A smart temperature control system and method using novel phase change materials

Abstract

This invention provides an intelligent temperature control system and control method utilizing a novel phase change material, relating to the field of temperature control system technology. The method includes: an environmental sensing module for real-time acquisition of environmental parameters; a heat exchange module including a heat exchanger using the novel phase change material; wherein the novel phase change material comprises a porous matrix, a phase change substrate filled in the porous matrix, and nanomaterials dispersed in the phase change substrate; a multifunctional environmental regulation module including an air purification unit and / or a humidity control unit; and an intelligent control module for analyzing and processing the environmental parameters, the operating parameters of the heat exchange module, and the multifunctional environmental regulation module using deep learning models and reinforcement learning algorithms to obtain the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module. This invention can significantly reduce operating energy consumption while improving the environmental adaptability of the equipment and overall user satisfaction, enabling temperature control equipment to evolve towards higher efficiency, intelligence, and multifunctionality.

Description

Technical Field

[0001] This invention relates to the field of temperature control system technology, and in particular to an intelligent temperature control system and control method using a novel phase change material. Background Technology

[0002] Modern HVAC systems not only need to provide basic cooling and heating functions, but also meet users' diverse needs for air purification and humidity control, while also requiring high energy efficiency. Phase change materials (PCMs), as important materials in the field of thermal management, can regulate temperature by absorbing or releasing latent heat; however, traditional PCMs suffer from low thermal conductivity, limiting the improvement of heat exchange efficiency.

[0003] In addition, existing intelligent temperature control systems mostly adopt basic sensing and parameter adjustment methods, which are insufficient in adaptive control in complex environments. Moreover, most systems only focus on temperature regulation, have low multi-functional integration, and rely heavily on manual inspection for fault diagnosis, resulting in limited efficiency and accuracy. They cannot meet the requirements of modern temperature control systems for high efficiency, intelligence, multi-functionality, and high reliability. Summary of the Invention

[0004] This invention provides an intelligent temperature control system and control method using novel phase change materials to solve the problems of low heat exchange efficiency and low multi-functional integration of existing temperature control systems.

[0005] In a first aspect, embodiments of the present invention provide an intelligent temperature control system utilizing a novel phase change material, comprising: An environmental sensing module is used to collect environmental parameters in real time; the environmental parameters include at least one of temperature, humidity, airflow speed and air quality. A heat exchange module includes a heat exchanger that applies a novel phase change material; wherein the novel phase change material includes a porous matrix, a phase change substrate filled in the porous matrix, and nanomaterials dispersed in the phase change substrate. A multi-functional environmental control module, including an air purification unit and / or a humidity control unit; The intelligent control module is used to analyze and process environmental parameters, operating parameters of the heat exchange module and the multi-functional environmental control module using deep learning models and reinforcement learning algorithms, to obtain the optimal operating parameters of the heat exchange module and the multi-functional environmental control module, and then apply them to the heat exchange module and the multi-functional environmental control module.

[0006] In one possible implementation, the porous matrix is ​​a metal foam, the phase change substrate includes paraffin wax, and the nanomaterials include carbon nanotubes and / or graphene.

[0007] In one possible implementation, the intelligent control module is specifically used for: Environmental parameters and historical operating data are input into a deep learning model to determine optimization objectives; these objectives include minimizing total system energy consumption, minimizing overall comfort deviation, and minimizing equipment lifespan loss. By inputting environmental parameters and optimization objectives into a reinforcement learning algorithm, the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module are determined.

[0008] In one possible implementation, the intelligent control module is also used for: After applying the optimal operating parameters to the heat exchange module and the multi-functional environmental control module, the rate of change of each environmental parameter is monitored and the comprehensive environmental change rate index is calculated. Based on the comprehensive environmental change rate index, the exploration rate parameter of the reinforcement learning algorithm is adjusted.

[0009] One possible implementation also includes: The intelligent fault diagnosis module is used to monitor the operating status data of the heat exchange module and the performance parameters of the novel phase change material in real time, analyze the operating status data and performance parameters, diagnose the malfunction of the heat exchange module and / or the phase change material, and generate and output corresponding adjustment commands to the intelligent control module when an malfunction is diagnosed, so as to adjust the internal parameters of the deep learning model and / or reinforcement learning algorithm.

[0010] In one possible implementation, the intelligent fault diagnosis module is specifically used for: The failure modes of the heat exchange module and / or phase change material are identified through machine learning models. Failure modes include phase change material phase change efficiency degradation and sensor data anomalies.

[0011] In one possible implementation, the intelligent fault diagnosis module is specifically used for: If the diagnosed fault mode is the decay of phase change efficiency of phase change material, then a first adjustment instruction is generated to increase the weight term related to equipment life loss in the reward function and at the same time decrease the weight term related to minimizing the total energy consumption of the system. If the diagnosed fault mode is abnormal sensor data, a second adjustment command is generated to suspend the use of the data channel corresponding to the abnormal sensor and switch to the backup control strategy based on historical safe operation data.

[0012] Secondly, embodiments of the present invention provide a control method, applied to the intelligent control module of an intelligent temperature regulation system using novel phase change materials as described in the first aspect or any possible implementation thereof, comprising: Obtain environmental parameters; wherein, the environmental parameters include at least one of temperature, humidity, airflow speed and air quality; By using deep learning models and reinforcement learning algorithms, the operating parameters of the environmental parameters, heat exchange module, and multifunctional environmental control module are analyzed and processed to obtain the optimal operating parameters of the heat exchange module and multifunctional environmental control module, and then applied to the heat exchange module and multifunctional environmental control module.

[0013] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the second aspect above or any possible implementation thereof.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described in the second aspect above or any possible implementation thereof.

[0015] This invention provides an intelligent temperature control system and method utilizing novel phase change materials. An environmental sensing module provides real-time, accurate environmental parameter data for regulation. The novel phase change material composite structure solves the problem of low thermal conductivity in traditional phase change materials at the material level, significantly improving the heat exchange efficiency of the heat exchange module. The multi-functional environmental control module integrates air purification and humidity control functions, overcoming the limitations of traditional single-function temperature control. The intelligent control module, combining deep learning models and reinforcement learning algorithms, can comprehensively analyze the parameters of each module and match optimal operating parameters, achieving dynamic and coordinated regulation of each module. This effectively optimizes energy utilization efficiency, reduces system energy consumption, and provides users with a comprehensive environmental control solution, significantly improving indoor environmental comfort and overall regulation effects. It significantly reduces operating energy consumption while enhancing the equipment's environmental adaptability and overall user satisfaction, providing a practical technical path for the evolution of temperature control equipment towards higher efficiency, intelligence, and multi-functionality. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of an intelligent temperature control system using a novel phase change material provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the implementation of the control method provided in this embodiment of the invention; Figure 3 This is a flowchart illustrating the implementation of the fault diagnosis method provided in this embodiment of the invention. Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0018] Figure 1 The diagram shows a schematic of a smart temperature control system using a novel phase change material according to an embodiment of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 1 As shown, a smart temperature control system 1 using a novel phase change material includes: The environmental sensing module 11 is used to collect environmental parameters in real time; wherein the environmental parameters include at least one of temperature, humidity, airflow speed and air quality; The heat exchange module 12 includes a heat exchanger that uses a novel phase change material; wherein the novel phase change material includes a porous matrix, a phase change substrate filled in the porous matrix, and nanomaterials dispersed in the phase change substrate. The multi-functional environmental control module 13 includes an air purification unit and / or a humidity control unit; The intelligent control module 14 is used to analyze and process the environmental parameters, the operating parameters of the heat exchange module and the multi-functional environmental control module using deep learning models and reinforcement learning algorithms, to obtain the optimal operating parameters of the heat exchange module and the multi-functional environmental control module, and to apply them to the heat exchange module and the multi-functional environmental control module.

[0019] In this embodiment, the environmental sensing module is responsible for collecting environmental parameters in real time. These parameters include one or more of temperature, humidity, airflow velocity, and air quality. Specifically, the temperature sensor can be a high-precision negative temperature coefficient thermistor or platinum resistance thermometer; the humidity sensor uses a polymer capacitive moisture-sensing element; the airflow velocity sensor is a hot-film anemometer; and the air quality sensor detects the concentration of volatile organic compounds and particulate matter based on the metal-oxide-semiconductor principle. The sensors can be arranged according to the room's geometry and airflow organization at key locations such as return air vents, activity areas, and heat exchanger surfaces. The sampling frequency can be set to once every ten seconds, and the data is collected to the intelligent control module via wired or wireless means. This module provides real-time environmental status perception for the system and is the foundation for subsequent optimized control.

[0020] The core of the heat exchange module is a heat exchanger utilizing a novel phase change material (PCM). This novel PCM consists of a porous matrix, a PCM substrate filling its pores, and nanomaterials dispersed within the PCM substrate. The porous matrix is ​​made of metal foam or carbon foam, possessing high specific surface area and excellent thermal conductivity. Its three-dimensional network structure provides a vast adhesion surface and thermal conductivity framework for the PCM substrate. The PCM substrate uses organic PCM or inorganic hydrated salts, capable of absorbing or releasing a large amount of latent heat within the phase change temperature range. The nanomaterials are zero-dimensional, one-dimensional, or two-dimensional high thermal conductivity nanoparticles, uniformly dispersed in the PCM substrate through physical blending or surface modification, constructing a dense nano-thermal conductive network within the substrate, effectively overcoming the low thermal conductivity of traditional PCMs. When this composite material is installed in an evaporator, condenser, or independent thermal energy storage unit, the PCM rapidly responds to changes in heat load when refrigerant flows through or air passes by, accelerating the refrigerant phase change process and significantly improving the instantaneous power and overall energy efficiency ratio of the heat exchanger.

[0021] The multi-functional environmental control module includes an air purification unit and a humidity control unit. The air purification unit uses a composite filter consisting of a pre-filter, a high-efficiency particulate air filter, and an activated carbon filter to intercept particulate matter in the air and adsorb gaseous pollutants such as formaldehyde and benzene compounds. To further enhance the purification effect, nano-titanium dioxide with photocatalytic function can be loaded onto the filter surface, working in conjunction with an ultraviolet lamp to decompose organic matter. The humidity control unit consists of a humidifier and a dehumidifier. The humidifier uses ultrasonic atomization or electrode heating vaporization, while the dehumidifier utilizes refrigeration dehumidification or rotary adsorption principles. Humidity control commands are sent by the intelligent control module based on the deviation between the current relative humidity and the user-set target. The air purification unit and humidity control unit can operate independently or in conjunction with the heat exchange module. For example, dehumidification can be activated simultaneously during summer cooling mode, or humidification can be activated as needed during winter heating mode, achieving comprehensive environmental control across multiple dimensions: temperature, humidity, and air quality.

[0022] The intelligent control module is the system's decision-making center, incorporating a deep learning model and reinforcement learning algorithm. This module first receives real-time data from the environmental sensing module, including temperature, humidity, airflow speed, and air quality. Simultaneously, it reads historical operating data from the heat exchange module, such as compressor frequency, fan speed, expansion valve opening, and the operating speed of the multi-functional module. This data is then combined into a state vector and input into the deep learning model, outputting an optimization objective weight vector for the current operating condition. The optimization objective includes at least three aspects: minimizing total system energy consumption, minimizing overall comfort deviation, and minimizing equipment lifespan loss. Total system energy consumption is calculated based on the cumulative power of components such as the compressor, fan, and pump. Overall comfort deviation is obtained by weighted summation of the differences between measured values ​​of temperature, humidity, airflow speed, and air quality and preset ideal ranges. Equipment lifespan loss is calculated using empirical formulas based on indicators such as compressor start-stop frequency, heat exchanger frosting degree, and cumulative fan operating time. The role of deep learning models is to adaptively adjust the relative importance of the three objectives mentioned above based on the characteristics of complex environments. For example, when outdoor temperatures are extreme, energy consumption constraints can be appropriately relaxed to prioritize comfort, or the weight of lifespan loss can be reduced under partial load to fully realize energy-saving potential.

[0023] Subsequently, the intelligent control module inputs the current environmental parameters and the optimization target weights output by the deep learning model into the reinforcement learning algorithm. The reinforcement learning algorithm employs a deep Q-network based on value function approximation, with its agent acting as the system's central controller. The action space is defined as a combination of continuous or discrete operating parameters, including compressor target frequency, indoor fan speed, electronic expansion valve opening, air purification level, humidification / dehumidification start / stop, and intensity. The state space incorporates optimization target weight vectors in addition to environmental parameters. The reward function is designed directly to correspond to the optimization target: the immediate reward equals the negative weighted sum of each optimization target, i.e., total system energy consumption multiplied by energy consumption weight, plus comprehensive comfort deviation multiplied by comfort weight, plus equipment lifespan loss term multiplied by lifespan loss weight. The reinforcement learning agent accumulates experience through interaction with the environment, stores transfer samples in an experience replay pool, and randomly samples small batches from the pool at fixed steps to update the Q-network parameters, maximizing the expected cumulative discount reward. After training convergence, the agent directly outputs the action that maximizes the reward function value based on the current state, which represents the optimal operating parameters for the heat exchange module and the multi-functional environmental control module. These parameters are sent to each actuator via fieldbus to achieve precise dynamic control of the system.

[0024] This invention provides a real-time and accurate environmental parameter data foundation for regulation through an environmental sensing module. The novel phase change material composite structure solves the problem of low thermal conductivity in traditional phase change materials at the material level, significantly improving the heat exchange efficiency of the heat exchange module. The multi-functional environmental regulation module integrates air purification and humidity control functions, breaking through the limitations of traditional equipment's single temperature control. The intelligent control module, combining deep learning models and reinforcement learning algorithms, can comprehensively analyze the parameters of each module and match the optimal operating parameters, achieving dynamic and coordinated regulation of each module. This effectively optimizes energy utilization efficiency, reduces system energy consumption, and provides users with a comprehensive environmental control solution, significantly improving indoor environmental comfort and overall regulation effects. It significantly reduces operating energy consumption while enhancing the equipment's environmental adaptability and overall user satisfaction, providing a feasible technical path for the evolution of temperature control equipment towards higher efficiency, intelligence, and multi-functionality.

[0025] In one possible implementation, the porous matrix is ​​a metal foam, the phase change substrate includes paraffin wax, and the nanomaterials include carbon nanotubes and / or graphene.

[0026] In this embodiment, the porous matrix is ​​made of metal foam material. Metal foam has high porosity, high specific surface area and continuous metal skeleton. Its three-dimensional open structure provides ample filling space and efficient heat conduction channels for the phase change substrate.

[0027] The phase change substrate uses paraffin-based organic phase change materials. Paraffin can reversibly absorb or release a large amount of latent heat during the solid-liquid phase change process. Its phase change temperature can be adjusted by the carbon chain length, making it suitable for typical operating temperature ranges of building environments and HVAC equipment.

[0028] Nanomaterials selected include carbon nanotubes, graphene, or a combination of the two. Carbon nanotubes are one-dimensional tubular structures with extremely high axial thermal conductivity, while graphene is a two-dimensional sheet structure with excellent in-plane thermal conductivity and high specific surface area.

[0029] During preparation, carbon nanotubes or graphene are uniformly mixed into liquid paraffin using mechanical stirring, ultrasonic dispersion, or surface modification to form a stable nanofluid suspension system. After the paraffin solidifies, the nanomaterials are anchored within the paraffin matrix, forming a dense nano-thermal conductive network. This composite material is then filled into the pores of a metal foam, forming a ternary synergistic structure where the metal foam skeleton provides continuous thermal conductivity, the paraffin matrix stores and releases latent heat, and the nanomaterials enhance heat transfer.

[0030] In one possible implementation, the intelligent control module is specifically used for: Environmental parameters and historical operating data are input into a deep learning model to determine optimization objectives; these objectives include minimizing total system energy consumption, minimizing overall comfort deviation, and minimizing equipment lifespan loss. By inputting environmental parameters and optimization objectives into a reinforcement learning algorithm, the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module are determined.

[0031] In this embodiment, the intelligent control module first combines the environmental parameters reported in real time by the environmental perception module and the historical operating data stored in the local database into a state feature vector, which is then input into the deep learning model. This deep learning model is a multi-layer feedforward neural network. Its input layer corresponds to the dimension of the state feature vector, the hidden layers extract high-dimensional abstract features layer by layer through nonlinear activation functions, and the output layer generates the optimization target weight vector under the current operating condition through a normalized exponential function or linear transformation. This optimization target can include three indicators: minimizing total system energy consumption, minimizing overall comfort deviation, and minimizing equipment lifespan loss. Total system energy consumption is calculated based on the real-time cumulative power of energy-consuming units such as compressors, fans, water pumps, and electrical control components. The overall comfort deviation is obtained by comparing the current measured values ​​of temperature, humidity, airflow speed, and air quality with their corresponding ideal comfort domains, and then normalizing and weighting the values ​​to obtain a dimensionless deviation value. Equipment lifespan loss is calculated based on indicators characterizing the aging process, such as compressor start-stop frequency, heat exchanger defrosting cycle count, and cumulative fan operating time, using an empirical model.

[0032] Deep learning models acquire mapping capabilities through offline supervised training. The training samples are derived from the optimization target weights defined by expert rules or traditional optimization algorithms under historical operating conditions. During training, the model learns the nonlinear relationship between the environmental state and the target weights.

[0033] After completing forward inference, the intelligent control module inputs the current environmental parameters and the optimization target weights output by the deep learning model into the reinforcement learning algorithm. The reinforcement learning algorithm employs a framework based on value functions or policy gradients. Its state space is composed of environmental parameters and optimization target weights, while its action space is a set of continuously or discretely adjustable operating parameters for the hot-swapping module and the multi-functional environmental adjustment module. The reward function is defined as the negative of the weighted sum of the optimization targets. During system operation, the reinforcement learning agent continuously interacts with the environment. Each time it performs an action, it observes the state at the next moment and calculates the immediate reward. Through experience replay and policy iteration, it updates the parameters of the value network or policy network, gradually approaching the optimal policy that maximizes the long-term cumulative reward. The action corresponding to this optimal policy in the current state represents the optimal operating parameters for the hot-swapping module and the multi-functional environmental adjustment module.

[0034] In one possible implementation, the intelligent control module is also used for: After applying the optimal operating parameters to the heat exchange module and the multi-functional environmental control module, the rate of change of each environmental parameter is monitored and the comprehensive environmental change rate index is calculated. Based on the comprehensive environmental change rate index, the exploration rate parameter of the reinforcement learning algorithm is adjusted.

[0035] In this embodiment, after the intelligent control module issues and executes the optimal operating parameters, the system continuously monitors the changes of various environmental parameters over time.

[0036] For four environmental indicators—temperature, humidity, airflow velocity, and air quality—the rate of change is calculated for each within a preset time window. To comprehensively assess the overall severity of environmental disturbances, the intelligent control module performs dimensionless normalization on the four rates of change and calculates their weighted sum of squares to obtain a single comprehensive environmental change rate index. The higher the value of this index, the more severe the fluctuations in the indoor environmental conditions, which may originate from disturbances such as sudden changes in outdoor weather, a sharp increase in indoor occupancy density, opening and closing of doors and windows, or switching of equipment control systems.

[0037] The intelligent control module dynamically adjusts the exploration rate parameter of the reinforcement learning algorithm based on the comprehensive environmental change rate index. The exploration rate is a hyperparameter in reinforcement learning where the agent randomly selects non-greedy actions to explore the unknown policy space. The specific adjustment logic is as follows: when the comprehensive environmental change rate index is higher than a preset first threshold, the system determines that the current operating condition has changed significantly, and the existing strategy may no longer be optimal. Therefore, the exploration rate is increased to a higher level to encourage the agent to try new actions to quickly capture the optimal strategy under the new operating condition. When the comprehensive environmental change rate index is lower than a preset second threshold, the system determines that the operating condition is becoming stable, and the converged strategy has high reliability. Therefore, the exploration rate is reduced to a lower level to fully utilize existing strategies and avoid unnecessary random disturbances. The first and second thresholds can be determined based on the distribution statistics of the system's historical operating data. For example, the 80th percentile value of the index in historical data can be set as the first threshold, and the 20th percentile value as the second threshold. Through this mechanism, the balance between exploration and utilization in the reinforcement learning algorithm can be dynamically and adaptively adjusted according to the environment, executing accurately in steady state and adapting quickly to drastic changes.

[0038] One possible implementation also includes: The intelligent fault diagnosis module is used to monitor the operating status data of the heat exchange module and the performance parameters of the novel phase change material in real time, analyze the operating status data and performance parameters, diagnose the malfunction of the heat exchange module and / or the phase change material, and generate and output corresponding adjustment commands to the intelligent control module when an malfunction is diagnosed, so as to adjust the internal parameters of the deep learning model and / or reinforcement learning algorithm.

[0039] In this embodiment, the intelligent fault diagnosis module is communicatively connected to the intelligent control module. It can be deployed as an independent physical unit or as an embedded functional component of the intelligent control module.

[0040] This module collects real-time operational status data of the heat exchange module and performance parameters of the novel phase change material through a dedicated sensor network. The operational status data of the heat exchange module includes compressor suction and discharge pressures and temperatures, evaporator and condenser tube wall temperatures, refrigerant mass flow rate, and fan operating current. The performance parameters of the novel phase change material are obtained through a miniature thermocouple array embedded inside the heat exchanger or distributed close to the material surface. This array provides real-time temperature time-series data from multiple spatial points within the material. The intelligent fault diagnosis module further calculates derived characteristics such as the phase change platform maintenance duration, latent heat release per unit mass, and material surface superheat based on the spatiotemporal temperature distribution, serving as quantitative indicators for evaluating the material's health status.

[0041] The intelligent fault diagnosis module incorporates a machine learning classification model. This model takes operational status data and derived features as input and, after offline training, is capable of identifying various abnormal patterns. During real-time operation, the intelligent fault diagnosis module periodically performs inference, inputting current features into the machine learning classification model and outputting the fault type and confidence level. When an abnormality is diagnosed in the heat exchange module or the novel phase change material, the intelligent fault diagnosis module generates an adjustment command and sends it to the intelligent control module. Upon receiving the command, the intelligent control module adaptively adjusts the internal parameters of the deep learning model or reinforcement learning algorithm. Adjustments include modifying the reward function weights, masking abnormal data, changing the strategy network structure, or switching control modes, thereby maintaining the system's basic functions and operational safety under conditions of equipment performance degradation or partial failure.

[0042] In one possible implementation, the intelligent fault diagnosis module is specifically used for: The failure modes of the heat exchange module and / or phase change material are identified through machine learning models. Failure modes include phase change material phase change efficiency degradation and sensor data anomalies.

[0043] In this embodiment, the machine learning model needs to be trained using supervised learning before use. The training dataset comes from feature samples collected synchronously during experimental setup and field operation by artificially injecting typical faults. The model's input feature vector consists of operating status data of the heat exchange module and performance parameters of the novel phase change material. The output layer adopts a multi-label classification architecture, capable of simultaneously outputting the probability distributions of multiple fault modes. After thorough training and validation, the model is deployed in real-time diagnostic tasks, performing fault mode recognition on the current feature at fixed intervals to obtain the fault mode recognition result.

[0044] Fault modes include phase change material (PCM) phase change efficiency degradation and sensor data anomalies. PCM efficiency degradation manifests as a significantly shortened plateau period for the PCM to maintain a constant temperature within the PCM temperature range and a decreased latent heat release rate per unit time. This is typically caused by microcapsule rupture after repeated PCM phase changes, sedimentation and agglomeration of thermally conductive additives, or aging of the encapsulation container. Sensor data anomalies manifest as sensor readings remaining consistently constant, exceeding limits, exceeding physically possible ranges, or complete signal loss. Causes include fatigue of sensitive components, drift in analog-to-digital conversion circuits, communication link interference, or unstable power supply. The intelligent fault diagnosis module packages the identified fault modes and their corresponding confidence levels into diagnostic results for subsequent adjustment command generation.

[0045] In one possible implementation, the intelligent fault diagnosis module is specifically used for: If the diagnosed fault mode is the decay of phase change efficiency of phase change material, then a first adjustment instruction is generated to increase the weight term related to equipment life loss in the reward function and at the same time decrease the weight term related to minimizing the total energy consumption of the system. If the diagnosed fault mode is abnormal sensor data, a second adjustment command is generated to suspend the use of the data channel corresponding to the abnormal sensor and switch to the backup control strategy based on historical safe operation data.

[0046] In this embodiment, when the diagnostic result indicates that the phase change efficiency of the phase change material is declining, the intelligent fault diagnosis module generates a first adjustment command. The core of this command is to modify the weight parameters of the reward function of the reinforcement learning algorithm. Specifically, the weights related to equipment lifespan degradation in the reward function are increased, while the weights related to minimizing the total system energy consumption are decreased accordingly. The magnitude of the weight adjustment is positively correlated with the diagnostic confidence level; the higher the confidence level, the greater the weight adjustment. The principle behind this adjustment logic is that the decline in phase change efficiency means a decrease in the dynamic thermal buffering capacity of the heat exchanger. If the compressor is frequently started and stopped or the load is rapidly changed with the goal of extremely low energy consumption as the priority, the risk of liquid slugging and mechanical fatigue will be aggravated, thus accelerating equipment failure. By increasing the weight of lifespan degradation, the reinforcement learning agent will spontaneously tend towards a smoother power change rate and a longer continuous operating time, thereby seeking a new balance between reliability and energy efficiency under the constraint of material performance degradation.

[0047] When the diagnostic result indicates abnormal sensor data, the intelligent fault diagnosis module generates a second adjustment command. This command first instructs the intelligent control module to suspend the use of the data channel corresponding to the abnormal sensor, meaning that the sensor's readings will no longer be included in the state space construction and reward function calculation. Simultaneously, the intelligent control module automatically switches to a backup control strategy based on historical safe operating data. This backup strategy can be an empirical mapping model fitted using offline data, approximating the missing environmental parameters with available information such as indoor temperature, outdoor temperature, and time-of-day characteristics; or it can be a timetable program embedded in the controller, maintaining basic temperature regulation according to a preset operating curve. The second adjustment command remains in effect until the abnormal sensor is manually repaired or replaced, restores normal communication, and passes its self-test. Both types of adjustment commands are transmitted in real-time through a high-speed message queue between the intelligent fault diagnosis module and the intelligent control module, ensuring that the system's response delay to faults is within the control cycle.

[0048] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] The following are method embodiments of the present invention. For details not described in detail, please refer to the corresponding system embodiments described above.

[0050] See Figure 2 The flowchart illustrating the implementation of the control method provided in this embodiment of the invention is shown below: Step 201: Obtain environmental parameters; wherein the environmental parameters include at least one of temperature, humidity, airflow speed and air quality; Step 202: Analyze and process the environmental parameters, operating parameters of the heat exchange module and the multi-functional environmental control module using deep learning models and reinforcement learning algorithms to obtain the optimal operating parameters of the heat exchange module and the multi-functional environmental control module, and apply them to the heat exchange module and the multi-functional environmental control module.

[0051] In one possible implementation, step 202 includes: Environmental parameters and historical operating data are input into a deep learning model to determine optimization objectives; these objectives include minimizing total system energy consumption, minimizing overall comfort deviation, and minimizing equipment lifespan loss. By inputting environmental parameters and optimization objectives into a reinforcement learning algorithm, the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module are determined.

[0052] In one possible implementation, the method further includes: After applying the optimal operating parameters to the heat exchange module and the multi-functional environmental control module, the rate of change of each environmental parameter is monitored and the comprehensive environmental change rate index is calculated. Based on the comprehensive environmental change rate index, the exploration rate parameter of the reinforcement learning algorithm is adjusted.

[0053] See Figure 3 This invention also provides a fault diagnosis method applied to an intelligent fault diagnosis module, comprising: Step 301: Monitor the operating status data of the heat exchange module and the performance parameters of the novel phase change material in real time, analyze the operating status data and performance parameters, diagnose the malfunction of the heat exchange module and / or the phase change material, and when a malfunction is diagnosed, generate and output corresponding adjustment commands to the intelligent control module to adjust the internal parameters of the deep learning model and / or reinforcement learning algorithm.

[0054] In one possible implementation, step 301 includes: The failure modes of the heat exchange module and / or phase change material are identified through machine learning models. Failure modes include phase change material phase change efficiency degradation and sensor data anomalies.

[0055] In one possible implementation, step 301 includes: If the diagnosed fault mode is the decay of phase change efficiency of phase change material, then a first adjustment instruction is generated to increase the weight term related to equipment life loss in the reward function and at the same time decrease the weight term related to minimizing the total energy consumption of the system. If the diagnosed fault mode is abnormal sensor data, a second adjustment command is generated to suspend the use of the data channel corresponding to the abnormal sensor and switch to the backup control strategy based on historical safe operation data.

[0056] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 40 and a memory 41. The memory 41 stores a computer program 42. When the processor 40 executes the computer program 42, it implements the steps in the various method embodiments described above. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module / unit in the various device embodiments described above.

[0057] For example, computer program 42 may be divided into one or more modules / units, which are stored in memory 41 and executed by processor 40 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0058] Electronic device 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0059] The processor 40 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0060] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store the computer program 42 and other programs and data required by the electronic device 4. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0061] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0062] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0063] This invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0064] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0065] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0066] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A smart temperature control system using a novel phase change material, characterized in that, include: An environmental sensing module is used to collect environmental parameters in real time; wherein the environmental parameters include at least one of temperature, humidity, airflow speed and air quality; A heat exchange module includes a heat exchanger that applies a novel phase change material; wherein the novel phase change material includes a porous matrix, a phase change substrate filled in the porous matrix, and nanomaterials dispersed in the phase change substrate; A multi-functional environmental control module, including an air purification unit and / or a humidity control unit; The intelligent control module is used to analyze and process the environmental parameters, the operating parameters of the heat exchange module and the multifunctional environmental regulation module using deep learning models and reinforcement learning algorithms, to obtain the optimal operating parameters of the heat exchange module and the multifunctional environmental regulation module, and apply them to the heat exchange module and the multifunctional environmental regulation module.

2. The intelligent temperature control system using a novel phase change material according to claim 1, characterized in that, The porous matrix is ​​a metal foam, the phase change substrate includes paraffin wax, and the nanomaterials include carbon nanotubes and / or graphene.

3. The intelligent temperature control system using a novel phase change material according to claim 1, characterized in that, The intelligent control module is specifically used for: The environmental parameters and historical operating data are input into a deep learning model to determine the optimization objectives; among which, the optimization objectives include minimizing the total system energy consumption, minimizing the overall comfort deviation, and minimizing equipment lifespan loss; The environmental parameters and the optimization objective are input into the reinforcement learning algorithm to determine the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module.

4. The intelligent temperature control system using a novel phase change material according to claim 3, characterized in that, The intelligent control module is also used for: After applying the optimal operating parameters to the heat exchange module and the multifunctional environmental control module, the rate of change of each environmental parameter is monitored and a comprehensive environmental change rate index is calculated. Based on the comprehensive environmental change rate index, the exploration rate parameter of the reinforcement learning algorithm is adjusted.

5. The intelligent temperature control system using a novel phase change material according to claim 1, characterized in that, Also includes: The intelligent fault diagnosis module is used to monitor the operating status data of the heat exchange module and the performance parameters of the novel phase change material in real time, analyze the operating status data and the performance parameters, diagnose the malfunction of the heat exchange module and / or the phase change material, and generate and output corresponding adjustment commands to the intelligent control module when an malfunction is diagnosed, so as to adjust the internal parameters of the deep learning model and / or reinforcement learning algorithm.

6. The intelligent temperature control system using a novel phase change material according to claim 5, characterized in that, The intelligent fault diagnosis module is specifically used for: The failure modes of the heat exchange module and / or the phase change material are identified by a machine learning model; the failure modes include phase change material phase change efficiency degradation and sensor data anomalies.

7. The intelligent temperature control system using a novel phase change material according to claim 5, characterized in that, The intelligent fault diagnosis module is specifically used for: If the diagnosed fault mode is the decay of phase change efficiency of phase change material, a first adjustment instruction is generated to increase the weight term related to equipment life loss in the reward function and at the same time decrease the weight term related to minimizing total system energy consumption. If the diagnosed fault mode is abnormal sensor data, a second adjustment command is generated to suspend the use of the data channel corresponding to the abnormal sensor and switch to the backup control strategy based on historical safe operation data.

8. A control method, characterized in that, An intelligent control module applied to an intelligent temperature control system using novel phase change materials as described in any one of claims 1 to 7, characterized in that it comprises: Obtain environmental parameters; wherein the environmental parameters include at least one of temperature, humidity, airflow speed, and air quality; The environmental parameters, the operating parameters of the heat exchange module and the multifunctional environmental control module are analyzed and processed using deep learning models and reinforcement learning algorithms to obtain the optimal operating parameters of the heat exchange module and the multifunctional environmental control module, and then applied to the heat exchange module and the multifunctional environmental control module.

9. The control method according to claim 8, characterized in that, The process of analyzing and processing the environmental parameters, the operating parameters of the heat exchange module, and the multifunctional environmental control module using deep learning models and reinforcement learning algorithms to obtain the optimal operating parameters of the heat exchange module and the multifunctional environmental control module includes: The environmental parameters and historical operating data are input into a deep learning model to determine the optimization objectives; among which, the optimization objectives include minimizing the total system energy consumption, minimizing the overall comfort deviation, and minimizing equipment lifespan loss; The environmental parameters and the optimization objective are input into the reinforcement learning algorithm to determine the optimal operating parameters for the heat exchange module and the multifunctional environmental regulation module.

10. The control method according to claim 8, characterized in that, Also includes: After applying the optimal operating parameters to the heat exchange module and the multifunctional environmental control module, the rate of change of each environmental parameter is monitored and a comprehensive environmental change rate index is calculated. Based on the comprehensive environmental change rate index, the exploration rate parameter of the reinforcement learning algorithm is adjusted.

Images