A tea production line automation control method and system

Abstract

The application relates to the technical field of tea production line automation control, and discloses a tea production line automation control method and system, which obtains initial state data of tea and obtains initial moisture content data according to physical property differences of fresh leaves, effectively solves the systematic deviation problem of a moisture content sensor caused by diversified fresh leaf batches in the prior art, and ensures the accuracy of initial data in a drying process. In the drying process, the method can obtain moisture state data of the tea, energy consumption data of a drying device and quality data of the tea in real time, and dynamically adjusts drying parameters based on the multidimensional data, so that the problems of low drying efficiency and unstable tea quality caused by inaccurate data of a proportional-integral-derivative controller are overcome.

Description

Technical Field

[0001] This invention relates to the field of automated control technology for tea production lines, and in particular to an automated control method and system for tea production lines. Background Technology

[0002] In modern tea processing, automated control systems are crucial for ensuring product quality and production efficiency. These systems cover multiple stages, from withering fresh leaves to drying and color sorting, through precise parameter adjustments and process management. Typically, when fresh leaves enter the production line, they undergo an initial assessment using high-precision moisture content sensors. These sensors are based on specific physical principles and are calibrated for specific production areas, harvesting seasons, and batches of fresh leaves with relatively stable moisture content. Under normal production conditions, the system accurately measures moisture content and transmits the data in real time to subsequent control modules, providing reliable initial data for the entire production process.

[0003] However, in the current market environment, due to the increasingly diversified consumer demand for tea varieties and flavors, as well as the impact of global climate change and regional supply and demand fluctuations, tea production lines often need to process batches of fresh leaves from multiple different geographical locations and ecological environments. These diverse fresh leaves may exhibit subtle but significant differences in their physical properties, such as leaf structure, surface tension, internal fiber density, cell wall thickness, and chemical composition. These differences exceed the applicable range of the original moisture content sensor calibration model. When measuring these non-standard batches of fresh leaves, the sensor's output readings begin to show systematic deviations. For example, if the sensor operates based on the principle of capacitance, changes in the internal structure or surface characteristics of the leaf will affect its dielectric constant, causing the mapping relationship between the measured capacitance value and the actual moisture content to become inaccurate, making it impossible for the system to obtain true moisture content information. This deviation is not a random error, but a systematic error with certain regularity, and is difficult to correct using simple statistical methods.

[0004] As the front-end sensing unit of the automated control system, the moisture content sensor's readings, with their systematic deviations, are directly input into the proportional-integral-derivative (PID) control module of the drying process. Drying is a crucial step in tea production, aiming to precisely control the degree of dryness to preserve aroma and flavor while avoiding over-drying or under-drying. When the moisture content data provided by the sensor contains systematic deviations, the PID controller cannot accurately determine the true dryness of the fresh leaves. For example, if the sensor consistently underestimates the actual moisture content of the fresh leaves, the controller may prematurely reduce the heating power or shorten the drying time, resulting in under-drying of the tea; conversely, if the sensor overestimates the moisture content, the controller may overheat or extend the drying time, causing the tea to become over-dried or even scorched. This inaccurate adjustment of control parameters significantly reduces drying efficiency and seriously affects the stability and consistency of tea quality.

[0005] Ultimately, the aforementioned series of problems led to severe distortion of batch production information. Because the screening standards in the color sorting process were artificially relaxed, the "pass rate" data recorded by the automated control system was artificially inflated, failing to accurately reflect the actual quality of the products. Simultaneously, the system accurately recorded abnormally high energy consumption data in the drying process due to tea stain buildup and inefficient operation. These two types of distorted data contaminated the entire batch production information tracking and recording data structure. When managers conducted data analysis, they found "normal" pass rates but "abnormal" energy consumption. This contradictory data prevented them from accurately assessing the true quality of batch products, tracing the root cause of quality problems, and effectively managing and optimizing energy consumption using conventional data analysis methods. This information distortion not only affected the decision-making of production managers but also weakened the transparency and traceability of the entire automated control system, rendering the data-driven quality control and production optimization system completely ineffective.

[0006] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0007] This invention provides an automated control method and system for tea production lines, aiming to solve the problems of inaccurate drying control, distorted batch production information, and difficulties in energy consumption management and quality traceability caused by systematic deviations of moisture content sensors when handling diverse batches of fresh leaves in existing automated control systems for tea production lines.

[0008] Firstly, in order to solve the above-mentioned technical problems, the present invention provides an automated control method for a tea production line, comprising: The initial state data of tea leaves is obtained, and the initial moisture content data is obtained based on the differences in the physical characteristics of fresh leaves in the initial state data. During the drying process, based on the initial moisture content data, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves are obtained. Adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data; Based on the quality data and energy consumption data, the accuracy of batch production is corrected, and the degradation of the physical performance of the drying equipment is identified.

[0009] Preferably, adjusting the drying parameters based on the moisture state data, the energy consumption data, and the quality data includes: An array of sensors is deployed inside the drying chamber to collect data on heat transfer efficiency and airflow velocity in local areas. Based on the heat transfer efficiency data and the airflow velocity data, identify local heat conduction efficiency degradation and uneven airflow distribution. When a decrease in local heat conduction efficiency or uneven airflow distribution is detected, a local compensation mechanism is activated to address the transient and inconsistent local physical environment inside the drying chamber by injecting high-pressure air or steam or adjusting the power of the local heating element. Through the local compensation mechanism, the self-optimizing regulator obtains a stable feedback signal and records the trigger frequency and compensation intensity of local compensation. When the trigger frequency or the compensation intensity reaches a preset value, a maintenance warning is issued. Based on the moisture content data, energy consumption data, and quality data, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency.

[0010] Preferably, adjusting the drying parameters based on the moisture state data, the energy consumption data, and the quality data includes: The drying process is divided into multiple drying stages; Based on the current drying stage, set the priority and adjustment range for the drying parameters; Based on the moisture state data, energy consumption data, and quality data of the current drying stage, calculate the comprehensive benefit score for the current stage. Based on the comprehensive benefit score, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. If the parameter adjustment in the current drying stage causes the overall benefit score to show a downward trend in subsequent drying stages, the parameter adjustment strategy for the current drying stage should be retrospectively adjusted.

[0011] Preferably, the step of correcting the accuracy of batch production based on the quality data and the energy consumption data, and identifying the decline in the physical performance of the drying equipment, includes: Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. Cross-analysis is performed on the heat transfer efficiency data, the airflow distribution data, the heating element operating status data, and the air duct sealing data to identify the type of degradation inside the drying equipment; Based on the described degradation type, the impact of each degradation on energy consumption and tea quality is quantified; Based on the quantitative impact, the accuracy of batch production is corrected, and maintenance alerts are provided.

[0012] Preferably, the step of correcting the accuracy of batch production based on the quantified impact and providing maintenance early warnings includes: Continuously monitor the production load data and environmental condition data of the drying equipment; Based on the production load data and environmental condition data, the quantitative impact of degradation on energy consumption and tea quality is dynamically adjusted. Based on the dynamically adjusted degradation impact, the production load data, and the preset production plan, the maintenance warnings are prioritized. The maintenance alerts, ordered by priority, are distributed to maintenance personnel.

[0013] Preferably, the step of dynamically adjusting the quantitative impact of degradation on energy consumption and tea quality based on the production load data and the environmental condition data includes: Continuously monitor the production load data and environmental condition data of the drying equipment; Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. A correlation analysis is performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types. Based on the aforementioned coupling effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified. Based on the independent effects described, the quantitative impact of the degradation on energy consumption and tea quality is adjusted.

[0014] Preferably, the correlation analysis of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types includes: Multivariate time series analysis was performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data. The multivariate time series analysis is used to obtain the temporal correlation and lag between data sequences, and to identify the nonlinear or dynamic coupling effects between degradation types. Based on the identified coupling effects, the quantitative model of the degradation effect is adjusted.

[0015] Preferably, the step of decoupling and quantifying the independent effects of each degradation on energy consumption and tea quality based on the coupling effect includes: During the long-term continuous operation of the drying equipment, the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element working status data, and air duct sealing data of the drying equipment are continuously monitored. A calibration procedure that periodically triggers degraded coupling effects; In the calibration procedure, historical trends of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data within the current time period are obtained. By analyzing the historical trends, patterns of coupling effects among various degradation types that evolve over time can be identified. Based on the evolution pattern, the quantification parameters of the coupling effect are adjusted to correct the decoupling and quantification results of the degradation effect. Based on the corrected decoupling and quantification results of the degradation effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified.

[0016] Secondly, the present invention provides an automated control module for a tea production line, comprising: The first acquisition module is used to acquire the initial state data of tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of fresh leaves in the initial state data. The second acquisition module is used to acquire, during the drying process, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves based on the initial moisture content data. The adjustment module is used to adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data. The calibration module is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment.

[0017] Thirdly, the present invention provides an automated control system for a tea production line, comprising: The input terminal is used to acquire the initial state data of the tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of the fresh leaves in the initial state data. The adjustment end is used to acquire, during the drying process, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves based on the initial moisture content data; and to adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data. The calibration end is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment. This invention provides an automated control method and system for a tea production line. By acquiring initial state data of the tea leaves and obtaining initial moisture content data based on the differences in the physical characteristics of fresh leaves, it effectively solves the problem of systematic deviation of moisture content sensors caused by diverse batches of fresh leaves in existing technologies, ensuring the accuracy of initial data during the drying process. During the drying process, this method can acquire real-time data on the moisture state of the tea leaves, the energy consumption data of the drying equipment, and the quality data of the tea leaves. Based on this multi-dimensional data, it dynamically adjusts the drying parameters, thereby overcoming the problems of low drying efficiency and unstable tea quality caused by inaccurate data in existing proportional-integral-derivative controllers. Furthermore, through comprehensive analysis of quality data and energy consumption data, this method can correct the accuracy of batch production and identify the decline in the physical performance of the drying equipment, effectively solving the problems of distorted batch production information, falsely high pass rates, and difficulty in tracing abnormal energy consumption in existing technologies. In summary, the technical solution of this application can significantly improve the accuracy, stability, and traceability of automated control in tea production lines, effectively ensuring the consistency of tea quality, reducing production energy consumption, and providing reliable data support for production managers' decision-making, thus overcoming the shortcomings of existing technologies and achieving unexpected technical effects. Attached Figure Description

[0018] Figure 1 This is a flowchart of an automated control method for a tea production line provided in an embodiment of the present invention; Figure 2 This is a flowchart of a method for adjusting drying parameters provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an automated control module for a tea production line provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an automated control system for a tea production line provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Reference Figure 1 , Figure 1 This is a flowchart of an automated control method for a tea production line provided by an embodiment of the present invention, including the following steps: S1, Obtain the initial state data of the tea leaves, and obtain the initial moisture content data based on the differences in the physical characteristics of the fresh leaves in the initial state data; S2, During the drying process, based on the initial moisture content data, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves are obtained; S3, adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data; S4. Based on the quality data and energy consumption data, correct the accuracy of batch production and identify the decline in the physical performance of the drying equipment.

[0021] In modern tea processing, automated control systems are crucial for ensuring product quality and production efficiency. These systems cover multiple stages, from withering fresh leaves to drying and color sorting, through precise parameter adjustments and process management. Typically, when fresh leaves enter the production line, they undergo an initial assessment using high-precision moisture content sensors. These sensors are based on specific physical principles and are calibrated for specific production areas, harvesting seasons, and batches of fresh leaves with relatively stable moisture content.

[0022] Under normal production conditions, the system can accurately measure moisture content and transmit the data to subsequent control modules in real time, providing reliable initial data for the entire production process. However, in the current market environment, due to the increasingly diversified consumer demand for tea varieties and flavors, as well as the impact of global climate change and regional supply and demand fluctuations, tea production lines often need to process batches of fresh leaves from multiple different geographical locations and ecological environments. These diverse fresh leaves may exhibit subtle but significant differences in their physical properties, such as leaf structure, surface tension, internal fiber density, cell wall thickness, and chemical composition. These differences exceed the applicable range of the original moisture content sensor calibration model. When measuring these non-standard batches of fresh leaves, the sensor's output readings begin to show systematic deviations.

[0023] For example, if the sensor operates based on the principle of capacitance, changes in the internal structure or surface characteristics of the leaves will affect their dielectric constant, causing the mapping between the measured capacitance value and the actual moisture content to become inaccurate, making it impossible for the system to obtain true moisture content information. This deviation is not a random error, but a systematic error with certain regularity, and it is difficult to correct through simple statistical methods. As the front-end sensing unit of the automated control system, the systematic deviation of the moisture content sensor readings is directly input into the proportional-integral-derivative (PID) control module of the drying process. Drying is a crucial step in tea production, aiming to precisely control the degree of dryness of the tea leaves to preserve their aroma and flavor while avoiding over-drying or under-drying. When there is a systematic deviation in the moisture content data provided by the sensor, the PID controller cannot accurately determine the true dryness state of the fresh leaves.

[0024] For example, if the sensor consistently underestimates the actual moisture content of the fresh leaves, the controller may prematurely reduce the heating power or shorten the drying time, resulting in insufficient drying of the tea. Conversely, if the sensor overestimates the moisture content, the controller may overheat or extend the drying time, causing the tea to become over-dried or even scorched. This inaccurate adjustment of control parameters significantly reduces drying efficiency and severely affects the stability and consistency of tea quality. Ultimately, these problems lead to serious distortion of batch production information. Because the screening standards in the color sorting process are artificially relaxed, the "pass rate" data recorded by the automated control system appears artificially high and cannot truly reflect the actual quality of the product.

[0025] Meanwhile, the system also accurately recorded the abnormally increased energy consumption during the drying process due to tea stain buildup and inefficient operation. These two types of distorted data contaminated the entire batch production information tracking data structure. When managers analyzed the data, they found that the pass rate was "normal" while energy consumption was "abnormal." This contradictory data prevented them from accurately assessing the true quality of the batch products, tracing the root cause of quality problems, or effectively managing and optimizing energy consumption using conventional data analysis methods. This information distortion not only affected the production managers' decisions but also weakened the transparency and traceability of the entire automated control system, rendering the data-driven quality control and production optimization system completely ineffective.

[0026] To address this issue, this application proposes an automated control method for a tea production line. By acquiring initial state data of the tea leaves and analyzing the differences in the physical characteristics of the fresh leaves based on this initial state data, initial moisture content data is obtained, thus more accurately reflecting the true moisture content of the tea leaves. During the drying process, based on the initial moisture content data, data on the moisture state of the tea leaves within the drying chamber, energy consumption data of the drying equipment, and quality data of the tea leaves are acquired, providing comprehensive information for subsequent parameter adjustments. Furthermore, based on the moisture state data, energy consumption data, and quality data, drying parameters are adjusted to achieve more precise drying control. Finally, based on the quality data and energy consumption data, the accuracy of batch production is corrected, and the decline in the physical performance of the drying equipment is identified, thereby effectively solving the problems of low drying efficiency, unstable tea quality, and distorted batch production information caused by inaccurate initial moisture content data in existing technologies.

[0027] This embodiment provides an automated control method for a tea production line, aiming to solve problems such as low drying efficiency, unstable tea quality, and distorted batch production information caused by inaccurate initial moisture content data when processing diverse batches of fresh leaves in existing tea production lines. This method optimizes the acquisition of initial moisture content by incorporating consideration of the differences in the physical characteristics of fresh leaves, and comprehensively utilizes multi-dimensional data for parameter adjustment and equipment status monitoring during the drying process, thereby improving the level of automation control and product quality in tea production.

[0028] "Initial state data" refers to a series of physical and chemical property measurements of fresh tea leaves before they enter the drying process, such as the type, origin, harvesting time, leaf size, color, and surface moisture. This data reflects the original characteristics of the fresh leaves and forms the basis for subsequent processing. "Differences in physical properties of fresh leaves" refers to the inherent differences in structure, density, and moisture content distribution between different batches of fresh leaves. These differences affect the rate of moisture evaporation and heat transfer efficiency. "Initial moisture content data" is a value that more accurately reflects the actual moisture content of the fresh leaves after correction based on these differences in physical properties.

[0029] "Drying chamber" refers to the internal space of tea drying equipment used to hold and dry tea leaves. "Moisture state data" refers to real-time data on the moisture content, water activity, and evaporation rate of the tea leaves' interior and surface during the drying process. "Energy consumption data" refers to data on the electrical and thermal energy consumed by the drying equipment during operation, used to evaluate drying efficiency and cost. "Quality data" refers to the sensory and physicochemical indicators of the dried tea leaves, such as color, aroma, taste, shape, and purity, used to evaluate the final quality of the tea.

[0030] "Drying parameters" refer to the various adjustable process parameters during the drying process, such as drying temperature, humidity, wind speed, drying time, and turning frequency. These parameters directly affect the drying effect and quality of the tea. "Accuracy of batch production" refers to whether the moisture content, quality, energy consumption, and other indicators of the tea in a specific production batch meet the preset standards and targets, and whether the production records accurately reflect the actual situation. "Degradation of the physical performance of the drying equipment" refers to the performance degradation of the drying equipment during long-term operation due to wear, aging, contamination, and other reasons, such as reduced heat transfer efficiency, uneven airflow, and heating element failure.

[0031] The core of the automated control method for the tea production line in this embodiment lies in the optimization and intelligent upgrading of the traditional drying control process.

[0032] Firstly, various methods can be used to acquire initial state data of tea leaves. For example, multispectral imaging technology can be used to scan fresh leaves, and by analyzing the reflectance or absorption spectra at different wavelengths, information such as chlorophyll content, cell structure, and surface wax layer thickness can be obtained. This information reflects the differences in the physical properties of the fresh leaves. Alternatively, near-infrared spectroscopy can be used to quickly and non-destructively acquire information on the chemical composition and moisture content of fresh leaves by measuring their absorption of near-infrared light. Furthermore, machine vision systems can be used to identify and classify the shape, size, and color of fresh leaves, and combined with a pre-set database, their physical properties can be inferred. After obtaining the initial state data, based on the differences in the physical properties of the fresh leaves in the initial state data, machine learning models, such as support vector machines or neural networks, can be used to correct the original moisture content sensor data. This model can be pre-trained with a large amount of experimental data on fresh leaves with different physical properties, learning the mapping relationship between the differences in the physical properties of fresh leaves and the deviation of the moisture content sensor readings. When a new batch of fresh leaves arrives, the system acquires its initial state data and inputs it into the trained model. The model then outputs a correction factor to correct the initial moisture content data measured by the sensor, thereby obtaining more accurate initial moisture content data.

[0033] Secondly, during the drying process, based on the initial moisture content data, the moisture state data of the tea leaves inside the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves are obtained. Moisture state data can be obtained by arranging multiple humidity and temperature sensors within the drying chamber to monitor the temperature and humidity changes of the environment surrounding the tea leaves in real time. This data, combined with the weight change data of the tea leaves (obtained through a weighing sensor), is used to calculate the real-time moisture content and evaporation rate of the tea leaves. Energy consumption data can be collected in real time by installing electricity meters or calorimeters on key components of the drying equipment, such as heating units and fans. Quality data can be obtained using an online spectral analyzer, such as a visible / near-infrared spectrometer, to scan the tea leaves during drying in real time. Analysis of spectral characteristics is used to evaluate quality indicators such as color and aroma precursor content. Furthermore, a machine vision system can be used to monitor the shape and integrity of the tea leaves in real time.

[0034] Next, the drying parameters are adjusted based on the moisture content data, energy consumption data, and quality data. For example, a fuzzy logic controller or an adaptive PID controller can be used. The fuzzy logic controller can take the moisture content data, energy consumption data, and quality data as inputs according to preset fuzzy rules and output corresponding adjustments to the drying parameters. For example, when the moisture evaporation rate is too fast and the quality data shows a risk of scorching in the tea leaves, the controller can lower the drying temperature or increase the humidity. The adaptive PID controller can dynamically adjust the PID parameters based on real-time data to better adapt to the nonlinearity and time-varying nature of the drying process. For example, when the moisture content of the tea leaves is close to the target value, the PID controller can reduce the proportional gain to avoid overshoot.

[0035] Finally, based on the quality data and energy consumption data, the accuracy of batch production is corrected, and the decline in the physical performance of the drying equipment is identified. The correction of batch production accuracy can be achieved by establishing a comprehensive evaluation model. This model takes the quality data of the dried tea leaves (e.g., grades obtained through sensory evaluation or physicochemical analysis) and the energy consumption data of the entire batch as inputs and compares them with standard data from historical batches. If the quality data of the current batch is good but the energy consumption is abnormally high, it may indicate an efficiency problem in the drying process, requiring correction of production accuracy. The identification of the decline in the physical performance of the drying equipment can be achieved through trend analysis of energy consumption data. For example, under the same production load and environmental conditions, if the energy consumption of the drying equipment continues to increase, it may indicate a decline in physical performance such as decreased heating element efficiency, blocked air ducts, or poor sealing. Furthermore, by analyzing the temperature distribution data of different areas within the drying chamber, it is possible to identify whether there are localized overheating or cooling zones, thereby determining whether the equipment has experienced a decline in physical performance.

[0036] The automated control method for tea production lines in this embodiment acquires initial state data of the tea leaves and obtains initial moisture content data based on the differences in the physical characteristics of the fresh leaves. This solves the systematic bias problem of traditional moisture content sensors when processing diverse batches of fresh leaves. By considering the differences in the physical characteristics of fresh leaves, this method can more accurately assess the true moisture content of the fresh leaves, providing reliable initial data for the subsequent drying process.

[0037] During the drying process, this method acquires data on the moisture state of the tea leaves within the drying chamber, the energy consumption of the drying equipment, and the quality of the tea leaves based on the initial moisture content data. This real-time acquisition of multi-dimensional data allows the control system to comprehensively understand all key indicators of the drying process, rather than relying solely on a single moisture content figure. This contrasts sharply with existing technologies that primarily rely on simple PID control based on sensor readings, significantly improving the comprehensiveness and accuracy of the data input. Furthermore, this method adjusts drying parameters based on the moisture content data, energy consumption data, and quality data. This parameter adjustment strategy, based on multi-dimensional data fusion, enables more precise control of the drying process, avoiding over-drying or under-drying caused by deviations in a single data point. For example, when the moisture content data shows a high tea moisture content, but the quality data indicates that aroma substances are beginning to volatilize, the system can prioritize adjusting the temperature or airflow to maximize the preservation of tea quality while ensuring the drying effect. This effectively distinguishes it from the problems of low drying efficiency and unstable tea quality caused by inaccurate moisture content data in existing technologies.

[0038] Ultimately, this method corrects the accuracy of batch production based on the quality data and energy consumption data, and identifies the decline in the physical performance of the drying equipment. Through cross-analysis of quality data and energy consumption data, this method can identify distortions in batch production information, such as inflated pass rates or abnormal increases in energy consumption, thereby providing a true assessment of production performance. Simultaneously, by analyzing trends in energy consumption data, it can promptly detect declines in the physical performance of the drying equipment, such as tea stain buildup and aging heating elements, thus enabling predictive maintenance and preventing equipment failures from impacting production. This represents a significant improvement over existing technologies that suffer from severely distorted batch production information, making it impossible to accurately assess product quality and trace the root causes of problems.

[0039] In summary, the automated control method for tea production lines in this embodiment comprehensively improves the level of automation in tea production by incorporating considerations of differences in the physical characteristics of fresh leaves, adjusting drying parameters through multi-dimensional data fusion, and correcting batch production accuracy and identifying equipment performance degradation. This method not only solves a series of problems in existing technologies, such as inaccurate initial moisture content data, low drying efficiency, unstable tea quality, and distorted batch production information, but also achieves refined management and optimization of the tea production process through real-time monitoring and intelligent adjustment, providing strong technical support for producing high-quality, highly consistent tea products.

[0040] In some embodiments described above, while adjusting drying parameters based on moisture content data, energy consumption data, and quality data is proposed, the physical environment inside the drying chamber often exhibits temporal and inconsistencies during actual tea drying. For example, localized decreases in heat transfer efficiency or uneven airflow distribution can lead to poor overall adjustment of drying parameters, affecting the uniformity of tea drying and its final quality. Therefore, this application further proposes optimizing the steps for adjusting drying parameters by introducing a local compensation mechanism to more precisely address changes in the local physical environment inside the drying chamber, thereby improving the control precision and effectiveness of the drying process.

[0041] For details, please refer to Figure 2 , Figure 2 This is a flowchart of a method for adjusting drying parameters provided in an embodiment of the present invention, which can be further refined into the following operations: S21, deploy an array of sensors inside the drying chamber to collect data on heat transfer efficiency and airflow velocity in local areas; S22, Based on the heat transfer efficiency data and the airflow velocity data, identify local heat conduction efficiency decreases and uneven airflow distribution; S23, when the decrease in local heat conduction efficiency or the uneven airflow distribution is detected, a local compensation mechanism is activated to cope with the instantaneous and inconsistent local physical environment inside the drying chamber by injecting high-pressure air or steam or adjusting the power of the local heating element. S24, through the local compensation mechanism, the self-optimizing regulator obtains a stable feedback signal and records the trigger frequency and compensation intensity of local compensation. When the trigger frequency or the compensation intensity reaches a preset value, a maintenance warning is issued. S25, based on the moisture state data, the energy consumption data, and the quality data, adjust the drying parameters to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency.

[0042] The sensor array refers to a network of multiple sensors strategically positioned within the drying chamber to acquire more detailed and comprehensive local environmental data than a single sensor. Heat transfer efficiency data reflects the effectiveness of heat transfer to the tea leaves in a specific area, while airflow velocity data characterizes the intensity and uniformity of airflow in that area. By comparing data from different areas with preset benchmarks or data from adjacent areas, it is possible to determine if there are areas where heat transfer is obstructed or airflow is stagnant. The local compensation mechanism aims to correct local environmental problems through targeted intervention.

[0043] Specifically, local airflow or heat transfer can be improved by injecting high-pressure air or steam, or local temperature can be precisely controlled by adjusting the power of local heating elements, thereby effectively addressing the transient and inconsistent local physical environment within the drying chamber. The self-optimizing regulator is an intelligent system capable of autonomously learning and adjusting its control strategy based on feedback information. The local compensation mechanism, by smoothing out fluctuations in the local environment, provides the self-optimizing regulator with purer and more representative global feedback, enabling it to more accurately optimize overall drying parameters. Simultaneously, the system records the trigger frequency and intensity of local compensation. When the trigger frequency or compensation intensity reaches a preset value—for example, if the compensation mechanism in a certain area is frequently activated or requires high-intensity compensation to maintain stability—the system will issue a maintenance warning, indicating potential mechanical failure or performance degradation in the equipment, requiring inspection and maintenance.

[0044] This application's solution, by deploying a sensor array within the drying chamber, can acquire real-time, precise data on localized heat transfer efficiency and airflow velocity, overcoming the limitations of traditional methods that rely solely on overall or average data and cannot accurately capture localized environmental changes. Because it can identify localized decreases in heat transfer efficiency and uneven airflow distribution, this application can promptly activate a local compensation mechanism. This mechanism directly and precisely intervenes in the instantaneous and inconsistent local physical environment by injecting high-pressure air or steam, or adjusting the power of localized heating elements. This localized, dynamic intervention effectively smooths out microscopic fluctuations within the drying chamber, providing a more stable and reliable feedback signal for the self-optimizing regulator, allowing adjustments to overall drying parameters to be based on more accurate environmental perception. Simultaneously, by recording the trigger frequency and intensity of localized compensation and issuing maintenance warnings accordingly, this application enables early prediction of potential degradation trends in the drying equipment, fundamentally avoiding reduced drying efficiency and uneven quality caused by localized performance degradation.

[0045] Through the above technical solution, this application can significantly improve the automation control precision of the tea drying process and its adaptability to the complex environment inside the drying chamber. Compared with the basic solution that only adjusts the overall parameters, this application effectively solves the problem of the instantaneous and inconsistent local physical environment inside the drying chamber through a local compensation mechanism, thereby ensuring that the tea is heated evenly and the moisture loss is consistent throughout the drying process, ultimately significantly improving the consistency of tea quality. In addition, by monitoring the trigger frequency and compensation intensity of local compensation and issuing maintenance warnings, this application also realizes the early identification and preventive maintenance of potential faults in the drying equipment, effectively reducing the equipment failure rate and maintenance costs, extending the service life of the equipment, and further ensuring the stable and efficient operation of the production line.

[0046] In some embodiments described above, a scheme for adjusting drying parameters based on moisture content data, energy consumption data, and quality data was proposed. However, in the actual tea drying process, the physicochemical properties of tea change significantly as moisture content decreases, resulting in the need for adjusting drying parameters not remaining constant throughout the drying cycle. If a single or static adjustment strategy is adopted, it may not adequately meet the specific needs of different drying stages, leading to suboptimal energy consumption, difficulty in ensuring consistent tea quality, and even potential unnecessary damage to the tea at certain stages.

[0047] In this regard, this application further proposes the following steps for adjusting the drying parameters: The drying process is divided into multiple drying stages; Based on the current drying stage, set the priority and adjustment range for the drying parameters; Based on the moisture state data, energy consumption data, and quality data of the current drying stage, calculate the comprehensive benefit score for the current stage; Based on the comprehensive benefit score, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. If the parameter adjustment in the current drying stage causes the overall benefit score to show a downward trend in subsequent drying stages, the parameter adjustment strategy for the current drying stage should be retrospectively adjusted.

[0048] Specifically, dividing the drying process into multiple drying stages refers to logically dividing the entire drying cycle into several sub-stages with different drying characteristics based on the changing patterns of key indicators such as moisture content, temperature, and enzyme activity during the drying process. For example, it can be divided into a preheating stage, a constant-rate drying stage, a decreasing-rate drying stage, and a final drying stage. The criteria for dividing each stage can be based on preset time thresholds, moisture content thresholds, or temperature thresholds.

[0049] The setting of adjustment priorities and ranges for drying parameters based on the current drying stage can be understood as pre-setting the focus and range of adjustment for drying parameters (such as temperature, wind speed, and humidity) at different drying stages. For example, in the constant-speed drying stage, priority may be given to quickly removing moisture, so the adjustment range can be larger; while in the slow-speed drying stage or the final drying stage, priority may be given to maintaining the aroma and color of the tea, so the adjustment range will be relatively smaller, and the priority of temperature adjustment will be higher than that of wind speed.

[0050] In practical applications, based on the moisture content data, energy consumption data, and quality data of the current drying stage, a comprehensive benefit score for the current stage is calculated. Specifically, this involves establishing a multi-objective optimization model to quantify the current tea moisture content, energy consumption efficiency, and quality indicators (such as color, aroma, and taste), and calculating a comprehensive score based on preset weighting coefficients. This score aims to comprehensively measure the merits of the current drying parameter settings, providing a quantitative basis for subsequent parameter adjustments.

[0051] Furthermore, adjusting the drying parameters based on the comprehensive benefit score to achieve the target moisture content of the tea, reduce energy consumption, and improve quality consistency refers to the system using a preset control algorithm (such as PID control, fuzzy control, or machine learning model) to adjust parameters such as temperature, wind speed, and humidity of the drying equipment in real time based on the calculated comprehensive benefit score. The goal of the adjustment is to continuously optimize the comprehensive benefit score, thereby ensuring that the moisture content of the tea reaches the preset target while minimizing energy consumption and improving the consistency of tea quality between batches.

[0052] Furthermore, when parameter adjustments in the current drying stage cause a downward trend in the overall benefit score in subsequent drying stages, the system can retrospectively adjust the parameter adjustment strategy for the current drying stage. This demonstrates the system's forward-looking and error-correcting capabilities. Through predictive models or historical data analysis, the potential impact of parameter adjustments in the current stage on the overall benefit score in subsequent drying stages is assessed. Once a downward trend in the score in subsequent stages is predicted, the system will immediately activate the retrospective mechanism to reassess and adjust the parameter adjustment strategy for the current drying stage that caused the downward trend, thereby avoiding potential negative impacts and ensuring global optimization of the entire drying process.

[0053] This application's solution breaks down the complex tea drying process into multiple manageable drying stages, allowing for more refined and targeted drying objectives and parameter adjustment strategies for each stage. By dynamically setting adjustment priorities and magnitudes at each stage, the system can flexibly prioritize moisture removal, energy efficiency, or quality maintenance based on the actual needs of the tea at different drying stages. The introduction of a comprehensive benefit score provides a quantitative, multi-dimensional evaluation standard, ensuring that drying parameter adjustments are no longer a single-objective optimization but rather a comprehensive consideration of the balance between moisture content, energy consumption, and quality. More importantly, by introducing a parameter adjustment backtracking mechanism, this application's solution effectively avoids the problem of local optima leading to global suboptimal results; that is, optimization at the current stage does not come at the expense of performance in subsequent stages. When the system predicts that a current adjustment may have a negative impact on subsequent stages, it can correct it in a timely manner, thereby ensuring the stability and optimality of the entire drying process and significantly improving the intelligence and adaptability of automated control.

[0054] Through the above technical solution, this application enables refined and intelligent control of the tea drying process. Compared to traditional single or static parameter adjustment methods, this application, through multi-stage division and dynamic priority setting, makes the adjustment of drying parameters more targeted and flexible, thereby significantly improving energy utilization efficiency and reducing production costs. Simultaneously, the introduction of comprehensive benefit scoring ensures that while pursuing efficiency, tea quality is more effectively guaranteed and improved, and batch-to-batch quality consistency is significantly improved. Most importantly, the parameter adjustment backtracking mechanism endows the system with self-learning and error-correction capabilities, effectively avoiding global performance degradation caused by local optimization, ensuring the robustness and optimality of the entire drying process, and ultimately producing higher quality, more competitive tea products.

[0055] In some embodiments described above, this application proposes using quality data and energy consumption data to correct batch production accuracy and identify degradation in the physical performance of drying equipment. However, relying solely on macroscopic quality and energy consumption data may not be sufficient to accurately diagnose the specific types of degradation within the drying equipment and their subtle impact on the production process, leading to insufficient accuracy in correction or inadequate timeliness of maintenance warnings. Therefore, this application further proposes a more refined method that involves in-depth analysis of the equipment's internal physical performance data to achieve more accurate batch correction and more targeted maintenance warnings.

[0056] The above-mentioned methods for correcting the accuracy of batch production based on the quality data and energy consumption data, and for identifying the decline in the physical performance of the drying equipment, include: Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. Cross-analysis is performed on the heat transfer efficiency data, the airflow distribution data, the heating element operating status data, and the air duct sealing data to identify the type of degradation inside the drying equipment; Based on the described degradation type, the impact of each degradation on energy consumption and tea quality is quantified; Based on the quantitative impact, the accuracy of batch production is corrected, and maintenance alerts are provided.

[0057] Specifically, collecting data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber involves deploying various sensors within the drying chamber, such as thermocouples, wind speed sensors, current / voltage sensors, and pressure sensors, to acquire key parameters reflecting the physical state of the equipment in real time or periodically. The aim is to comprehensively monitor the operating status of the drying equipment from multiple dimensions, providing detailed foundational data for subsequent degradation identification.

[0058] The cross-analysis of heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data can be understood as using data mining, pattern recognition, or machine learning techniques to comprehensively compare and correlate different types of data. For example, when the heat transfer efficiency of a certain area decreases, the airflow distribution in that area becomes abnormal, and the corresponding heating element's operating status shows normal, it may indicate a problem with the duct sealing. The aim is to extract meaningful degradation patterns from complex data relationships, thereby identifying specific types of internal equipment degradation, such as heating element aging, duct blockage, and seal failure.

[0059] In practical applications, based on the aforementioned degradation types, the impact of each degradation on energy consumption and tea quality is quantified. Specifically, this involves establishing mathematical models or empirical curves relating degradation types to the increase in energy consumption and the degree of decline in tea quality. For example, historical data analysis can show that a 10% blockage in the air duct leads to a 5% increase in energy consumption and a 2% decrease in the uniformity of tea drying. The aim is to transform abstract degradation phenomena into measurable economic and quality indicators, providing a quantitative basis for subsequent decision-making.

[0060] Therefore, by quantifying the impact, the system can correct the accuracy of batch production and provide maintenance warnings. This means that based on the quantified degradation effects, the system can more accurately adjust the drying parameters of the current batch to compensate for the negative effects of equipment degradation, ensuring that tea quality and energy efficiency meet preset targets. Simultaneously, when a certain degradation reaches a preset threshold, the system will promptly issue a maintenance warning, prompting maintenance personnel to inspect or repair, thus achieving a shift from reactive maintenance to proactive prevention.

[0061] This application's solution overcomes the limitations of relying solely on macroscopic quality and energy data for correction and identification by introducing refined collection and analysis of physical performance data within the drying chamber. Specifically, by collecting data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing, the system obtains microscopic details of the equipment's operating status. After cross-analysis of this detailed data, the specific types of degradation leading to decreased drying efficiency or uneven quality can be accurately identified, such as localized heating element failure, uneven airflow due to duct blockage, or heat loss caused by aging seals. Furthermore, by quantifying the specific impact of each type of degradation on energy consumption and tea quality, the system can establish a direct correlation between the degree of degradation and production efficiency. This quantification allows the system to adjust parameters specifically when correcting batch production accuracy. For example, if a decrease in heat transfer efficiency is identified in a certain area, the system can appropriately increase the heating power or extend the drying time in that area to compensate for heat loss. Simultaneously, when the degradation reaches a certain level, the system can issue timely maintenance warnings, prompting maintenance personnel to intervene before the problem worsens, thereby avoiding production losses and quality fluctuations caused by hidden equipment degradation.

[0062] Through the aforementioned technical solution, this application significantly improves the precision and predictive capability of automated control in tea production lines. Compared to relying solely on macroscopic data for judgment, this solution achieves precise identification and quantification of degradation types and their impacts through in-depth monitoring and analysis of the internal physical properties of the equipment. This not only allows for more accurate correction of batch production parameters, ensuring that tea moisture content meets targets, energy consumption is reduced, and quality consistency is improved, but also transforms maintenance warnings from passive response to proactive prevention. This proactive prevention mechanism helps extend the service life of drying equipment, reduces the risk of unplanned downtime, and optimizes maintenance resource allocation, thereby bringing higher economic benefits and more stable product quality to tea production enterprises.

[0063] In some preferred embodiments, assuming that after a tea drying production line has been running continuously for a period of time, the system, through a sensor array deployed within the drying chamber, collects data showing that the heat transfer efficiency in the first region is consistently below normal levels. Simultaneously, airflow distribution data in this region shows the presence of localized eddies, while the heating element's operating status data indicates normal power output. After cross-analyzing this data, the system identifies the degradation type as a decrease in the air duct sealing in the first region, leading to heat loss and airflow turbulence. Furthermore, based on historical data and a preset model, the system quantifies that this level of air duct sealing degradation would increase the energy consumption of the current batch of tea by 3%, and decrease the drying uniformity of the tea in this region by 1.5%. Based on this quantified impact, the system automatically adjusts the drying parameters, for example, slightly increasing the drying temperature and extending the drying time, to compensate for heat loss and ensure drying uniformity.

[0064] At the same time, since the deterioration of the air duct sealing has reached the preset maintenance threshold, the system will immediately issue a maintenance warning to the maintenance personnel, prompting them to check and repair the air duct sealing in the first area, thereby avoiding greater losses and quality problems caused by the continued deterioration of sealing issues.

[0065] In some embodiments described above, this application proposes a scheme to quantify the impact of degradation type on energy consumption and tea quality, and to correct the accuracy of batch production and provide maintenance warnings accordingly. However, in actual tea production, the production load data of drying equipment and external environmental conditions are dynamically changing. These factors significantly affect the actual performance of equipment degradation and its true impact on production efficiency and product quality. If maintenance warnings are provided solely based on static degradation quantification results, the accuracy and timeliness of the warnings may be insufficient, failing to effectively cope with the complex and ever-changing production environment, thereby affecting the rational allocation of maintenance resources and the continuous and stable operation of the production line.

[0066] In this regard, this application further proposes that the steps mentioned above for correcting the accuracy of batch production based on quantified impact and providing maintenance alerts include: Continuously monitor the production load data and environmental condition data of the drying equipment; Based on the production load data and environmental condition data, the quantitative impact of degradation on energy consumption and tea quality is dynamically adjusted. Based on the dynamically adjusted degradation impact, the production load data, and the preset production plan, the maintenance warnings are prioritized. The maintenance alerts, ordered by priority, are distributed to maintenance personnel.

[0067] Specifically, continuously monitoring the production load data and environmental condition data of the drying equipment refers to acquiring the current operating status of the equipment in real time, such as production load information like the amount of tea leaves fed, drying batches, and operating time, as well as environmental condition information such as temperature, humidity, and air pressure outside the drying chamber. The purpose is to provide real-time contextual information for subsequent dynamic adjustments. Dynamically adjusting the quantitative impact of degradation on energy consumption and tea quality based on the production load data and environmental condition data can be understood as using this real-time data to correct a pre-established degradation impact model.

[0068] For example, under high production loads or high ambient humidity, even slight degradation of heating elements can lead to a more significant increase in energy consumption or a decline in quality, thus requiring a higher quantification of the degradation impact. The aim is to make the assessment of degradation impact more closely reflect actual operating conditions.

[0069] In practical applications, maintenance warnings are prioritized based on dynamically adjusted degradation impacts, production load data, and pre-set production plans. Specifically, this involves comprehensively considering the severity of degradation impacts, the urgency of current production tasks, and future production schedules to assess the importance of necessary maintenance operations. For example, even a moderate degradation warning might be elevated to high priority for an upcoming critical batch production run. The aim is to ensure that maintenance resources are prioritized for the most critical and urgent maintenance tasks.

[0070] Furthermore, distributing the prioritized maintenance alerts to maintenance personnel refers to sending priority-ranked maintenance notifications to the relevant technical personnel or maintenance teams through an automated system. For example, notifications can be sent via SMS, email, or internal system messages, along with detailed degradation information and suggested maintenance measures. The aim is to achieve accurate delivery of maintenance information and timely maintenance response.

[0071] This application's solution introduces continuous monitoring of drying equipment production load data and environmental condition data, enabling dynamic adjustment of the quantitative impact of degradation on energy consumption and tea quality based on actual operating conditions. Because the quantification of degradation impact is no longer static but reflects the real-time production environment and load, the accuracy of maintenance early warnings is significantly improved. Based on this, by combining the dynamically adjusted degradation impact, current production load data, and preset production plans, maintenance early warnings are prioritized, ensuring that maintenance resources are allocated rationally and efficiently. In this way, the system can identify the most critical degradation issues under specific production conditions, avoiding unnecessary maintenance and promptly addressing key issues that could significantly impact production.

[0072] Through the above technical solution, this application overcomes the limitations of traditional static degradation assessment, making maintenance early warning more accurate and timely. Dynamically adjusting the quantification of degradation impact ensures that the assessment of equipment degradation impact under different production load data and environmental conditions truly reflects its actual impact on energy consumption and tea quality. Furthermore, prioritizing maintenance early warnings allows maintenance personnel to address the most critical equipment issues based on actual needs and resource availability, avoiding blind maintenance or delays in critical maintenance, thereby significantly improving maintenance efficiency and the overall operational stability of the production line, and reducing the risk of unplanned downtime and operating costs.

[0073] In some embodiments described above, while a method for dynamically adjusting the quantitative impact of degradation on energy consumption and tea quality based on production load data and environmental condition data is proposed, in actual drying equipment operation, various degradation types (such as decreased heat transfer efficiency, uneven airflow distribution, heating element failure, and duct sealing problems) often do not occur independently but may have complex interactions or coupling effects. If these coupling effects are not considered, simply superimposing or independently evaluating the impact of each degradation type may lead to misjudgments of the actual equipment performance degradation, thereby affecting the accuracy of batch production correction and maintenance warnings, resulting in less than ideal dynamic adjustment effects. Therefore, this application further proposes a more refined dynamic adjustment method. By performing correlation analysis on multi-source data, it identifies and decouples the coupling effects between various degradation types, thereby more accurately quantifying the independent impact of each degradation type on energy consumption and tea quality, achieving more precise dynamic adjustment.

[0074] The above-mentioned dynamic adjustment of the quantitative impact of degradation on energy consumption and tea quality based on production load data and environmental condition data includes: Continuously monitor the production load data and environmental condition data of the drying equipment; Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. A correlation analysis is performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types. Based on the aforementioned coupling effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified. Based on the independent effects described, the quantitative impact of the degradation on energy consumption and tea quality is adjusted.

[0075] Specifically, continuously monitoring the production load data and environmental condition data of the drying equipment refers to acquiring the current operating status of the drying equipment in real time through sensors and system interfaces. This includes data related to production load such as the amount of tea processed, operating time, set temperature, and humidity, as well as environmental condition data such as temperature and humidity outside the drying chamber. This data provides macroscopic operational background information for subsequent correlation analysis.

[0076] The collection of data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber involves using various sensors deployed within the chamber, such as thermocouples, heat flow meters, wind speed sensors, pressure sensors, and current and voltage sensors for the heating elements, to obtain detailed data on key physical parameters within the equipment. Heat transfer efficiency data reflects the effectiveness of heat transfer to the tea leaves; airflow distribution data reveals the uniformity of airflow within the drying chamber; heating element operating status data indicates the health and output power of the heating components; and duct sealing data assesses the integrity of the hot air circulation system. These data provide direct evidence for identifying the type and extent of equipment degradation.

[0077] Furthermore, correlation analysis is performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types. This can be understood as using data analysis techniques, such as multivariate statistical analysis and machine learning algorithms (e.g., correlation analysis, regression analysis, cluster analysis, neural networks), to explore the interrelationships and influence mechanisms between different types of data. The aim is to discover whether the occurrence of one type of degradation accelerates or slows down other degradations, or whether the combined effects of multiple degradations exhibit a non-linear additive characteristic on energy consumption and tea quality. For example, a decrease in duct sealing may lead to uneven airflow distribution, thereby affecting local heat transfer efficiency.

[0078] In practical applications, decoupling and quantifying the independent impact of each type of degradation on energy consumption and tea quality, based on the aforementioned coupling effect, refers to identifying the coupling relationship between degradation types and then establishing a mathematical model or algorithm to separate these interrelated influences, thereby accurately calculating the independent contribution of each degradation type in the absence of other degradation interferences. For example, partial least squares, structural equation modeling, or decoupling algorithms based on physical models can be used to separate the coupling effect from the total impact, obtaining specific quantitative values ​​for the increase in energy consumption and decrease in tea quality caused by each type of degradation (such as decreased heat transfer efficiency, uneven airflow, etc.). The purpose is to avoid duplicate calculations or omissions caused by coupling effects and ensure the accuracy of the degradation impact assessment.

[0079] Therefore, adjusting the quantitative impact of degradation on energy consumption and tea quality based on the aforementioned independent effects means that after obtaining the independent quantitative impact of each type of degradation, it is used as a more precise input to update and adjust the previously established degradation impact quantification model. For example, if it is found that uneven airflow distribution and decreased heat transfer efficiency are positively coupled, and after decoupling, it is found that the independent impact of uneven airflow distribution is greater than previously estimated, then the weight or impact coefficient of uneven airflow distribution in the quantification model will be increased accordingly. The purpose is to make the basis for dynamic adjustment closer to the actual operating conditions of the equipment and improve the accuracy of the adjustment.

[0080] The proposed solution constructs a comprehensive data acquisition system by continuously monitoring the production load data and environmental condition data of the drying equipment, and combining this data with heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data in different areas of the drying chamber.

[0081] Building upon this foundation, by performing correlation analysis on these multi-source data, we can deeply uncover and identify the complex coupling effects that may exist between various degradation types. It is precisely because these coupling effects have been identified that this application can further decouple these coupled influences, thereby accurately quantifying the independent impact of each degradation type on energy consumption and tea quality. This decoupling mechanism avoids the potential for double counting or underestimation of degradation effects in traditional methods, making the assessment of equipment performance degradation more accurate. Ultimately, based on these more precise independent effects, the quantitative impact of degradation on energy consumption and tea quality is dynamically adjusted, providing a more reliable and refined basis for subsequent batch production accuracy correction and maintenance early warning, effectively solving the problem of insufficient adjustment accuracy caused by the failure to consider degradation coupling effects in the basic scheme.

[0082] Through the above technical solutions, this application enables a more comprehensive and in-depth understanding of the degradation mechanisms within drying equipment, especially when multiple degradation types coexist and influence each other. By identifying and decoupling the coupling effects between degradation types, a more accurate independent quantitative impact of each degradation type on energy consumption and tea quality can be obtained, significantly improving the accuracy of degradation assessment. This precise quantitative impact allows for more accurate correction of batch production accuracy, and the prioritization and distribution of maintenance warnings are more targeted, effectively avoiding misjudgments and unnecessary maintenance caused by degradation coupling effects, reducing operating costs, and further ensuring the consistency of tea production quality and energy efficiency.

[0083] This application further proposes the above-mentioned correlation analysis of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types, including: Multivariate time series analysis was performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data. The multivariate time series analysis is used to obtain the temporal correlation and lag between data sequences, and to identify the nonlinear or dynamic coupling effects between degradation types. Based on the identified coupling effects, the quantitative model of the degradation effect is adjusted.

[0084] Specifically, "multivariate time series analysis" refers to an advanced statistical analysis method that aims to simultaneously analyze two or more interrelated time series data to reveal their dynamic relationships, interdependencies, and patterns of change over time. For example, methods such as vector autoregression (VAR) models, Granger causality tests, dynamic time warping (DTW) algorithms, or state-space models can be used for analysis. Its purpose is to uncover hidden, time-varying patterns and potential causal relationships from complex, interrelated production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data.

[0085] The "temporal correlation and lag" mentioned here can be understood as the mutual influence relationship between different data sequences in the time dimension. Temporal correlation indicates the degree of correlation between two or more variables at different points in time, while lag refers to the time delay required for a change in one variable to affect another. For example, a change in the operating state of a heating element may lead to a decrease in heat transfer efficiency within the drying chamber only after a period of time, or an increase in ambient humidity may not significantly affect the air duct sealing performance until several hours later. By identifying these temporal correlations and lags, the evolution of the degradation process and the transmission path of its effects can be understood more accurately.

[0086] In practical applications, the "nonlinear or dynamically changing coupling effect" specifically refers to the fact that the relationship between degradation types is not a simple linear superposition, but rather a complex interaction that may vary with operating conditions or time stages. For example, in low-temperature and high-humidity environments, slight degradation of duct sealing may have a nonlinear amplification effect with a decrease in heating element efficiency, leading to a sharp increase in energy consumption. Alternatively, the coupling mode of degradation factors may dynamically change during the initial startup and stable operation phases of equipment. These nonlinear or dynamically changing coupling modes can be identified through multivariate time series analysis, for example, by introducing nonlinear terms or using nonlinear models for modeling.

[0087] Furthermore, the "quantitative model for adjusting the effects of degradation" refers to modifying and optimizing the mathematical model used to assess the impact of each type of degradation on energy consumption and tea quality based on the identified coupling effects. For example, if a significant nonlinear coupling effect is found between the decrease in heating element efficiency and uneven airflow distribution, an interaction term or nonlinear function needs to be introduced into the quantitative model to accurately describe this combined effect, rather than simply calculating the two independently. The aim is to enable the quantitative model to more accurately reflect the combined effects of various degradation factors in actual production and improve the accuracy of predictions.

[0088] This application's solution, by introducing multivariate time series analysis, can deeply explore the complex temporal correlations and lags between production load data, environmental condition data, heat transfer efficiency data in different areas of the drying chamber, airflow distribution data, heating element operating status data, and duct sealing data. It is precisely because of the dynamic changes and interactions of these data over time that traditional static or simple correlation analysis struggles to capture the nonlinear or dynamic coupling effects between different types of degradation. By comprehensively analyzing these multi-source, heterogeneous time series data, deeper mechanisms can be revealed, such as how heating element aging and decreased duct sealing jointly accelerate heat loss under specific production loads, or how changes in environmental humidity lag influencing the uniformity of airflow distribution. This precise identification of coupling effects allows for more accurate adjustment of the quantitative model of degradation impacts, thereby avoiding evaluation biases caused by neglecting complex interactions.

[0089] Through the aforementioned technical solution, this application can more comprehensively and accurately identify the complex coupling effects between various degradation types within drying equipment, especially those coupling relationships exhibiting time-series correlation, hysteresis, and nonlinear or dynamic changes. Compared to simple correlation analysis, multivariate time series analysis can reveal deeper degradation mechanisms, resulting in more accurate decoupling and quantification of the independent impact of each degradation type on energy consumption and tea quality. This precise quantification of degradation impact further improves the reliability of batch production accuracy correction and enables maintenance warnings to be prioritized and distributed based on a more realistic and comprehensive equipment status, effectively guiding maintenance personnel to perform precise maintenance, reducing the risk of unplanned downtime, and ultimately optimizing the overall operating efficiency and product quality stability of the tea production line.

[0090] In some embodiments described above, this application proposes identifying the coupling effects between various degradation types through correlation analysis, and thereby decoupling and quantifying the independent impact of each degradation type on energy consumption and tea quality. However, during the long-term continuous operation of drying equipment, the coupling effects between various degradation types are not static; they may dynamically evolve with changes in time, production load, or environmental conditions. If this dynamic nature of the coupling effects is not addressed, decoupling and quantification based solely on static or initially identified coupling effects may lead to inaccurate assessments of degradation impacts, thereby affecting the accuracy of batch production corrections and the reliability of maintenance warnings. Therefore, this application further proposes a method for dynamically adjusting the quantification parameters of degradation coupling effects through periodic calibration and historical trend analysis to ensure the accuracy of the decoupling and quantification results of degradation effects.

[0091] Based on the aforementioned coupling effect, the independent effects of each type of degradation on energy consumption and tea quality are decoupled and quantified, specifically including: During the long-term continuous operation of the drying equipment, the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element working status data, and air duct sealing data of the drying equipment are continuously monitored. A calibration procedure that periodically triggers degraded coupling effects; In the calibration procedure, historical trends of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data within the current time period are obtained. By analyzing the historical trends, patterns of coupling effects among various degradation types that evolve over time can be identified. Based on the evolution pattern, the quantification parameters of the coupling effect are adjusted to correct the decoupling and quantification results of the degradation effect. Based on the corrected decoupling and quantification results of the degradation effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified.

[0092] Specifically, during the long-term continuous operation of the drying equipment, continuous monitoring of its production load data, environmental condition data, heat transfer efficiency data in different areas of the drying chamber, airflow distribution data, heating element operating status data, and duct sealing data refers to the uninterrupted collection of data related to the equipment's operating status and environmental conditions through sensors deployed at various key locations within the drying equipment. This data includes, but is not limited to, the equipment's current production volume, ambient temperature, humidity, temperature at different locations within the drying chamber, airflow velocity, heating element power output, and whether there are air leaks in the ducts. The purpose is to provide comprehensive and real-time foundational data for subsequent degradation analysis and calibration.

[0093] The periodic calibration procedure for triggering degradation coupling effects can be understood as the system automatically initiating a process specifically designed to evaluate and update the degradation coupling model at preset time intervals (e.g., every few hours, daily, or weekly) or when specific events occur (e.g., production batch changeover, after equipment maintenance). Its purpose is to ensure that the decoupling and quantification model of degradation effects can adapt to long-term changes in equipment operating conditions and environmental conditions.

[0094] In the calibration procedure, acquiring historical trends of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data within the current time period refers to the system retrieving records of changes in various data monitored over a past period (e.g., the most recent 24 hours, 7 days, or longer) from the database when the calibration procedure is triggered. These historical trend data may include statistical characteristics such as average, maximum, minimum, fluctuation range, and rate of change. The purpose is to provide a temporal reference for identifying the dynamic evolution of deterioration coupling effects.

[0095] Analyzing historical trends to identify patterns in the coupling effects between various degradation types over time involves using data analysis algorithms (e.g., time series analysis, regression analysis, machine learning models) to deeply mine acquired historical trend data and discover how the intensity, direction, and form of the interactions between different degradation types change over time. For example, the correlation between uneven airflow distribution and decreased heating efficiency may strengthen as equipment wear intensifies. The aim is to capture the dynamic characteristics of degradation coupling effects, making its quantitative model more adaptable.

[0096] Adjusting the quantification parameters of the coupling effect according to the evolution pattern to correct the decoupling and quantification results of the degradation impact means that once the evolution pattern of the coupling effect is identified, the system will update the parameters in the mathematical model or algorithm used for decoupling and quantifying the degradation impact accordingly. For example, if a certain coupling effect is found to become more significant under specific conditions, the weight of that coupling effect in the model will be increased. The purpose is to ensure that the decoupling and quantification results accurately reflect the true independent impact of various degradations on energy consumption and tea quality under the current equipment condition.

[0097] This application's solution effectively addresses the dynamic nature of degradation coupling effects by introducing a periodic calibration procedure and historical trend analysis. Specifically, during the long-term continuous operation of the drying equipment, multi-dimensional data is continuously monitored, providing a comprehensive information foundation for subsequent analysis. The periodically triggered calibration procedure ensures that the system can periodically review and update the degradation coupling model. During the calibration procedure, by acquiring and analyzing historical trend data, patterns in the evolution of coupling effects between degradation types over time can be identified. For example, the strength or nature of the mutual influence of certain degradations may change during specific operating phases or after accumulated operating time. Based on these identified evolution patterns, the system can dynamically adjust the quantitative parameters used to decouple and quantify degradation effects, thereby correcting the decoupling and quantification results of degradation effects. This dynamic adjustment mechanism enables the system to more accurately separate the independent impacts of each degradation on energy consumption and tea quality, avoiding evaluation biases caused by changes in coupling effects, thus providing a more reliable basis for batch production accuracy correction and maintenance early warning.

[0098] Through the above technical solution, this application enables dynamic and accurate assessment of the coupled effects of degradation on drying equipment. Compared to methods relying solely on static coupling models, this application, through continuous monitoring, periodic calibration, and historical trend analysis, allows the decoupling and quantification results of degradation effects to adapt in real time to long-term changes in equipment operating status and environmental conditions. This significantly improves the accuracy of assessing the independent impact of each type of degradation on energy consumption and tea quality, thereby enabling more refined accuracy correction for batch production and greatly enhancing the reliability and timeliness of maintenance warnings. Ultimately, this helps extend equipment lifespan, reduce operating costs, and ensure the continuous stability of tea product quality.

[0099] refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an automated control module for a tea production line provided in an embodiment of the present invention, comprising: The first acquisition module is used to acquire the initial state data of tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of fresh leaves in the initial state data. The second acquisition module is used to acquire, during the drying process, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves based on the initial moisture content data. The adjustment module is used to adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data. The calibration module is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment.

[0100] This application also discloses the aforementioned automated control module for a tea production line, aiming to solve problems such as low drying efficiency, unstable tea quality, and distorted batch production information caused by inaccurate initial moisture content data when processing diverse batches of fresh leaves in existing tea production lines. By considering the differences in the physical characteristics of fresh leaves through the first acquisition module, the acquisition of initial moisture content is optimized, thus providing more accurate initial data for subsequent processing. The second acquisition module acquires multi-dimensional data in real time during the drying process, providing a comprehensive decision-making basis for the adjustment module. Based on this data, the adjustment module makes precise adjustments to the drying parameters to optimize the drying effect. Finally, the calibration module, through comprehensive analysis of quality data and energy consumption data, corrects the accuracy of batch production and identifies equipment performance degradation, thereby improving the level of automated control and product quality in tea production, and achieving refined management and optimization of the production process.

[0101] This embodiment provides an automated control module for a tea production line, which aims to achieve intelligent control of key aspects of the tea production line through modular design.

[0102] The "first acquisition module" can be understood as a hardware or software unit responsible for data acquisition and preprocessing. Specifically, this module can be a standalone embedded system integrating sensor interfaces and processing chips; alternatively, it can serve as a software service module of the central control unit, interacting with external sensor systems via an application programming interface (API). As a preferred embodiment, the first acquisition module can consist of one or more sensors (e.g., multispectral imaging sensors, near-infrared spectral sensors, machine vision sensors) and a data processing unit configured with a pre-trained machine learning model. Its purpose is to provide accurate initial moisture content data, overcoming the limitations of traditional sensors when processing diverse batches of fresh leaves. The above embodiments have already described the specific implementation of acquiring initial state data of tea leaves and obtaining initial moisture content data based on the differences in the physical characteristics of the fresh leaves in the initial state data, which will not be repeated here.

[0103] The "second acquisition module" can be understood as a hardware or software unit that continuously monitors and collects data during the drying process. Specifically, this module may include multiple distributed sensor networks, such as humidity sensors, temperature sensors, weighing sensors, energy meters, calorimeters, and online spectrometers. These sensors are deployed at key locations inside and outside the drying chamber to collect real-time data on moisture status, energy consumption, and quality.

[0104] The second acquisition module can be a data acquisition server or an industrial PC connected to various sensor interfaces. Its purpose is to provide comprehensive, real-time, multi-dimensional information for subsequent parameter adjustments. The above embodiments have already described the specific implementation method for acquiring the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves based on the initial moisture content data during the drying process, and will not be repeated here.

[0105] The "adjustment module" can be understood as a control unit that dynamically optimizes drying parameters based on real-time data. Specifically, this module can be a programmable logic controller (PLC) or an industrial computer, internally running a fuzzy logic controller, an adaptive PID controller, or a model-based predictive control algorithm. This module receives data from the second acquisition module and, based on a preset control strategy or self-learning algorithm, calculates and outputs optimal drying parameters such as temperature, humidity, wind speed, and drying time. In practical applications, the adjustment module can be a standalone control cabinet or integrated into the main control system of the production line. Its purpose is to achieve precise control of the drying process, ensuring optimal tea quality and energy consumption. The specific implementation method of adjusting drying parameters based on the moisture state data, energy consumption data, and quality data has been described in the above embodiments and will not be repeated here.

[0106] The "calibration module" can be understood as an analytical unit that assesses the accuracy of production batches and diagnoses equipment performance. Specifically, this module can be a data analysis server configured with data mining and pattern recognition algorithms. This module receives quality data and energy consumption data from the second acquisition module and compares them with historical data and preset standards to identify batch production accuracy deviations. Furthermore, this module can perform trend analysis on energy consumption data and, combined with other equipment operating parameters, identify the decline in the physical performance of the drying equipment. The calibration module can be an independent diagnostic system or a functional module of an Enterprise Resource Planning (ERP) system, aiming to provide accurate production performance assessments and enable predictive maintenance of equipment. The specific implementation methods for calibrating batch production accuracy and identifying the decline in the physical performance of the drying equipment based on the quality data and energy consumption data have been described in the above embodiments and will not be repeated here.

[0107] Traditional automated control systems for tea production lines suffer from systematic deviations in initial moisture content sensor readings when processing diverse batches of fresh leaves from different geographical locations and ecological environments. This leads to low drying efficiency, unstable tea quality, and ultimately, severely distorted batch production information, making it impossible for managers to accurately assess product quality and trace the root cause of problems.

[0108] To address this issue, this application proposes a modular automated control module for a tea production line. This module, through a first acquisition module that considers the differences in the physical characteristics of fresh leaves, solves the problem of inaccurate initial moisture content data at its source, providing a reliable foundation for subsequent control. Compared to the limitations of existing technologies that rely solely on sensor readings, this module's second acquisition module can acquire multi-dimensional data in real time, including moisture status, energy consumption, and quality data, greatly enriching the control system's sensing capabilities. Based on this, the adjustment module can intelligently adjust drying parameters based on this comprehensive data, avoiding the inaccuracy caused by data deviations in traditional PID control, and significantly improving drying efficiency and the consistency of tea quality. Furthermore, the correction module, through cross-analysis of quality and energy consumption data, can effectively identify and correct distortions in batch production information and provide timely warnings of equipment performance degradation, thereby achieving transparent management and predictive maintenance of the production process—something impossible in existing technologies.

[0109] Through the above modular design, the control module of this application not only solves a series of interrelated technical problems in the prior art, but also provides a solution with higher integration and stronger intelligence, significantly improving the level of automation control and overall efficiency of tea production.

[0110] refer to Figure 4 , Figure 4 This is a schematic diagram of an automated control system for a tea production line provided in an embodiment of the present invention, comprising: The input terminal is used to acquire the initial state data of the tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of the fresh leaves in the initial state data. The adjustment end is used to acquire, during the drying process, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves based on the initial moisture content data; and to adjust the drying parameters based on the moisture state data, the energy consumption data, and the quality data. The calibration end is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment.

[0111] Traditional automated control systems in existing tea production lines often rely on a single, pre-calibrated moisture content sensor when handling diverse batches of fresh leaves, leading to systematic biases in the initial data. This bias further affects the precise control of the drying process, resulting in low drying efficiency, unstable tea quality, and ultimately distorted batch production information, making effective quality traceability and energy consumption management difficult.

[0112] To address this issue, this application proposes an automated control system for a tea production line. By setting an input terminal to acquire initial state data of the tea leaves, and based on the differences in the physical characteristics of the fresh leaves, initial moisture content data is obtained, thus more accurately reflecting the true moisture content of the tea. During the drying process, by setting an adjustment terminal, data on the moisture state of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves are acquired based on the initial moisture content data. Drying parameters are then adjusted based on these data to achieve more precise drying control. Finally, by setting a calibration terminal, the accuracy of batch production is corrected based on the quality data and energy consumption data, and the decline in the physical performance of the drying equipment is identified. This effectively solves the problems of low drying efficiency, unstable tea quality, and distorted batch production information caused by inaccurate initial moisture content data in existing technologies.

[0113] This embodiment provides an automated control system for a tea production line, aiming to solve problems such as low drying efficiency, unstable tea quality, and distorted batch production information caused by inaccurate initial moisture content data when processing diverse batches of fresh leaves in existing tea production lines. This system optimizes the acquisition of initial moisture content by incorporating consideration of the differences in the physical characteristics of fresh leaves, and comprehensively utilizes multi-dimensional data for parameter adjustment and equipment status monitoring during the drying process, thereby improving the level of automation control and product quality in tea production.

[0114] The "input end" refers to the set of hardware and software modules used by the system to acquire initial state data of tea leaves and correct for moisture content based on differences in the physical characteristics of fresh leaves. Its purpose is to provide accurate initial moisture content data. The "adjustment end" refers to the set of hardware and software modules used by the system to monitor the moisture state of tea leaves, equipment energy consumption, and tea quality in real time during the drying process, and dynamically adjust drying parameters accordingly. Its purpose is to achieve refined control of the drying process. The "correction end" refers to the set of hardware and software modules used by the system to evaluate the accuracy of batch production and identify deterioration in the physical performance of the drying equipment. Its purpose is to provide accurate production performance evaluation and equipment maintenance early warning.

[0115] The automated control system for the tea production line in this embodiment comprehensively improves the level of automation in tea production by incorporating considerations of differences in the physical characteristics of fresh leaves, adjusting drying parameters through multi-dimensional data fusion, and correcting batch production accuracy and identifying equipment performance degradation. This system not only solves a series of problems in existing technologies, such as inaccurate initial moisture content data, low drying efficiency, unstable tea quality, and distorted batch production information, but also achieves refined management and optimization of the tea production process through real-time monitoring and intelligent adjustment, providing strong technical support for producing high-quality, highly consistent tea products.

[0116] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An automated control method for a tea production line, characterized in that, include: The initial state data of tea leaves is obtained, and the initial moisture content data is obtained based on the differences in the physical characteristics of fresh leaves in the initial state data. During the drying process, data on the moisture state of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves are acquired. An array of sensors is deployed inside the drying chamber to collect data on heat transfer efficiency and airflow velocity in local areas. Based on the heat transfer efficiency and airflow velocity data, local decreases in heat conduction efficiency and uneven airflow distribution are identified. When a decrease in local heat conduction efficiency or uneven airflow distribution is detected, a local compensation mechanism is activated. This is achieved by injecting high-pressure air or steam, or by adjusting the power of local heating elements, to address the transient and inconsistent local physical environment within the drying chamber. Through this local compensation mechanism, a self-optimizing regulator obtains a stable feedback signal and records the trigger frequency and intensity of local compensation. When the trigger frequency or compensation intensity reaches a preset value, a maintenance warning is issued. Based on the moisture content data, energy consumption data, and quality data, drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. Based on the quality data and energy consumption data, the accuracy of batch production is corrected, and the degradation of the physical performance of the drying equipment is identified.

2. The automated control method for a tea production line according to claim 1, characterized in that, The step of adjusting drying parameters based on the moisture state data, the energy consumption data, and the quality data includes: The drying process is divided into multiple drying stages; Based on the current drying stage, set the priority and adjustment range for the drying parameters; Based on the moisture state data, energy consumption data, and quality data of the current drying stage, calculate the comprehensive benefit score for the current stage. Based on the comprehensive benefit score, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. If the parameter adjustment in the current drying stage causes the overall benefit score to show a downward trend in subsequent drying stages, the parameter adjustment strategy for the current drying stage should be retrospectively adjusted.

3. The automated control method for a tea production line according to claim 1, characterized in that, The step of correcting the accuracy of batch production based on the quality data and the energy consumption data, and identifying the decline in the physical performance of the drying equipment, includes: Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. Cross-analysis is performed on the heat transfer efficiency data, the airflow distribution data, the heating element operating status data, and the air duct sealing data to identify the type of degradation inside the drying equipment; Based on the described degradation type, the impact of each degradation on energy consumption and tea quality is quantified; Based on the quantitative impact, the accuracy of batch production is corrected, and maintenance alerts are provided.

4. The automated control method for a tea production line according to claim 3, characterized in that, The method of correcting batch production accuracy based on quantified impact and providing maintenance alerts includes: Continuously monitor the production load data and environmental condition data of the drying equipment; Based on the production load data and environmental condition data, the quantitative impact of degradation on energy consumption and tea quality is dynamically adjusted. Based on the dynamically adjusted degradation impact, the production load data, and the preset production plan, the maintenance warnings are prioritized. The maintenance alerts, ordered by priority, are distributed to maintenance personnel.

5. The automated control method for a tea production line according to claim 4, characterized in that, The step of dynamically adjusting the quantitative impact of degradation on energy consumption and tea quality based on the production load data and environmental condition data includes: Continuously monitor the production load data and environmental condition data of the drying equipment; Collect data on heat transfer efficiency, airflow distribution, heating element operating status, and duct sealing in different areas of the drying chamber. A correlation analysis is performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data to identify the coupling effects between various degradation types. Based on the aforementioned coupling effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified. Based on the independent effects described, the quantitative impact of the degradation on energy consumption and tea quality is adjusted.

6. The automated control method for a tea production line according to claim 5, characterized in that, The analysis of the correlation between the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data identifies the coupling effects between various degradation types, including: Multivariate time series analysis was performed on the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data. The multivariate time series analysis is used to obtain the temporal correlation and lag between data sequences, and to identify the nonlinear or dynamic coupling effects between degradation types. Based on the identified coupling effects, the quantitative model of the degradation effect is adjusted.

7. The automated control method for a tea production line according to claim 5, characterized in that, The decoupling and quantification of the independent effects of each degradation on energy consumption and tea quality based on the coupling effect includes: During the long-term continuous operation of the drying equipment, the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element working status data, and air duct sealing data of the drying equipment are continuously monitored. A calibration procedure that periodically triggers degraded coupling effects; In the calibration procedure, historical trends of the production load data, environmental condition data, heat transfer efficiency data, airflow distribution data, heating element operating status data, and duct sealing data within the current time period are obtained. By analyzing the historical trends, patterns of coupling effects among various degradation types that evolve over time can be identified. Based on the evolution pattern, the quantification parameters of the coupling effect are adjusted to correct the decoupling and quantification results of the degradation effect. Based on the corrected decoupling and quantification results of the degradation effect, the independent effects of each degradation on energy consumption and tea quality are decoupled and quantified.

8. An automated control module for a tea production line, characterized in that, include: The first acquisition module is used to acquire the initial state data of tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of fresh leaves in the initial state data. The second acquisition module is used to acquire, during the drying process, the moisture state data of the tea leaves in the drying chamber, the energy consumption data of the drying equipment, and the quality data of the tea leaves. An adjustment module is used to deploy a sensor array inside the drying chamber to collect heat transfer efficiency data and airflow velocity data in local areas; based on the heat transfer efficiency data and airflow velocity data, it identifies local heat conduction efficiency degradation and uneven airflow distribution; when a local heat conduction efficiency degradation or uneven airflow distribution is detected, a local compensation mechanism is activated, which addresses the transient and inconsistent local physical environment inside the drying chamber by injecting high-pressure air or steam, or adjusting the power of local heating elements; through the local compensation mechanism, the self-optimizing regulator obtains a stable feedback signal and records the trigger frequency and compensation intensity of local compensation; when the trigger frequency or compensation intensity reaches a preset value, a maintenance warning is issued; based on the moisture state data, energy consumption data, and quality data, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. The calibration module is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment.

9. An automated control system for a tea production line, characterized in that, include: The input terminal is used to acquire the initial state data of the tea leaves and obtain the initial moisture content data based on the differences in the physical characteristics of the fresh leaves in the initial state data. The adjustment unit is used to acquire data on the moisture content of the tea leaves, the energy consumption of the drying equipment, and the quality of the tea leaves during the drying process. An array of sensors is deployed inside the drying chamber to collect data on heat transfer efficiency and airflow velocity in local areas. Based on the heat transfer efficiency and airflow velocity data, it identifies local decreases in heat transfer efficiency and uneven airflow distribution. When a decrease in local heat transfer efficiency or uneven airflow distribution is detected, a local compensation mechanism is activated. This is achieved by injecting high-pressure air or steam, or by adjusting the power of local heating elements, to address the transient and inconsistent local physical environment within the drying chamber. Through this local compensation mechanism, the self-optimizing regulator obtains a stable feedback signal and records the trigger frequency and intensity of local compensation. When the trigger frequency or compensation intensity reaches a preset value, a maintenance warning is issued. Based on the moisture content, energy consumption, and quality data, the drying parameters are adjusted to achieve the target moisture content of the tea leaves, reduce energy consumption, and improve quality consistency. The calibration end is used to correct the accuracy of batch production based on the quality data and the energy consumption data, and to identify the decline in the physical performance of the drying equipment.

Images