A cloud platform-based intelligent beverage maker temperature control method

Abstract

This invention provides a cloud-based intelligent beverage making machine temperature control method, comprising: responding to a beverage making trigger request, collecting beverage attributes, cup attributes, environmental conditions, water quality, and equipment heating parameters under the current operating conditions of the equipment; simultaneously acquiring multi-zone temperature of the cup, beverage liquid surface status, and water quality scale thermal resistance correlation data; constructing an operating condition parameter set and uploading it to a cloud service platform; this solution eliminates temperature control deviations caused by missing operating condition information from the data acquisition source, realizing adaptive temperature control capabilities under different water qualities, environments, and equipment conditions, and significantly improving the overall operating condition adaptability and basic control accuracy of the temperature control solution.

Description

Technical Field

[0001] This invention relates to the field of temperature control methods, and in particular to a temperature control method for an intelligent beverage making machine based on a cloud platform. Background Technology

[0002] In related technologies, the temperature control solutions for intelligent beverage making machines mostly adopt a standalone control mode with locally fixed parameters and single temperature threshold closed-loop regulation. They lack a cloud-edge collaborative system for comprehensive condition perception, multi-field coupled precise calculation, dynamic deviation correction, and model self-iterative optimization. These technologies rely solely on a single temperature parameter and fixed heating logic for temperature control, failing to comprehensively cover complex thermal interference factors such as beverage phase change, cup heat storage, scale thermal resistance, and environmental heat exchange. They cannot dynamically generate adaptive temperature control strategies based on real-time operating conditions and lack a closed-loop feedback and iteration mechanism for operational data. This leads to the continuous accumulation of temperature control errors during long-term operation, resulting in core technical problems such as low temperature control accuracy, poor adaptability to operating conditions, weak dynamic correction capabilities, and an inability to adapt to changes in operating conditions. Consequently, they struggle to meet the high-precision, stable, and intelligent temperature control requirements for beverages in complex scenarios. Summary of the Invention

[0003] In view of this, the present invention aims to provide a temperature control method for a cloud-based intelligent beverage making machine to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial option.

[0004] To solve the above-mentioned technical problems, one technical solution adopted in this application is: to provide a temperature control method for an intelligent beverage making machine based on a cloud platform, comprising: In response to the beverage making trigger request, the system collects beverage attributes, cup attributes, environmental status, water quality and equipment heating parameters under the current operating conditions of the equipment. Simultaneously, it acquires multi-zone temperature of the cup, beverage liquid level and water quality scale thermal resistance related data, constructs a set of operating parameters and uploads them to the cloud service platform. Receive the temperature control reference curve, theoretical total heating amount, and segmented power control sequence obtained by the cloud service platform based on the operating condition parameter set and through a multi-field coupling calculation model; A composite temperature control logic combining pre-judgment and micro-area thermal field correction is adopted. The segmented power control sequence is used as the pre-control parameter, and the deviation between the beverage temperature in multiple zones and the temperature control reference curve is used as the dynamic compensation parameter. The device drive command is generated by fusion to control the heating device to complete the segmented power adjustment and constant temperature maintenance. The actual runtime sequence data and corresponding operating condition parameter set of this temperature control process are uploaded to the cloud service platform, and the model parameters optimized by the cloud service platform based on three types of deviation characteristics: steady-state temperature drift, dynamic temperature surge, and heat transfer hysteresis are received to complete the update of the local model parameters.

[0005] Preferably, the steps for performing thermal equilibrium calculations using the thermally coupled computational model built into the cloud service platform include: The system pre-establishes a mapping relationship between various types of operating condition parameters and thermal property coefficients. After receiving the set of operating condition parameters uploaded by the local device, it matches the basic thermal parameters corresponding to beverage attributes, the thermal conduction and heat dissipation parameters corresponding to cup attributes, the heat transfer correction parameters corresponding to environmental conditions, the heat loss compensation parameters corresponding to water quality, and the thermal resistance correction parameters corresponding to scale adhesion. It integrates all the matched thermal correlation parameters, introduces the liquid-gas interface heat transfer abrupt change characteristic parameters for multi-dimensional coupling calculation, solves the total heating quantization value corresponding to the current operating condition, and the time-series mapping relationship of time, temperature, and power, and outputs the temperature control reference curve and the segmented power control sequence.

[0006] Preferably, the multi-dimensional parameter coupling operation process includes: The acquired thermal baseline parameters, heat conduction and dissipation parameters, heat exchange correction parameters, heat loss compensation parameters, and scale thermal resistance correction parameters are normalized to eliminate the dimensional differences of the parameters in each dimension. All normalized parameters are then input into a preset thermal balance coupling algorithm. Based on the real-time operating condition stability, the thermal influence weights corresponding to each parameter are adaptively matched, and the temperature control nodes and power output nodes of the entire heating process are output in time sequence to construct an operating condition-adaptive temperature control time sequence model.

[0007] Preferably, the execution method of the composite temperature control logic of the local device includes: The local device pre-stores segmented power pre-control rules. After receiving the segmented power control sequence from the cloud, it matches the corresponding preset power parameters step by step according to the heating sequence to complete the pre-heating power allocation. It collects beverage temperature data from multiple areas, including the bottom, wall, and surface of the cup, in real time. It compares the real-time temperature of multiple areas with the time-series data of the temperature control reference curve and generates corresponding dynamic deviation compensation parameters based on the deviation type. In each control cycle, it superimposes the pre-heating power parameters and dynamic deviation compensation parameters to generate real-time device drive commands. Based on the drive commands, it adjusts the output power and operating status of the heating device.

[0008] Preferably, the execution process of the segmented power regulation includes: The local equipment divides the heating time interval into multiple continuous segments based on the temperature control reference curve, and matches the power parameters corresponding to the segmented power control sequence for each time interval. In the early heating time interval, high power is used to increase the temperature. In the middle heating time interval, the output power is gradually reduced according to the state of foam on the liquid surface. In the later time interval, which is close to the reference temperature, low power is used for fine adjustment based on the heat storage state of the cup, so as to adjust the temperature of the beverage to the preset constant temperature range.

[0009] Preferably, the execution method of the temperature constant maintenance operation includes: The local device collects environmental parameters and heating equipment operating parameters in real time. It updates the environmental heat loss parameters based on the real-time environmental parameters and updates the equipment power loss parameters based on the equipment operating status and the degree of scale adhesion. Based on the updated heat loss parameters and power loss parameters, and combined with the heat storage status of the cup and heating element, it predicts the amount of heat storage and release, and adjusts the output power in advance during the constant temperature stage to maintain the constant temperature of the beverage.

[0010] Preferably, the incremental iterative optimization steps of the thermally coupled computational model include: The cloud service platform pre-sets time-series data deviation evaluation rules, receives actual runtime time-series data uploaded by local devices, compares the actual runtime time-series data with the theoretical solution time-series data of the model frame by frame, quantifies the time-series deviation index, steady-state deviation index, and dynamic fluctuation index, and classifies the deviation correction categories; based on the quantified deviation index and deviation category, it updates the fixed basic coefficients, dynamic heat conduction and dissipation coefficients, and heat loss compensation coefficients inside the thermally coupled calculation model in layers, and completes the incremental iteration of model parameters; the iteratively updated differential model parameters are synchronously distributed to each local device.

[0011] Preferably, the incremental iterative update process of the model parameters includes: The system presets the hierarchical model parameter iteration correction threshold and convergence conditions. Based on the matching relationship between the quantization deviation index and the iteration threshold, and combined with the similarity of working condition samples, it determines the single coefficient correction magnitude. Within a single iteration cycle, it performs incremental fine-tuning on the coefficients of dynamic class models that exceed the threshold, and keeps the parameters unchanged on the coefficients of basic class models that meet the convergence conditions, thus completing the incremental iterative update of model parameters.

[0012] To solve the above-mentioned technical problems, another technical solution adopted in this application is: providing a cloud-based intelligent beverage making machine temperature control system, applied to the temperature control method described above, including: The data acquisition and upload unit is used to respond to beverage making trigger requests, collect the operating parameters of the equipment under the current operating conditions, construct the operating parameter set, and upload it to the cloud service platform. The receiving unit is used to receive the temperature control reference curve, theoretical total heating and segmented power control sequence calculated by the cloud service platform, as well as the iteratively optimized model parameters. The control execution unit is used to generate equipment drive commands based on the segmented power control sequence and the temperature control reference curve using composite temperature control logic, and to control the heating equipment to complete segmented power adjustment and constant temperature maintenance. The update unit is used to update the locally stored model parameters based on the received optimized model parameters.

[0013] To solve the above-mentioned technical problems, another technical solution adopted in this application is to provide a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the temperature control method for a cloud-based intelligent beverage making machine as described above.

[0014] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: 1. This invention collects five basic operating condition parameters—beverage, cup, environment, water quality, and equipment operation—from a local device, simultaneously capturing implicit thermal correlation data such as multi-zone temperature, liquid level, and scale thermal resistance. A complete set of operating condition parameters is constructed and uploaded to the cloud. Relying on a complete closed-loop logic of cloud-based multi-field coupled calculation, local composite correction and control, operational data feedback iteration, and model parameter differential synchronization, it replaces the traditional single-machine, single-parameter, fixed-logic temperature control mode. This solution eliminates temperature control deviations caused by missing operating condition information at the data acquisition source, achieving adaptive temperature control capabilities under different water qualities, environments, and equipment conditions, significantly improving the overall operating condition adaptability and basic control accuracy of the temperature control solution.

[0015] 2. This invention pre-constructs the correlation mapping relationship between operating parameters and thermal property coefficients, and specifically matches multi-dimensional thermal correlation parameters such as beverage thermal basis, cup body heat conduction, environmental heat exchange, water quality loss, and scale thermal resistance. At the same time, it introduces the abrupt change characteristics of heat exchange at the liquid-gas interface to participate in the coupling calculation, breaking through the limitation of traditional temperature control relying solely on a single thermodynamic parameter. This solution can accurately quantify various complex thermal influence factors, and solve the time-series matching relationship of temperature, power, and heating amount through multi-dimensional linkage calculation, outputting a temperature control benchmark curve and segmented power sequence that fits the real physical operating conditions, thereby improving the accuracy and fit of heat balance calculation from the algorithm level.

[0016] 3. This invention performs normalization and standardization processing on multi-dimensional and multi-dimensional thermal correlation parameters, eliminating computational biases caused by differences in the numerical dimensions of different types of parameters. Simultaneously, it dynamically and adaptively adjusts the influence weights of each thermal parameter based on the real-time stability of the operating conditions, replacing the traditional static algorithm model with fixed weights and coefficients. Traditional algorithms cannot adapt to fluctuating operating conditions; using the same parameter weights for stable and fluctuating conditions easily leads to computational distortion. This solution constructs a condition-adaptive temperature control time series model through dynamic weight matching, which can adapt to complex fluctuating conditions and stable, conventional conditions, effectively improving the model's generalization ability and computational stability in different scenarios.

[0017] 4. This invention combines a dual control logic of pre-judgment power allocation and dynamic temperature correction in multiple micro-zones. It uses a power sequence sent from the cloud to perform pre-judgment temperature control, avoiding the lag inherent in traditional pure closed-loop feedback temperature control. Simultaneously, relying on multi-zone temperature acquisition from the cup bottom, cup wall, and liquid surface, it accurately identifies local temperature differences and temporal temperature deviations in the beverage, classifies and generates dynamic compensation parameters, and integrates them in real time for driving the process. This solution achieves precise fine-tuning in each control cycle through full-domain temperature monitoring and periodic dynamic compensation, significantly improving the temperature uniformity and real-time control accuracy of the dynamic heating process.

[0018] 5. This invention divides the heating time sequence into multiple stages based on the temperature control reference curve, matching differentiated power control logic. In the early stage, high power ensures rapid heating efficiency; in the middle stage, power is gradually reduced based on the state of foam on the liquid surface to prevent overflow; and in the later stage, low power is used for fine-tuning and precise temperature control based on the heat storage state of the cup. This solution, through a phased, condition-linked stepped power adjustment mode, effectively avoids overflow and overheating defects while ensuring rapid heating efficiency of beverages, achieving a synergistic balance between heating efficiency, temperature control accuracy, and operational safety.

[0019] 6. During the constant temperature maintenance phase, this invention updates parameters in real time regarding environmental heat loss and power loss due to equipment scale buildup and component aging. It also pre-corrects the heat preservation power based on the heat storage and release characteristics of the cup and heating element, replacing the traditional fixed heat preservation power control mode. This solution, through dynamic loss prediction and pre-correction of power, continuously counteracts various thermal interferences under steady-state conditions, significantly improving the temperature stability of beverages during the constant temperature phase and reducing steady-state temperature control errors.

[0020] 7. This invention compares actual operating data frame by frame with theoretical calculation data, quantifies and classifies various indicators such as time-series deviation, steady-state deviation, and dynamic fluctuation, and optimizes them accordingly. It then optimizes the model's fundamental coefficients, thermal conductivity, and heat loss compensation coefficients in a targeted, layered manner, completing incremental iterations of the cloud-based model and synchronous updates across the entire domain. This solution relies on real operating data to achieve closed-loop self-learning and self-correction of the model, continuously offsetting systematic deviations caused by long-term operation and ensuring that the equipment's temperature control accuracy does not diminish over the long term.

[0021] 8. This invention achieves progressive iterative updates by setting hierarchical iterative correction thresholds and convergence criteria, and by combining the similarity of working condition samples to precisely control the magnitude of single parameter corrections. It fine-tunes out-of-range dynamic coefficients and locks the convergence base coefficients. This scheme, through its iterative logic of threshold-level constraints and differentiated incremental corrections, ensures a smooth, controllable, and convergent model optimization process. It achieves precise error correction while preserving the model's basic adaptability, significantly improving the stability and reliability of model iterative optimization.

[0022] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a schematic diagram of the temperature response curve during the temperature control process in an embodiment of the present invention; Figure 3 This is a schematic diagram of the heating power control curve during the temperature control process in an embodiment of the present invention; Figure 4 This is a schematic diagram showing the statistical results of key parameters in the temperature control process according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the modules of the device of the present invention. Detailed Implementation

[0025] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0026] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0027] Figure 1 This is a flowchart illustrating a temperature control method for a cloud-based intelligent beverage making machine according to an embodiment of the present invention. It should be noted that if substantially the same result is achieved, the method of this application is not necessarily identical. Figure 1 The illustrated process sequence is limited. For example... Figure 1As shown: A temperature control method for a cloud-based intelligent beverage making machine includes the following steps: S100, Operating Condition Data Acquisition and Cloud Upload: Traditional beverage preparation temperature control methods rely solely on single temperature data for adjustment, failing to comprehensively cover multi-dimensional operating condition factors such as beverage, equipment, environment, and water quality. This easily leads to problems such as temperature control benchmark deviation and heating anomalies, making it unsuitable for complex and dynamic preparation scenarios. Therefore, this method adopts a multi-dimensional operating condition synchronous acquisition and real-time cloud upload mode, ensuring the comprehensiveness and accuracy of temperature control calculation data from the source.

[0028] When the equipment responds to a beverage preparation trigger request, it simultaneously collects various operating parameters corresponding to the current operating condition of the equipment, temperature data of multiple zones in the cup, beverage liquid level data, and water quality, scale, and thermal resistance correlation data. Among them, the operating parameters cover five core categories: beverage attribute parameters, cup attribute parameters, environmental parameters, water quality parameters, and equipment heating operating parameters.

[0029] The equipment integrates and standardizes all collected data to construct a complete set of operating parameters, and uploads them to the cloud service platform in real time via an encrypted communication link, providing accurate and real-time raw data support for subsequent cloud-based thermal coupling calculations.

[0030] Specifically, this step may include: Unified definition of global parameters: Define the global operating condition parameter set as a multi-dimensional time series matrix. All parameters are real-time time-series variables, varying with heating duration. Dynamically updated, the core parameters are categorized and defined as follows: (1) Beverage attribute parameters This includes the beverage's specific heat capacity, initial temperature, solution concentration, foaming coefficient, and phase change endothermic threshold. (2) Cup body attribute parameters This includes the cup's thermal conductivity, wall thickness, volume, heat dissipation area, and heat storage coefficient. (3) Environmental parameters This includes ambient temperature, air humidity, atmospheric pressure, and ambient convective heat transfer coefficient. (4) Water quality and scale parameters This includes water hardness, pure water purity, scale buildup thickness, and scale thermal resistance coefficient. ; (5) Equipment heating parameters This includes the rated power of the heating element, real-time output power, equipment operating time, and heating loss coefficient. (6) Refined state parameters Includes multi-zone temperature control within the cup. (i = bottom of cup / cup wall / liquid level), liquid level height, foam coverage.

[0031] Operating condition parameter set fusion algorithm: To eliminate the problems of inconsistent dimensions and asynchronous timing of various parameters, this method adopts a timing alignment fusion algorithm to construct a standardized operating condition parameter set. The fusion formula is as follows: ; In the formula: The full-dimensional operating condition parameter matrix at time t is standardized. All sub-parameters are preprocessed by time alignment, outlier filtering, and dimension normalization to ensure that the operating condition parameters at the same time correspond one-to-one and avoid algorithm calculation errors caused by time misalignment.

[0032] Execution process: After the device responds to the beverage preparation trigger command, it synchronously samples all dimensions of parameters at a fixed acquisition period. Abnormal sensor data is removed by a median filtering algorithm, and the data is then substituted into the above fusion formula to construct a real-time operating condition parameter set. The data is uploaded to the cloud service platform in real time via an encrypted communication link. This step replaces traditional qualitative description with quantitative parameter modeling, realizing the digital representation of factors under all operating conditions. This provides complete and unified input variables for subsequent multi-field coupled heat balance formula solutions, improving the operating condition adaptability and calculation accuracy of the temperature control model from the algorithm source.

[0033] S200, cloud-based multi-field coupled thermal calculation to generate temperature control benchmarks and control sequences: Traditional equipment uses fixed temperature control curves and constant heating power, failing to consider multi-field coupled interference such as beverage phase change heat absorption, cup body heat storage lag, and scale thermal resistance attenuation. This results in poor adaptability to operating conditions and easily leads to problems such as inefficient heating, temperature overshoot, and beverage overflow. To address this, this method relies on a cloud-based multi-field coupled thermal calculation model to achieve differentiated thermal balance calculation based on real-time operating conditions, adaptively generating temperature control strategies to match the scenario.

[0034] After receiving the set of operating parameters, the cloud service platform uses a multi-field coupled thermal coupling calculation model that integrates phase change heat absorption, heat storage hysteresis, and scale thermal resistance to perform differentiated heat balance calculations. This ultimately generates a temperature control reference curve, theoretical total heating amount, and segmented power control sequence adapted to the current operating conditions. The segmented power control sequence is configured with multiple sets of differentiated parameters to adapt to different heating stages while simultaneously meeting the anti-overflow foaming requirements for beverages.

[0035] Specifically, this step may include: Model core coupling formula definition: Constructing the core equation for multi-field coupled thermal equilibrium: ; In the formula: The total effective heat absorbed by the beverage at time t; To generate heat for the equipment in real time; This refers to the amount of heat loss due to environmental heat dissipation. This refers to the heat loss due to scale thermal resistance. To store and delay heat in the cup body and heating element; This refers to the heat loss due to phase change in beverages.

[0036] Overall execution logic: Receive real-time operating condition parameter sets from the cloud. Based on the pre-stored parameter-thermal property mapping relationship, coefficient matching is completed. After normalized weight coupling operation, the temperature-time-power mapping relationship is calculated in a time-series manner, and the temperature control reference curve is output. With segmented power control sequence ,and Built-in anti-overflow foam constraint threshold to adapt to the foaming characteristics of different beverages.

[0037] S201. Thermal property parameter association matching: The cloud pre-establishes the corresponding association between various types of operating condition parameters and thermal property coefficients. After receiving the set of operating condition parameters, it accurately matches the corresponding thermal correlation parameters of each dimension, including the basic thermal parameters corresponding to beverage attributes, the heat conduction and heat dissipation parameters corresponding to cup attributes, the heat exchange correction parameters corresponding to environmental conditions, the heat loss compensation parameters corresponding to water quality, and the thermal resistance correction parameters corresponding to scale adhesion conditions, so as to achieve accurate adaptation of thermal parameters in all dimensions.

[0038] Among them, a one-to-one mapping matching algorithm between operating parameters and thermophysical property coefficients is established. Automatic parameter matching is completed through a fixed correlation function. The matching formula is as follows: ; In the formula: It is a set of thermal property coefficients across all dimensions; The basic caloric coefficient of beverages (matching) ); For the thermal conductivity and heat dissipation coefficient of the cup body (matching) ); For environmental heat transfer correction factor (matching) ); Water quality heat loss compensation coefficient (matching) ); For the scale thermal resistance correction factor (matching) ).

[0039] The cloud-based system uses the aforementioned mapping function to automatically update all thermal property coefficients based on real-time operating parameters, achieving precise adaptive matching of thermal parameters under different operating conditions.

[0040] S202, Multi-dimensional Parameter Coupling Calculation: The cloud integrates all matched thermally correlated parameters and, combined with the actual characteristics of abrupt changes in heat transfer at the liquid-gas interface, performs multi-dimensional parameter coupling calculations to obtain the total heating quantification value under the current operating condition, as well as the time-series mapping relationship between time, temperature, and power. Finally, it outputs a standardized temperature control reference curve and a piecewise power control sequence. The main purpose is to: based on the matched set of thermophysical property coefficients... By combining the heat transfer abrupt change characteristics of the liquid-gas interface, multi-dimensional coupled calculations are performed to solve the heating time sequence mapping relationship and output a standard temperature control strategy.

[0041] S2021, Parameter Normalization Processing: The cloud platform performs unified normalization processing on the acquired thermal basic parameters, heat conduction and heat dissipation parameters, heat exchange correction parameters, heat loss compensation parameters, and scale thermal resistance correction parameters, effectively eliminating the dimensional differences of parameters in different dimensions and avoiding calculation deviations caused by inconsistent parameter dimensions.

[0042] To eliminate the dimensional differences of parameters across dimensions, an extreme value normalization algorithm is used to standardize all thermal property coefficients. The normalization formula is as follows: ; In the formula: These are the normalized coefficients; The original thermal property coefficients; These are the global maximum and minimum thresholds for the corresponding coefficients. After normalization, all coefficients take values ​​in the range [0,1] to ensure the rationality of multi-parameter linkage calculations.

[0043] S2022, Adaptive Weighted Linkage Calculation: The normalized parameters of each dimension are substituted into the preset thermal balance coupling algorithm to complete the linkage calculation. At the same time, the thermal influence weights of each parameter are dynamically and adaptively matched according to the real-time operating condition stability to ensure that the calculation results are consistent with the actual operating conditions.

[0044] Among them, based on the stability of the operating conditions Dynamically adaptively matching the thermal influence weights of each parameter, weight allocation formula: ; ; In the formula: Real-time weights for each thermal field parameter; For the stability of operating conditions, the greater the fluctuation in operating conditions, the higher the weight of the dynamic loss parameter; This is a weighted adaptive adjustment function. Through dynamic weight allocation, it accurately adapts to the influence ratio of each thermal field under different operating conditions.

[0045] S2023. Construct a temperature control timing model adapted to operating conditions: output the temperature control nodes and power output nodes of the entire heating process in a time sequence, build a temperature control timing model adapted to real-time operating conditions, and provide a standard timing basis for segmented and precise temperature control of local equipment.

[0046] Specifically, by substituting normalized weight parameters into the core thermal balance equation, the temperature and power time-series nodes of the entire heating process are obtained through time-series solving, and a time-series mapping model is constructed: ; In the formula: This is the temperature control reference curve; It is a segmented power control sequence; This is a function for solving multi-field coupled thermal equilibrium. The final output is a standardized temperature control strategy with timing constraints and anti-bubbling constraints, providing a quantitative basis for local equipment control.

[0047] The S300 and local device employ combined temperature control logic to generate and execute drive commands. However, the macroscopic temperature control strategy calculated in the cloud has a certain lag and cannot handle dynamic conditions such as instantaneous thermal field fluctuations, localized temperature unevenness, and sudden changes in liquid surface state during heating. Relying solely on cloud commands can easily lead to insufficient temperature control accuracy and untimely correction. Therefore, this method employs a combined temperature control logic that integrates local pre-judgment with micro-area thermal field correction, achieving deep integration of cloud strategies and local real-time fine-tuning to ensure real-time and accurate temperature control.

[0048] The local device determines the pre-control parameters based on the segmented power control sequence sent from the cloud. It combines the deviation between the beverage temperature in multiple zones and the temperature control reference curve, classifies and determines the dynamic deviation type, and determines the dynamic compensation parameters. It then merges the two types of parameters to generate equipment drive commands, thereby controlling the heating equipment to complete the segmented power adjustment and constant temperature maintenance operations.

[0049] This step may include: generating real-time drive power by superimposing the pre-power formula and the dynamic deviation compensation formula to achieve high-precision dynamic temperature control.

[0050] Core control formula: ; In the formula: Provides the real-time output power of the equipment; This serves as the cloud-based timing reference power. Power for dynamic deviation compensation.

[0051] S301, Pre-set power parameter matching and allocation: The local device pre-stores the pre-set control rules corresponding to the segmented power control. After receiving the segmented power control sequence from the cloud, it matches the preset power parameters step by step according to the heating sequence, and completes the pre-set power allocation of the heating process in advance to avoid the heating lag problem.

[0052] Among them, the local equipment pre-stores a segmented timing power mapping table, based on the heating timing. By matching the standard power sequence sent from the cloud, the preceding reference power is obtained: ; The pre-set power is a fixed reference power for each stage, used to ensure the overall heating rhythm and avoid the problem of pure system lag.

[0053] S302, Dynamic Deviation Compensation Parameter Generation: The device collects beverage temperature data from multiple areas including the bottom of the cup, the cup wall, and the liquid surface in real time, continuously compares the real-time temperature of each area with the time-series values ​​of the temperature control baseline curve, distinguishes different deviation types based on the deviation differences, and adaptively generates corresponding dynamic deviation compensation parameters.

[0054] Specifically, this step involves collecting real-time temperatures from multiple zones. Calculate the dynamic deviation between the zone average temperature and the reference temperature: ; In the formula: The real-time temperature deviation is represented by 'n', where 'n' is the number of temperature measurement zones. A PID compensation algorithm is used to generate dynamic compensation power based on the deviation. ; In the formula: These are proportional, integral, and derivative compensation coefficients, respectively. The parameter group is adaptively switched according to the type of deviation to achieve overheat suppression, temperature drift correction, and hysteresis compensation.

[0055] S303 Real-time drive command generation and control execution: The equipment superimposes the pre-set power parameters and dynamic deviation compensation parameters in each control cycle to generate real-time drive commands. Based on the commands, the output power and operating status of the heating equipment are precisely controlled to complete the fine-tuning of the beverage temperature throughout the process.

[0056] Specifically, when adjusting the output of the heating module in real time, the real-time output power is obtained by superimposing the pre-amplifier power and the compensation power. The device uses this quantized value as the driving instruction.

[0057] S311. Heating time sequence interval division: Based on the temperature control reference curve, the local equipment divides the complete heating process into multiple continuous heating time sequence intervals, and each interval is matched with the exclusive power parameters corresponding to the segmented power control sequence.

[0058] S312, High-power rapid heating in the early stage: During the early heating phase, the equipment executes a high-power output mode to quickly increase the overall temperature of the beverage, effectively shortening the beverage preparation time and improving operating efficiency.

[0059] S313, Mid-term power reduction and anti-overflow control: During the mid-heating time interval, the equipment monitors the foam status of the liquid surface in real time and gradually reduces the output power according to the foam generation situation, effectively suppressing the foaming and overflow of beverages, and is suitable for the production of easily foamed beverages such as milk and soy milk.

[0060] S314, Low-power Precise Fine-tuning in the Later Stages: In the later stages of heating, close to the reference temperature, the device performs low-power fine-tuning based on the heat storage status of the cup to counteract the interference of residual heat and precisely bring the beverage temperature to the preset constant temperature range.

[0061] The segmented power regulation timing algorithm described in S311-S314 may include: The entire heating sequence is divided into a heating phase, an anti-bubbling phase, and a fine-tuning phase. The segmented power constraint formulas are as follows: The initial rapid temperature rise phase: Full power for rapid heat storage, improving heating efficiency; Mid-term anti-overflow foaming stage: , The foam suppression attenuation coefficient decreases progressively with increasing foam coverage. Post-production fine-tuning phase: Based on temperature deviation, low-power fine-tuning is used to offset residual heat from heat storage.

[0062] S321. Real-time update of environmental heat loss parameters: During the constant temperature maintenance phase, the equipment collects the current environmental parameters in real time and dynamically updates the heat loss parameters corresponding to environmental heat dissipation, adapting to the heat dissipation fluctuations caused by changes in environmental temperature, humidity, and air pressure.

[0063] S322, Equipment power loss parameter update: The equipment dynamically updates its heating power loss parameters based on its real-time operating status and the degree of scale adhesion, thus offsetting the impact of heat exchange efficiency reduction caused by device aging and scaling.

[0064] S323, Constant Temperature Heat Storage Prediction and Power Fine-Tuning: Based on the updated heat loss parameters and power loss parameters, the equipment predicts the heat storage and release of the cup and heating element in advance, actively fine-tunes the output power during the constant temperature stage, continuously maintains the stable temperature of the beverage, and eliminates constant temperature drift.

[0065] As described in S321-S323, the isothermal maintenance dynamic correction algorithm may include: During the constant temperature phase, the heat dissipation loss and scale loss coefficients are updated in real time, and the constant temperature power is dynamically adjusted using the heat storage prediction formula. ; In the formula: The reference isothermal power; This is the amount of environmental heat dissipation compensation; This is the amount to compensate for scale loss. To predict and compensate for heat storage and release, a constant temperature with no static error is maintained.

[0066] S400, Operational Data Feedback and Layered Incremental Iterative Optimization of Cloud Model: The initial parameters of the thermally coupled model are general and fixed, which cannot adapt to dynamic evolution scenarios such as long-term scaling and aging of equipment, water quality deterioration, and seasonal changes in operating conditions. Long-term use will lead to a gradual decrease in temperature control accuracy. To address this, this method constructs a closed-loop iterative optimization mechanism. Through operational data feedback, deviation quantification analysis, and layered iterative updates, it achieves adaptive evolution of model parameters, ensuring stable temperature control accuracy throughout the equipment's lifecycle.

[0067] After a single beverage temperature control process is completed, the local device collects the actual time-series data and corresponding operating condition parameter set for this operation, and uploads them to the cloud service platform in encryption. Based on three core deviation characteristics—steady-state temperature drift, dynamic temperature surge, and heat transfer hysteresis—the cloud performs hierarchical incremental iterative optimization of the parameters of the thermal coupling calculation model, and synchronously updates the optimized parameter differences to all local devices.

[0068] Specifically, this step may include: quantifying the residuals between theoretical data and actual operating data, updating model coefficients in layers, and ensuring temperature control accuracy throughout the entire life cycle.

[0069] Core residual definition: ; In the formula: The real-time temperature residual is divided into three categories: steady-state residual, dynamic temperature surge residual, and hysteresis residual, which serve as the core basis for model iteration.

[0070] S401. Operational data comparison and deviation quantification classification: The cloud presets multiple types of time series data deviation evaluation rules, compares the actual runtime time series data uploaded by the device with the theoretical solution data of the model frame by frame, quantifies the three core indicators of time series deviation, steady-state deviation and dynamic fluctuation, and accurately classifies the correction category corresponding to the deviation.

[0071] Frame-by-frame comparison of time-series data in the cloud to quantify three types of deviation indicators: steady-state temperature drift index Dynamic temperature control index Heat exchange hysteresis index The deviation correction category is determined based on the indicator threshold, and the corresponding matching model coefficients to be optimized are determined.

[0072] S402, Layered Incremental Iterative Update of Model Parameters: Based on the quantified deviation indicators and deviation categories, the cloud layered iterative update of the fixed basic coefficients, dynamic heat conduction and dissipation coefficients and heat loss compensation coefficients within the model, achieving refined incremental optimization of model parameters and avoiding the adaptation risks caused by resetting the overall parameters.

[0073] Specifically, a hierarchical incremental correction formula is used to iteratively optimize the model coefficients: ; In the formula: These are the model coefficients before and after the update, respectively. This represents the maximum single correction magnitude; Weights for similarity in working conditions; This is the convergence criterion function for deviation.

[0074] S4021. Set iteration thresholds and convergence conditions: The cloud pre-configures hierarchical model parameter iteration correction thresholds and convergence judgment conditions, distinguishing between correction standards for basic parameters and dynamic parameters, to ensure the standardization and stability of iterative optimization.

[0075] S4022. Determine the single parameter correction range: The cloud combines quantitative deviation indicators, preset iteration thresholds and working condition sample similarity to accurately calculate the single correction range of model coefficients, ensuring that parameter optimization fits the actual working condition deviation.

[0076] S4023, Incremental Iterative Update: Within a single iteration cycle, only the coefficients of dynamic class models that exceed the threshold are incrementally fine-tuned, while the original state of the coefficients of basic class models that meet the convergence conditions is retained, thereby achieving incremental optimization of the model and preventing excessive parameter correction from causing the model to become inaccurate.

[0077] As described in S4021-S4023, by setting the convergence threshold of the basic coefficients and the correction threshold of the dynamic coefficients, incremental fine-tuning is performed only on the dynamic coefficients that exceed the thresholds, while the basic coefficients remain unchanged when convergence is achieved, thus realizing gradual iteration and avoiding model oscillation and instability.

[0078] S403, Synchronous Update of Parameters for All Devices: After the model iteration and optimization is completed in the cloud, the updated differential model parameters are synchronized to each local device in batches, realizing the unified upgrade of temperature control calculation parameters for all devices.

[0079] In this step, the cloud only extracts the differential parameters of the iterative changes. An encrypted parameter package is generated. After verifying the matching of operating conditions on online devices, the local model parameters are partially replaced to complete the lightweight and highly secure parameter synchronization upgrade across the entire domain, ensuring the consistency of algorithm models across all terminals.

[0080] Specifically, this may include: S4031. Differential Parameter Encryption Packaging: After a single iteration is completed in the cloud, only the changed parameters are extracted to generate a differential update parameter package with a version identifier, and then encrypted packaging is performed to reduce the amount of data transmitted and ensure update security.

[0081] S4032, Global Synchronization Command Push: The cloud monitors the online status of devices in real time and pushes parameter synchronization commands to all online local devices, triggering the device parameter update process.

[0082] S4033, Local Parameter Verification and Replacement Update: After receiving the parameter package, the local device first completes the working condition matching verification. After the verification is passed, the parameter package is parsed, and the locally stored model change parameters are partially replaced to accurately complete the synchronous update of parameters of all devices.

[0083] S500, Cloud-based Personalized Temperature Control Adaptation Optimization: Traditional unified temperature control strategies cannot adapt to differentiated scenarios such as geographical altitude, air pressure, climate, and user drinking preferences, resulting in weak scenario adaptability and insufficient personalized experience. To address this, this method relies on cloud-based big data clustering analysis to construct a scenario-based temperature control mapping model, achieving personalized temperature control adaptation for each user.

[0084] The cloud continuously collects and stores historical user operation data, regional environmental time-series data, altitude and air pressure data, and user usage preference data for each device, builds a multi-dimensional user scenario database, and accumulates full-scenario temperature control sample data.

[0085] The cloud-based system conducts cluster analysis on the association between user scenarios, geographical environment and temperature control parameters based on the scenario database. It establishes a precise mapping relationship between user taste and physical sensation and temperature control parameters. Based on the clustering results, it dynamically adjusts the standard temperature control baseline curve parameters, generates exclusive temperature control strategies adapted to different regions, scenarios and users, and accurately distributes them to the corresponding local devices to complete personalized temperature control adaptation and optimization.

[0086] In this step, the personalized correction formula is as follows: ; In the formula: A user-specific temperature control curve; Geographical environment correction factor (altitude, air pressure, temperature and humidity adaptation); Adjust the coefficient according to user preferences (adapt to warm, hot, or cool taste).

[0087] The cloud-based clustering training uses massive amounts of scenario data to dynamically update and correct coefficients. It generates multi-scenario exclusive temperature control strategies and distributes them to local devices, achieving a quantitative integration of standardized temperature control and personalized adaptation.

[0088] The present invention also provides embodiments implemented according to the method of the present invention: Basic operating conditions: To produce 300ml of pure milk, the target constant temperature is 65℃, the initial temperature is 25℃, the ambient temperature is 25℃, the standard atmospheric pressure is 101.325kPa, the air humidity is 55%, and an ordinary glass cup is used as the container. The equipment has slight scaling (scale thickness is 0.1mm), the tap water has medium hardness, and the rated power of the heating equipment is 1200W.

[0089] I. Operating Condition Data Acquisition and Parameter Set Construction With a data acquisition period of 10 seconds, initial full-dimensional operating condition parameters are obtained at t=0s, and a standardized operating condition matrix is ​​constructed. The core actual values ​​are as follows: 1. Beverage parameters: Specific heat capacity of pure milk Concentration 12%, foaming coefficient 0.15, phase change threshold 68℃, mass 0.3kg; 2. Cup body parameters: Thermal conductivity of the glass cup Heat dissipation area Heat storage coefficient ; 3. Environmental parameters: Ambient temperature 25℃, convective heat transfer coefficient ; 4. Scale and water quality parameters: Scale thermal resistance coefficient Water hardness 150 mg / L; 5. Equipment parameters: Rated power 1200W, heating loss coefficient 0.92.

[0090] Substitute into the operating condition fusion formula: ; The initial time-normalized load case matrix is ​​obtained: After median filtering to remove anomalies, the data is uploaded to the cloud in real time to complete the model input initialization.

[0091] II. Cloud-based multi-field coupled thermal decomposition 2.1 Calculation of matching thermophysical property parameters Through mapping function The specific thermophysical property coefficients for this operating condition were obtained by matching: Basic caloric coefficient of beverages The thermal conductivity and heat dissipation coefficient of the cup body Environmental heat transfer correction coefficient Water quality heat loss compensation coefficient Scale thermal resistance correction factor .

[0092] 2.2 Parameter Normalization Calculation The extreme value normalization formula is used: ; Take the global threshold of the coefficient Normalized parameters: .

[0093] 2.3 Adaptive Weight Allocation Calculation Stability of operating conditions during initial heating Real-time weights are allocated through a weight adjustment function to satisfy... Final weights: .

[0094] 2.4 Multi-field Coupled Thermal Equilibrium Core Calculation Using the core formula: ; Take the heating steady-state time t=100s and substitute it with the actual monitored values: The equipment generates heat in real time. Environmental heat loss Scale heat exchange loss Heat loss in the cup body Beverage phase change endothermic ; Calculation process: ; Based on the time-series calculation of the total effective heat absorption, a specific temperature control strategy for this operating condition is generated: 1. Reference temperature profile: The target temperature is a constant 65℃; 2. Segmented power control sequence 0-120s high power 850W, 120-180s medium power 550W, constant temperature maintenance power after 180s 180W.

[0095] III. Local Composite Temperature Control Drive Calculation 3.1 Pre-amplifier power matching Heating for t=60s is in the rapid heating phase, with the pre-set reference power. .

[0096] 3.2 Calculation of Dynamic Temperature Deviation and Compensation Power At t=60s, the measured average temperature of multiple zones reference temperature Temperature deviation: ; PID compensation formula is used: ; Take the appropriate compensation factor for heating milk: Under single-cycle steady-state deviation, the integral and differential terms are approximately zero, and the calculation yields: .

[0097] 3.3 Real-time output power fusion calculation Core formula: ; Calculation process: ; The equipment outputs 828.4W of power in real time to raise the temperature, compensating for slight temperature lag deviations; after entering the 120s anti-foaming stage, the power is automatically reduced to 550W to suppress milk foaming and prevent overflow.

[0098] 3.4 Power Correction Calculation During the Isothermal Maintenance Stage At t=180s, the temperature reaches the isothermal stage. Loss parameters are updated, and the isothermal power formula is used: ; Substitute the values: ; Calculation process: ; The equipment operates at a fine-tuning constant temperature of 200W to offset environmental factors, scale buildup, and heat loss, and stably maintains the milk temperature in the range of 64.5℃-65.5℃.

[0099] IV. Incremental Iterative Optimization Calculation of the Model 4.1 Residual Quantification Calculation Steady-state temperature residual after a single temperature control cycle: ; The absolute value of the residual is less than the conventional threshold of 0.5℃, which is considered a small steady-state deviation.

[0100] 4.2 Calculation of Incremental Correction for Model Coefficients Iteration formula: ; Take the old value of the thermal resistance coefficient of scale Maximum single correction amount Operating condition similarity Deviation convergence coefficient ; Calculation process: ; Only the dynamic scale coefficient is iteratively updated, while the basic thermal property coefficients remain in a convergent steady state. The incremental optimization of the model is completed, and the updated differential parameter package is synchronized to the local device.

[0101] V. Personalized Temperature Control Adaptation Correction Calculation The user preference for this sample is standard warm milk (65℃), with no bias towards hot or cold temperatures. The geographic location is a plain with a normal temperature environment. The correction factor is... .

[0102] This application example achieves high-precision temperature control of 300ml of pure milk with no overflow, no overshoot, and a steady-state constant temperature error of ≤±0.2℃ through full-parameter quantitative calculation, dynamic power compensation, and model iterative correction. Compared with traditional fixed-power heating, the temperature stability is improved by more than 75%, making it suitable for complex coupled working conditions.

[0103] like Figures 2-4 As shown, Figure 2 This is a schematic diagram of the temperature response curve of the temperature control process in this embodiment, which includes: Initial stage (0–40s): The actual temperature rises approximately linearly, indicating that the heating system is in a rapid heating phase with a stable temperature rise rate.

[0104] Later stage (40–51s): The slope of the curve slows down significantly, entering the precise fine-tuning stage. The heating power is reduced, and the temperature rise slows down to avoid overheating.

[0105] At 51 seconds, the actual temperature was approximately 62.61℃, which deviated from the target temperature of 65℃ by 2.39℃, and was within the acceptable temperature control error range of the system.

[0106] The entire process showed no significant overshoot (temperature exceeding the target value), indicating that the segmented power control strategy effectively avoided temperature overshoot.

[0107] Figure 3 This is a schematic diagram of the heating power control curve for the temperature control process in this embodiment, which includes: 0–42s stage: The power stabilizes at approximately 1150W, which is the rated high-power heating stage, corresponding to the rapid temperature rise stage of the temperature curve.

[0108] 42–51s stage: The power drops sharply to about 400W, entering the low-power fine-tuning stage, which corresponds to the slowdown of the slope of the temperature curve. The low power is used to supplement the heat and achieve a smooth transition close to the target temperature.

[0109] The absence of frequent fluctuations in the power curve indicates that the control strategy is a segmented mode of open-loop prediction and primary power reduction, which is consistent with the design logic of anti-overflow and heat storage correction.

[0110] Figure 4 This is a schematic diagram showing the statistical results of key parameters in the temperature control process of this embodiment. This embodiment verifies the actual operating effect of the temperature control method of the present invention under the condition of a target temperature of 65℃: Heating efficiency: With rapid heating at 1150W high power in the early stage, most of the temperature rise is completed in about 40 seconds, meeting the efficiency requirements for beverage heating.

[0111] Temperature overshoot control: The system automatically adjusts to low power heating in the later stages, effectively avoiding the temperature overshoot problem common in traditional constant power heating. The final temperature stabilizes at 62.61℃, with an error of less than 3℃.

[0112] Segmented control verification: The step-like change of the power curve corresponds perfectly to the two-stage characteristics of the temperature curve, verifying the effectiveness of the pre-judgment + dynamic compensation composite control logic.

[0113] Data closed-loop basis: The actual temperature, power time series data and final deviation results of this operation will be uploaded to the cloud as sample data for subsequent hierarchical incremental iterative optimization of model parameters.

[0114] like Figure 5 As shown, Figure 5 This is a schematic diagram of the module of the device of the present invention. The present invention also provides a cloud platform-based intelligent beverage making machine temperature control system, applied to the temperature control method described above, including: The data acquisition and upload unit is used to respond to beverage making trigger requests, collect the operating parameters of the equipment under the current operating conditions, construct the operating parameter set, and upload it to the cloud service platform. The receiving unit is used to receive the temperature control reference curve, theoretical total heating and segmented power control sequence calculated by the cloud service platform, as well as the iteratively optimized model parameters. The control execution unit is used to generate equipment drive commands based on the segmented power control sequence and the temperature control reference curve using composite temperature control logic, and to control the heating equipment to complete segmented power adjustment and constant temperature maintenance. The update unit is used to update the locally stored model parameters based on the received optimized model parameters.

[0115] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the cloud-based intelligent beverage making machine temperature control method as described above.

[0116] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A temperature control method for an intelligent beverage making machine based on a cloud platform, characterized in that, include: In response to the beverage making trigger request, the system collects beverage attributes, cup attributes, environmental status, water quality and equipment heating parameters under the current operating conditions of the equipment. Simultaneously, it acquires multi-zone temperature of the cup, beverage liquid level and water quality scale thermal resistance related data, constructs a set of operating parameters and uploads them to the cloud service platform. Receive the temperature control reference curve, theoretical total heating amount, and segmented power control sequence obtained by the cloud service platform based on the operating condition parameter set and through a multi-field coupling calculation model; A composite temperature control logic combining pre-judgment and micro-area thermal field correction is adopted. The segmented power control sequence is used as the pre-control parameter, and the deviation between the beverage temperature in multiple zones and the temperature control reference curve is used as the dynamic compensation parameter. The device drive command is generated by fusion to control the heating device to complete the segmented power adjustment and constant temperature maintenance. The actual runtime sequence data and corresponding operating condition parameter set of this temperature control process are uploaded to the cloud service platform, and the local model parameters are updated by receiving the model parameters iteratively optimized by the cloud service platform based on three types of deviation characteristics: steady-state temperature drift, dynamic temperature surge, and heat transfer hysteresis.

2. The temperature control method for a cloud-based intelligent beverage making machine according to claim 1, characterized in that, The steps for performing thermal equilibrium calculation using the built-in thermally coupled computational model of the cloud service platform include: The system pre-establishes a mapping relationship between various types of operating condition parameters and thermal property coefficients. After receiving the set of operating condition parameters uploaded by the local device, it matches the basic thermal parameters corresponding to beverage attributes, the thermal conduction and heat dissipation parameters corresponding to cup attributes, the heat transfer correction parameters corresponding to environmental conditions, the heat loss compensation parameters corresponding to water quality, and the thermal resistance correction parameters corresponding to scale adhesion. It integrates all the matched thermal correlation parameters, introduces the liquid-gas interface heat transfer abrupt change characteristic parameters for multi-dimensional coupling calculation, solves the total heating quantization value corresponding to the current operating condition, and the time-series mapping relationship of time, temperature, and power, and outputs the temperature control reference curve and the segmented power control sequence.

3. The temperature control method for a cloud-based intelligent beverage making machine according to claim 2, characterized in that, The multi-dimensional parameter coupling operation process includes: The acquired thermal baseline parameters, heat conduction and dissipation parameters, heat exchange correction parameters, heat loss compensation parameters, and scale thermal resistance correction parameters are normalized to eliminate the dimensional differences of the parameters in each dimension. All normalized parameters are then input into a preset thermal balance coupling algorithm. Based on the real-time operating condition stability, the thermal influence weights corresponding to each parameter are adaptively matched, and the temperature control nodes and power output nodes of the entire heating process are output in time sequence to construct an operating condition-adaptive temperature control time sequence model.

4. The temperature control method for a cloud-based intelligent beverage making machine according to claim 1, characterized in that, The execution methods of the composite temperature control logic of the local device include: The local device pre-stores segmented power pre-control rules. After receiving the segmented power control sequence from the cloud, it matches the corresponding preset power parameters step by step according to the heating sequence to complete the pre-heating power allocation. It collects beverage temperature data from multiple areas, including the bottom, wall, and surface of the cup, in real time. It compares the real-time temperature of multiple areas with the time-series data of the temperature control reference curve and generates corresponding dynamic deviation compensation parameters based on the deviation type. In each control cycle, it superimposes the pre-heating power parameters and dynamic deviation compensation parameters to generate real-time device drive commands. Based on the drive commands, it adjusts the output power and operating status of the heating device.

5. The temperature control method for a cloud-based intelligent beverage making machine according to claim 1, characterized in that, The execution process of the segmented power regulation includes: The local equipment divides the heating time interval into multiple continuous segments based on the temperature control reference curve, and matches the power parameters corresponding to the segmented power control sequence for each time interval. In the early heating time interval, high power is used to increase the temperature. In the middle heating time interval, the output power is gradually reduced according to the state of foam on the liquid surface. In the later time interval, which is close to the reference temperature, low power is used for fine adjustment based on the heat storage state of the cup, so as to adjust the temperature of the beverage to the preset constant temperature range.

6. The temperature control method for a cloud-based intelligent beverage making machine according to claim 1, characterized in that, The execution methods of the temperature constant maintenance operation include: The local device collects environmental parameters and heating equipment operating parameters in real time. It updates the environmental heat loss parameters based on the real-time environmental parameters and updates the equipment power loss parameters based on the equipment operating status and the degree of scale adhesion. Based on the updated heat loss parameters and power loss parameters, and combined with the heat storage status of the cup and heating element, it predicts the amount of heat storage and release, and adjusts the output power in advance during the constant temperature stage to maintain the constant temperature of the beverage.

7. The temperature control method for a cloud-based intelligent beverage making machine according to claim 1, characterized in that, The execution steps of the incremental iterative optimization of the thermally coupled computational model include: The cloud service platform pre-sets time-series data deviation evaluation rules, receives actual runtime time-series data uploaded by local devices, compares the actual runtime time-series data with the theoretical solution time-series data of the model frame by frame, quantifies the time-series deviation index, steady-state deviation index, and dynamic fluctuation index, and classifies the deviation correction categories; based on the quantified deviation index and deviation category, it updates the fixed basic coefficients, dynamic heat conduction and dissipation coefficients, and heat loss compensation coefficients inside the thermally coupled calculation model in layers, and completes the incremental iteration of model parameters; the iteratively updated differential model parameters are synchronously distributed to each local device.

8. The temperature control method for a cloud-based intelligent beverage making machine according to claim 7, characterized in that, The incremental iterative update process of the model parameters includes: The system presets the hierarchical model parameter iteration correction threshold and convergence conditions. Based on the matching relationship between the quantization deviation index and the iteration threshold, and combined with the similarity of working condition samples, it determines the single coefficient correction magnitude. Within a single iteration cycle, it performs incremental fine-tuning on the coefficients of dynamic class models that exceed the threshold, and keeps the parameters unchanged on the coefficients of basic class models that meet the convergence conditions, thus completing the incremental iterative update of model parameters.

9. A temperature control system for a cloud-based intelligent beverage making machine, applied to the temperature control method as described in any one of claims 1-8, characterized in that, include: The data acquisition and upload unit is used to respond to beverage making trigger requests, collect the operating parameters of the equipment under the current operating conditions, construct the operating parameter set, and upload it to the cloud service platform. The receiving unit is used to receive the temperature control reference curve, theoretical total heating and segmented power control sequence calculated by the cloud service platform, as well as the iteratively optimized model parameters. The control execution unit is used to generate equipment drive commands based on the segmented power control sequence and the temperature control reference curve using composite temperature control logic, and to control the heating equipment to complete segmented power adjustment and constant temperature maintenance. The update unit is used to update the locally stored model parameters based on the received optimized model parameters.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the temperature control method for a cloud-based intelligent beverage making machine as described in any one of claims 1-8.

Images