An automatic temperature regulation system and method for tea processing

Abstract

The application relates to the technical field of temperature control, in particular to an automatic temperature regulation system and method for tea processing, which comprises a data acquisition module, which is used for acquiring real-time environmental parameters in a tea processing cabin, wherein the real-time environmental parameters include airflow speed variation, humidity variation and first temperature variation; a difficult control evaluation module, which is used for carrying out partition analysis on the tea processing cabin according to the real-time environmental parameters to obtain a difficult control degree evaluation value of at least one processing partition; and a first control module, which is used for carrying out temperature compensation regulation on the at least one processing partition according to the difficult control degree evaluation value to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds to the processing partition one by one. According to the difficult control degree evaluation value of each processing partition, the system can carry out temperature compensation regulation according to different temperature control difficulties, so that the temperature of each partition can be maintained in an optimal processing range at all times, and the processing efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of temperature control technology, specifically to an automated temperature control system and method for tea processing. Background Technology

[0002] With the expansion of tea production, the efficiency of traditional manual processing and early mechanized processing methods can no longer meet market demand. The stability and consistency of tea quality has become the key to product competitiveness. Traditional temperature control systems, due to their reliance on manual operation, low control precision, and slow response, are prone to quality fluctuations during tea processing. In order to meet the market's demand for high-quality tea, automated temperature control systems are particularly important. They can maintain temperature control consistency in large-scale production, avoid errors caused by manual operation, and improve production efficiency.

[0003] Currently, most traditional systems rely on a single temperature sensor for temperature measurement and control, which cannot acquire and monitor more environmental variables in real time. Therefore, it is difficult to ensure the accuracy of temperature control when the temperature changes greatly or the environment is complex, which can easily lead to unstable tea quality. Furthermore, it is impossible to dynamically adjust the temperature according to the different levels of difficulty in control of the processing areas. The temperature of all areas usually adopts a uniform standard, ignoring the actual situation that different processing stages may have different temperature control requirements, which can easily lead to uneven temperature and thus affect the processing effect of tea.

[0004] Furthermore, traditional systems often employ fixed heating modes or heating arrays, failing to dynamically optimize heat source configuration based on real-time data. This can lead to localized overheating or underheating, resulting in uneven processing and potential energy waste. The lack of real-time monitoring or early warning mechanisms makes it impossible to detect overheated or underheated areas promptly. If temperature control issues arise, they are typically only discovered when processing efficiency significantly decreases or a malfunction occurs, leading to losses and waste. Summary of the Invention

[0005] To achieve the above objectives, the present invention provides the following technical solution: an automated temperature control system for tea processing, comprising:

[0006] The data acquisition module is used to acquire real-time environmental parameters inside the tea processing chamber, wherein the real-time environmental parameters include changes in airflow speed, humidity, and a first temperature.

[0007] The difficulty assessment module is used to perform zonal analysis on the tea processing chamber based on the real-time environmental parameters to obtain a difficulty assessment value for at least one processing zone, wherein the difficulty assessment value is used to indicate the degree of difficulty in temperature control of the processing zone.

[0008] The first control module is used to perform temperature compensation and regulation on the at least one processing zone according to the difficulty assessment value to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; and adjust the output mode of the heating array based on the at least one target temperature parameter.

[0009] The fluctuation detection module is used to acquire the second temperature change in the tea processing chamber after a preset time following the adjustment of the output mode of the heating array, and generate a reference temperature curve and dynamic fluctuation spectrum of the second temperature change; based on the dynamic fluctuation spectrum and the preset heat source configuration spectrum, it generates a regional overheating early warning spectrum and a regional underheating compensation spectrum.

[0010] The second control module is used to determine the control parameters based on the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map; determine the temperature deviation value based on the standard temperature control parameters corresponding to the preset heat source configuration map and the control parameters; and determine the output power of the heating module based on the temperature deviation value.

[0011] Preferably, the tea processing chamber is subjected to zoning analysis based on the real-time environmental parameters to obtain a controllability assessment value for at least one processing zone, including:

[0012] The tea processing chamber is divided into one or more processing zones;

[0013] Based on the real-time environmental parameters of each processing zone and the correlation between the real-time environmental parameters, an environmental parameter correlation map is constructed.

[0014] Based on the graph structure of the environmental parameter correlation graph, parameter correlation features and dynamic change features of the processing zone are extracted. The parameter correlation features include parameter coupling degree, parameter influence weight and parameter synergy coefficient. The dynamic change features include parameter fluctuation frequency, parameter change amplitude and parameter stability duration.

[0015] Obtain the standard difficulty controllability feature distribution parameters, and calculate the difficulty controllability deviation of the processing zone based on the standard difficulty controllability feature distribution parameters, the parameter correlation features, and the dynamic change features;

[0016] The difficulty level of the processing zone whose difficulty deviation is greater than the preset difficulty threshold is determined as the corresponding difficulty evaluation value.

[0017] Preferably, an environmental parameter correlation map is constructed based on the real-time environmental parameters of each processing zone and the correlation between these parameters, including:

[0018] Determine the correlation between the real-time environmental parameters of each processing zone;

[0019] Create a graph structure class, and store the real-time environmental parameters of each processing partition and the associated parameter relationships through the graph structure class to obtain the graph structure;

[0020] Based on the graph structure, each real-time environmental parameter is mapped to a graph node, and the relationships between each real-time environmental parameter are mapped to graph edges, thereby constructing the environmental parameter association graph.

[0021] Preferably, the standard difficulty-to-control characteristic distribution parameters are obtained, and based on the standard difficulty-to-control characteristic distribution parameters, the parameter correlation characteristics, and the dynamic change characteristics, the difficulty-to-control deviation of the processing zone is calculated, including:

[0022] Statistical analysis of the environmental parameter characteristics of historical normal processing zones is performed to obtain the standard difficulty controllability characteristic distribution parameters, wherein the standard difficulty controllability characteristic distribution parameters include standard parameter correlation characteristics and standard dynamic change characteristics;

[0023] Based on the standard parameter correlation features and the standard dynamic change features, a standard controllability feature vector is generated;

[0024] Clustering is performed on the standard difficulty control feature vector to obtain at least one feature cluster center of the historical normal processing partition in the environmental parameter space;

[0025] Based on the parameter association features and dynamic change features of the processing partition, a difficult-to-control feature vector of the processing partition is generated;

[0026] The distance between the uncontrollable feature vector of the processing partition and the nearest feature cluster center is calculated to obtain the uncontrollable deviation.

[0027] Preferably, temperature compensation and control are applied to the at least one processing zone based on the difficulty-to-control assessment value to obtain at least one target temperature parameter, including:

[0028] The difficulty-to-control assessment value is converted into a compensation feature vector, and the compensation feature vector is fused with the basic temperature control feature to obtain the fused feature. The basic temperature control feature is obtained by feature extraction of the initial temperature data of the processing zone.

[0029] Based on the fusion characteristics, the temperature deviation of the processing zone is calculated using a pre-trained temperature compensation model to obtain the temperature compensation amount;

[0030] The target temperature parameter is obtained by superimposing the temperature compensation amount with the reference temperature of the processing zone.

[0031] Preferably, the training method for the temperature compensation model includes:

[0032] Historical temperature control data from tea processing was used as a training dataset.

[0033] The training dataset is input into the temperature compensation model to obtain the predicted temperature parameters and the first deviation value output by the temperature compensation model.

[0034] The temperature compensation model is optimized based on the first deviation value until the first deviation value is less than or equal to the first set value.

[0035] The first deviation value is related to the controllability evaluation value corresponding to the training dataset, and the controllability evaluation value corresponding to the training dataset is related to the airflow speed change, humidity change, and first temperature change recorded in the training dataset.

[0036] Preferably, the preset heat source configuration map includes at least one heat source control area, each heat source control area corresponds to a heating module, the area overheating early warning map is used to indicate the overheating risk information corresponding to at least one heating module, and the area underheating compensation map is used to indicate the underheating compensation information corresponding to at least one heating module.

[0037] Preferably, based on the dynamic fluctuation map and the preset heat source configuration map, a regional overheating early warning map and a regional underheating compensation map are generated, including:

[0038] For any data acquisition point in the dynamic fluctuation spectrum and the preset heat source configuration spectrum, determine the fluctuation coefficient corresponding to the data acquisition point in the dynamic fluctuation spectrum, and determine the heat source parameter corresponding to the data acquisition point in the preset heat source configuration spectrum;

[0039] The overheating warning coefficient and underheating compensation coefficient corresponding to the data acquisition point are determined based on the fluctuation coefficient and the heat source parameters.

[0040] Based on the overheating warning coefficient corresponding to each of the data collection points, an overheating warning map of the region is generated; and based on the underheating compensation coefficient corresponding to each of the data collection points, an underheating compensation map of the region is generated.

[0041] Preferably, the control parameters are determined by using the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map, including:

[0042] Based on the regional overheating early warning map, the regional overheating areas in the heat source control area are determined, and the real-time temperature data of the regional overheating areas are matched with the reference temperature curve to determine the control parameters;

[0043] Based on the regional underheating compensation map, the regional underheating areas in the heat source control area are determined, and the real-time temperature data of the regional underheating areas are matched with the reference temperature curve to determine the control parameters.

[0044] An automated temperature control method for tea processing, applicable to the aforementioned automated temperature control system for tea processing, includes:

[0045] The real-time environmental parameters inside the tea processing chamber are obtained, including changes in airflow velocity, humidity, and a first temperature.

[0046] The tea processing chamber is analyzed by partitioning based on the real-time environmental parameters to obtain a controllability assessment value for at least one processing partition, wherein the controllability assessment value is used to indicate the degree of difficulty in temperature control of the processing partition.

[0047] Based on the difficulty-to-control assessment value, temperature compensation and control are performed on the at least one processing zone to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; the output mode of the heating array is adjusted based on the at least one target temperature parameter;

[0048] After adjusting the output mode of the heating array for a preset time, the second temperature change inside the tea processing chamber is obtained, and a reference temperature curve and dynamic fluctuation spectrum of the second temperature change are generated.

[0049] Based on the dynamic fluctuation map and the preset heat source configuration map, a regional overheating early warning map and a regional underheating compensation map are generated.

[0050] The control parameters are determined by the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map; the temperature deviation value is determined by the standard temperature control parameters corresponding to the preset heat source configuration map and the control parameters; and the output power of the heating module is determined by the temperature deviation value.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] (1) This invention achieves more precise temperature control by real-time monitoring of environmental parameters in the tea processing chamber and analysis of the dynamic changes of these parameters. This can effectively avoid tea quality problems caused by unstable temperature. Furthermore, by assessing the difficulty of control of each processing zone, the system can perform temperature compensation control according to different degrees of difficulty in temperature control, thereby ensuring that the temperature of each zone is always maintained within the optimal processing range and improving processing efficiency.

[0053] (2) Through the analysis of heat source configuration patterns and dynamic fluctuation patterns, the system can intelligently optimize the output mode of the heating array, avoiding uneven processing or energy waste caused by overheating or underheating, and has overheating warning and underheating compensation functions. Through real-time monitoring of overheating and underheating areas, it can issue warnings in a timely manner and adjust the temperature control of the corresponding areas to avoid tea processing problems caused by abnormal temperatures;

[0054] (3) This invention optimizes temperature control through a temperature compensation model and improves the system’s adaptability to environmental fluctuations through training and feedback adjustment using historical data, ensuring the accuracy and stability of temperature regulation. Furthermore, by constructing an environmental parameter correlation map and dynamic change characteristics, it can deeply analyze the relationship between different environmental parameters and further optimize the temperature control strategy. This big data analysis-based method can accurately predict and regulate temperature changes, thereby improving overall production efficiency and tea quality. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the overall system architecture in one embodiment of the present invention;

[0056] Figure 2 This is a schematic flowchart of the overall method in one embodiment of the present invention.

[0057] In the diagram: 1. Data acquisition module; 2. Difficulty control assessment module; 3. First control module; 4. Fluctuation detection module; 5. Second control module. Detailed Implementation

[0058] 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.

[0059] Example 1, please refer to Figure 1 This invention provides a technical solution: an automated temperature control system for tea processing, comprising:

[0060] Data acquisition module 1 is used to acquire real-time environmental parameters inside the tea processing chamber, including changes in airflow speed, humidity, and temperature.

[0061] Difficulty assessment module 2 is used to perform zone analysis on the tea processing chamber based on real-time environmental parameters to obtain a difficulty assessment value for at least one processing zone. The difficulty assessment value is used to indicate the degree of difficulty in temperature control of the processing zone.

[0062] The first control module 3 is used to perform temperature compensation and regulation on at least one processing zone according to the difficulty assessment value to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; and to adjust the output mode of the heating array based on at least one target temperature parameter.

[0063] The fluctuation detection module 4 is used to acquire the second temperature change in the tea processing chamber after a preset time following the adjustment of the output mode of the heating array, and generate a reference temperature curve and dynamic fluctuation spectrum of the second temperature change; based on the dynamic fluctuation spectrum and the preset heat source configuration spectrum, it generates a regional overheating early warning spectrum and a regional underheating compensation spectrum.

[0064] The second control module 5 is used to determine the control parameters based on the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map; determine the temperature deviation value based on the standard temperature control parameters and control parameters corresponding to the preset heat source configuration map; and determine the output power of the heating module based on the temperature deviation value.

[0065] It should be noted that real-time acquisition of environmental parameters within the tea processing chamber includes: airflow velocity changes (the speed of airflow within the chamber, which affects temperature distribution); humidity changes (tea processing requires specific humidity levels, and changes in humidity can affect drying or fermentation); and temperature changes (temperature variations within the chamber, particularly the impact of heat sources on ambient temperature). For example, during tea roasting, temperature sensors may detect a temperature rise within the processing chamber; changes in humidity or airflow may affect temperature uniformity. Based on these real-time environmental parameters, the processing chamber is analyzed by zone to assess the ease of temperature control in different areas. The resulting controllability assessment value represents the difficulty of temperature control in a specific zone. A high controllability value means that temperature control in that zone is more difficult and requires more adjustments. For example, a tea processing chamber may have multiple zones; one zone may be closer to the heating equipment, resulting in larger temperature variations and higher controllability, while another zone may be farther from the heating equipment, with smaller temperature variations and lower controllability. Function: Based on the controllability assessment value, temperature compensation adjustments are made to the processing zones to ensure a more balanced temperature across each zone. By adjusting the output mode of the heating equipment, the temperature of each zone is ensured to reach the target temperature. If the temperature of a zone varies greatly (e.g., due to its proximity to the heating source), the first control... The control module will compensate and adjust the area, maintaining a stable temperature by reducing heating power or changing airflow speed. After adjusting the output mode of the heating array, the fluctuation detection module will monitor the temperature changes in the tea processing chamber within a preset time (e.g., after a few minutes), generating a baseline temperature curve and plotting a dynamic fluctuation map. Then, combined with a preset heat source configuration map, it will generate an overheating warning map and an underheating compensation map for the area to further optimize heating control. For example, assuming the system adjusts the output mode of the heating equipment, the fluctuation detection module will record the temperature changes and analyze the temperature fluctuations using algorithms. If the temperature fluctuation in a certain area is too large, the system will generate... The system generates an overheat warning graph to indicate that the heating in a certain area may be too strong; if the temperature in a certain area is insufficient, the system generates an underheat compensation graph to remind that additional heating is needed; the second control module determines new control parameters and calculates the temperature deviation value based on information such as the reference temperature curve, overheat warning graph, and underheat compensation graph; the output power of the heating module is adjusted according to the temperature deviation value to ensure that the temperature of the entire tea processing chamber is within the ideal range; for example, if the temperature in a certain area is too high, the second control module will detect the temperature deviation and reduce the heating power in that area; if the temperature in a certain area is too low, the heating power will be increased to ensure more precise temperature control in each area.

[0066] In an optional embodiment, the tea processing chamber is analyzed by zoning based on real-time environmental parameters to obtain a controllability assessment value for at least one processing zone, including:

[0067] The tea processing chamber is divided into one or more processing zones;

[0068] Based on the real-time environmental parameters of each processing zone and the correlation between the real-time environmental parameters, an environmental parameter correlation map is constructed.

[0069] Based on the graph structure of the environmental parameter correlation graph, parameter correlation features and dynamic change features of the processing zone are extracted. The parameter correlation features include parameter coupling degree, parameter influence weight and parameter synergy coefficient, and the dynamic change features include parameter fluctuation frequency, parameter change amplitude and parameter stability duration.

[0070] Obtain the standard difficulty controllability characteristic distribution parameters, and calculate the difficulty controllability deviation of the processing zone based on the standard difficulty controllability characteristic distribution parameters, parameter correlation characteristics, and dynamic change characteristics;

[0071] The difficulty level of processing zones with a deviation greater than the preset difficulty threshold is determined as the corresponding difficulty assessment value.

[0072] It should be noted that the space within the tea processing chamber is divided into multiple zones (or areas). These zones may have different environmental characteristics due to factors such as distance from the heating source, airflow, or humidity. For example, suppose there are three zones within the tea processing chamber: Zone 1 is close to the heating equipment, Zone 2 is far from the heating equipment, and Zone 3 is located in a location with strong airflow. The environmental parameters (temperature, humidity, airflow, etc.) of each zone may vary, and the system needs to monitor and adjust these zones individually. By collecting real-time environmental parameters (e.g., temperature, humidity, airflow speed) from each processing zone, an environmental parameter correlation graph is constructed. This graph shows the relationships between various environmental parameters, helping the system understand how these parameters interact with each other. Influences; for example, the relationship between temperature and humidity, the effect of airflow velocity on temperature distribution, etc.; for example, in a certain area, the system may find that when the airflow velocity is high, the temperature fluctuation is small; on the other hand, when the humidity is high, the temperature fluctuation is large. Environmental parameter correlation maps can help the system identify these patterns and make corresponding adjustments; by analyzing environmental parameter correlation maps, features of each partition can be extracted, including: parameter coupling degree: describing how two or more parameters change together (such as the relationship between temperature and humidity); parameter influence weight: describing the degree of influence of a parameter on other parameters or the final temperature; parameter synergy coefficient: describing whether multiple parameters work together to affect temperature changes; parameter fluctuation frequency: referring to the frequency of parameter fluctuations. The rate of change, such as rapid or slow temperature fluctuations; the magnitude of parameter change: the range of parameter change, which may involve the upper and lower limits of temperature fluctuations; the duration of parameter stability: the duration during which a parameter remains in a stable state within a certain timeframe; examples: Suppose that within a zone, temperature and humidity are highly coupled, and humidity fluctuates significantly with temperature changes. This means that humidity has a significant impact on temperature in this area, potentially requiring special adjustments to the humidity control system; another example: frequent and large-amplitude temperature changes in a certain area may indicate a temperature control problem, requiring the system to take measures to minimize temperature fluctuations; by analyzing the correlation and dynamic change characteristics of environmental parameters, the system can... The system calculates the controllability deviation for each zone; this is a quantitative indicator used to represent the difficulty of temperature control in a processing zone. A higher controllability deviation indicates greater difficulty in temperature control for that zone. For example, if a processing zone experiences large temperature fluctuations and unstable humidity, the system will find that the controllability deviation for that area is high, meaning that the temperature control requirements for that area are higher, requiring more attention and adjustment. Based on the calculated controllability deviation, the system can classify the temperature control difficulty of each processing zone into different levels. When the controllability deviation exceeds a preset threshold, the area will be assessed as "highly difficult to control," requiring more adjustment and monitoring. For example, suppose the system sets the controllability threshold to "5".If the difficulty-to-control deviation of a certain area is "6", then the difficulty level of that area is assessed as "high difficulty-to-control", and the system will initiate more automatic adjustment measures, such as increasing heater output, adjusting airflow patterns, and even adjusting the humidity control system.

[0073] In an optional embodiment, an environmental parameter correlation map is constructed based on the real-time environmental parameters of each processing partition and the correlation between the real-time environmental parameters, including:

[0074] Determine the correlation between the real-time environmental parameters of each processing zone;

[0075] Create a graph structure class to store the real-time environmental parameters of each processing zone and the associated parameter relationships, thus obtaining the graph structure;

[0076] Based on the graph structure, each real-time environmental parameter is mapped to a graph node, and the relationships between each real-time environmental parameter are mapped to graph edges, thus constructing an environmental parameter association graph.

[0077] It should be noted that the environmental parameters of each processing zone (such as temperature, humidity, airflow, etc.) are analyzed, and the relationships between these parameters are examined. For example, temperature and humidity may influence each other, and airflow may affect temperature uniformity. Through data analysis, the system can identify the correlations between these parameters. For example, in a certain processing zone, it was found that changes in humidity usually lead to temperature fluctuations. The system found through data collection that for every 10% increase in humidity, the temperature rises by 2°C, indicating a strong correlation between humidity and temperature. The graph structure class is a container used to store environmental parameters and their relationships. The graph structure class contains all the environmental parameters of the processing zones and clearly defines how these parameters interact. This type of graph structure not only helps in understanding the current parameter relationships but also plays a crucial role in subsequent optimization. For example, suppose a processing zone has three environmental parameters: temperature, humidity, and airflow. A graph structure class is created where each parameter is a node, and the relationships between parameters are edges in the graph. For example, the edge between the temperature node and the humidity node represents their mutual influence. In the graph structure, each environmental parameter is mapped to a node in the graph; a node represents a specific environmental parameter (such as temperature, humidity, etc.). These nodes (such as airflow) will be connected to other nodes through edges to form a complete graph. Assume there are environmental parameters for a region: temperature, humidity, and airflow. These three parameters are represented as three nodes: temperature node, humidity node, and airflow node. In the graph structure, different environmental parameter nodes are connected to each other through "edges." These edges represent the relationships between different parameters. Through these edges, the system can clearly understand how different environmental parameters affect each other. For example, if there is a strong correlation between temperature and humidity, then an edge connects the temperature node and the humidity node, and the weight of the edge represents the strength of their correlation. For instance, if humidity fluctuates significantly when temperature changes, then this edge has a higher weight. Through the preceding steps, a complete environmental parameter correlation graph will be constructed. This graph will include all environmental parameter nodes of the processing region and the edges connecting them, helping the system better understand the dynamic changes and mutual influences of different parameters. For example, suppose a processing region has three environmental parameters: temperature, humidity, and airflow, and they have the following relationships: there is a strong positive correlation between temperature and humidity (humidity also increases when temperature rises); there is an inverse correlation between airflow and temperature (increased airflow leads to smaller temperature changes).

[0078] In an optional embodiment, standard difficulty-to-control characteristic distribution parameters are obtained, and based on the standard difficulty-to-control characteristic distribution parameters, parameter correlation characteristics, and dynamic change characteristics, the difficulty-to-control deviation of the processing zone is calculated, including:

[0079] Statistical analysis was performed on the environmental parameter characteristics of historical normal processing zones to obtain the standard difficulty control characteristic distribution parameters, which include standard parameter correlation characteristics and standard dynamic change characteristics.

[0080] Based on the standard parameter correlation features and standard dynamic change features, a standard controllability feature vector is generated.

[0081] Clustering is performed on the standard difficulty control feature vector to obtain at least one feature cluster center of the historical normal processing partition in the environmental parameter space;

[0082] Based on the parameter correlation features and dynamic change features of the processing partition, a difficult-to-control feature vector of the processing partition is generated;

[0083] The distance between the uncontrollable feature vector of the processing partition and the nearest feature cluster center is calculated to obtain the uncontrollable deviation.

[0084] It should be noted that by statistically analyzing historical normal processing zones (i.e., environmental data with parameters within normal ranges), the system can extract standard parameter correlation characteristics and dynamic change characteristics. These characteristics describe how environmental parameters in the processing zone change, the normal fluctuation range, and the correlation between different parameters. For example, suppose in a tea processing zone, historical data shows that temperature fluctuations are within a stable range, and humidity changes are relatively stable. Through analysis, the system finds that temperature and humidity have a relatively fixed correlation characteristic (e.g., for every 1% increase in humidity, the temperature increases by 0.5°C), and temperature changes fluctuate within 10°C. The system will organize this data into standard controllability characteristic distribution parameters, i.e., parameter correlation. Standard parameter correlation characteristics and dynamic change characteristics are indicators describing the relationships and variation patterns of parameters in a normal processing environment. Parameter correlation characteristics refer to the interaction relationships between different environmental parameters, while dynamic change characteristics refer to the trends and fluctuation ranges of these parameters over time. Examples: Standard parameter correlation characteristics: the correlation between temperature and humidity (e.g., humidity increases as temperature rises); Standard dynamic change characteristics: the range and frequency of temperature and humidity changes (e.g., temperature typically fluctuates between 20°C and 25°C, and humidity varies between 50% and 60%). Converting standard parameter correlation characteristics and dynamic change characteristics into feature vectors facilitates subsequent data analysis and calculation. A feature vector is a multi-feature vector... A dimensional vector, where each dimension represents a specific characteristic or variation pattern of an environmental parameter. For example, suppose the standard characteristics obtained through analysis are as follows: the correlation between temperature and humidity is 0.8 (a strong positive correlation); the temperature fluctuation range is 5°C; and the humidity fluctuation range is 10%. Then, the generated standard controllability feature vector might be: [0.8, 5, 10], where: 0.8 represents the correlation between temperature and humidity; 5 represents the temperature fluctuation range; and 10 represents the humidity fluctuation range. By performing cluster analysis on the standard controllability feature vector, one or more cluster centers representing the characteristics of normal processing zones can be found. The purpose of clustering is to group the feature vectors of environmental parameters so that the feature vectors in each group are similar to each other, thereby obtaining cluster centers representing the characteristics of normal processing zones. Cluster centers for normal environmental parameter characteristics; Example: Suppose there is data from multiple normal processing zones. Through clustering algorithms, the system may obtain a cluster center, such as [0.75, 4.8, 9]. This indicates that the environmental parameter characteristics of the processing zones in the cluster are roughly within these ranges, reflecting the temperature, humidity, and airflow characteristics under normal conditions. For a new processing zone or real-time data, the system needs to generate a "difficult-to-control feature vector" based on the parameter correlation characteristics and dynamic change characteristics of the zone. This feature vector represents the degree of difference between the environmental parameters of the zone and the normal standard. Example: Suppose the temperature and humidity of a certain processing zone change abnormally, resulting in its feature vector being [0.9, 7, 15], while the standard feature vector is [0.75, 4.8, 9].[8,5,10]; the eigenvectors of this new partition reflect a high degree of difficulty in control.

[0085] In an optional embodiment, temperature compensation control is applied to at least one processing zone based on a difficulty-to-control assessment value to obtain at least one target temperature parameter, including:

[0086] The difficulty-to-control assessment value is transformed into a compensation feature vector, and the compensation feature vector is fused with the basic temperature control feature to obtain the fused feature. The basic temperature control feature is obtained by feature extraction from the initial temperature data of the processing zone.

[0087] Based on the fusion characteristics, the temperature deviation of the processing zone is calculated using a pre-trained temperature compensation model to obtain the temperature compensation amount;

[0088] The target temperature parameter is obtained by superimposing the temperature compensation amount with the reference temperature of the processing zone.

[0089] It should be noted that, from the preceding analysis, the system obtains a "difficult-to-control feature vector," which reflects the difference between the environmental parameters of the processing zone and the standard. By converting this evaluation value into a compensation feature vector, the system can adjust the environmental parameters to be closer to the standard value, thereby achieving effective control. After the compensation feature vector is calculated, the system will also fuse it with the initial temperature data (basic temperature control feature) of the processing zone. The basic temperature control feature usually refers to the temperature data of the processing zone under normal conditions, obtained after feature extraction. For example, suppose that in a certain processing zone, the basic temperature control feature is [25°C], which means that the initial temperature of this zone is 25°C. By fusing it with the compensation feature vector [0.05, -2, -5], the temperature compensation model is a machine learning model based on historical data and environmental features. The learning model can predict and calculate the temperature deviation of each processing zone and generate an appropriate compensation amount based on these deviations. This compensation calculation takes into account the influence of various environmental factors (such as humidity and airflow). For example, assuming that the temperature in a certain processing zone deviates significantly from the standard value, the system uses a trained temperature compensation model (such as a regression model or neural network) to calculate the temperature compensation amount. Based on the input environmental parameters (such as humidity and wind speed) and historical data, the model may determine that the temperature compensation amount is -0.05°C. This compensation amount indicates that the current temperature needs to be lowered by 0.05°C. The final step is to add or subtract the calculated temperature compensation amount from the current reference temperature to obtain the target temperature parameter. This target temperature parameter is the temperature that needs to be adjusted to ensure that the processing continues within a stable temperature range.

[0090] In an optional embodiment, the method for training the temperature compensation model includes:

[0091] Historical temperature control data from tea processing was used as a training dataset.

[0092] Input the training dataset into the temperature compensation model to obtain the predicted temperature parameters and the first deviation value output by the temperature compensation model;

[0093] The temperature compensation model is optimized based on the first deviation value until the first deviation value is less than or equal to the first set value.

[0094] Among them, the first deviation value is related to the difficulty assessment value corresponding to the training dataset, and the difficulty assessment value corresponding to the training dataset is related to the airflow speed change, humidity change, and first temperature change recorded in the training dataset.

[0095] It's important to note that historical temperature control data is collected and organized, serving as a training dataset for the temperature compensation model. This dataset includes environmental parameters for each processing stage, such as temperature, humidity, and airflow velocity. The historical data is input into the trained temperature compensation model, which calculates the temperature compensation amount for each processing stage. The output of the temperature compensation model typically includes: predicted temperature parameters (the model predicts the ideal temperature under the current processing environment); and a first deviation value (the difference between the calculated actual temperature and the target temperature, representing the error of the current temperature control system). For example, if the model predicts a target temperature of 29°C, while the actual processing temperature is 30°C, the first deviation value calculated by the model is 1°C. This deviation value indicates that the temperature control system needs to adjust the temperature to get closer to the target temperature. To ensure more accurate temperature control, the temperature compensation model needs continuous optimization. If the first deviation value is large, the system needs to adjust the model's parameters (such as weights or biases in the algorithm) until the first deviation value is less than or equal to the set target value. This target value is usually a tolerance range, such as 0. 0.1°C; Example: Suppose the model's initial prediction has a first deviation of 1°C; if the set threshold for the first deviation is 0.1°C, the system will adjust the model parameters based on the deviation, possibly by adjusting certain parameters in the algorithm (such as the learning rate, the number of model layers, etc.) to reduce the deviation; when the model predicts again, the first deviation might be 0.05°C, meeting the set target value, indicating that the model has been successfully optimized; The difficulty-to-control assessment value is an indicator used to represent the current performance of the temperature control system; this assessment value is affected by multiple factors, including changes in airflow velocity and humidity. Variations and temperature changes, among other factors, allow the model to better understand and adjust the temperature control system. For example, suppose that during a processing operation, the temperature changes significantly (e.g., from 28°C to 32°C), the humidity fluctuates (e.g., from 60% to 65%), and the airflow velocity is unstable (e.g., fluctuating between 2 m / s and 2.5 m / s). These variations would result in a high difficulty-to-control rating (e.g., 0.8). A high difficulty-to-control rating indicates that the temperature control system is difficult to control precisely, while a low difficulty-to-control rating (e.g., 0.2) indicates that the temperature control system is well-controlled.

[0096] In an optional embodiment, the preset heat source configuration map includes at least one heat source control area, each heat source control area corresponds to a heating module, the area overheating early warning map is used to indicate the overheating risk information corresponding to at least one heating module, and the area underheating compensation map is used to indicate the underheating compensation information corresponding to at least one heating module.

[0097] It should be noted that a heat source control area refers to an area in the processing zone controlled by one or more heat sources, such as the upper heating zone of the drying zone or a section of a tea drum dryer; a heating module corresponds to a specific control unit of the heat source control area, which can be an electric heater, steam pipeline, or hot air circulation system; a preset heat source configuration map is a schematic diagram or data structure showing the location of each heating module and its corresponding area in the processing equipment, used for system management and control; for example, assuming there is a tea dryer divided into three heating zones: upper heating zone (heating module A), middle heating zone (heating module B), and lower heating zone (heating module C), the preset heat source configuration map will display the location and number of the control area corresponding to these three heating modules; an area overheat warning map is a chart or set of charts / data structures used to monitor in real time whether the temperature of each heating module exceeds the safe range and to provide a warning; it determines whether there is overheating based on preset temperature thresholds. The overheat warning map identifies and marks the corresponding heat source control areas. For example, if the temperature sensor of heating module B detects that the temperature exceeds the set upper limit (e.g., 80°C), the regional overheat warning map will mark the central heating zone as having an "overheat risk," prompting the system to reduce heating power or activate cooling measures. The map can be represented by colors: green for safety, yellow for warning, and red for overheating. The regional underheating compensation map, in contrast to the overheat warning map, is used to display the current temperature of the heating module being lower than the target temperature and provides corresponding compensation information. Compensation information can include increasing heating power, extending heating time, or adjusting hot air circulation. For example, if heating module C measures a temperature lower than the set value (e.g., target temperature 70°C, but actual temperature 65°C), the regional underheating compensation map will mark the lower heating zone as needing supplemental heating and indicate that heating power should be increased or heating time extended. The map can be displayed as arrows or a heat gradient graph, visually representing the area and degree of insufficient heating.

[0098] In an optional embodiment, a regional overheating early warning map and a regional underheating compensation map are generated based on a dynamic fluctuation map and a preset heat source configuration map, including:

[0099] For any data acquisition point in the dynamic fluctuation spectrum and the preset heat source configuration spectrum, determine the fluctuation coefficient corresponding to the data acquisition point in the dynamic fluctuation spectrum, and determine the heat source parameter corresponding to the data acquisition point in the preset heat source configuration spectrum.

[0100] The overheating warning coefficient and underheating compensation coefficient corresponding to the data collection point are determined based on the fluctuation coefficient and heat source parameters.

[0101] Based on the overheating warning coefficient corresponding to each data collection point, a regional overheating warning map is generated; and based on the underheating compensation coefficient corresponding to each data collection point, a regional underheating compensation map is generated.

[0102] It should be noted that in the dynamic fluctuation spectrum, the fluctuation coefficient of each data acquisition point reflects the fluctuation range of temperature, power, or other thermal parameters at that point. A higher fluctuation coefficient indicates greater thermal fluctuation at that point, potentially requiring more control or compensation. In the preset heat source configuration spectrum, the heat source parameters corresponding to each data acquisition point may include the target temperature, heating power, and heat source type (e.g., electric heating, steam heating). For example, suppose that in the dynamic fluctuation spectrum of a drying equipment, there is a data acquisition point located in the central heating zone (heating module B); based on the temperature fluctuation data, the fluctuation coefficient for this point is calculated to be 0.15 (small fluctuation range); simultaneously, in the preset heat source configuration spectrum, the heat source parameters... The target temperature for this point is displayed as 75°C, and the heating power is 500W. Based on the fluctuation coefficient and heat source parameters, the overheating risk factor can be estimated. Generally, the larger the fluctuation coefficient or the higher the target temperature, the greater the risk of overheating. Therefore, the overheating warning factor is calculated based on the combination of the fluctuation coefficient and the heating power. The underheating compensation factor is determined based on the fluctuation coefficient and the current temperature (or insufficient heating power) to determine the compensation requirement. If the current temperature is lower than the target temperature, the system will calculate an underheating compensation factor to adjust the heating power or time. Example: Assume the fluctuation coefficient for this data acquisition point is 0.15, and the target temperature is 75°C. If the current temperature is 73°C (lower than the target temperature), then... Based on this information, an underheating compensation coefficient will be calculated. Assuming this coefficient is 0.05, it means an additional 5% heating power is needed to compensate for the underheating. If the target temperature of the same heating module is close to its upper limit (e.g., 80°C), the system may calculate an overheating warning coefficient, such as 0.1, indicating a low risk of overheating in that area. The regional overheating warning map aggregates the overheating warning coefficients from all data collection points to form an overall warning map of the heat source area. The system will automatically adjust and display the overheating risk of each area based on the overheating warning coefficient of each point. For example, in a drying device, the overheating warning coefficient for the central heating zone is 0.1, while other areas may have a coefficient of 0.3 or lower. If the overheating warning coefficient of a region exceeds the set safety threshold (e.g., 0.2), the system will use color markings or graphics to indicate that the region may be overheating, reminding operators or the automatic control system to make adjustments. The regional underheating compensation map summarizes the underheating compensation coefficients of all data collection points to form a compensation demand map for a region. The system will automatically display which regions need to add heat sources to meet temperature requirements based on the underheating compensation coefficient of each point. For example, if the underheating compensation coefficient of a certain data collection point in the lower heating zone is 0.05, it means that the region needs 5% additional heating power. The regional underheating compensation map will then use color (e.g., light blue) to identify the underheating situation in the region and prompt the system to add the corresponding heat source.

[0103] In an optional embodiment, the control parameters are determined by the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map, including:

[0104] Based on the regional overheating early warning map, identify the regional overheating areas within the heat source control area, match the real-time temperature data of the regional overheating areas with the reference temperature curve, and determine the control parameters.

[0105] Based on the regional underheating compensation map, the regional underheating areas in the heat source control area are identified. The real-time temperature data of the regional underheating areas are matched with the reference temperature curve to determine the control parameters.

[0106] It should be noted that, based on the regional overheat warning map, the system can identify which areas have an overheating risk. These areas typically display a higher overheat warning coefficient. The reference temperature curve is a reference curve for the target temperature, representing the ideal temperature distribution of the equipment under different operating conditions. For example, suppose in a drying equipment, the regional overheat warning map shows that the overheat warning coefficient for the central heating zone is 0.3 (higher than the set safety threshold). This means that there is a potential risk of overheating in this area. The real-time temperature data for this area is 85°C, while the reference temperature curve shows that the ideal temperature for this area should be 75°C. Based on the difference between the actual temperature of the overheated area and the reference temperature curve, the necessary control measures are determined. Typically, these control measures include adjusting the heating power, adding cooling systems, etc. For example, in the example above, the real-time temperature (85°C) of the central heating zone is 10°C higher than the reference temperature (75°C). Due to the overheat warning in this area... When the coefficient is high (0.3), the system will automatically adjust the control parameters based on this temperature difference, such as reducing the heating power by 10% or activating the cooling mechanism, to bring the temperature of that area back to the ideal range. Based on the regional underheating compensation map, the system can identify which areas have temperatures lower than the target temperature; these areas will display a higher underheating compensation coefficient. The reference temperature curve is similar to that of the overheated area and can also help the system identify the ideal temperature range for comparison with real-time temperature data. For example, suppose in the lower heating zone of the equipment, the regional underheating compensation map shows an underheating compensation coefficient of 0.1 (meaning a 10% increase in heating power is needed); the real-time temperature of this area is 68°C, while the reference temperature curve shows a target temperature of 75°C. Similar to overheating control, the control of underheated areas is also based on the difference between the real-time temperature and the target temperature. Control measures typically involve increasing the heating power or extending the heating time to ensure the temperature reaches the target value.

[0107] Example 2, please refer to Figure 2 This invention provides a technical solution: an automated temperature control method for tea processing, applicable to the aforementioned automated temperature control system for tea processing, comprising:

[0108] S1. Obtain real-time environmental parameters inside the tea processing chamber, including changes in airflow speed, humidity, and temperature.

[0109] S2. Based on real-time environmental parameters, perform zone analysis on the tea processing chamber to obtain a controllability assessment value for at least one processing zone. The controllability assessment value is used to indicate the degree of difficulty in temperature control of the processing zone.

[0110] S3. Perform temperature compensation and control on at least one processing zone based on the difficulty assessment value to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; adjust the output mode of the heating array based on at least one target temperature parameter;

[0111] S4. After adjusting the output mode of the heating array for a preset time, obtain the second temperature change in the tea processing chamber and generate the reference temperature curve and dynamic fluctuation spectrum of the second temperature change.

[0112] S5. Generate a regional overheating early warning map and a regional underheating compensation map based on the dynamic fluctuation map and the preset heat source configuration map.

[0113] S6. Determine the control parameters based on the reference temperature curve, the regional overheat warning map, and the regional underheat compensation map; determine the temperature deviation value based on the standard temperature control parameters and control parameters corresponding to the preset heat source configuration map, and determine the output power of the heating module based on the temperature deviation value.

[0114] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. An automated temperature control system for tea processing, characterized in that, include: The data acquisition module is used to acquire real-time environmental parameters inside the tea processing chamber, wherein the real-time environmental parameters include changes in airflow speed, humidity, and a first temperature. The difficulty assessment module is used to perform zonal analysis on the tea processing chamber based on the real-time environmental parameters to obtain a difficulty assessment value for at least one processing zone, wherein the difficulty assessment value is used to indicate the degree of difficulty in temperature control of the processing zone. The first control module is used to perform temperature compensation and regulation on the at least one processing zone according to the difficulty assessment value to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; and adjust the output mode of the heating array based on the at least one target temperature parameter. The fluctuation detection module is used to acquire the second temperature change in the tea processing chamber after a preset time following the adjustment of the output mode of the heating array, and generate a reference temperature curve and dynamic fluctuation spectrum of the second temperature change; based on the dynamic fluctuation spectrum and the preset heat source configuration spectrum, it generates a regional overheating early warning spectrum and a regional underheating compensation spectrum. The second control module is used to determine the control parameters based on the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map; determine the temperature deviation value based on the standard temperature control parameters corresponding to the preset heat source configuration map and the control parameters; and determine the output power of the heating module based on the temperature deviation value. Specifically, based on the real-time environmental parameters, a zoning analysis is performed on the tea processing chamber to obtain a controllability assessment value for at least one processing zone, including: The tea processing chamber is divided into one or more processing zones; Based on the real-time environmental parameters of each processing zone and the correlation between each real-time environmental parameter, an environmental parameter correlation map is constructed. Based on the graph structure of the environmental parameter correlation graph, parameter correlation features and dynamic change features of the processing zone are extracted. The parameter correlation features include parameter coupling degree, parameter influence weight and parameter synergy coefficient. The dynamic change features include parameter fluctuation frequency, parameter change amplitude and parameter stability duration. Obtain the standard difficulty controllability feature distribution parameters, and calculate the difficulty controllability deviation of the processing zone based on the standard difficulty controllability feature distribution parameters, the parameter correlation features, and the dynamic change features; The difficulty level of the processing zone whose difficulty deviation is greater than the preset difficulty threshold is determined as the corresponding difficulty evaluation value.

2. The automated temperature control system for tea processing according to claim 1, characterized in that, Based on the real-time environmental parameters of each processing zone and the correlations between these parameters, an environmental parameter correlation map is constructed, including: Determine the correlation between the real-time environmental parameters of each processing zone; Create a graph structure class, and store the real-time environmental parameters and associated parameter relationships of each processing partition through the graph structure class to obtain the graph structure; Based on the graph structure, each real-time environmental parameter is mapped to a graph node, and the relationships between each real-time environmental parameter are mapped to graph edges, thereby constructing the environmental parameter association graph.

3. The automated temperature control system for tea processing according to claim 2, characterized in that, Obtain standard difficulty-to-control characteristic distribution parameters, and calculate the difficulty-to-control deviation of the processing zone based on the standard difficulty-to-control characteristic distribution parameters, the parameter correlation characteristics, and the dynamic change characteristics, including: Statistical analysis of the environmental parameter characteristics of historical normal processing zones is performed to obtain the standard difficulty controllability characteristic distribution parameters, wherein the standard difficulty controllability characteristic distribution parameters include standard parameter correlation characteristics and standard dynamic change characteristics; Based on the standard parameter correlation features and the standard dynamic change features, a standard controllability feature vector is generated; Clustering is performed on the standard difficulty control feature vector to obtain at least one feature cluster center of the historical normal processing partition in the environmental parameter space; Based on the parameter association features and dynamic change features of the processing partition, a difficult-to-control feature vector of the processing partition is generated; The distance between the uncontrollable feature vector of the processing partition and the nearest feature cluster center is calculated to obtain the uncontrollable deviation.

4. The automated temperature control system for tea processing according to claim 3, characterized in that, Based on the difficulty-to-control assessment value, temperature compensation and control are applied to the at least one processing zone to obtain at least one target temperature parameter, including: The difficulty-to-control assessment value is converted into a compensation feature vector, and the compensation feature vector is fused with the basic temperature control feature to obtain the fused feature. The basic temperature control feature is obtained by feature extraction of the initial temperature data of the processing zone. Based on the fusion characteristics, the temperature deviation of the processing zone is calculated using a pre-trained temperature compensation model to obtain the temperature compensation amount; The target temperature parameter is obtained by superimposing the temperature compensation amount with the reference temperature of the processing zone.

5. An automated temperature control system for tea processing according to claim 4, characterized in that, The training method for the temperature compensation model includes: Historical temperature control data from tea processing was used as a training dataset. The training dataset is input into the temperature compensation model to obtain the predicted temperature parameters and the first deviation value output by the temperature compensation model. The temperature compensation model is optimized based on the first deviation value until the first deviation value is less than or equal to the first set value. The first deviation value is related to the controllability evaluation value corresponding to the training dataset, and the controllability evaluation value corresponding to the training dataset is related to the airflow speed change, humidity change, and first temperature change recorded in the training dataset.

6. An automated temperature control system for tea processing according to claim 5, characterized in that, The preset heat source configuration map includes at least one heat source control area, and each heat source control area corresponds to a heating module. The area overheating early warning map is used to indicate the overheating risk information corresponding to at least one of the heating modules, and the area underheating compensation map is used to indicate the underheating compensation information corresponding to at least one of the heating modules.

7. An automated temperature control system for tea processing according to claim 6, characterized in that, Based on the dynamic fluctuation map and the preset heat source configuration map, a regional overheating early warning map and a regional underheating compensation map are generated, including: For any data acquisition point in the dynamic fluctuation spectrum and the preset heat source configuration spectrum, determine the fluctuation coefficient corresponding to the data acquisition point in the dynamic fluctuation spectrum, and determine the heat source parameter corresponding to the data acquisition point in the preset heat source configuration spectrum; The overheating warning coefficient and underheating compensation coefficient corresponding to the data acquisition point are determined based on the fluctuation coefficient and the heat source parameters. Based on the overheating warning coefficient corresponding to each of the data collection points, an overheating warning map of the region is generated; and based on the underheating compensation coefficient corresponding to each of the data collection points, an underheating compensation map of the region is generated.

8. An automated temperature control system for tea processing according to claim 7, characterized in that, The control parameters are determined by the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map, including: Based on the regional overheating early warning map, the regional overheating areas in the heat source control area are determined, and the real-time temperature data of the regional overheating areas are matched with the reference temperature curve to determine the control parameters; Based on the regional underheating compensation map, the regional underheating areas in the heat source control area are determined, and the real-time temperature data of the regional underheating areas are matched with the reference temperature curve to determine the control parameters.

9. An automated temperature control method for tea processing, applicable to the automated temperature control system for tea processing as described in any one of claims 1-8, characterized in that, include: The real-time environmental parameters inside the tea processing chamber are obtained, including changes in airflow velocity, humidity, and a first temperature. The tea processing chamber is analyzed by partitioning based on the real-time environmental parameters to obtain a controllability assessment value for at least one processing partition, wherein the controllability assessment value is used to indicate the degree of difficulty in temperature control of the processing partition. Based on the difficulty-to-control assessment value, temperature compensation and control are performed on the at least one processing zone to obtain at least one target temperature parameter, wherein the target temperature parameter corresponds one-to-one with the processing zone; the output mode of the heating array is adjusted based on the at least one target temperature parameter; After adjusting the output mode of the heating array for a preset time, the second temperature change inside the tea processing chamber is obtained, and a reference temperature curve and dynamic fluctuation spectrum of the second temperature change are generated. Based on the dynamic fluctuation map and the preset heat source configuration map, a regional overheating early warning map and a regional underheating compensation map are generated. The control parameters are determined by the reference temperature curve, the regional overheating early warning map, and the regional underheating compensation map; the temperature deviation value is determined by the standard temperature control parameters corresponding to the preset heat source configuration map and the control parameters; and the output power of the heating module is determined by the temperature deviation value.

Images