removing the top 5% and bottom 5% of outliers, the arithmetic mean is taken to obtain the kelp wet weight data W (in grams). The measured data is converted by a 24-bit high-precision analog-to-digital converter and transmitted to the central processing unit via the RS485 bus. It is updated in real time to the kelp characteristics database and associated with a unique kelp unit identification code. The system automatically analyzes the average kelp thickness H (in millimeters) based on the acquired kelp wet weight data (W, g) and macroscopic surface area (S, square centimeters). If the thickness value is less than 0.5 mm or greater than 5 mm, an anomaly detection mechanism is triggered, prompting data re-collection. Three consecutive anomalies trigger a warning message on the industrial computer. A NIR-2000 near-infrared moisture content sensor is used to perform multi-point scanning of a single piece or cluster of fresh kelp. The sensor has a spectral range of 850-2500 nm, a spectral resolution of 2 nm, a signal-to-noise ratio of 5000:1, and a sampling rate of 50 milliseconds per point. The scanning device, driven by a stepper motor, places nine fixed sampling points along a Z-shaped path on the kelp surface, with a spacing of one-third of the kelp's maximum length and width. Three measurements are taken at each sampling point and the average is calculated to ensure data stability. The sensor probe maintains a fixed distance of 5 mm from the kelp surface, controlled in real time by a precision distance sensor. Each scan acquires reflectance spectrum data at 1024 wavelength points, forming a 9×1024 spectral matrix, which is transmitted to the spectral analysis module via high-speed optical fiber at a data transmission rate of 100 megabits per second. The collected kelp surface spectrum data is first subjected to baseline drift correction, and the baseline noise is removed using a polynomial fitting method. The specific steps are: 1000, 1200, 1800, and 2300 nanometers are determined as baseline anchor points, and a cubic spline function is used for baseline fitting. The fitting formula is: ,in, is the baseline value at wavelength λ, where λ is the wavelength, 、 、 、 is the fitting coefficient. The fitting coefficient is solved by the least square method and the complete baseline curve is calculated. ,in is the original spectral reflectance, is the reflectivity after baseline correction. The second stage is filtering, using the Savitzky-Golay smoothing filter algorithm, with the window width set to 15 data points and the polynomial order to 3. The filtering formula is: ,in is the spectrum value of point i after filtering, j value is from -n to n, Rc(i+j) is the spectrum value of point i+j after correction, is the convolution coefficient, and n is the half-width of the window. The standard deviation judgment method is used to eliminate outliers, and the threshold is set to 3 times the standard deviation. After correction and filtering, the system normalizes the spectral data of the 9 measurement points to generate kelp surface correction spectral data in a standard format, and the data accuracy reaches ±0.001 reflectance unit. The system identifies the characteristic bands of the kelp surface correction spectral data through the preset kelp spectral calibration information library. The calibration information library contains 500 sets of standard spectral data of kelp samples with different moisture contents (35%-95%). The samples are calibrated to the true value of moisture content by the 105°C oven drying method. A spectrum-moisture content mathematical model is established. The continuous wavelet transform method is used to identify the characteristic bands, and 1450 nanometers and 1940 nanometers are determined as the main peaks of moisture absorption, and 970 nanometers is determined as the secondary peak. The moisture content is calculated using a multiple linear regression model: , where W is the moisture content (%), 、 、 、 、 、 are the corrected spectral reflectances at the corresponding wavelengths, 、 、 、 The system calculates the moisture content at each of the nine measurement points and determines its uniformity. If the difference between the maximum and minimum values ​​exceeds 10%, the sample is marked as "uneven," requiring specific adjustment of drying parameters. The system calculates the average of the nine points as the average initial moisture content of the kelp and simultaneously records a moisture content distribution map, forming a complete multi-point moisture content dataset for the kelp surface.

[0058] Preferably, the kelp automated production operation parameters include the preheating operation benchmark data of the first zone, the dehumidification operation benchmark data of the second zone, the drying operation benchmark data of the third zone, and the shaping operation benchmark data of the fourth zone. The drying parameter planning module is specifically as follows:

[0059] Perform automated cleaning and blowing treatment on single piece / cluster fresh kelp units based on the queue data of kelp to be dried, generating kelp pre-cleaning status data;

[0060] Processing the target preheating time of one zone according to the kelp pre-cleaning state data and the target kelp average thickness data in the target kelp monitoring characteristic data to generate the target preheating time data of one zone;

[0061] The preheating circulation fan speed of the first zone is set according to the preheating target time data of the first zone, and the operation control benchmark is integrated according to the preheating target time data of the first zone to obtain the preheating operation benchmark data of the first zone;

[0062] According to the multi-point moisture content of the kelp surface in the target kelp monitoring characteristic data, the dehumidification target temperature of the second temperature zone, the initial air valve target opening percentage of the dehumidification fan, and the dehumidification treatment time are planned to obtain the dehumidification operation benchmark data of the second zone;

[0063] According to the wet weight data of the target kelp in the monitoring characteristic data of the target kelp, the target temperature for heating and drying, the target wind speed value of the main air duct of the powerful dehumidification fan and the duration of heating and drying treatment are set to obtain the benchmark data of the three-zone drying operation;

[0064] The cooling temperature and the target air supply speed of the cooling fan are set according to the target kelp monitoring characteristic data, and the target moving speed of the conveyor belt is processed to obtain the four-zone standardized operation benchmark data.

[0065] In an embodiment of the present invention, based on the data of the kelp queue to be dried, the system automatically starts the cleaning-blowing pre-processing process. The kelp queue to be dried is placed on a mesh stainless steel conveyor belt by an automatic sorting mechanism in a single piece / single cluster manner, and the conveyor belt speed is set to 0.5 meters per minute. The cleaning process uses a high-pressure fresh water spray system, the spray pressure is maintained at 0.6MPa, the nozzle spacing is 10 cm, and the spray time is 60 seconds to ensure that the salt and impurities attached to the surface of the kelp are fully removed. Subsequently, a multi-stage centrifugal high-speed fan array blows the kelp dry, with a fan speed of 3000 rpm, a wind speed of 15 meters per second, and a drying time of 45 seconds. During the process, distributed optical sensors and infrared moisture sensors collect the appearance characteristics and surface moisture distribution data of the kelp in real time, and generate a pre-cleaning state data matrix containing information such as kelp morphological parameters, surface moisture distribution map, and salt content. Single pieces or clusters of fresh kelp units are sequentially fed into a fully automatic transport track system, and the kelp surface is thoroughly cleaned using a multi-head high-pressure water jet device. After cleaning, a multi-nozzle air knife system is used to blow dry the surface. During the cleaning process, an image recognition camera is used to capture the residual stains on the kelp surface, and the pre-treatment state recognition module generates kelp pre-cleaning state data. Subsequently, the thickness data of the target kelp is collected. The thickness is measured using a laser displacement sensor, which accurately outputs the average thickness value of each piece of kelp in millimeters. The preheating target time uses the thickness parameter as the input variable and is calculated using the following empirical formula: Preheating time T_pre (seconds) = k_pre × H, where T_pre represents the preheating target time for a zone, H is the average thickness of the kelp (mm), and k_pre is a preset empirical constant with a value range of 8-12. The average value obtained based on historical data fitting is 10. T_pre is output to the preheating control system, which sets the speed of the circulating hot air fan. The fan speed V_pre is controlled by a frequency converter within a range of 800-1600 rpm to ensure heat supply within the T_pre range. The operation control benchmark integration module aggregates T_pre, V_pre, and the hot air temperature parameter θ_pre (initially set at 55°C) to form the preheating benchmark data for a zone. An infrared moisture meter installed between the preheating zone outlet and the dehumidification zone entrance performs non-contact moisture content measurement on multiple areas of the kelp surface, acquiring multi-point moisture content data. The system collects data from at least five measurement points for each piece of kelp and calculates the average moisture content W_deh (in mass percentage). Based on the W_deh value, the dehumidification strategy model sets the dehumidification target temperature θ_deh (degrees Celsius), the dehumidification fan initial damper opening P_deh (percentage), and the dehumidification process duration D_deh (seconds). The calculation formula is as follows: θ_deh=θ_deh0- ×(W_deh-W_targ), P_deh=P_base+μ×(W_deh-W_targ), D_deh=ν×(W_deh-W_targ); where: θ_deh0 is the default dehumidification temperature (50 degrees Celsius), W_targ is the target moisture content (65%), P_base is the basic air valve opening (30%), , μ, and ν are system empirical coefficients, set to 0.5, 1.2, and 10, respectively. All parameters were obtained through fitting and analysis of historical production data. The dehumidification zone uses a heat pump dehumidification device. Temperature control is achieved through a PID regulator that automatically adjusts the heater power. The damper opening is controlled by an electric actuator to control the damper angle. Dehumidification operation baseline data is uniformly generated by the control system and transmitted to the dehumidification zone execution unit. Before the kelp unit that has completed the dehumidification process enters the three-zone drying zone, the wet weight M_wet (in grams) of each kelp piece is measured in real time using a dynamic weighing module. The relationship between M_wet and the drying target is modeled using an artificial intelligence prediction model, setting the heating drying target temperature θ_dry, the main air duct wind speed V_dry, and the drying process time D_dry. The model uses multiple regression fitting to obtain the following functional relationships: θ_dry = θ_ref + α × lg(M_wet / M_targ), V_dry = V_base + β × (M_wet - M_targ), and D_dry = γ × Where: θ_ref is the preheating reference temperature (reference value) for zone 1, M_targ is the target mass after drying (set to 15 grams), α, β, and γ are fitting coefficients, set to 5, 0.2, and 15, respectively, and V_base is the base wind speed (3 meters per second). The three-zone drying area uses a multi-stage electric heating module with a temperature control accuracy of ±1°C. A wind speed sensor provides closed-loop regulation of the main air duct. Drying time is precisely controlled in seconds. The system control module integrates θ_dry, V_dry, and D_dry to form the baseline data for the three-zone drying operation. After drying, the kelp enters the shaping area. A thermocouple temperature sensor first measures the current kelp temperature (θ_curr) in degrees Celsius. The system sets the target cooling fan air speed (V_cool) in meters per second based on the difference between θ_curr and the target cooling temperature (θ_cool) (set at 30 degrees Celsius): Δθ = θ_curr - θ_cool. This is calculated as: V_cool = V_min + σ × Δθ, where V_min is the minimum air speed (2 meters per second) and σ is the adjustment factor, set to 0.3. The cooling fan uses variable frequency control, with an adjustable speed range of 2-6 meters per second. An infrared sensor positioning system then measures the spacing and size of the kelp. This, combined with the dried kelp length (L), sets the conveyor speed (in meters per minute) to ensure that the kelp does not overlap or curl during the shaping process, achieving simultaneous cooling and shaping.

[0066] Preferably, the preheating and sweating production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes:

[0067] Based on the queue data of kelp to be dried, the kelp drying unit is controlled by a hanging conveyor belt to enter the first temperature zone of a double-line hanging multi-temperature zone double-layer tunnel drying structure;

[0068] The preheating operation of the first temperature zone is controlled by using the preheating operation benchmark data of the first zone in the kelp automated production operation parameters, and the surface temperature of the kelp drying unit is continuously monitored by a temperature sensor to obtain the kelp surface temperature distribution data;

[0069] The humidity sensor is used to sense the local microenvironment humidity around the kelp drying unit in real time and generate the local humidity of the kelp surface;

[0070] Calculate the average surface temperature of kelp and the temperature uniformity index based on the kelp surface temperature distribution data;

[0071] The current sweating state of the kelp is evaluated by the preset ideal sweating state parameters, including the local surface humidity of the kelp, the average surface temperature of the kelp, and the temperature uniformity index, to generate the kelp segmented sweating evaluation data.

[0072] In this embodiment of the present invention, the kelp drying unit feeding system utilizes a dual-track suspended conveyor structure driven by a high-precision servo motor, with a fixed conveyor speed of 0.3 m / s. The system automatically sorts the kelp into batches based on the queue data for drying, with the total weight of each batch controlled within the range of 75 ± 2 kg. The kelp units are secured with 304 stainless steel hooks, spaced 250 mm apart, and the load per hook controlled to 200 ± 20 g. The conveyor utilizes a chain-type structure with a 25 mm pitch and a mechanical strength of 3500 Newtons. The feeding mechanism is equipped with a high-resolution infrared sensor. If a kelp unit deviates more than 10 mm, it automatically triggers a correction mechanism to adjust its position. The dual-track suspension system consists of two layers, with an 800 mm spacing between them. A total of 32 hooks constitute a standard batch unit. An automatic disinfectant spray device is installed at the conveyor system entrance, with a spray pressure controlled at 0.4 MPa, to ensure that the kelp surface is free of bacterial contamination before entering the drying tunnel. Under the precise scheduling of the conveyor belt control unit, each batch of kelp units smoothly enters the first temperature zone preheating area and starts the subsequent preheating and sweating process. The first temperature zone preheating operation control is based on the predetermined first zone preheating operation benchmark data, including a preheating temperature set point of 57°C, a humidity set point of 65%, a circulating fan speed of 1300 rpm, and a preheating time of 180 seconds. The control system uses a distributed PLC controller, model Siemens S7-1500 series, which executes an operation cycle of 30 milliseconds per time. The temperature control adopts the proportional-integral-differential (PID) algorithm, with a proportional coefficient set to 2.5, an integral time of 120 seconds, and a differential time of 30 seconds, with a temperature control accuracy of ±0.5°C. 16 PT100 platinum resistance temperature sensors are installed in the first temperature zone drying room, evenly distributed around the drying room, with a sampling frequency of 2 seconds per time. Eight MLX90640 infrared array temperature sensors, with a resolution of 32×24 pixels, are aimed directly at the kelp surface for non-contact temperature measurement, with a range of 20–120°C and an accuracy of ±1°C. Each kelp drying unit's surface is divided into 5×4 temperature monitoring zones. The system continuously collects real-time temperature data from these 20 zones, forming a complete kelp surface temperature distribution matrix. Temperature data is transmitted to the central control unit via an RS485 bus with a data rate of 19,200 bps and a data collection cycle of 5 seconds. Twelve DHT22 digital thermistor humidity sensors, with a measurement range of 0–100% RH and an accuracy of ±2% RH, are deployed in the first temperature zone. These sensors are positioned at varying heights around the drying unit. Each sensor is kept within 50–100 mm of the kelp surface, forming a three-dimensional monitoring network. The sensor sampling cycle is 3 seconds, and data is transmitted to a regional data concentrator via a miniature wireless transmitter module.The system also installs a capacitive humidity sensor, model HYT271, above, below, and on both sides of each kelp cell. Its measurement range is 0–100% RH, with an accuracy of ±1.8% RH and a response time of less than 10 seconds. These sensors are connected to a regional data integration unit via an I2C bus, forming a local microenvironment humidity monitoring network. The system performs spatiotemporal fusion processing on the collected humidity data, reconstructing the humidity field around the kelp using a cubic spline interpolation algorithm with a resolution of 10 mm × 10 mm × 10 mm. After Gaussian filtering for noise reduction, the humidity data is generated into a local humidity matrix corresponding to 20 regions on the kelp surface, with a data update frequency of 5 seconds. The acquired temperature data for the 20 regions is validated, and outliers outside the normal range (25–80°C) are removed. For valid temperature points, the system assigns different weights based on the area represented by each temperature point: a weight of 1.2 for the central region, 0.8 for the peripheral region, and 1.0 for the remaining regions. The average surface temperature is calculated by multiplying the product of each zone's temperature and its corresponding weight by the total weight. The temperature uniformity index (TUI) is calculated using a modified coefficient of variation method. The standard deviation of all valid temperature points is calculated, then divided by the average temperature value, and multiplied by 100 to obtain a uniformity index expressed as a percentage. The system uses a three-level uniformity evaluation standard: an index less than 5% is considered excellent uniformity, 5%-10% is considered good uniformity, and greater than 10% is considered uneven uniformity. The system updates the average surface temperature and uniformity index calculations every 10 seconds and displays them visually on the user interface using both numerical and color-coded values. If the uniformity index exceeds 12% for three consecutive calculations, the system automatically triggers an uneven heating alarm and adjusts the heating strategy. Ideal sweating parameters are determined based on extensive historical production data and include three key indicators: a localized surface humidity range of 75%-85%, an average surface temperature range of 53-58°C, and a TUI of less than 8%. The system uses a fuzzy evaluation method to assess the current sweating state, constructing a three-dimensional state space and mapping each indicator to a scoring range of 0-100. The local humidity scoring function is a bell-shaped function, with the highest score occurring at 80% humidity; the average temperature scoring function is a trapezoidal function, with the highest score occurring in the 54-57°C range; and the uniformity index scoring function is a decreasing function, with lower indexes resulting in higher scores. The system scores the sweating state of each of the 20 zones on the kelp drying unit's surface, forming a complete segmented evaluation data matrix. The scoring weights are: 0.4 for humidity, 0.35 for temperature, and 0.25 for uniformity.The system divides the sweating state into four levels based on the comprehensive score of each area: 90 points or above is the best sweating state, 75-90 points is a good sweating state, 60-75 points is a general sweating state, and below 60 points is a poor sweating state. It generates kelp segmented sweating evaluation data, including the sweating score of each area, sweating uniformity, sweating completion percentage and remaining expected sweating time.

[0073] Preferably, the balanced dehumidification production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes:

[0074] Perform sweat difference evaluation for one area based on the segmented sweat evaluation data of kelp to generate sweat difference data for one area;

[0075] Dynamically correct the micro-air vent angle and local radiation heating power on the inner wall of the first temperature zone through the sweating difference data of the first zone, and generate dynamic fine-tuning execution data for the first zone;

[0076] Based on the dynamic fine-tuning execution data of the first zone, the kelp preheating qualification is judged. When the kelp preheating is qualified, the kelp drying unit that has completed the preheating in the first temperature zone is controlled to enter the second temperature zone. The initial temperature, air valve opening and fresh air supply amount of the second temperature zone are set according to the dehumidification operation benchmark data of the second zone in the kelp automated production operation parameters to obtain the initial environmental setting data of the second zone;

[0077] In the second temperature zone, a weighing sensor and a near-infrared moisture sensor are used to continuously monitor the real-time weight and surface moisture content changes of the kelp drying unit, calculate the water loss rate, and generate real-time water loss rate data for the second zone;

[0078] The actual local humidity and actual average wind speed around the kelp drying unit are monitored in real time through the humidity sensors and wind speed sensors in the drying temperature zone monitoring network, generating real-time local humidity and wind speed data for the second zone;

[0079] Perform abnormal dehumidification state analysis based on the real-time water loss rate data of the second zone and the real-time local wet speed data of the second zone to generate abnormal dehumidification state data;

[0080] Based on the abnormal dehumidification status data, the initial environmental setting data of the second zone is intelligently adjusted to the weak wind dehumidification mode, and the second zone discharge status of the kelp drying unit is monitored to generate the second zone discharge status data.

[0081] In this embodiment of the present invention, the system divides the kelp surface into 20 regions in a 5×4 matrix, extracts the sweating state score for each region, and calculates the standard deviation σ and coefficient of variation CV of the scores for all regions. When the standard deviation σ is greater than 8.5 or the coefficient of variation CV exceeds 15%, the system determines high variability; when the standard deviation is between 5.5-8.5 or the coefficient of variation is between 10%-15%, it is considered medium variability; and when the standard deviation is less than 5.5 and the coefficient of variation is less than 10%, it is considered low variability. The system also calculates the temperature gradient distribution on the kelp surface through thermal imaging analysis, marking areas with a temperature gradient exceeding 3.2°C / cm as critical intervention areas. The evaluation algorithm uses a weighted approach to comprehensively consider the sweating state score difference and temperature gradient, with a weight ratio of 7:3. It generates a sweating variability data package for each region, which contains the variability level, the coordinates of the key intervention areas, and the intervention priority ranking. The data is refreshed every 3 seconds. The drying chamber's inner wall is equipped with 36 independently controlled micro-vents, each equipped with a high-precision servo motor-driven guide vane. The angle can be adjusted from 0 to 85 degrees with an accuracy of ±0.5 degrees. The micro-vents have a diameter of 25 mm and a maximum air velocity of 4 m / s. They are spaced 300 mm apart and evenly distributed in a matrix pattern. The localized radiant heating system consists of 24 carbon fiber far-infrared heating units, each rated at 150 watts, with a power adjustment range of 30%-100% in 1% increments. Based on the coordinates of key intervention zones from the sweat differential data within a zone, the system precisely locates the kelp areas requiring intervention and activates the micro-vents and radiant heating units accordingly. For low-temperature, high-humidity areas, the system increases the corresponding vent angle to 55-65 degrees and boosts the radiant power to 80-90%. For high-temperature, low-humidity areas, the system decreases the vent angle to 15-25 degrees and reduces the radiant power to 40-50%. Correction parameters are calculated in real time by a PID controller with a 2-second update cycle. This generates a dynamic fine-tuning execution data matrix for Zone 1, containing 36 air outlet angle values ​​and 24 heating power values. This data is then distributed to each execution unit via the fieldbus network. The kelp preheating compliance assessment system combines Zone 1 dynamic fine-tuning execution data with real-time monitoring feedback to implement a three-stage assessment process. The first stage verifies whether the average kelp surface temperature remains stable within the range of 56±2°C for at least 30 seconds. The second stage verifies whether the sweating state score reaches 80 points or above and that inter-zone variability has been reduced to a low level. The third stage confirms whether the fine-tuning execution parameters have remained within the stable range for five consecutive adjustment cycles. Once all three stages meet the criteria, the system determines that the kelp preheating is qualified, triggering a start signal for the conveyor system. The transfer conveyor, operating at a speed of 0.2 m / s, transports the kelp drying unit to the second temperature zone. Simultaneously, the system reads the dehumidification benchmark data for Zone 2, including a target temperature of 50°C, an initial damper opening of 40%, and a fresh air supply of 25 cubic meters per minute, and sets the environmental parameters for Zone 2 accordingly.The dehumidification zone is equipped with four temperature control systems with a control accuracy of ±0.8°C; eight electric damper actuators with a control accuracy of ±1.2%; and six fresh air inlets with a flow control range of 10-60 cubic meters per minute. The system transmits the initial setpoints to the second temperature zone control unit, generating a data package for the second zone's initial environmental settings, including a matrix of temperature zone setpoints, an array of damper openings, and a fresh air supply adjustment curve. The second temperature zone's real-time monitoring system features eight high-precision HBM C16 suspended load cells installed at conveyor nodes, with a range of 0-5 kg, an accuracy of 0.01%, and a sampling frequency of 50 Hz. Each kelp drying unit is connected to the load cells via dedicated hooks, enabling continuous dynamic weighing during the drying process. The system records the initial weight, Minitial, of the kelp entering the second temperature zone and the real-time weight, Mactual, every 10 seconds. The water loss rate is calculated based on the weight change per unit time. At the same time, the system deploys 16 near-infrared moisture sensors, using 940 nm and 1450 nm dual-wavelength scanning technology, with a measurement range of 15%-95%, an accuracy of ±1.5%, and a scanning interval of 50 mm, covering all key areas of the kelp surface. The moisture content data is transmitted to the data processing unit via optical fiber, and cross-validated and calibrated in combination with weight data. The system uses a sliding window method to smooth the water loss rate data within 30 consecutive seconds, calculates the average water loss rate after eliminating outliers, and identifies the three typical stage characteristics of water loss acceleration, stability, and deceleration. All data are integrated into a two-zone real-time water loss rate data package, which includes the current water loss rate value, water loss status judgment result, moisture content distribution map, and moisture content change trend forecast. The data update cycle is 5 seconds. The drying zone monitoring network deploys a comprehensive sensing system within the second zone. This system includes 24 capacitive humidity sensors with a measurement range of 0-100% RH, an accuracy of ±1.5% RH, and a response time of less than 8 seconds; and 16 thermal wind speed sensors with a measurement range of 0-10 m / s and an accuracy of ±0.2 m / s + 3% of reading. The sensors are arranged in a matrix configuration, covering the entire dehumidification area. Vertically, the sensors are positioned at 50 mm, 200 mm, and 400 mm from the kelp surface, and horizontally, they are evenly spaced at 2-meter intervals. The data acquisition unit utilizes a 24-bit analog-to-digital converter with a sampling rate of 100 Hz, transmitting real-time data to a central processing system via an RS485 bus. The system calculates the average humidity (Hlocal) and average wind speed (Vactual) within a 200 mm radius around the kelp, while also recording the spatial gradients of humidity and wind speed. Triangular interpolation is performed on the collected raw data to generate a three-dimensional model of the humidity and wind speed fields with a resolution of 100 mm × 100 mm × 100 mm. The data processing algorithm is combined with time series analysis to identify the changing trends of humidity and wind speed, and generates real-time local humidity and wind speed data for the second zone with a 5-second update cycle, including humidity field distribution map, wind speed field distribution map, gradient change rate and microenvironment status evaluation results.The system sets a normal dehumidification reference range: a water loss rate of 0.8-1.5 g / min, a local humidity of 45%-65%, and an average wind speed of 1.8-2.5 m / s. The system constructs a dehumidification state feature vector and matches the current state against a pre-set standard pattern library to identify potential anomalies. Abnormal patterns include: moisture resistance accumulation (local humidity greater than 70%, water loss rate less than 0.6 g / min), excessive dryness (surface moisture content variation greater than 3% / min, water loss rate greater than 1.8 g / min), air duct blockage (local wind speed less than 1.2 m / s with areas of significant uneven wind speed), and thermal and moisture imbalance (local humidity and water loss rate are negatively correlated). The system uses a fuzzy inference algorithm to calculate the degree of match between the current state and each abnormal pattern, determining the type and severity of the anomaly. Severity is categorized into four levels: mild (matching degree 0.3-0.5), moderate (matching degree 0.5-0.7), severe (matching degree 0.7-0.85), and extreme (matching degree greater than 0.85). The system is equipped with eight independently controlled dehumidification fans with a power range of 0.5-2.5 kW and an air volume range of 800-4000 cubic meters per hour; 12 electric damper controllers with an opening adjustment range of 5%-100%; and four variable-frequency heaters with a power adjustment range of 3-15 kW. For moisture accumulation, the system increases the damper opening by 25% and lowers the temperature in zone 2 by 3°C. For overdryness, the system reduces air speed by 30% and increases fresh air supply by 5 cubic meters per minute. For duct blockage, the system activates auxiliary ducts and temporarily increases the main fan speed by 20%. For heat and moisture imbalance, the system adjusts the heating power to air speed ratio to maintain an optimal range of 1.8-2.2 kW·s / m. The adjustment parameters are updated every 10 seconds, and the adjustment effect is continuously monitored. At the same time, the discharge status monitoring system of Zone 2 has deployed 4 high-precision infrared moisture meters with a detection accuracy of ±1% and a scanning width of 800 mm, covering the entire width of the conveyor belt; 2 thermal imagers with a temperature resolution of 0.05°C and a pixel resolution of 384×288; and a high-precision weighing platform with an accuracy of ±5 grams. The system conducts a comprehensive inspection of the kelp that is about to leave the second temperature zone, records the moisture content, temperature distribution and weight data of the discharge, and determines whether the dehumidification effect meets the standards. When the moisture content of the kelp drops to 65%±3% and the temperature uniformity index is less than 5%, the system determines that the dehumidification is qualified, generates detailed discharge status data for Zone 2, and controls the kelp to enter the next process.

[0082] Preferably, the heating and drying production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and adjustment module includes:

[0083] Obtain the upper and lower layer load data of the third temperature zone; make upper and lower layer tunnel operation decisions based on the discharge status data of the second zone and the upper and lower layer load data of the third temperature zone, and control the kelp drying unit that has completed dehumidification in the second temperature zone to enter the third temperature zone;

[0084] According to the three-zone drying operation benchmark data in the kelp automated production operation parameters, the heating drying target temperature of the third temperature zone and the target wind speed value of the main air duct of the powerful dehumidification fan are set to obtain the initial drying environment parameters of the three zones;

[0085] Based on the initial drying environment parameters of the three zones, the kelp drying unit is heated and dried, and the real-time weight change and surface moisture content distribution of the kelp drying unit in the third temperature zone are continuously monitored to generate real-time drying status data for the three zones;

[0086] The temperature sensors and wind speed sensors in the drying temperature zone monitoring network are used to detect the actual temperature gradient and wind speed distribution around the kelp drying unit, generating local drying environment data for the three zones.

[0087] The drying uniformity index is obtained by evaluating the drying uniformity based on the real-time drying status data of the three zones and the local drying environment data of the three zones.

[0088] When the drying uniformity index is lower than the preset threshold, a drying heat energy utilization gradient analysis is performed based on the local drying environment data of the three zones, and the hanging height of the kelp drying unit is adjusted to generate three-zone drying balance adjustment data.

[0089] In the embodiment of the present invention, four infrared counters are installed at the entrances of the upper and lower tunnels respectively, with a model of TR-52H, an accuracy of 99.8%, and a sampling frequency of 10 Hz, to count the number of kelp drying units currently on each layer in real time. At the same time, eight suspended weighing sensors are deployed in the upper and lower tunnels, with a model of LCM-103, a range of 0-10 kg, and an accuracy of 0.05%, to monitor the total weight load of each layer. The system uses a data fusion algorithm to integrate the number of units and the total weight to generate a standardized load index Li with a range of 0-100. When the difference between the upper load index Lu and the lower load index Ld exceeds 15, the load balancing mechanism is triggered. The upper and lower tunnel operation decision controllers receive the discharge status data of the second zone, analyze the kelp moisture content distribution and weight parameters, and implement the optimal allocation strategy in combination with the real-time load conditions of the third temperature zone. The decision-making rules are as follows: when |Lu-Ld|>25, 100% of the new batch of kelp is allocated to the low-load tunnel; when |Lu-Ld|<15<25, the distribution ratio is 70% low-load tunnel and 30% high-load tunnel; when |Lu-Ld|≤15, intelligent diversion is implemented, with 55% heavy kelp allocated to the upper tunnel (where it has a more favorable heat-rising property) and 45% light kelp allocated to the lower tunnel. The system uses a diversion mechanism consisting of 25 pneumatically operated steering baffles to precisely guide the kelp drying units, with a controlled transfer speed of 0.25 m / s. The target drying temperature parameters are read and set at 87°C for the upper tunnel and 85°C for the lower tunnel. The temperature differential is set to offset the natural temperature gradient caused by rising hot air. The temperature control system consists of eight high-power electric heaters, each with a power output of 18 kilowatts, a temperature control accuracy of ±0.8°C, and a heating rate of 3°C / minute. The powerful dehumidification fan system includes 4 centrifugal main fans, with a single air volume of 15,000 cubic meters per hour, a speed range of 800-2400 rpm, and a wind speed adjustment accuracy of 0.1 meters per second. The target wind speed value of the main air duct is set to 9.5 meters per second based on the benchmark data, and closed-loop control is formed by real-time feedback from the wind speed sensor. The system also sets auxiliary parameters, including a 95% balance between the upper and lower air ducts, a humidity control target of 40%, and a fresh air introduction ratio of 15%. The environmental parameter actuators include 24 automatic dampers, 16 groups of humidity adjustment units, and 8 temperature adjustment loops, all of which are connected to the central controller through the on-site industrial bus network. The system fine-tunes the baseline parameters based on the characteristic parameters of the current batch of kelp in the kelp characteristic database, generates an accurate three-zone initial drying environment parameter set, and sends it to each execution unit in real time through the optical fiber network to start the temperature increase and drying process. The system implements a precise temperature ramp curve control: the first stage of the temperature ramp is from 65°C to 75°C at a rate of 2°C / minute for 2 minutes; the second stage of the temperature ramp is at a rate of 1.5°C / minute to 85°C for 5 minutes; and the third stage of the temperature ramp is slowly increased to 87°C and maintained stable. The entire temperature monitoring network is composed of 32 K-type thermocouple temperature sensors with a measurement range of 0-1000°C and an accuracy of ±0.5°C.The system also deploys 12 high-precision weighing units within the drying tunnel, with a range of 0-5 kg, an accuracy of 0.02%, and a sampling rate of 100 Hz, to record mass changes within the kelp drying unit in real time. Sixteen near-infrared spectroscopy moisture analyzers (wavelength range 900-1700 nm, resolution 2 nm) are installed every 1.5 meters along the drying tunnel, covering the entire drying area with a scanning width of 1 meter. They continuously monitor the surface moisture distribution of the kelp. The system uses a data fusion algorithm to integrate the mass change rate, moisture content gradient, and temperature response curve to generate a three-dimensional state matrix. The data processing unit uses the fourth-order Runge-Kutta method to predict moisture content trends and calculates drying efficiency indicators based on the mass change rate. The system updates data every 5 seconds, integrating key parameters such as the mass change curve, moisture content distribution, drying efficiency index, and predicted residual drying time into a real-time drying status data package for the three zones. Fifty-six PT100 platinum resistance temperature sensors were deployed throughout the tunnel, with a measurement range of 0-150°C, an accuracy of ±0.1°C, and a response time of less than 5 seconds. The three-dimensional layout formed an 8×7 sensor matrix, with probe spacing of 0.8 meters horizontally and 0.4 meters vertically. The wind speed monitoring system, comprised of 32 hot-wire wind speed sensors, had a measurement range of 0-15 m / s, an accuracy of ±0.2 m / s, and a response time of 0.2 seconds, covering all key locations in the main and auxiliary air ducts. All sensors were connected to a data acquisition system via an RS485 bus, with a sampling period of 1 second and a transmission rate of 19,200 bps. The system employed a cubic spline interpolation algorithm to reconstruct data from discrete measurement points into continuous three-dimensional temperature and wind speed fields, achieving a spatial resolution of 0.1 m × 0.1 m × 0.1 m. A data processing unit calculated the temperature gradient vector field and wind speed divergence field, identifying areas of temperature inhomogeneity and airflow dead zones. The system specifically monitors microenvironmental parameters within a 200 mm radius around the kelp drying unit, calculating the distribution of the drying driving force index (the product of temperature gradient and wind speed). Monitoring data is updated every three seconds, generating three-zone local drying environment data, including a temperature gradient distribution map, a wind speed vector map, airflow vortex identification results, and a drying driving force distribution map. Multidimensional analysis is performed based on the real-time drying status data and local drying environment data from the three zones. The system first divides the kelp surface into a 6×5 grid, with a total of 30 evaluation units, and calculates three key indicators: moisture content, drying rate, and temperature response. Moisture content uniformity is calculated using standard deviation normalization: the standard deviation of the moisture content of the 30 zones is divided by the average moisture content and multiplied by 100 to obtain a percentage index. A similar method is used to calculate the coefficient of variation of the drying rate for each zone. Temperature response uniformity is calculated using surface temperature distribution maps captured by a FLIR T640 thermal imager with a resolution of 640×480 pixels, a temperature resolution of 0.03°C, and an imaging frequency of 30 Hz.The system uses a weighted fusion algorithm to integrate three indicators, with weights assigned as follows: moisture uniformity (40%), drying rate uniformity (35%), and temperature response uniformity (25%). This results in a comprehensive drying uniformity index (DUI), which ranges from 0 to 100, with higher values ​​indicating more uniform drying. Preset thresholds are determined through statistical analysis of historical production data: the standard process threshold is set at 75, and the strict process threshold is set at 85. The system calculates the DUI value every 10 seconds and maintains a uniformity trend chart within a 10-minute sliding window. If the DUI falls below the preset threshold for three consecutive times, an uneven drying alarm is triggered, initiating the drying balance adjustment process. Three-dimensional computational fluid dynamics analysis is performed on the local drying environment data in the three zones to create a complete thermal energy flow map within the drying tunnel, identifying areas of high and low thermal energy density. The thermal energy density calculation comprehensively considers local temperature, wind speed, and humidity, and converts it into an effective drying energy density value using a heat and mass transfer model. The system calculates the thermal energy gradient distribution vertically at 5-centimeter intervals within a height range of 0-2 meters, generating a vertical thermal energy density curve. At the same time, the suspension height adjustment execution system consists of 16 groups of chain lifting devices driven by precision stepper motors. Each group has a load capacity of 50 kg, an adjustment accuracy of 1 mm, an adjustment range of 0-500 mm, and an adjustment speed of 5 mm / s. The system calculates the optimal suspension height based on the results of the thermal energy gradient analysis and the current drying state of the kelp, and makes precise height adjustments to kelp units that are drying unevenly. For kelp that dries too quickly on the top, the system moves it down 80-120 mm; for kelp that dries slowly at the bottom, the system moves it up 100-150 mm; for kelp that dries unevenly on the left and right sides, the system achieves horizontal adjustment by changing the suspension angle. All adjustment parameters are integrated into a three-zone drying balance adjustment data package, which includes the adjustment target height, adjustment rate, and adjustment sequence. It is sent to the execution unit through the industrial control network to achieve precise drying balance control.

[0090] Preferably, the cooling and shaping production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and adjustment module includes:

[0091] When the drying of the kelp drying unit in the third temperature zone meets the preset conditions, the kelp drying unit is controlled by the hanging conveyor belt to enter the fourth temperature zone of the corresponding level;

[0092] Based on the four-zone shaping operation benchmark data, the fourth temperature zone is controlled to cool down and shape. The drying temperature zone monitoring network is used to monitor the kelp surface temperature and environmental parameters until the preset shaping requirements are met. The conveyor belt target moving speed in the four-zone shaping operation benchmark data is processed to control the finished kelp drying unit to pass through the drying discharge station, completing the kelp drying production process.

[0093] The weighing sensor and near-infrared moisture content sensor are used to evaluate the final moisture content and shaping quality of the kelp drying unit in the fourth temperature zone, and the kelp dried products are graded to generate grading data for the finished kelp products.

[0094] In an embodiment of the present invention, when the kelp drying unit meets the preset conditions (moisture content reaches 22±2%, surface temperature is 60-65°C, and moisture uniformity index ≥0.9) during drying in the third temperature zone, the system triggers the transfer operation of the kelp drying unit. The preset conditions are obtained through real-time monitoring by the NIR-100 near-infrared moisture content sensor and the PT100 temperature sensor, with a sampling frequency of 2 minutes per time. When the conditions are met for three consecutive sampling results, the system determines that the transfer standard has been met. The transfer instruction is transmitted to the Siemens S7-400 PLC control unit via the industrial field bus, which drives the transfer device between the third and fourth temperature zones. The hanging conveyor belt adopts variable frequency speed control, with the initial speed set to 1.2 meters per minute. When the hanging unit approaches 5 meters from the entrance of the fourth temperature zone, the conveyor belt speed automatically decreases to 0.8 meters per minute to ensure a smooth transition. The system uses RFID readers (model JT-R340, with a read range of 3 meters) mounted at the exit of the third and entrances to the fourth temperature zone to identify the kelp units and record the precise time of transfer between zones. During transfer, the kelp drying units enter the fourth temperature zone through corresponding partition doors (electric roller shutters with an opening and closing speed of 0.5 meters per second). The monitoring system tracks the position of the units in real time, with a deviation of no more than ±10 mm. Based on standardized operational benchmark data for the four zones, the system precisely controls the environmental parameters of the fourth temperature zone using FCU fan coil units and inverter-driven fans (cooling capacity of 15 kW). Relative humidity is maintained at 35 ± 3% using a combination of ultrasonic humidifiers and dehumidifiers. The drying zone monitoring network utilizes an array of 16 temperature sensors and 8 humidity sensors with a sampling period of 30 seconds. Monitoring data is transmitted to the central control system via a data acquisition module. The system continuously monitors the kelp surface temperature. When the surface temperature drops to 30±2°C, the temperature uniformity index is ≥0.95, and the holding time reaches the benchmark value (10 minutes), the pre-set shaping requirements are met. The system then controls the conveyor line according to the target conveyor speed specified in the four-zone shaping benchmark. When the hanging unit passes the drying discharge station, a photoelectric switch (diffuse reflection type, detection range 5 meters) triggers a counter, while an infrared thermometer simultaneously monitors the final surface temperature to ensure it does not exceed 32°C. An automatic unloading mechanism (rotating, 360° turntable structure) removes the finished kelp from the hanging unit and places it on the discharge conveyor, completing the drying process. A DS-1 high-precision load cell measures the final weight of the finished kelp with an accuracy of ±1 gram. A near-infrared moisture sensor scans the finished kelp at nine points to measure its final moisture content. The system conducts a comprehensive assessment of the shaping quality of the finished kelp. The evaluation indicators include: final moisture content (target value 18±2%), color uniformity (image capture through RGB camera and calculation of standard deviation), surface hardness (elastic modulus, measured by pressure sensor), and shape retention (using 3D scanner to compare the matching degree between the original shape and the finished product shape).The system categorizes grades based on the overall score, with the following scales: Special Grade (95-100 points), Grade I (85-94 points), Grade II (75-84 points), Grade III (60-74 points), and Standard Grade (<60 points). Grading is weighted: Total score = 30% × Moisture Score + 25% × Color Score + 25% × Hardness Score + 20% × Shape Score. Each score is calculated using a normal distribution model.

[0095] Preferably, the intelligent intervention and regulation module also includes a temperature zone waste heat exchange heat compensation function, specifically:

[0096] Conduct real-time heat demand assessment for the first temperature zone and generate current heat load data for the zone;

[0097] Measure the recoverable waste heat in the hot and humid air discharged from the third temperature zone to obtain the recoverable waste heat value of the three zones;

[0098] Calculate the thermal energy utilization efficiency of the warm zone based on the recoverable waste heat value of the three zones;

[0099] When the thermal energy utilization efficiency of the temperature zone is lower than the preset thermal energy utilization threshold, the waste heat recovery channel is activated to collect waste heat from the exhaust gas discharged from the third temperature zone and generate waste heat recovery data;

[0100] The waste heat replenishment ratio is calculated based on the waste heat recovery data and the current heat load data of a zone, and the waste heat exchange heat compensation processing is performed on the first temperature zone to generate a waste heat recycling strategy.

[0101] In this embodiment of the present invention, 16 high-precision temperature sensors (model PT100, accuracy ±0.1°C) are evenly distributed throughout the preheating zone to construct a comprehensive temperature field. The system also deploys eight heat flux sensors (model HFP01, measurement range -2000 to +2000 watts / square meter, accuracy ±3%) to directly measure the heat transfer rate. Sensor data is transmitted in real time to the heat load calculation unit via a data acquisition module (sampling frequency 10 Hz, 24-bit analog-to-digital conversion accuracy). The heat load assessment algorithm calculates the current required heating power based on five key parameters: the real-time temperature field distribution, the current preheating zone load (kelp quantity and quality data provided by the feed detection system), the difference between the preset target temperature (57°C) and the current actual temperature, the heating time required, and the system heat loss (measured by the wall heat flux sensors). The system uses a sliding window method to smooth the heat load data for the past five minutes and, combined with a kelp feed prediction model, generates a heat load forecast curve for the next 30 minutes. Heat load data is measured in kilowatts and is divided into base heat load (for maintaining system temperature) and dynamic heat load (for heating newly introduced kelp). Four high-temperature thermocouples (model K, measuring range 0-1000°C, accuracy ±1.0°C) and four humidity sensors (model HX85A, measuring range 0-100% RH, high-temperature compatible, accuracy ±2% RH) are installed at the main exhaust duct inlet, evenly distributed across the duct cross-section to collect real-time exhaust gas temperature and humidity parameters. Gas flow is measured using a Pitot tube flowmeter (range 0-20 m / s, accuracy ±1.5%) installed in the center of the exhaust duct, continuously recording the exhaust flow rate. The duct cross-sectional area is 0.5 square meters, and the system calculates the volumetric flow rate by dividing the flow rate by the cross-sectional area. The waste heat calculation unit comprehensively considers three key parameters: exhaust temperature, humidity, and flow rate. Based on the principle of enthalpy calculation, it determines the sensible and latent heat carried per unit mass of air. The system takes into account the actual heat exchange efficiency limitations of the recovery process and sets a recovery coefficient of 0.7, meaning that 70% of the theoretically recoverable total heat is actually recoverable. Waste heat calculations are reported in kilowatts, updated every 15 seconds, and a complete data package containing temperature distribution, humidity distribution, flow rate, and recoverable heat values ​​is transmitted to the central control system, generating a three-zone recoverable waste heat data set. A comprehensive energy input model was established, including electric heater power (directly measured by a power transmitter with an accuracy of ±0.5%), gas heater heat output (calculated using a gas flow meter and combustion efficiency), and circulation fan power consumption (derived from inverter power feedback). The energy output model includes effective heat energy (heat used for kelp drying, calculated based on changes in kelp moisture content and mass), exhaust heat loss (based on measured recoverable waste heat values ​​in the three zones), and other heat losses (calculated using system wall temperature sensors and ambient temperature). The thermal energy utilization efficiency for each zone is calculated as the ratio of effective heat energy to total energy input, expressed as a percentage.The system features a historical data comparison function, comparing current efficiency with the average efficiency over the past seven days to identify abnormal fluctuations. Preset heat utilization thresholds are determined through big data analysis and are set at 65% for standard operating conditions, 62% for high-load conditions, and 70% for low-load conditions. Efficiency calculations are performed every minute, with results accurate to one decimal place. A comprehensive data report is generated, including real-time efficiency values, historical comparison curves, and threshold differences. If a temperature zone's heat utilization efficiency falls below the preset threshold three times in a row, the waste heat recovery mechanism is automatically triggered. The activation process first activates the electric damper actuator (Honeywell ML7421, 20 Nm torque, 90 seconds run time), turning the three-way ventilation valve in the main exhaust duct from the direct discharge position to the recovery position at a 90-degree angle. Simultaneously, the system activates the waste heat recovery fan (a variable frequency centrifugal type, 5.5 kW power, 12,000 cubic meters / hour air volume) to create the necessary airflow pressure differential. The waste heat recovery channel is constructed from stainless steel piping and houses an aluminum fin-and-tube heat exchanger. The heat exchange area is 32 square meters, with a designed heat exchange efficiency of 85%. The recovery system utilizes a dual-circuit design. The primary circuit uses ethylene glycol-water solution (30% concentration, flow rate 15 cubic meters / hour) as the heat transfer medium, driven by a 2.2 kW pipeline circulation pump (20 meters head). The real-time heat recovery monitoring system includes four flow meters (accuracy ±0.5%) and eight pairs of temperature sensors (one at the inlet and outlet, accuracy ±0.1°C). This system calculates the actual heat recovery by measuring fluid flow and the inlet and outlet temperature differential. A condensate collection device is also deployed to measure condensate flow (electromagnetic flowmeter, accuracy ±0.2%) and calculate the amount of latent heat recovered. All data is integrated into a waste heat recovery data package, which includes four core metrics: total heat recovery, sensible heat recovery, latent heat recovery, and recovery efficiency. The data is updated every 10 seconds. The waste heat replenishment ratio η (the ratio of recovered waste heat to the current heat load in a zone) is calculated and typically maintained within a range of 10%-40%. Depending on the η value, the system employs different compensation strategies: when η < 15%, a full heat replenishment mode is used, with all recovered heat used directly for heating zone 1; when 15% ≤ η < 25%, a mixed replenishment mode is used, with 85% of the recovered heat used for zone 1 and 15% used for preheating fresh air; and when η ≥ 25%, an optimized distribution mode is adopted, with 70% used for zone 1, 20% for preheating fresh air, and 10% for floor radiant heating. The heat transfer system consists of a plate heat exchanger (heat exchange area of ​​18 square meters, design pressure drop < 0.05 MPa) and a three-way control valve (accuracy ±2%, response time < 8 seconds) to ensure precise heat distribution. The zone 1 replenishment system includes four hot water coils (total heat exchange area of ​​25 square meters) and six hot air mixers to ensure even heat distribution. The control system adopts a feedforward-feedback combined control strategy, monitors the temperature field changes in one zone in real time through 12 temperature sensors, and dynamically adjusts the heat distribution ratio.The system automatically generates a 24-hour waste heat recycling strategy based on the kelp drying production plan, including a predicted heat recovery curve, distribution plan, and energy-saving benefit evaluation. It performs full-process optimization control through the central control unit, and displays the waste heat utilization status in real time on the control interface, updating the strategy data every 5 minutes.

[0102] The beneficial effects of this application are that it accurately identifies and analyzes the characteristics of kelp through intelligent perception, performs personalized treatment according to the actual conditions of different batches of kelp, accurately controls the stages according to multiple temperature zones, and provides the most suitable temperature and humidity environment for different drying stages according to the law of moisture migration during the kelp drying process, which greatly improves the rehydration and taste of the product, while shortening the drying cycle and reducing energy consumption. In particular, the intelligent intervention and adjustment in the four key stages of preheating and sweating, balanced dehumidification, heating and drying, and cooling and shaping ensures the balanced evaporation of moisture inside and outside the kelp, prevents surface conjunctiva phenomenon, forms tiny channels that are conducive to moisture discharge, and makes the product texture more uniform. The implementation of the waste heat recycling strategy significantly reduces the energy consumption of the system. Through intelligent thermal energy allocation, the waste heat in the high-temperature area is accurately compensated to the low-temperature area, and the energy utilization efficiency is improved by about 30%, achieving the purpose of energy saving and environmental protection. The double-line hanging multi-temperature zone double-layer tunnel structure design increases the production capacity by more than 50% under the same floor area, realizing the efficient use of space resources. The entire kelp drying system adopts multi-temperature zone and staged temperature control, adjustable speed, automatic control, energy saving and environmental protection, safe operation process, high degree of continuity, automation and intelligence, and the baked kelp is of uniform quality, pure and hygienic.

[0103] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0104] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A fully automated management system for kelp drying production process based on artificial intelligence, characterized in that: The AI-based fully automated management system for the kelp drying production process adopts a dual-line hanging multi-temperature zone double-layer tunnel drying structure, including the following modules: The kelp characteristic perception module is used to analyze the kelp monitoring characteristics of single pieces / clusters of fresh kelp units to obtain target kelp monitoring characteristic data; based on the target kelp monitoring characteristic data, a hanging queue layout is performed to generate queue data for kelp to be dried; The drying parameter planning module is used to automatically clean and pre-dry single pieces or clusters of fresh kelp using the queue data of the kelp to be dried, and to set the multi-temperature zone production parameters based on the monitoring characteristic data of the target kelp to obtain the automated production parameters of the kelp. An intelligent intervention and adjustment module is used to optimize multi-temperature zone kelp drying production based on automated kelp production parameters, classify the finished kelp products, and generate grading data for the dried kelp products. Multi-temperature zone kelp drying optimization includes preheating and sweating optimization, balanced dehumidification optimization, heating and drying optimization, and cooling and shaping optimization. The production parameter intelligent optimization module uses a preset convolutional neural network model to transfer learning of kelp drying product grading data and kelp automated production operation parameters, and provides automated production parameter feedback to obtain intelligent production operation parameters; Production visualization management module, used to monitor the kelp drying process in real time, so as to achieve comprehensive and transparent management of the kelp drying production process; Among them, the double-line hanging multi-temperature zone double-layer tunnel drying structure includes: Two independently operated drying lines are set up, each drying line is provided with a hanging conveyor belt, and a plurality of hanging units are installed on the hanging conveyor belt to obtain a double-line hanging conveying mechanism; Each hanging unit is equipped with a weighing sensor and a near-infrared moisture content sensor, and a three-dimensional laser scanner is deployed at the entrance of the double-line hanging transmission mechanism; The double-line hanging transmission mechanism is set to a tunnel structure, including upper and lower layers, and both the upper and lower layers can be used for the kelp carried by the hanging unit to pass through for drying, thereby obtaining a double-layer reuse tunnel structure; Along the length of the double-layer reuse tunnel structure, the multiple independent temperature zones within the tunnel are divided into at least four physically isolated temperature zones, resulting in multiple drying function temperature zones. The multiple independent temperature zones include a first temperature zone for preheating and sweating the kelp, a second temperature zone for balanced dehumidification, a third temperature zone for heating and drying, and a fourth temperature zone for cooling and setting. Independently adjustable temperature sensors, humidity sensors, and wind speed sensors are arranged on the inner walls and top partitions of the multi-section drying function temperature zones to build a drying temperature zone monitoring network.

2. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 1, characterized in that: The kelp characteristic perception module is specifically: Use a 3D laser scanner to perform non-contact contour scanning on the single piece / single cluster of fresh kelp units entering the automatic hanging station to obtain the 3D morphological data of the kelp; 3D surface reconstruction was performed based on the 3D morphological data of kelp, and the macroscopic surface area of ​​kelp was estimated; The kelp monitoring characteristics are analyzed based on the macroscopic surface area of ​​the kelp to obtain the target kelp monitoring characteristic data; wherein, the target kelp monitoring characteristic data includes the kelp wet weight data, the target kelp average thickness data and the water content at multiple points on the kelp surface; The hanging distance between the front and rear hanging units is evaluated based on the macroscopic surface area of ​​the kelp to obtain the target kelp hanging distance value; According to the target kelp hanging spacing value, the hanging unit is controlled to adjust the spacing on the conveyor chain to obtain real-time hanging queue layout data; According to the average thickness data of the target kelp and the macroscopic surface area of ​​the kelp, the spraying pressure and the spraying time are matched to obtain the spraying instructions for the cleaning area; The air knife drying parameters are set according to the target kelp monitoring characteristic data and the macroscopic surface area of ​​the kelp, and the kelp air knife drying control instructions are obtained; The real-time hanging queue layout data is used to associate the cleaning area spraying instructions and the kelp air knife drying control instructions with production instructions to obtain the kelp queue data to be dried.

3. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 2, is characterized in that: Kelp monitoring characteristics analysis based on kelp macroscopic surface area includes: Use a weighing sensor to weigh a single piece or cluster of fresh kelp to generate kelp wet weight data; The average thickness of kelp is evaluated based on the wet weight data of kelp and the macroscopic surface area of ​​kelp to obtain the target average thickness data of kelp; A near-infrared moisture content sensor is used to perform multi-point near-infrared spectral rapid scanning of a single piece or cluster of fresh kelp to generate kelp surface spectrum data. Performing baseline drift correction and filtering on the kelp surface spectrum data to generate kelp surface corrected spectrum data; The characteristic bands of the kelp surface corrected spectral data were identified using the preset kelp spectral calibration information library, and the average initial moisture content of the kelp surface was evaluated to obtain the multi-point moisture content of the kelp surface.

4. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 3 is characterized in that, The operating parameters for automated kelp production include the preheating benchmark data for zone 1, the dehumidification benchmark data for zone 2, the drying benchmark data for zone 3, and the shaping benchmark data for zone 4. The drying parameter planning module is as follows: Perform automated cleaning and blowing treatment on single piece / cluster fresh kelp units based on the queue data of kelp to be dried, generating kelp pre-cleaning status data; Processing the target preheating time of one zone according to the kelp pre-cleaning state data and the target kelp average thickness data in the target kelp monitoring characteristic data to generate the target preheating time data of one zone; The preheating circulation fan speed of the first zone is set according to the preheating target time data of the first zone, and the operation control benchmark is integrated according to the preheating target time data of the first zone to obtain the preheating operation benchmark data of the first zone; According to the multi-point moisture content of the kelp surface in the target kelp monitoring characteristic data, the dehumidification target temperature of the second temperature zone, the initial air valve target opening percentage of the dehumidification fan, and the dehumidification treatment time are planned to obtain the dehumidification operation benchmark data of the second zone; According to the wet weight data of the target kelp in the monitoring characteristic data of the target kelp, the target temperature for heating and drying, the target wind speed value of the main air duct of the powerful dehumidification fan and the duration of heating and drying treatment are set to obtain the benchmark data of the three-zone drying operation; The cooling temperature and the target air supply speed of the cooling fan are set according to the target kelp monitoring characteristic data, and the target moving speed of the conveyor belt is processed to obtain the four-zone standardized operation benchmark data.

5. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 4 is characterized in that, The preheating and sweating production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes: Based on the queue data of kelp to be dried, the kelp drying unit is controlled by a hanging conveyor belt to enter the first temperature zone of a double-line hanging multi-temperature zone double-layer tunnel drying structure; The preheating operation of the first temperature zone is controlled by using the preheating operation benchmark data of the first zone in the kelp automated production operation parameters, and the surface temperature of the kelp drying unit is continuously monitored by a temperature sensor to obtain the kelp surface temperature distribution data; The humidity sensor is used to sense the local microenvironment humidity around the kelp drying unit in real time and generate the local humidity of the kelp surface; Calculate the average surface temperature of kelp and the temperature uniformity index based on the kelp surface temperature distribution data; The current sweating state of the kelp is evaluated by the preset ideal sweating state parameters, including the local surface humidity of the kelp, the average surface temperature of the kelp, and the temperature uniformity index, to generate the kelp segmented sweating evaluation data.

6. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 5 is characterized in that: The balanced dehumidification production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes: Perform sweat difference evaluation for one area based on the segmented sweat evaluation data of kelp to generate sweat difference data for one area; Dynamically correct the micro-air vent angle and local radiation heating power on the inner wall of the first temperature zone through the sweating difference data of the first zone, and generate dynamic fine-tuning execution data for the first zone; Based on the dynamic fine-tuning execution data of the first zone, the kelp preheating qualification is judged. When the kelp preheating is qualified, the kelp drying unit that has completed the preheating in the first temperature zone is controlled to enter the second temperature zone. The initial temperature, air valve opening and fresh air supply amount of the second temperature zone are set according to the dehumidification operation benchmark data of the second zone in the kelp automated production operation parameters to obtain the initial environmental setting data of the second zone; In the second temperature zone, a weighing sensor and a near-infrared moisture sensor are used to continuously monitor the real-time weight and surface moisture content changes of the kelp drying unit, calculate the water loss rate, and generate real-time water loss rate data for the second zone; The actual local humidity and actual average wind speed around the kelp drying unit are monitored in real time through the humidity sensors and wind speed sensors in the drying temperature zone monitoring network, generating real-time local humidity and wind speed data for zone 2. Perform abnormal dehumidification state analysis based on the real-time water loss rate data of the second zone and the real-time local wet speed data of the second zone to generate abnormal dehumidification state data; Based on the abnormal dehumidification status data, the initial environmental setting data of the second zone is intelligently adjusted to the weak wind dehumidification mode, and the second zone discharge status of the kelp drying unit is monitored to generate the second zone discharge status data.

7. The fully automated management system for the kelp drying production process based on artificial intelligence according to claim 6 is characterized in that: The optimization of the drying process in the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes: Obtain the upper and lower layer load data of the third temperature zone; make upper and lower layer tunnel operation decisions based on the discharge status data of the second zone and the upper and lower layer load data of the third temperature zone, and control the kelp drying unit that has completed dehumidification in the second temperature zone to enter the third temperature zone; According to the three-zone drying operation benchmark data in the kelp automated production operation parameters, the heating drying target temperature of the third temperature zone and the target wind speed value of the main air duct of the powerful dehumidification fan are set to obtain the initial drying environment parameters of the three zones; Based on the initial drying environment parameters of the three zones, the kelp drying unit is heated and dried, and the real-time weight change and surface moisture content distribution of the kelp drying unit in the third temperature zone are continuously monitored to generate real-time drying status data for the three zones; The temperature sensors and wind speed sensors in the drying temperature zone monitoring network are used to detect the actual temperature gradient and wind speed distribution around the kelp drying unit, generating local drying environment data for the three zones. The drying uniformity index is obtained by evaluating the drying uniformity based on the real-time drying status data of the three zones and the local drying environment data of the three zones. When the drying uniformity index is lower than the preset threshold, a drying heat energy utilization gradient analysis is performed based on the local drying environment data of the three zones, and the hanging height of the kelp drying unit is adjusted to generate three-zone drying balance adjustment data.

8. The fully automated management system for kelp drying production process based on artificial intelligence according to claim 7 is characterized in that: The cooling and shaping production optimization of the multi-temperature zone kelp drying production optimization process in the intelligent intervention and regulation module includes: When the drying of the kelp drying unit in the third temperature zone meets the preset conditions, the kelp drying unit is controlled by the hanging conveyor belt to enter the fourth temperature zone of the corresponding level; Based on the four-zone shaping operation benchmark data, the fourth temperature zone is controlled to cool down and shape. The drying temperature zone monitoring network is used to monitor the kelp surface temperature and environmental parameters until the preset shaping requirements are met. The conveyor belt target moving speed in the four-zone shaping operation benchmark data is processed to control the finished kelp drying unit to pass through the drying discharge station, completing the kelp drying production process. The weighing sensor and near-infrared moisture content sensor are used to evaluate the final moisture content and shaping quality of the kelp drying unit in the fourth temperature zone, and the kelp dried products are graded to generate grading data for the finished kelp products.

9. The fully automated management system for kelp drying production process based on artificial intelligence according to claim 1 is characterized in that: The intelligent intervention and regulation module also includes the temperature zone waste heat exchange heat compensation function, specifically: Conduct real-time heat demand assessment for the first temperature zone and generate current heat load data for the zone; Measure the recoverable waste heat in the hot and humid air discharged from the third temperature zone to obtain the recoverable waste heat value of the three zones; Calculate the thermal energy utilization efficiency of the warm zone based on the recoverable waste heat value of the three zones; When the thermal energy utilization efficiency of the temperature zone is lower than the preset thermal energy utilization threshold, the waste heat recovery channel is activated to collect waste heat from the exhaust gas discharged from the third temperature zone and generate waste heat recovery data; The waste heat replenishment ratio is calculated based on the waste heat recovery data and the current heat load data of a zone, and the waste heat exchange heat compensation processing is performed on the first temperature zone to generate a waste heat recycling strategy.

Images