An intelligent baking temperature control system and method based on the Internet of Things

Abstract

The application provides an intelligent baking temperature control system and method based on the Internet of Things. The system includes a data sensing module, a dynamic modeling module, an intelligent decision-making module, and an interactive monitoring module. First, multi-source heterogeneous data is collected, and data cleaning and feature alignment are performed to output a standardized baking data set. Next, a temperature field space-time model is constructed based on the standardized baking data set to generate a digital twin. Then, based on the digital twin, control instruction sets are generated by jointly analyzing temperature control strategies and energy optimization, and the equipment is driven to perform temperature control operations, with real-time feedback of execution state data forming a closed-loop control. Finally, the interactive monitoring module provides a visual interface to display temperature field evolution, equipment status, and material response information, supporting user adjustment of control instructions. The application improves temperature control accuracy, energy efficiency, and user operation experience through multi-source data fusion, temperature modeling, intelligent optimization analysis, and user interaction.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent baking temperature control, in particular to an intelligent baking temperature control system and method based on the Internet of Things. BACKGROUND

[0002] With the continuous development of the baking industry, temperature control technology plays an increasingly important role in improving the quality of baked products, optimizing production processes and saving energy. Traditional baking temperature control technology usually relies on temperature sensors for real-time monitoring, combined with experience or pre-set temperature control schemes for adjustment. However, due to the lack of comprehensive monitoring and intelligent adjustment capabilities of the traditional temperature control system for the baking process, problems such as insufficient temperature control accuracy and energy waste are prone to occur, and it is difficult to fully respond to complex and variable baking environments and material characteristics. Therefore, exploring more accurate, intelligent and energy-saving temperature control methods has become a trend in current technology development.

[0003] In recent years, with the introduction of Internet of Things technology and intelligent control systems, baking temperature control technology has made significant progress. Existing technologies have introduced temperature feedback closed-loop control systems that automatically adjust the heating intensity of equipment by monitoring temperature and feedback errors in real time, thereby improving the accuracy and stability of temperature control. In this way, the system can more flexibly respond to temperature fluctuations, avoiding excessive heating or inefficient operation. At the same time, by monitoring the operating state of the heating equipment, the operating mode of the equipment can be adjusted in a timely manner, improving the energy efficiency of the equipment and reducing energy consumption.

[0004] However, existing technologies mainly rely on a single temperature sensor, which cannot fully capture the material response characteristics (such as expansion, color change, etc.) during the baking process, resulting in a lack of comprehensive perception and prediction capabilities of the system for the baking process. Although temperature feedback closed-loop control can adjust the overall temperature, it lacks precise regulation of different areas within the equipment, which can cause local overheating or uneven temperature. Moreover, existing technologies focus on temperature control and ignore energy efficiency management, making it difficult to achieve low energy consumption while achieving ideal baking results. SUMMARY

[0005] To solve the technical problems mentioned in the background art, the present application proposes an intelligent baking temperature control system and method based on the Internet of Things.

[0006] To this end, the technical solution adopted by the present application is as follows:

[0007] An intelligent baking temperature control system based on the Internet of Things, characterized in that the system comprises:

[0008] M1, a data perception module, collects multi-source heterogeneous data from the roasting equipment, the multi-source heterogeneous data including temperature distribution data and material morphology images; processes the multi-source heterogeneous data through data cleaning and feature alignment, and performs data fusion on the processed multi-source heterogeneous data to output a standardized roasting data set;

[0009] M2, a dynamic modeling module, constructs a temperature field space-time model based on the standardized roasting data, the temperature field space-time model containing equipment state parameters and material response characteristics; according to the temperature field space-time model, a digital twin is output;

[0010] M3, an intelligent decision-making and collaborative execution module, based on the digital twin, performs joint analysis of temperature control strategy and energy consumption optimization, generates a temperature control strategy and energy consumption optimization scheme, and outputs a control instruction set; converts the control instruction set into device executable signals to drive the roasting equipment execution mechanism to complete the operation, and collects the execution state data in real time and feeds back to the dynamic modeling module to form a closed loop control loop;

[0011] M4, an interactive monitoring module, provides a visual interface to display temperature field evolution trend, equipment state diagram and material response characteristic information, supports user to modify the control instruction set, and synchronizes the modified control instruction set to the intelligent decision-making and collaborative execution module.

[0012] Further, the multi-source heterogeneous data is collected by temperature sensors and RGB cameras, the temperature sensors collect temperature distribution data, and the RGB collects material morphology image data,

[0013] The data cleaning is performed by Kalman filtering to remove interference signals in the multi-source heterogeneous data to obtain cleaned multi-source heterogeneous data,

[0014] The feature alignment aligns the temperature distribution data and material morphology image data on the time axis by linear interpolation method to obtain aligned multi-source heterogeneous data,

[0015] The data fusion fuses the temperature distribution data and material morphology image data by Bayesian fusion method, and the fused data is standardized as a roasting data set D std .

[0016] Further, the temperature field space-time model adopts a multi-dimensional heat conduction modeling method and is constructed based on a heat conduction equation, the formula being:

[0017]

[0018] wherein T(x, t) is a temperature field at position x and time t; k(x, t; D std ) is thermal conductivity; Q(x, t; Dstd ) is a heat source term.

[0019] Further, the equipment state parameters include heating intensity, wind speed level and microwave source changes, the temperature field space-time model is introduced through the heat source term,

[0020] The material response characteristics are introduced into the temperature field space-time model through the thermal conductivity,

[0021] Through the temperature field space-time model, the digital twin is generated, including temperature field data, equipment running state and material response characteristics,

[0022] The temperature field data is the temperature distribution T(x, t) and the predicted temperature

[0023] The equipment running state is the running state of the heating element, the wind speed and the microwave equipment;

[0024] The material response characteristics are the expansion degree and the surface color change of the material.

[0025] Further, the joint analysis is performed through a multi-objective optimization method, and balance is achieved among multiple objectives, including temperature control error, energy consumption error and baking quality error, and the objective function of the multi-objective optimization method is represented as:

[0026] min (λ1E temp + λ2E energy + λ3E quality )

[0027] Wherein, E temp is the temperature control error, indicating the difference between the actual temperature and the target temperature; E energy is the energy consumption error, reflecting the optimization degree of energy consumption; E quality is the baking quality error, measuring the influence of temperature control on the final product quality; λ1, λ2, λ3 are weight coefficients.

[0028] Through a genetic algorithm, iterative optimization is performed among multiple objective functions, the iterative optimization includes initialization, selection, crossover and mutation and iterative update, and finally a balanced solution space is obtained, according to which the temperature control strategy and the energy consumption optimization scheme are generated,

[0029] The temperature control strategy is a control strategy for heating elements, wind speed levels and microwave sources,

[0030] The energy consumption optimization scheme determines the working mode of the heating element, the wind speed regulator and the microwave source according to the output of the genetic algorithm.

[0031] Further, the control instruction set is converted into device executable signals through the device control interface, including heating intensity instructions, wind speed level instructions, and microwave compensation amount instructions,

[0032] The heating intensity instructions adjust the power output of the heating element through PWM control signals,

[0033] The wind speed level instructions adjust the fan speed according to the temperature control requirements of different areas,

[0034] The microwave compensation amount instructions adjust the heating intensity and frequency of the microwave source according to the real-time material state (expansion degree, color change),

[0035] During the execution of the control instruction set, the execution state data is synchronously collected, including actual temperature data, device running state data, and material response characteristic data, and the execution state data is fed back to the dynamic modeling module, and the update of the digital twin is performed according to the execution state data, including temperature field feedback correction, device state optimization, and material response characteristic optimization,

[0036] The temperature field feedback correction updates the temperature field space-time model through the comparison of actual temperature and predicted temperature,

[0037] The device state optimization adjusts the operation of the baking equipment actuator by analyzing whether the baking equipment is in an overworked or inefficient state through feedback data,

[0038] The material response characteristic optimization changes the heating intensity and wind speed level according to whether the expansion degree and surface color change of the material are abnormal.

[0039] Further, the temperature field evolution trend chart displays the temperature change trend of different areas in the baking equipment, and the temperature field evolution trend chart uses a 3D curved surface chart to display the temperature of each area through color depth (red represents high temperature and blue represents low temperature), and is updated in real time, and the rate and trend of temperature change are displayed,

[0040] The device state chart displays the working state of the baking equipment, including the running state of the heating element, the wind speed controller, and the microwave source device, and the device state chart presents the power output, wind speed level, and microwave compensation amount information of the device in the form of charts and real-time animations, so that the user can clearly see the current working mode of the device and check whether there are abnormal and unstable situations,

[0041] The material response characteristic information provides a visual image of the surface state of the baking material, including the expansion condition and color change, and through image acquisition and processing, the thermal response characteristics of the material are displayed in the form of images and dynamic charts,

[0042] In the visualization interface, the user can interactively modify the current control instruction set, directly adjust the power intensity of the heating element, the speed of the fan, and the heating intensity and frequency of the microwave source through a sliding bar, an input box, and a graphical interface, and submit the modified control instruction set,

[0043] The modified control instruction set is synchronized to the intelligent decision-making and collaborative execution module, and a new heating intensity, wind speed level, and microwave compensation control instruction set is generated, and the new control instruction set is fed back to the baking equipment actuator.

[0044] An intelligent baking temperature control method based on the Internet of Things, the method comprising:

[0045] S1, collecting multi-source heterogeneous data from the baking equipment, including temperature distribution data and material morphology images, and processing and fusing the multi-source heterogeneous data through data cleaning and feature alignment to output a standardized baking data set;

[0046] S2, based on the standardized baking data, constructing a temperature field space-time model, the temperature field space-time model containing device state parameters and material response characteristics; outputting a digital twin according to the temperature field space-time model;

[0047] S3, according to the digital twin, performing joint analysis of temperature control strategy and energy consumption optimization, generating a control instruction set, and converting the control instruction set into a device executable signal to drive the baking equipment actuator to complete the operation, and collecting the execution state data in real time and feeding back to the dynamic modeling module to form a closed loop control loop;

[0048] S4, displaying the temperature field evolution trend, device state graph, and material response characteristic information through a visualization interface, and supporting user modification of the control instruction set, and synchronizing the modified control instruction set to step 3.

[0049] Compared with the prior art, the advantages of the present application are:

[0050] 1. The present application collects multi-source heterogeneous data through temperature sensors and RGB cameras, and processes them through Kalman filtering and Bayesian fusion method, which considers both thermal parameters and material surface characteristics, and is more accurate in baking state perception.

[0051] 2. The present application can simulate the temperature distribution in the baking process by constructing a temperature field space-time model, and realize fine regulation and control of the whole area through digital twin prediction control, ensuring that every part of the baking process can be uniformly heated.

[0052] 3. The present application introduces a multi-objective optimization algorithm, which jointly analyzes the temperature control error, energy consumption error and baking quality error, optimizes the balance between energy consumption and temperature control effect, and ensures that the temperature precision is guaranteed while the energy consumption is minimized.

[0053] 4. The present application displays the temperature field evolution trend, equipment state and material response characteristics through a visual interface, and provides real-time interaction function, allowing users to adjust the control instructions according to actual needs, and improving the flexibility and user experience of the system. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Fig. 1 Flow chart of the intelligent baking temperature control system of the present application;

[0056] Fig. 2 Flow chart of the dynamic modeling module of the present application;

[0057] Fig. 3 Flow chart of the intelligent decision-making and collaborative execution module of the present application. DETAILED DESCRIPTION

[0058] In order to achieve the above purpose, the present application is realized by the following technical solutions. The present application provides an intelligent baking temperature control system based on Internet of Things, please refer to Figs. 1-3 The system comprises:

[0059] M1, data perception module, collecting multi-source heterogeneous data from baking equipment, the multi-source heterogeneous data including temperature distribution data and material morphology image; processing and fusing the multi-source heterogeneous data through data cleaning and feature alignment, outputting standardized baking data set,

[0060] The data perception module is responsible for collecting multi-source heterogeneous data from the baking equipment, and performing data cleaning, feature alignment and fusion. The core task of this module is to provide high-quality standardized data for the subsequent dynamic modeling module,

[0061] The collection content includes collecting temperature distribution data by using temperature sensor, and collecting material morphology image by using high-resolution RGB camera;

[0062] The collected multi-source heterogeneous data is processed, including data cleaning and feature alignment,

[0063] The multi-source heterogeneous data acquired by the sensor contains noise, and the interference signal needs to be removed through a data cleaning step. In this embodiment, Kalman filtering is used for data cleaning to obtain cleaned multi-source heterogeneous data,

[0064] Due to the different sampling frequencies and timestamps of different sensor data, time synchronization and spatial alignment technology is adopted for processing. In this embodiment, the linear interpolation method is used to align the temperature data and material image data on the time axis to obtain aligned multi-source heterogeneous data,

[0065] The aligned multi-source heterogeneous data is fused. In this embodiment, the data from different sensors is fused by the Bayesian fusion method, and the fused data is standardized into a unified baking data set D std The standardized baking data set is used as the output of this module for subsequent model construction.

[0066] M2, a dynamic modeling module, constructs a temperature field spatiotemporal model based on the standardized baking data, wherein the temperature field spatiotemporal model contains device state parameters and material response characteristics; and outputs a digital twin based on the temperature field spatiotemporal model,

[0067] The dynamic modeling module aims to construct a temperature field spatiotemporal model with predictability, adaptability and high fidelity, and to construct a baking process digital twin through model driving. This module integrates multi-source heterogeneous data driving mechanism, hybrid modeling method based on physical prior, continuous self-updating mechanism and uncertainty quantification capability, and is the key to realizing intelligent temperature control precise closed-loop regulation;

[0068] The temperature field spatiotemporal model aims to accurately simulate the spatial and temporal evolution of temperature in the baking process. A multi-dimensional heat conduction modeling method is adopted to solve the shortcomings of traditional models in dealing with complex materials, equipment aging and dynamic heat sources,

[0069] The temperature field spatiotemporal model is constructed based on the heat conduction equation, and the formula is:

[0070]

[0071] Wherein, T(x,t) is the temperature field at position x and time t; k(x,t;D std ) is the thermal conductivity; Q(x,t;D std ) is the heat source term;

[0072] The device state parameters reflect the running state of the baking equipment, including the change of heating intensity, wind speed level and microwave source. The heat source term Q(x,t;D std ) is introduced into the model. Specifically, the change of the device state parameters directly affects the intensity and distribution of the heat source term. This information is obtained through the standardized baking data set D stdPassed to the dynamic modeling module, Q(x,t;D std ) represents the heat distribution generated by the baking equipment. According to the heat source density generated by the working state of the equipment during the actual baking process, the baking equipment is in a high heating state. Q(x, t; D std ) will increase accordingly, driving the change of temperature field;

[0073] The material response characteristics reflect the material's ability to respond to heat transfer, which is expressed by the thermal conductivity k(x,t;D std ) indicates that the thermal conductivity of the material will change with time and space, depending on the type, thickness, humidity and temperature of the material. In this embodiment, the material response characteristics are expressed by the thermal conductivity k(x, t; D std ) reflects that in the modeling formula, the thermal conductivity k(x,t;D std ) as a position- and time-dependent function, reflects the thermal conductivity of the material at different time and space positions. Material image data is used to identify changes in the material surface state, such as expansion and coking, which in turn affect the thermal conductivity k(x, t; D std ), the surface of the material becomes dry or hard, the thermal conductivity will decrease, resulting in reduced heat conduction efficiency.

[0074] The equipment state parameters are expressed by the heat source term Q(x, t; D std ) is reflected in the model, reflecting the impact of factors such as equipment heating intensity and power changes on the temperature field;

[0075] The material response characteristics are characterized by thermal conductivity k(x,t;D std ) is reflected in the model, which represents the heat conduction capacity of the material under different time and space conditions;

[0076] The equipment state parameters and material response characteristics jointly determine the evolution of the temperature field during the baking process, and the changes in the equipment state parameters and material response characteristics will be updated and predicted in real time through the model.

[0077] To improve the accuracy of the model, a physics-guided neural network (PINN) is used for model training. PINN combines the physical priors of the heat conduction equation with data-driven deep learning capabilities to ensure that the model conforms to physical laws while being able to learn complex temperature field changes from data. During the training process, the network weights are optimized through backpropagation, and the model is gradually adjusted to ensure that it captures the nonlinear thermal behavior of the baking process from the data while ensuring physical consistency.

[0078] Through the temperature field spatiotemporal model, the dynamic modeling module generates a digital twin, including temperature field data, equipment operating status and material response characteristics.

[0079] The temperature field data is the temperature distribution T(x, t) at the current time and the predicted temperature T(x, t+Δt) at the predicted time;

[0080] The equipment operation state represents the operation state of the monitoring heating element, air speed, microwave, etc. equipment, and provides the basis for equipment adjustment,

[0081] The material response characteristics represent the expansion degree, surface color change, etc. of the material.

[0082] M3, intelligent decision-making and collaborative execution module, joint analysis of temperature control strategy and energy consumption optimization, generate temperature control strategy and energy consumption optimization scheme, output control instruction set; convert the control instruction set into device executable signal, drive the baking equipment execution mechanism to complete the operation, and real-time collection of execution state data feedback to the dynamic modeling module, forming a closed loop control loop,

[0083] Based on the digital twin, the joint analysis of temperature control strategy and energy consumption optimization is carried out by using multi-objective optimization method. The optimization process aims to balance three main targets, including temperature control error, energy consumption error and baking quality error. The form of the optimization objective function is:

[0084] min(λ1E temp +λ2E energy +λ3E quality )

[0085] Wherein, E temp is the temperature control error, which represents the difference between the actual temperature and the target temperature; E energy is the energy consumption error, which reflects the optimization degree of energy consumption; E quality is the baking quality error, which measures the influence of temperature control on the final product quality; λ1, λ2, λ3 are weight coefficients, which are used to balance the importance of different optimization targets;

[0086] Through genetic algorithm, continuous iteration optimization is carried out among multiple objective functions, and finally the balanced solution space is obtained. The optimization process includes initialization, selection, crossover and mutation, and iteration update. During the algorithm running process, the temperature control strategy and energy efficiency optimization are optimized through joint analysis. Specifically, the joint analysis of temperature control strategy optimization and energy efficiency optimization reflects the balance between control parameters (heating intensity, air speed, microwave compensation amount) and equipment energy efficiency.

[0087] Through the joint analysis process of multi-objective optimization method, the temperature control strategy and energy consumption optimization scheme are finally generated,

[0088] The temperature control strategy is the control strategy of heating element, air speed level and microwave source. These strategies control the working state of the equipment to ensure the uniformity and accuracy of the baking process.

[0089] The energy consumption optimization scheme determines the working modes of the heating element, the air speed regulator, and the microwave source according to the output of the genetic algorithm, to ensure that the temperature control target is reached while minimizing energy consumption;

[0090] Based on the results of the optimization algorithm, the optimized temperature control strategy and the energy consumption optimization scheme generate a control instruction set, including heating intensity, air speed level, and microwave compensation amount;

[0091] The control instruction set is converted into device executable signals through the device control interface to drive the baking equipment actuators to complete the operation, specifically,

[0092] The heating intensity instruction adjusts the power output of the heating element through the PWM control signal to achieve precise temperature adjustment in different areas of the baking cavity;

[0093] The air speed level instruction adjusts the fan speed according to the temperature control requirements of different areas to help distribute the temperature evenly;

[0094] The microwave compensation amount instruction adjusts the heating intensity and frequency of the microwave source according to the real-time material state (such as expansion degree, color change, etc.), to optimize the heating effect;

[0095] During execution, the intelligent decision-making and collaborative execution module collects execution state data in real time, including actual temperature data, device running state data, and material response characteristic data, and feeds back to the dynamic modeling module for updating the digital twin, including temperature field feedback correction, device state optimization, and material response characteristic optimization, forming a closed-loop control loop, specifically,

[0096] The temperature field feedback correction updates the temperature field space-time model in real time through the comparison of actual temperature and predicted temperature, to optimize the subsequent temperature control strategy;

[0097] The device state optimization dynamically optimizes the operation of the device actuators through feedback data analysis to determine whether the device is overworked or in an inefficient state, to improve overall energy efficiency;

[0098] The material response characteristic optimization changes the heating intensity and air speed level by analyzing whether the material's expansion degree and surface color change are abnormal.

[0099] M4, the interactive monitoring module, provides a visual interface to display temperature field evolution trends, device state graphs, and material response characteristic information, supports users to modify the control instruction set, and synchronizes the modified control instruction set to the intelligent decision-making and collaborative execution module,

[0100] The interactive monitoring module displays key data during the baking process to the user through a visual interface, helping the user to monitor the temperature field changes, device running state, and material response characteristics in real time,

[0101] The temperature field evolution trend chart displays the temperature change trend of different areas in the baking equipment, and the temperature field evolution chart uses a 3D surface chart to show the temperature of each area through color depth (such as red for high temperature and blue for low temperature). The chart is updated in real time to reflect the dynamic changes of the current temperature field and show the rate and trend of temperature change, providing an intuitive temperature control effect for the user;

[0102] The equipment state chart displays the working state of the baking equipment, including the running state of the heating element, the wind speed controller and the microwave source equipment. The equipment state chart presents the power output, wind speed level and microwave compensation amount information of the equipment through charts and real-time animations. The user can clearly see the current working mode of the equipment and check whether there is any abnormal or unstable situation,

[0103] The material response characteristic information provides a visual image of the surface state of the baking material, including the expansion condition, color change, surface dryness degree, etc., helping the user to understand the response of the material to heat conduction. Through image acquisition and processing, the thermal response characteristics of the material will be displayed in the form of images or dynamic charts, which facilitates the user to identify the baking state of the material,

[0104] In the visualization interface, the user can perform interactive operations to modify the current control instruction set. When the temperature of a certain baking area exceeds the maximum threshold value or is lower than the minimum threshold value, the user can manually adjust the power intensity of the heating element and the speed of the fan to meet the baking requirements. According to the expansion and color change of the baking material, the heating intensity and frequency of the microwave source are adjusted to ensure uniform heating of the material and avoid excessive heating or uneven heating. The specific operation is,

[0105] In the visualization interface, the user directly adjusts the power intensity of the heating element, the speed of the fan and the heating intensity and frequency of the microwave source through the slide bar, input box and graphical interface. The system reflects the adjustment of the parameters in real time and shows the potential impact on the temperature field evolution. After the user confirms the modification, the user can submit the modified control instruction set.

[0106] Once the user modifies the control instruction set, the modified control instruction set is synchronized in real time to the intelligent decision-making and collaborative execution module. According to the user-modified control instruction set, new heating intensity, wind speed level and microwave compensation amount instructions are generated, and the new control instruction set is fed back to the baking equipment execution mechanism;

[0107] The interactive monitoring module displays the real-time temperature field evolution trend, equipment state diagram and material response characteristic information through a visual interface, helps users to intuitively understand the temperature control effect and equipment running state of the baking process, and users can adjust the control instruction set in real time through the interactive correction function, and synchronize the corrected instruction set to the intelligent decision and collaborative execution module, to ensure the optimization and efficient operation of the temperature control system. Through these functions, the interactive monitoring module not only improves the operability and flexibility of the system, but also ensures the intelligentization, accuracy and safety of the temperature control process, and provides strong support for the optimization of the entire baking process.

[0108] An intelligent baking temperature control method based on the Internet of Things, the method comprising:

[0109] S1, collecting multi-source heterogeneous data from the baking equipment, including temperature distribution data and material morphology images, and processing and fusing the multi-source heterogeneous data through data cleaning and feature alignment to output a standardized baking data set;

[0110] S2, based on the standardized baking data, constructing a temperature field space-time model, the temperature field space-time model containing equipment state parameters and material response characteristics; outputting a digital twin according to the temperature field space-time model;

[0111] S3, according to the digital twin, performing temperature control strategy and energy consumption optimization analysis through a multi-objective optimization algorithm, generating a control instruction set, and converting the control instruction set into a device executable signal, driving the baking equipment actuator to complete the operation through the device executable signal, and collecting the execution state data in real time Feedback to the dynamic modeling module to form a closed loop control loop;

[0112] S4, display the temperature field evolution trend, equipment state diagram and material response characteristic information through a visual interface, and support users to correct the control instruction set, and synchronize the corrected control instruction set to step 3.

[0113] The present application provides an intelligent baking temperature control system and method based on the Internet of Things, through the data sensing module, combining temperature distribution data and material morphology image data, using data cleaning, feature alignment and data fusion technology, improving the temperature control precision and response ability; by constructing a temperature field space-time model, combining a digital twin for joint analysis of temperature control strategy and energy consumption optimization, using a multi-objective optimization algorithm to ensure the balance of temperature control precision and energy efficiency, the present application also provides a visual interactive interface, supporting users to monitor and adjust control parameters in real time, improving the operation experience of users, finally realizing precise temperature control, dynamic energy efficiency optimization and all-round user interaction experience for the baking process, making the baking production process more intelligent, energy-saving and efficient.

[0114] In summary, the application has the advantages that the temperature control precision is improved by multi-source heterogeneous data fusion and temperature field space-time modeling, the balance between temperature control precision and energy efficiency is realized by joint analysis of multi-objective optimization algorithm, the self-adaptability and real-time performance of the system are ensured by digital twin and closed-loop feedback mechanism, the operability and flexibility of the user are enhanced by visual interactive interface, and the intelligentization and precise control capability of the system are greatly improved.

[0115] The above merely describes a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An Internet of Things based intelligent baking temperature control system, characterized in that, The system comprises: M1, a data perception module, collecting multi-source heterogeneous data from a roasting device, the multi-source heterogeneous data including temperature distribution data and material morphology images; processing the multi-source heterogeneous data through data cleaning and feature alignment, and performing data fusion on the processed multi-source heterogeneous data to output a standardized roasting data set; M2, a dynamic modeling module, constructing a temperature field space-time model based on the standardized roasting data, the temperature field space-time model containing device state parameters and material response characteristics; outputting a digital twin based on the temperature field space-time model; M3, an intelligent decision-making and collaborative execution module, based on the digital twin, performing joint analysis of temperature control strategies and energy consumption optimization to generate temperature control strategies and energy consumption optimization schemes, and outputting control instruction sets; converting the control instruction sets into device executable signals to drive the roasting device execution mechanism to complete the operation, and collecting execution state data in real time and feeding back to the dynamic modeling module to form a closed-loop control loop; M4, an interactive monitoring module, providing a visual interface to display temperature field evolution trends, device state diagrams and material response characteristic information, supporting user modification of the control instruction sets, and synchronizing the modified control instruction sets to the intelligent decision-making and collaborative execution module.

2. The intelligent baking temperature control system based on the Internet of Things according to claim 1, characterized in that, The multi-source heterogeneous data is collected by temperature sensors and RGB cameras, the temperature sensors collect temperature distribution data, and the RGB cameras collect material morphology image data, The data cleaning is performed by Kalman filtering to remove interference signals in the multi-source heterogeneous data to obtain cleaned multi-source heterogeneous data, The feature alignment aligns the temperature distribution data and material morphology image data on the time axis by a linear interpolation method to obtain aligned multi-source heterogeneous data, The data fusion fuses the temperature distribution data and the material morphology image data through a Bayesian fusion method, and the fused data is standardized as a baking data set .

3. The intelligent baking temperature control system based on the Internet of Things according to claim 2, characterized in that, The temperature field space-time model is constructed based on a heat conduction equation by a multi-dimensional heat conduction modeling method, and the formula is: wherein, is the temperature field at position x and time t; is the thermal conductivity; is the heat source term.

4. The intelligent baking temperature control system based on the Internet of Things according to claim 3, characterized in that, The device state parameters include heating intensity, wind speed level and microwave source changes, which are introduced into the temperature field space-time model through the heat source term, The material response characteristics are introduced into the temperature field space-time model through the thermal conductivity, The digital twin is generated based on the temperature field space-time model, including temperature field data, device operating state and material response characteristics, The temperature field data is the temperature distribution at the current time and the predicted time and the predicted temperature ; The device operating state is the operating state of heating elements, wind speed and microwave devices; The material response characteristics are the expansion degree and surface color change of the material.

5. The intelligent baking temperature control system based on the Internet of Things according to claim 4, characterized in that, The joint analysis is performed by a multi-objective optimization method to achieve balance among multiple objectives, including temperature control error, energy consumption error and roasting quality error, and the objective function of the multi-objective optimization method is represented as: wherein, is a temperature control error, representing the difference between the actual temperature and the target temperature; is an energy consumption error, reflecting the optimization degree of energy consumption; is a baking quality error, measuring the influence of temperature control on the final product quality; ; Through a genetic algorithm, iterative optimization is performed among multiple objective functions, including initialization, selection, crossover and mutation, and iterative updating, and finally a balanced solution space is obtained, and based on the balanced solution space, the temperature control strategies and energy consumption optimization schemes are generated, The temperature control strategies are control strategies for heating elements, wind speed levels and microwave sources, The energy consumption optimization scheme determines the working modes of heating elements, wind speed regulators and microwave sources according to the output of the genetic algorithm.

6. The intelligent baking temperature control system based on the Internet of Things according to claim 5, characterized in that, The control instruction set is converted into device executable signals through the device control interface, including heating intensity instructions, wind speed level instructions, and microwave compensation amount instructions, The heating intensity instructions adjust the power output of the heating element through PWM control signals, The wind speed level instructions adjust the speed of the fan according to the temperature control requirements of different areas, The microwave compensation amount instructions adjust the heating intensity and frequency of the microwave source according to the real-time material state, During the execution of the control instruction set, execution state data is synchronously collected, including actual temperature data, device operating state data, and material response characteristic data, and the execution state data is fed back to the dynamic modeling module, and the digital twin is updated according to the execution state data, including temperature field feedback correction, device state optimization, and material response characteristic optimization, The temperature field feedback correction updates the temperature field space-time model through the comparison of actual temperature and predicted temperature, The device state optimization adjusts the operation of the baking equipment actuator by analyzing whether the baking equipment is in an overworked or inefficient state through feedback data, The material response characteristic optimization changes the heating intensity and wind speed level according to the expansion degree of the material and whether the surface color change is abnormal.

7. The intelligent baking temperature control system based on the Internet of Things according to claim 6, characterized in that, The temperature field evolution trend chart displays the temperature change trend of different areas in the baking equipment, and the temperature field evolution trend chart uses a 3D curved surface chart to display the temperature of each area through color depth, and is updated in real time, and displays the rate and trend of temperature change, The device state chart displays the working state of the baking equipment, including the running state of the heating element, the wind speed controller, and the microwave source device, and the device state chart presents the power output, wind speed level, and microwave compensation amount information of the device in the form of charts and real-time animations, so that the user can clearly see the current working mode of the device and check whether there are abnormal and unstable conditions, The material response characteristic information provides a visual image of the surface state of the baking material, including the expansion condition and color change, and through image acquisition and processing, the thermal response characteristics of the material are displayed in the form of images and dynamic charts, In the visualization interface, the user can perform interactive operations to modify the current control instruction set, directly adjust the power intensity of the heating element, the speed of the fan, and the heating intensity and frequency of the microwave source through a sliding bar, an input box, and a graphical interface, and submit the modified control instruction set, The modified control instruction set is synchronized to the intelligent decision-making and collaborative execution module, and new heating intensity, wind speed level, and microwave compensation amount control instruction sets are generated, and the new control instruction set is fed back to the baking equipment actuator.

8. An intelligent baking temperature control method based on the Internet of Things, the method comprising: S1, collecting multi-source heterogeneous data from the baking equipment, including temperature distribution data and material morphology images, and processing and fusing the multi-source heterogeneous data through data cleaning and feature alignment to output a standardized baking data set; S2, based on the standardized baking data, a temperature field space-time model is constructed, which contains device state parameters and material response characteristics; a digital twin is output according to the temperature field space-time model; S3, according to the digital twin, a combined analysis of temperature control strategy and energy consumption optimization is carried out, a control instruction set is generated, and the control instruction set is converted into a device executable signal to drive the baking equipment actuator to complete the operation, and the execution state data is fed back to the dynamic modeling module in real time to form a closed loop control loop; S4, the temperature field evolution trend, device state diagram and material response characteristic information are displayed through the visual interface, and the user can correct the control instruction set, and the corrected control instruction set is synchronized to step 3.

Images