A temperature control system, method and cooking apparatus for a cooking apparatus

Abstract

The application provides a temperature control system and method for a cooking device and the cooking device, comprising an intelligent decision module, a core control module and a sensor module; the sensor module is used to acquire current state information of the cooking device and send the current state information to the intelligent decision module and the core control module; the intelligent decision module is used to analyze a control strategy based on an agent, the current state information and a target cooking instruction, obtain a temperature control strategy and send the temperature control strategy to the core control module; the temperature control strategy is used to control working parameters of the cooking device, so that an operation temperature of the cooking device in a specified period meets a preset dynamic curve; the core control module comprises an adaptive model prediction module, which is used to update the temperature control strategy according to updated state information of the cooking device in the execution process of the temperature control strategy. The application realizes intelligent control of the temperature by using the agent, and has fast response speed, high precision and strong robustness.

Description

Technical Field

[0001] This invention relates to the intersection of smart home appliances and advanced control technology, and in particular to a temperature control system, method and cooking equipment for cooking equipment. Background Technology

[0002] Currently, the temperature control systems of commercially available and mainstream research cooking equipment (such as ovens) are mainly based on the classic PID control scheme. The system obtains the actual temperature of the internal cavity through sensors, compares it with the temperature value set by the user to obtain the temperature deviation, and then directly outputs the control signal to the heating actuator (such as a relay or solid-state relay) through a linear combination of proportional, integral, and derivative operations.

[0003] Some existing improvement schemes combine feedforward compensation or safety threshold modules with the classic PID, such as forcibly cutting off the power when the temperature exceeds the limit. However, the above-mentioned existing improvement schemes still have significant shortcomings and limitations in achieving precise control of the internal cavity temperature, and it is difficult to balance control accuracy, response speed and stability. Summary of the Invention

[0004] To address the problems existing in the prior art, the present invention provides a temperature control system, method, and cooking equipment for cooking devices; the technical solution is as follows: On the one hand, the present invention provides a temperature control system for cooking equipment, including an intelligent decision-making module, a core control module, and a sensor module; The sensor module is used to acquire the current status information of the cooking equipment and send the current status information to the intelligent decision module and the core control module; The intelligent decision-making module is used to parse the current state information and target cooking instructions based on the intelligent agent to obtain a temperature control strategy, and then send the temperature control strategy to the core control module. The temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment meets the preset dynamic curve within a specified time period. The core control module includes an adaptive model prediction module, which is used to update the temperature control strategy based on the updated status information of the cooking equipment during the execution of the temperature control strategy.

[0005] Furthermore, the intelligent decision-making module includes: The sensing module is used to analyze the current status information and the target cooking command to obtain the initial operating parameters of the cooking equipment; The evaluation module is used to predict the simulated cooking process corresponding to the initial working parameters based on the initial working parameters, the preset thermodynamic model and historical cooking data, and obtain the simulated cooking state data corresponding to the simulated cooking process. The simulated cooking state data is used to indicate the continuous cooking operation and cooking quality information of the cooking equipment during the simulated cooking process. The decision-making module is used to generate a strategy based on the current state information and the simulated cooking state data through a multi-objective optimization model, thereby obtaining the temperature control strategy. The execution sending module is used to send the temperature control strategy to the core control module.

[0006] Furthermore, the multi-objective optimization model is a multi-objective reward function, which is used to predict temperature tracking accuracy, cooking energy consumption, cooking result quality, and equipment wear and tear costs.

[0007] Furthermore, the intelligent decision-making module also includes: The learning submodule is used to perform simulation optimization on the thermodynamic model based on the current state information, the target cooking command, and the temperature control strategy through simulation algorithms to obtain an updated thermodynamic model; The learning submodule is also used to associate and store the current state information, the target cooking command, and the temperature control strategy as the historical cooking data; the historical cooking data includes multiple historical state information, multiple historical target cooking commands, and multiple corresponding historical temperature control strategies in multiple historical cooking processes.

[0008] Furthermore, the adaptive model prediction module is used for: During the execution of the temperature control strategy, compensation parameters are predicted based on the updated state information to obtain the adaptive compensation parameters of the cooking equipment. The operating parameters in the current temperature control strategy are compensated according to the adaptive compensation parameters to obtain an updated temperature control strategy. The updated temperature control strategy is used to control the operating temperature of the cooking equipment to meet the updated dynamic curve after adaptive compensation.

[0009] Furthermore, the intelligent decision-making module also includes: The monitoring submodule is used to receive the updated status information sent by the sensor module during the execution of the temperature control strategy. The intelligent decision-making module is also used to repeatedly perform control strategy parsing on the updated state information and the target cooking instruction to obtain a replanned temperature control strategy, and send the replanned temperature control strategy to the core control module. The adaptive model prediction module is used to cyclically execute the temperature control strategy update operation during the execution of the replanning temperature control strategy.

[0010] Furthermore, the core control module also includes: An event-triggered compensation module is used to monitor sudden interference information of the cooking equipment during the execution of the temperature control strategy. The sudden interference information is used to indicate a sudden operation that changes the current environmental state of the cooking equipment. The temperature control strategy is fed forward based on the sudden interference information to obtain the temperature control strategy after feedforward compensation. The adaptive model prediction module is also used to update the feedforward compensated temperature control strategy according to the updated state information of the cooking equipment during the execution of the temperature control strategy.

[0011] Furthermore, the temperature control system also includes a safety monitoring module, which includes: The preventive health management module is used to evaluate the current status information to obtain the deterioration trend information of the cooking equipment, and the deterioration trend information is used to indicate the confidence level of the cooking equipment malfunctioning. The fault diagnosis module is used to perform fault diagnosis based on the current status information and determine the fault information in the cooking equipment. The fault information is used to indicate the fault that has occurred in the cooking equipment. The threshold hard protection module is used to control the hardware circuit to trigger power-off protection when the current state information is detected to exceed a preset safety threshold.

[0012] On the other hand, the present invention also provides a temperature control method for a cooking device, implemented based on a temperature control system for a cooking device as described in any of the preceding claims, the method comprising: The current status information of the cooking device is obtained and sent to the intelligent decision-making module and the core control module. Based on the intelligent agent, the current state information and target cooking instructions are parsed to obtain a temperature control strategy, which is then sent to the core control module. The temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment meets the preset dynamic curve within a specified time period. During the execution of the temperature control strategy, the temperature control strategy is updated based on the updated status information of the cooking equipment.

[0013] On the other hand, the present invention also provides a cooking apparatus that performs cooking based on a temperature control system for a cooking apparatus as described in any of the preceding claims or a temperature control method for a cooking apparatus as described above.

[0014] Implementing this invention has the following beneficial effects: The intelligent decision-making module of this invention uses an agent as the core decision-making unit and, together with the adaptive model prediction module of the core control module, constructs an integrated collaborative control architecture of "perception-decision-execution-learning". It deeply integrates agent technology into the top layer of the control system, realizes intelligent control of the internal temperature of the cooking equipment, and has fast response speed, high precision, strong robustness, excellent energy efficiency, and personalized learning ability. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0016] Figure 1 This is a schematic diagram of a temperature control system for a cooking device provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an intelligent decision-making module provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a core control module provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of another intelligent decision-making module provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of a preferred intelligent decision-making module provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a safety monitoring module provided in an embodiment of the present invention; Figure 7 A logic structure diagram of a temperature control method for a cooking device provided in an embodiment of the present invention; Figure 8 This is a logical structure diagram of an intelligent agent control strategy parsing method provided in an embodiment of the present invention; Figure 9 A logical structure diagram of an adaptive update method for a temperature control strategy provided in an embodiment of the present invention; Figure 10 A logical structure diagram of a feedforward compensation method for a temperature control strategy provided in an embodiment of the present invention; Figure 11 A logical structure diagram of a cyclic iterative method for a temperature control strategy provided in an embodiment of the present invention; Figure 12 A logical structure diagram of a learning iteration method for a temperature control system provided in an embodiment of the present invention; Figure 13 A logical structure diagram of a security monitoring method provided in an embodiment of the present invention; Figure 14 This is a hardware structure block diagram of an electronic device that performs a temperature control method for a cooking device, according to an embodiment of the present invention. Detailed Implementation

[0017] 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 a part of the embodiments of the present invention, and not all of the embodiments, and therefore should not be construed as limiting the present invention. 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.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those shown in the figures or descriptions below. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0019] Existing solutions for improving the temperature control systems of cooking equipment still have many shortcomings and limitations: 1) It is difficult to balance control accuracy, response speed and stability: Traditional PID controllers, due to their fixed parameters, inevitably sacrifice response speed to reduce overshoot when facing the inherent thermal inertia and hysteresis of ovens, resulting in long preheating and temperature recovery times; while pursuing parameters for rapid temperature rise tuning can easily cause significant overshoot and oscillation.

[0020] 2) Weak resistance to sudden interference: Existing solutions lack a dedicated and intelligent response mechanism for sudden strong interference such as door opening and dehumidification; PID control usually only responds passively after the interference occurs, and the recovery strategy is singular, resulting in large fluctuations in cavity temperature and a slow recovery process.

[0021] 3) Lack of personalized adaptation and complex scenario handling capabilities: The system cannot autonomously handle complex and variable factors such as food type, weight, initial state and user taste preferences; the pre-programmed curves cannot adapt to all actual situations, and user manual adjustments rely on experience, resulting in poor consistency of baking results; that is, the existing solution is essentially an "open-loop" recipe execution rather than a "closed-loop" quality achievement.

[0022] 4) Lack of system intelligence and self-evolution capabilities: The core control logic of the existing solution is fixed after leaving the factory, and it cannot learn and optimize from historical usage data, cannot adapt to the usage habits of different users, and cannot self-adjust as the components age; the system does not have the ability to simulate expert experience for dynamic planning, decision-making and continuous improvement, which limits its long-term performance and user experience.

[0023] To address at least one of the following problems in existing cooking equipment temperature control systems: difficulty in simultaneously achieving control precision, response speed, and stability; lack of personalized adaptation and complex scenario handling capabilities; and lack of system intelligence and self-evolution capabilities, this invention provides a temperature control system, method, and cooking equipment for cooking devices. The cooking equipment may include kitchen utensils such as ovens, steamers, woks, rice cookers, and pressure cookers. The cooking equipment performs cooking based on its temperature control system or its temperature control method, which achieves precise and reliable temperature control based on the temperature control system. The system comprises an intelligent decision-making module, a core control module, and a sensor module. First, the sensor module acquires the current status information of the cooking equipment and sends this information to the intelligent decision-making module and the core control module. The intelligent decision-making module, based on an intelligent agent, analyzes the current status information and target cooking instructions to derive a temperature control strategy, which is then sent to the core control module. This temperature control strategy controls the operating parameters of the cooking equipment to ensure that the operating temperature of the equipment meets a preset dynamic curve within a specified time period. The core control module includes an adaptive model prediction module, which updates the temperature control strategy based on the updated status information of the cooking equipment during the execution of the temperature control strategy.

[0024] Thus, this temperature control system for cooking equipment deeply integrates the agent as the core decision-making unit into the top layer of the entire control system. It can proactively plan and adjust the temperature control strategy from a global and multi-objective perspective (quality, time consumption, energy consumption, etc.) based on the current state information and target cooking instructions, no longer passively executing fixed programs. This breaks through the limitations of traditional local optimization and achieves true system optimization. Furthermore, during the execution of the temperature control strategy, in conjunction with the adaptive model prediction module, the temperature control module is updated based on the updated state information of the cooking equipment. Through its online adaptive capability, even when the cooking equipment experiences complex operating conditions such as load changes and component aging, the temperature control system can still effectively adjust the temperature control strategy during execution, maintain high-precision temperature tracking, and achieve dynamic closed-loop control at the top-level planning and execution levels. The entire temperature control system has a fast response speed, high precision, strong robustness, excellent energy efficiency, and personalized learning capabilities.

[0025] The following is in conjunction with the instruction manual. Figure 1-6 This invention introduces a temperature control system for a cooking device according to an embodiment of the present invention.

[0026] like Figure 1 As shown in the figure, an embodiment of the present invention provides a temperature control system for a cooking device, including an intelligent decision module 120, a core control module 130, and a sensor module 110.

[0027] The sensor module 110 is used to acquire the current status information of the cooking device and send the current status information to the intelligent decision module 120 and the core control module 130.

[0028] That is, the sensor module 110 is used to monitor the cooking equipment so that the intelligent decision-making module 120 can make proactive plans based on the current status information, and the core control module 130 can adjust the strategy during the execution process based on the current status information.

[0029] The status information acquired by the sensor module 110 can be updated in real time or periodically. This current status information is used to indicate the current environmental status of the cooking device and the status of the cooking device itself, including the temperature array (i.e., temperature spatial distribution) inside the cooking device cavity, the humidity inside the cavity, the weight of the food it carries, the door status, visual images, etc.

[0030] Next, as Figure 1As shown, the intelligent decision-making module 120 is used to analyze the current state information and target cooking instructions based on the intelligent agent to obtain a temperature control strategy, and send the temperature control strategy to the core control module 130; the temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment meets the preset dynamic curve within a specified time period.

[0031] In the intelligent decision-making module 120, the target cooking instruction is used to indicate the desired cooking result of the cooking equipment. For example, roasting golden and crispy chicken wings is a user-level instruction that needs to be perceived and analyzed by the intelligent agent before further decision-making and planning can be carried out.

[0032] The operating parameters are settable values ​​during the cooking process, such as heating and baking, in the cooking equipment. Examples include temperature settings, time settings, heating methods, and power settings. The temperature control strategy includes control commands. In some exemplary embodiments, the control commands are used to control the switching of the operating state of the cooking equipment, such as enabling steam or switching control modes, to change the operating state of the cooking equipment, thereby regulating the operating temperature and other states during the cooking process and improving the accuracy and response speed of the temperature control strategy.

[0033] The preset dynamic curve is part of the temperature control strategy obtained through control strategy analysis. It is a generated dynamic temperature-time set curve. After planning based on the current state information, in the absence of external interference factors, the operating temperature of the cooking equipment can be controlled according to the preset dynamic curve to achieve the expected cooking result indicated by the target cooking command.

[0034] Next, the core control module 130 includes an adaptive model prediction module 310, which is used to update the temperature control strategy according to the updated status information of the cooking equipment during the execution of the temperature control strategy.

[0035] The adaptive model prediction module 310 can adaptively modify the temperature control strategy based on the temperature control strategy issued by the intelligent decision module 120 and the updated status information of the cooking equipment obtained during the execution process, and iterate in a loop so that the desired cooking result indicated by the target cooking command can be achieved in the end.

[0036] Specifically, such as Figure 2 As shown, the intelligent decision-making module 120 includes: The sensing module 210 is used to analyze the current status information and the target cooking command to obtain the initial operating parameters of the cooking device; Evaluation module 220 is used to predict the simulated cooking process corresponding to the initial working parameters based on the initial working parameters, the preset thermodynamic model and historical cooking data, and obtain simulated cooking state data corresponding to the simulated cooking process. The simulated cooking state data is used to indicate the continuous cooking operation and cooking quality information of the cooking equipment during the simulated cooking process. Decision module 230 is used to generate a strategy based on the current state information and the simulated cooking state through a multi-objective optimization model to obtain the temperature control strategy; The sending module 240 is used to send the temperature control strategy to the core control module 130.

[0037] The perception module 210 parses the current state information and the target cooking command, thereby expressing the state information reflecting the cooking equipment environment in a regular, parsable, and computable structural form, realizing a structured environmental state representation, that is, the initial working parameters. These initial working parameters are a time-related parameter array, so that the agent can perceive, understand, and make decisions based on the current state information.

[0038] In the evaluation module 220, the preset thermodynamic model is a mathematical and physical model used to indicate the changes in heat generation, transfer and temperature distribution inside the cooking equipment over time. By establishing a mathematical model that includes multiple modes of heat transfer matrix such as thermal radiation, thermal convection and thermal conduction, the transient temperature changes at various points in the inner cavity of the cooking equipment can be predicted.

[0039] Historical cooking data includes multiple historical state information from multiple historical cooking processes, multiple historical target cooking instructions, and corresponding multiple historical temperature control strategies, which are used to indicate the relationship between various ingredients, multiple cooking techniques, and the quality of cooking results.

[0040] The evaluation module 220 can understand the current state corresponding to the initial working state, and predict the consequences of performing the operation in the initial working state, evaluate the cooking stage that can be achieved and the quality of the final cooking result, with good accuracy and high reliability.

[0041] Specifically, in the decision module 230, the multi-objective optimization model is a multi-objective reward function. This multi-objective reward function is a composite reward function that integrates temperature tracking reward, energy consumption penalty, equipment wear penalty, and estimated cooking result quality reward. It is used to predict temperature tracking accuracy, cooking energy consumption, cooking result quality, and equipment wear cost. In other words, the objective reward function is used to predict the above four optimization objectives. The decision objective of this multi-objective optimization model is to maximize the long-term cumulative value of the multi-objective reward function to balance the various optimization objectives. For example, in each decision, it automatically selects "baking well," "baking quickly," and "saving electricity" to obtain a temperature control strategy that can achieve the optimal cooking effect, thereby improving the decision control accuracy and robustness.

[0042] In some exemplary implementations, the multi-objective reward function includes penalty terms (negative incentives) and reward terms (positive incentives). The penalty terms include penalty parameters such as the square of temperature deviation, temperature fluctuation rate, average power, equipment switching fatigue, thermal stress, and overcooking. The reward terms include reward parameters such as color, texture, and moisture retention scores. By balancing multiple negative and positive incentives, the system prioritizes low-power, smoothly changing temperature control strategies while maintaining accurate temperature, encouraging high-quality baking results (through visual / humidity feedback), and suppressing frequent switching and large thermal shock operations that damage the lifespan of cooking equipment.

[0043] Correspondingly, the control instructions also include adjusting and optimizing the weights of the objectives; the perception module 210 and the evaluation module 220 eliminate the uncertainty of the ingredients' parameters through perception means such as ingredient weight estimation and visual assistance; at the same time, the target cooking instructions are mostly abstract instructions describing the taste, such as "crispy on the outside and tender on the inside". The agent can map the abstract target cooking instructions to the adjustment of the relevant weights in the multi-objective reward function, such as the weight ratio of surface color reward to internal tenderness reward, so as to adjust the temperature control strategy, improve the cooking effect, and achieve good handling ability for uncertainty and complex preferences.

[0044] The execution sending module 240 is used to send the generated temperature control strategy to the core control module 130, so that the core control module 130 can execute the temperature control strategy. The temperature control strategy generated by the intelligent decision module 120 is expressed in a high-level language or abstract form, such as natural language, pseudocode, mathematical models, or programming languages. The core control module 130, as a module with execution capabilities, runs on a different platform or hardware and uses a different underlying language or instruction set (e.g., assembly, C, PLC code, device-specific instruction protocols, etc.) than the intelligent decision module 120. Therefore, before sending the temperature control strategy, the execution sending module 240 also translates the temperature control strategy generated by the decision module 230 to obtain a translated temperature control strategy. The translated temperature control strategy uses the same instruction set as the core control module 130. Then, the execution sending module 240 sends the translated temperature control strategy to the core control module 130, so that the core control module 130 can understand and execute the translated temperature control strategy.

[0045] Thus, after the user selects the type of ingredients and cooking preferences, the intelligent decision-making module 120, based on the initial state of the ingredients perceived by the intelligent agent, combined with the thermodynamic model and historical cooking data, generates, simulates, and makes decisions to generate a preliminary personalized cooking plan, namely a preliminary temperature control strategy, and sends it to the core control module 130. The system autonomously makes decisions and plans to achieve multi-objective optimization, rather than passively executing a fixed program, which greatly improves the control accuracy, response speed, and stability of the cooking equipment, and the system has a high degree of intelligence.

[0046] Specifically, after the intelligent decision-making module 120 issues the temperature control strategy, the core control module 130 is used to accurately and quickly execute the agent's tactical commands; among which, the adaptive model prediction module 310 is used for: During the execution of the temperature control strategy, compensation parameters are predicted based on the updated state information to obtain the adaptive compensation parameters of the cooking equipment. The operating parameters in the current temperature control strategy are compensated according to the adaptive compensation parameters to obtain an updated temperature control strategy. The updated temperature control strategy is used to control the operating temperature of the cooking equipment to meet the updated dynamic curve after adaptive compensation.

[0047] The adaptive compensation parameter is used to indicate the difference in the working parameters that the cooking device dynamically adjusts when there are uncertainties, malfunctions, or changes in environmental conditions, so as to maintain the expected cooking result indicated by the target cooking command. That is, in the process of executing the temperature control strategy issued by the intelligent agent, the adaptive model prediction module 310 still obtains the updated state information of the sensor module 110, performs compensation parameter prediction, obtains the adaptive compensation parameter of the cooking device, and compensates the working parameters in the current temperature control strategy and the preset dynamic curve according to the adaptive compensation.

[0048] For example, if the temperature value inside the cooking device cavity is detected to be below the expected temperature value indicated by the preset dynamic curve at a preset time, then based on the current temperature control strategy (including the expected temperature value at the preset time) and the updated status information (including the temperature value that is below the preset dynamic curve at the preset time), millisecond-level rolling optimization is performed according to the difference between the two to determine the adaptive compensation parameters (including the difference between the expected temperature value and the actual temperature value), and the optimal heating power is calculated for compensation to obtain an updated temperature control strategy. This allows for rapid compensation of the difference between the temperature value and the expected temperature value, so that the updated temperature control strategy can still effectively achieve the expected cooking result indicated by the target cooking command.

[0049] In some alternative implementations, the adaptive model prediction module 310 employs an adaptive model prediction controller (A-MPC) with built-in recursive least squares (RLS) for precise control, fast response, and strong online identification capabilities, which can greatly improve the ability to track the time-varying characteristics of cooking equipment.

[0050] Specifically, such as Figure 3 As shown, the core control module 130 also includes: The event-triggered compensation module 320 is used to monitor sudden interference information of the cooking equipment during the execution of the temperature control strategy. The temperature control strategy is fed forward based on the sudden interference information to obtain the temperature control strategy after feedforward compensation. The adaptive model prediction module 310 is further configured to update the feedforward compensated temperature control strategy based on the updated status information of the cooking equipment during the execution of the temperature control strategy.

[0051] The sudden interference information is used to indicate sudden operations that change the current environmental state of the cooking equipment, such as opening the door, which will rapidly change the temperature field inside the cooking equipment. In some exemplary embodiments, the time-triggered compensation module can refer to the time-triggered robust compensator. The event-triggered compensation module 320 and the adaptive model prediction module 310 run in parallel and independently monitor the sudden interference information of the cooking equipment. Once the sudden interference information is detected, the event-triggered compensation module 320 is triggered to immediately intervene and provide feedforward compensation, which cancels the temperature change before the sudden operation disturbance affects it. Then, it works in conjunction with the adaptive model prediction module 310 to quickly resist disturbances and greatly improve the efficiency and stability of anti-interference.

[0052] Thus, the intelligent decision-making module 120 of the intelligent agent generates a temperature control strategy based on the current state information and the target cooking command, which includes a temperature-time preset dynamic curve that takes into account both rapid heating and stable maintenance, rather than a single fixed value. For example, the preset dynamic curve initially sets a relatively high temperature to achieve rapid preheating, and automatically transitions smoothly when it approaches the desired cooking result, reducing the possibility of overshoot from the source and realizing global dynamic curve planning.

[0053] Furthermore, the adaptive model prediction module 310 of the core control module 130 performs millisecond-level rolling optimization tracking of the temperature control strategy containing the preset dynamic curve; its built-in online parameter identification can update the thermodynamic model of the cooking equipment in real time, ensuring that the controller always "understands" the characteristics of the current object, so that even when there is lag or time-varying, the temperature control strategy updated after adaptive compensation can still output accurate control quantity, balance response speed and overshoot, and achieve local adaptive high-precision tracking.

[0054] Meanwhile, the event-triggered compensation module 320 operates independently and in parallel. Its active anti-interference mechanism is dedicated to detecting and handling sudden interference such as door opening. Once triggered, it immediately injects a feedforward compensation signal into the adaptive model prediction module 310 to perform feedforward compensation, enabling it to "actively counter" interference the moment it occurs, rather than responding passively. This greatly shortens the recovery time and suppresses fluctuations.

[0055] This invention employs a hierarchical control strategy that combines global planning with local optimization and feedforward compensation with feedback correction. The intelligent agent performs forward-looking global planning to avoid conflicts. The adaptive model prediction module 310's adaptive capability ensures that even with load changes and device aging, the temperature control system can still perform high-precision local tracking, maintaining control accuracy under complex operating conditions. The synergy between the two enables the temperature control system to predict future states, reduce control intensity in advance, optimize the heating process, and achieve rapid, overshoot-free preheating. The event-triggered compensation module 320 specializes in handling sudden disturbances, shortening the recovery time of the temperature control system to sudden interferences, reducing temperature fluctuation amplitude, and significantly enhancing stability, thereby balancing control accuracy, response speed, and stability.

[0056] Specifically, such as Figure 4 As shown, the intelligent decision-making module 120 also includes: The monitoring submodule 250 is used to receive the updated status information sent by the sensor module 110 during the execution of the temperature control strategy. The intelligent decision-making module 120 is also used to repeatedly perform control strategy parsing on the updated state information and the target cooking instruction to obtain a replanned temperature control strategy, and send the replanned temperature control strategy to the core control module 130. The adaptive model prediction module 310 is used to cyclically execute the temperature control strategy update operation during the execution of the replanning temperature control strategy.

[0057] The monitoring submodule 250 is used to send and receive various information, receive updated status information sent by the sensor module 110, and send the updated status information to the perception module 210 so that the intelligent decision module 120 can perform online replanning and realize the iterative cycle of the temperature control strategy. That is, the intelligent decision module 120 uses the updated status information as the current status information for the new round of decision-making, repeatedly executes the control strategy analysis of the updated status information and the target cooking command, obtains the replanned temperature control strategy, and sends the replanned temperature control strategy to the core control module 130. Then, the adaptive model prediction module 310 in the core control module 130 repeatedly executes the temperature control strategy update operation during the execution of the replanned temperature control strategy to further update the replanned temperature control strategy.

[0058] After the user selects the type of ingredients and cooking preferences to initiate the intelligent planning process, the intelligent decision-making module 120 employs an intelligent agent. The perception module 210 senses the initial current state information of the cooking equipment (including the weight of the ingredients, etc.) to form initial working parameters. The evaluation module 220 makes predictions based on the initial working parameters, the preset thermodynamic model, and historical cooking data to obtain simulated cooking state data. The decision-making module 230 generates a temperature control strategy through a multi-objective optimization model and translates the temperature control strategy before sending it to the core control module 130. The adaptive model prediction module 310 of the core control module 130 calculates and outputs a fine power control signal to adjust the temperature control strategy based on the received temperature control strategy and its own online adaptive model. Meanwhile, the event-triggered compensation module 320 monitors in real time and performs feedforward compensation to improve anti-interference capability. Afterward, the agent continuously acquires the updated status information perceived by the sensor module 110 and continuously evaluates, for example, whether the temperature rise rate deviates from the preset dynamic curve. If a deviation occurs, the evaluation module 220 can analyze the cause (such as the initial temperature of the food being low or the initial weight of the ingredients being too heavy) and determine that the original temperature control strategy may not be able to achieve the expected cooking result on time. The decision module 230 dynamically adjusts and updates according to the deviation to achieve online replanning and obtains the replanned temperature control strategy, such as extending the preheating time so that the temperature change performed by the cooking equipment meets the preset dynamic curve, realizing perception-based dynamic closed-loop control and maintaining the quality of the final cooking result.

[0059] Thus, the temperature control system for cooking equipment provided in this embodiment of the invention, It can transform ingredients of different weights and initial states, along with simple user-defined cooking commands, into a multi-objective (quality, time, energy consumption) optimization problem through an intelligent agent. Based on the perception and evaluation of real-time status information, it automatically makes closed-loop dynamic decisions, generates and executes customized temperature control strategies, and realizes a paradigm shift from "executing a fixed program" to "achieving the user's expected results," enabling personalized and adaptive cooking. At the same time, it can autonomously handle unexpected situations, such as if the user opens the door to check midway, and dynamically adjusts the temperature control strategy through online replanning to maintain the final cooking result close to the expected result indicated by the target cooking command. It has robustness in handling complex scenarios, lowers the professional threshold for user operation, and users do not need to be proficient in parameters such as temperature and time. They only need to issue simple target cooking commands, and the temperature control system can reliably deliver consistent high-quality cooking results, improving the user experience and cooking success rate.

[0060] Specifically, such as Figure 5 As shown, the intelligent decision-making module 120 further includes: The learning submodule 260 is used to perform simulation optimization on the thermodynamic model based on the current state information, the target cooking command, and the temperature control strategy through a simulation algorithm to obtain an updated thermodynamic model; The learning submodule 260 is also used to associate and store the current status information, the target cooking instruction, and the temperature control strategy as the historical cooking data.

[0061] The updated thermodynamic model can be iteratively optimized during the cooking process to achieve online real-time fine-tuning of the temperature control strategy. The updated thermodynamic model can also be updated after the cooking process ends to achieve offline deep evolution of the temperature control strategy in the next cooking process.

[0062] The simulation algorithm includes at least one of online adaptive learning and offline reinforcement learning / imitation learning; among them, the online adaptive algorithm includes the Model Predictive Path Integral (MPPI) algorithm, which does not require gradient information and can perform prediction optimization in real time through sampling. It has good robustness. This online adaptive learning algorithm can explore the improvement space of the current temperature control strategy in real time during each cooking process, and perform strategy optimization on a very short time scale, that is, online real-time fine-tuning, which can immediately improve the decision effect of the current temperature control strategy.

[0063] Offline reinforcement learning / imitation learning can acquire state information, operation information, and cooking results throughout the cooking process via sensor module 110 after each cooking task. Based on the state information, operation information, and cooking results, as well as the current state information, target cooking instructions, and temperature control strategy, it performs offline learning to update and iterate the multi-objective optimization model of decision module 230, resulting in an updated multi-objective optimization model. Decision module 230 can then continue to update its strategy based on the current state information and simulated cooking state data using the updated multi-objective optimization model, obtaining an offline-learned optimized temperature control strategy. This achieves continuous optimization of the temperature control strategy during the current cooking process or the next cooking process. Correspondingly, this offline reinforcement learning / imitation learning enables the temperature control system to abstract better general decision principles from a large amount of historical experience data, that is, to abstract a general optimized multi-objective optimization model, rather than being limited to memorizing a single cooking process.

[0064] Thus, the learning submodule 260 embeds the ability to "learn from experience" into the temperature control system of the cooking equipment. Through a mechanism that combines online adaptation with the simulation algorithm, it analyzes the data throughout the process and the final execution result of the final temperature control strategy. During long-term use, it continuously iterates and optimizes the temperature control strategy and feeds it back to the evaluation module 220 and decision module 230 of the intelligent decision module 120 to continuously update the thermodynamic model, historical cooking data, and multi-objective optimization model. In other words, it uses the experience data of each cooking session (current state information, target cooking instructions, and corresponding temperature control strategies) to continuously optimize the temperature control strategy for the current and next cooking sessions, achieving personalization and long-term performance evolution. The overall energy efficiency, cooking success rate, and adaptability of the system can continuously improve with the increase of usage time, and the system has good intelligence and self-evolution performance.

[0065] Furthermore, this temperature control system learns and adapts to the individual characteristics of specific cooking equipment, such as slight differences in heating element efficiency and internal heat distribution characteristics, thereby forming an optimal temperature control strategy tailored to the cooking equipment, achieving personalized adaptation of the equipment, which is something that existing pre-programmed systems cannot achieve. Moreover, the autonomous optimization capability of this temperature control system reduces the reliance on manual maintenance for cooking equipment due to performance degradation caused by component aging, which helps to reduce long-term maintenance and upgrade costs.

[0066] In some preferred embodiments, the learning submodule 260 continuously optimizes the thermodynamic model and temperature control strategy through closed-loop control that combines online adaptive learning and offline reinforcement learning / imitation learning. During online operation, the temperature control system uses recursive least squares (RLS) in conjunction with the learning submodule 260 to update model parameters (such as equivalent heat capacity and thermal resistance) in real time, making the predictions more realistic. The adaptive model prediction module 310 recalculates the optimal control output based on the updated thermodynamic model and multi-objective optimization model through rolling optimization. After each cooking cycle, the complete "state-action-reward" sequence is generated. Data is stored, and the aforementioned algorithm is used for offline batch training when the temperature control system and cooking equipment are idle to update the agent. For example, when the food is too heavy and the heating is too slow, RLS detects that the prediction error is continuously too large and adjusts the heat capacity parameter from 5000 to 5200. The adaptive model prediction module 310 re-optimizes the temperature control strategy generated by the corrected agent and calculates a higher heating power (e.g., from 75% to 85%) to compensate for the heat demand. After the task is completed, the system learns from historical experience and further optimizes the decision-making for similar scenarios in the future, forming a continuous closed loop of "perception-execution-learning-evolution".

[0067] Furthermore, in some exemplary embodiments, the learning submodule 260 is also connected to the cloud for communication, enabling information interaction with at least one other cooking device. The learning submodule 260 can upload historical cooking data to the cloud, where the cloud is used to share the historical cooking data of multiple cooking devices. The learning submodule 260 is also used to send a sharing request to the cloud, so that the cloud responds to the sharing request and sends the historical cooking data of multiple cooking devices to the learning submodule 260, enabling the learning submodule 260 to perform shared learning based on the multiple historical cooking data sent from the cloud, thereby achieving intelligent evolution of multiple cooking device groups.

[0068] Specifically, such as Figure 6 As shown, the temperature control system further includes a safety monitoring module 140, which includes: The preventive health management module 410 is used to evaluate the current status information to obtain the deterioration trend information of the cooking equipment, and the deterioration trend information is used to indicate the confidence level of the cooking equipment malfunctioning. Fault diagnosis module 420 is used to perform fault diagnosis based on the current status information and determine fault information in the cooking equipment. The fault information is used to indicate the faults that have occurred in the cooking equipment. The threshold hard protection module 430 is used to control the hardware circuit to trigger power-off protection when the current status information is detected to exceed a preset safety threshold.

[0069] The safety monitoring module 140 serves as an independent protection unit for the temperature control system of the cooking equipment. It operates independently of the intelligent decision module 120 and the core control module 130, possesses the highest priority hardware intervention capability, and can implement multi-level safety strategies, greatly improving the overall operational stability and safety of the temperature control system.

[0070] For example, the threshold hard protection module 430 can cut off power in an emergency if it detects that the current status information shows an overheating.

[0071] In some exemplary embodiments, the fault diagnosis module 420 can perform fault diagnosis based on the current status information, determine the faults of sensors in the cooking equipment and the faults of the model in the temperature control system of the cooking equipment, and issue an early warning, or directly switch the sensor hardware to replace the faulty sensor with a backup sensor in the bypass, thereby improving the overall operational stability and safety of the temperature control system.

[0072] In other exemplary embodiments, the preventive health management module 410 can perform preventive health management on cooking equipment, such as monitoring the cumulative thermal fatigue of heating elements in the cooking equipment, predicting the confidence level of failure before the heating element fails, effectively preventing failures and maintaining the overall operational stability and safety of the temperature control system.

[0073] The temperature control system for cooking equipment provided in this embodiment of the invention features an intelligent decision-making module 120 whose intelligent agent plans from a global and multi-objective (quality, time, energy consumption) perspective, breaking through the limitations of traditional local optimization. Global intelligent optimization achieves true system optimization. Furthermore, through online learning and self-adaptation, it can automatically adapt to different food loads, user habits, and individual differences in cooking equipment, providing an adaptive and personalized cooking experience. Simultaneously, the intelligent agent of the intelligent decision-making module 120 and the time-triggered compensation module of the core control module 130 form a two-tiered "strategic-tactical" anti-interference system, capable of intelligently predicting, responding to, and mitigating interference. The temperature control system for cooking equipment exhibits superior stability compared to traditional single-layer control logic, significantly enhancing its anti-interference performance and robustness. Furthermore, the intelligent decision-making module 120, core control module 130, and safety monitoring module 140 collaboratively construct a three-layer architecture, decoupling yet coordinating "high-performance intelligent decision-making" with "extremely high-reliability safety protection." This allows the temperature control system to achieve its performance ceiling while greatly improving safety and reliability. In addition, the learning submodule 260 of the temperature control system for cooking equipment possesses the ability to learn from historical experience, continuously improving its performance over time and demonstrating excellent long-term performance.

[0074] Corresponding to the temperature control system for cooking equipment provided in the above embodiments of the present invention, the temperature control method for cooking equipment provided in the present invention controls the temperature based on the temperature control system for cooking equipment in the above system embodiments, wherein, as... Figure 7 As shown, the temperature control method for cooking equipment includes: S101, Obtain the current status information of the cooking device, and send the current status information to the intelligent decision module and the core control module; S103, based on the intelligent agent, the current state information and target cooking instructions are parsed to obtain a temperature control strategy, and the temperature control strategy is sent to the core control module; the temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment within a specified time period meets the preset dynamic curve. S105, during the execution of the temperature control strategy, the temperature control strategy is updated according to the updated status information of the cooking equipment.

[0075] Specifically, such as Figure 8 As shown, the step S103, which involves parsing the current state information and target cooking instructions based on an intelligent agent to obtain a temperature control strategy, and then sending the temperature control strategy to the core control module, includes: S202, parse the current status information and the target cooking command to obtain the initial operating parameters of the cooking equipment; S204, based on the initial working parameters, the preset thermodynamic model and historical cooking data, predict the simulated cooking process corresponding to the initial working parameters to obtain simulated cooking state data corresponding to the simulated cooking process. The simulated cooking state data is used to indicate the continuous cooking operation and cooking quality information of the cooking equipment during the simulated cooking process. S206, The temperature control strategy is obtained by generating a strategy based on the current state information and the simulated cooking state data through a multi-objective optimization model. S208, the temperature control strategy is sent to the core control module.

[0076] Specifically, such as Figure 9 As shown, during the execution of the temperature control strategy, the temperature control strategy is updated according to the updated status information of the cooking equipment. That is, step S105 includes: S301, during the execution of the temperature control strategy, compensation parameters are predicted based on the updated state information to obtain the adaptive compensation parameters of the cooking device; S303, the operating parameters in the current temperature control strategy are compensated according to the adaptive compensation parameters to obtain an updated temperature control strategy. The updated temperature control strategy is used to control the operating temperature of the cooking equipment to meet the updated dynamic curve after adaptive compensation.

[0077] Specifically, such as Figure 10 As shown, in some exemplary embodiments, before updating the temperature control strategy based on the updated status information of the cooking device during the execution of the temperature control strategy, that is, before step S105; or, before step S301, the method further includes: S305, during the execution of the temperature control strategy, monitor the sudden interference information of the cooking equipment, the sudden interference information is used to indicate a sudden operation that changes the current environmental state of the cooking equipment; S307, perform feedforward compensation on the temperature control strategy based on the sudden interference information to obtain the feedforward compensated temperature control strategy.

[0078] Accordingly, step S105 specifically includes: During the execution of the temperature control strategy, the feedforward compensated temperature control strategy is updated based on the updated status information of the cooking equipment.

[0079] Alternatively, correspondingly, steps S301-S303 specifically include: During the execution of the temperature control strategy after feedforward compensation, the compensation parameters are predicted based on the updated state information to obtain the adaptive compensation parameters of the cooking equipment. The operating parameters in the current feedforward compensated temperature control strategy are compensated according to the adaptive compensation parameters to obtain an updated temperature control strategy. The updated temperature control strategy is used to control the operating temperature of the cooking equipment to meet the updated dynamic curve after adaptive compensation.

[0080] Specifically, such as Figure 11 As shown, during the execution of the temperature control strategy, after updating the temperature control strategy according to the updated status information of the cooking device, that is, after step S105, the method further includes: S107, during the execution of the temperature control strategy, receive the updated status information sent by the sensor module; Repeat steps S103-S105 to parse the updated status information and the target cooking command into a control strategy, obtain a replanned temperature control strategy, and send the replanned temperature control strategy to the core control module. During the execution of the replanned temperature control strategy, the update operation of the temperature control strategy is performed cyclically.

[0081] Specifically, such as Figure 12 As shown, after step S105, the method further includes: S109, Using a simulation algorithm, the thermodynamic model is optimized based on the current state information, the target cooking command, and the temperature control strategy to obtain an updated thermodynamic model; S111, the current status information, the target cooking command, and the temperature control strategy are associated and stored as the historical cooking data; the historical cooking data includes multiple historical status information, multiple historical target cooking commands, and corresponding multiple historical temperature control strategies in multiple historical cooking processes.

[0082] Specifically, such as Figure 13 As shown, the method further includes: S402, Based on the current status information, an evaluation is performed to obtain the deterioration trend information of the cooking equipment, which is used to indicate the confidence level of the cooking equipment malfunctioning; S404, perform fault diagnosis based on the current status information to determine fault information in the cooking equipment, wherein the fault information is used to indicate the fault that has occurred in the cooking equipment; S406, if the current status information is detected to exceed a preset safety threshold, the control hardware circuit triggers a power-off protection.

[0083] It should be noted that the temperature control system for cooking equipment provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment can be divided into different functional modules to complete all or part of the functions described above. In addition, the temperature control method for cooking equipment provided in the above embodiments and the system embodiments belong to the same concept, and the specific implementation process can be found in the system embodiments, which will not be repeated here.

[0084] The temperature control system for the cooking equipment includes a processor and a memory. The processor (or CPU (Central Processing Unit)) is the core component of the temperature control system for the cooking equipment. Its main function is to interpret memory instructions and process data fed back from various modules. The processor's structure is roughly divided into an arithmetic logic unit and a register unit. The arithmetic logic unit mainly performs related logical calculations (such as shift operations, logical operations, fixed-point or floating-point arithmetic operations, and address operations), while the register unit is used to temporarily store instructions, data, and addresses.

[0085] A memory is a storage device used to store software programs and modules. A processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory mainly includes a program storage area and a data storage area. The program storage area may store the operating system, including but not limited to Windows (an operating system), Linux (an operating system), etc., which are not limited in this invention. In addition, it may also store application programs required for functions. For example, the memory storage space also contains at least one instruction suitable for being loaded and executed by the processor; these instructions may be one or more computer programs (including program code). The data storage area may store data created based on the use of the device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0086] The methods and embodiments provided in this invention can be executed in electronic devices such as mobile terminals, computer terminals, servers, or similar computing devices. Figure 14 This is a hardware structure block diagram of an electronic device for a temperature control method in a cooking appliance, provided in an embodiment of the present invention. Figure 14 As shown, the electronic device 1400 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 1410 (CPUs 1410 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 1430 for storing data, and one or more storage media 1420 (e.g., one or more mass storage devices) for storing application programs 1423 or data 1422. The memory 1430 and storage media 1420 may be temporary or persistent storage. The program stored in the storage media 1420 may include one or more modules, each module including a series of instruction operations on the electronic device. Furthermore, the CPU 1410 may be configured to communicate with the storage media 1420 and execute the series of instruction operations in the storage media 1420 on the electronic device 1400. Electronic device 1400 may also include one or more power supplies 1460, one or more wired or wireless network interfaces 1450, one or more input / output interfaces 1440, and / or one or more operating systems 1421, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0087] The input / output interface 1440 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 1400. In one example, the input / output interface 1440 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 1440 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0088] Those skilled in the art will understand that Figure 14 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device 1400 may also include... Figure 14 The more or fewer components shown, or having the same Figure 14 The different configurations shown.

[0089] This invention also provides a storage medium storing at least one instruction or at least one program segment, wherein the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the temperature control method for cooking equipment described above. Optionally, the storage medium may be located at at least one network server among multiple network servers in a computer network. Furthermore, the storage medium may include, but is not limited to, random access memory (RAM), read-only memory (ROM), non-volatile memory (NVM), USB flash drive, portable hard drive, disk storage device, flash memory device, other volatile solid-state storage devices, and other storage media capable of storing program code.

[0090] According to one aspect of the present invention, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0091] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0093] The above description is merely some embodiments of the present invention and is not intended to limit the present invention. Those skilled in the art should understand that the present invention can have various changes and improvements, and any modifications, equivalent substitutions and improvements made in accordance with the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A temperature control system for cooking equipment, characterized in that, It includes an intelligent decision-making module, a core control module, and a sensor module; The sensor module is used to acquire the current status information of the cooking equipment and send the current status information to the intelligent decision module and the core control module; The intelligent decision-making module is used to analyze the current state information and target cooking instructions based on the intelligent agent to obtain a temperature control strategy, and then send the temperature control strategy to the core control module. The temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment within a specified time period meets the preset dynamic curve. The core control module includes an adaptive model prediction module, which is used to update the temperature control strategy based on the updated status information of the cooking equipment during the execution of the temperature control strategy.

2. The temperature control system for cooking equipment according to claim 1, characterized in that, The intelligent decision-making module includes: The sensing module is used to analyze the current status information and the target cooking command to obtain the initial operating parameters of the cooking equipment; The evaluation module is used to predict the simulated cooking process corresponding to the initial working parameters based on the initial working parameters, the preset thermodynamic model and historical cooking data, and obtain the simulated cooking state data corresponding to the simulated cooking process. The simulated cooking state data is used to indicate the continuous cooking operation and cooking quality information of the cooking equipment during the simulated cooking process. The decision-making module is used to generate a strategy based on the current state information and the simulated cooking state data through a multi-objective optimization model, thereby obtaining the temperature control strategy. The execution sending module is used to send the temperature control strategy to the core control module.

3. The temperature control system for cooking equipment according to claim 2, characterized in that, The multi-objective optimization model is a multi-objective reward function, which is used to predict temperature tracking accuracy, cooking energy consumption, cooking result quality, and equipment wear and tear costs.

4. The temperature control system for cooking equipment according to claim 2, characterized in that, The intelligent decision-making module also includes: The learning submodule is used to perform simulation optimization on the thermodynamic model based on the current state information, the target cooking command, and the temperature control strategy through simulation algorithms to obtain an updated thermodynamic model; The learning submodule is also used to associate and store the current state information, the target cooking command, and the temperature control strategy as the historical cooking data; the historical cooking data includes multiple historical state information, multiple historical target cooking commands, and multiple corresponding historical temperature control strategies in multiple historical cooking processes.

5. The temperature control system for cooking equipment according to claim 1, characterized in that, The adaptive model prediction module is used for: During the execution of the temperature control strategy, compensation parameters are predicted based on the updated state information to obtain the adaptive compensation parameters of the cooking equipment. The operating parameters in the current temperature control strategy are compensated according to the adaptive compensation parameters to obtain an updated temperature control strategy. The updated temperature control strategy is used to control the operating temperature of the cooking equipment to meet the updated dynamic curve after adaptive compensation.

6. The temperature control system for cooking equipment according to claim 5, characterized in that, The intelligent decision-making module also includes: The monitoring submodule is used to receive the updated status information sent by the sensor module during the execution of the temperature control strategy. The intelligent decision-making module is also used to repeatedly perform control strategy parsing on the updated state information and the target cooking instruction to obtain a replanned temperature control strategy, and send the replanned temperature control strategy to the core control module. The adaptive model prediction module is used to cyclically execute the temperature control strategy update operation during the execution of the replanning temperature control strategy.

7. The temperature control system for a cooking apparatus according to any one of claims 1-6, characterized in that, The core control module also includes: An event-triggered compensation module is used to monitor sudden interference information of the cooking equipment during the execution of the temperature control strategy. The sudden interference information is used to indicate a sudden operation that changes the current environmental state of the cooking equipment. The temperature control strategy is fed forward based on the sudden interference information to obtain the temperature control strategy after feedforward compensation. The adaptive model prediction module is also used to update the feedforward compensated temperature control strategy according to the updated state information of the cooking equipment during the execution of the temperature control strategy.

8. The temperature control system for a cooking apparatus according to any one of claims 1-6, characterized in that, The temperature control system further includes a safety monitoring module, which includes: The preventive health management module is used to evaluate the current status information to obtain the deterioration trend information of the cooking equipment, and the deterioration trend information is used to indicate the confidence level of the cooking equipment malfunctioning. The fault diagnosis module is used to perform fault diagnosis based on the current status information and determine the fault information in the cooking equipment. The fault information is used to indicate the fault that has occurred in the cooking equipment. The threshold hard protection module is used to control the hardware circuit to trigger power-off protection when the current state information is detected to exceed a preset safety threshold.

9. A temperature control method for cooking equipment, characterized in that, Based on the temperature control system for cooking equipment as described in any one of claims 1-8, the method includes: The current status information of the cooking device is obtained and sent to the intelligent decision-making module and the core control module. Based on the intelligent agent, the current state information and target cooking instructions are parsed to obtain a temperature control strategy, which is then sent to the core control module. The temperature control strategy is used to control the operating parameters of the cooking equipment so that the operating temperature of the cooking equipment meets the preset dynamic curve within a specified time period. During the execution of the temperature control strategy, the temperature control strategy is updated based on the updated status information of the cooking equipment.

10. A cooking device, characterized in that, Cooking is performed based on the temperature control system for a cooking device as described in any one of claims 1-8 or the temperature control method for a cooking device as described in claim 9.

Images