Indoor temperature intelligent control system

Abstract

The invention relates to the technical field of indoor temperature control, and discloses an indoor temperature intelligent control system, which comprises a distributed temperature sensor array, a multi-modal environment sensing module, a multi-modal temperature sensing module, a multi-modal temperature sensing module, a multi-modal temperature sensing module and an indoor temperature control module, wherein the distributed temperature sensor array is deployed in a plurality of indoor areas and is configured to acquire three-dimensional space temperature data in real time; a temperature and humidity sensor, a human body infrared sensor, a door and window state detector, an intelligent control center, a machine learning processor, a knowledge graph database, a self-adaptive execution mechanism group, a variable frequency air conditioner, a floor heating control valve, a fresh air adjusting device, an edge computing gateway, a local decision engine and a cloud collaboration interface are integrated. According to the indoor temperature intelligent control system, three-dimensional space temperature data is collected in real time through the distributed temperature sensor array, the multi-mode environment sensing module integrates various sensors, the intelligent control center comprises a machine learning processor, a knowledge graph database and the like, and accurate control and optimal adjustment of the indoor temperature can be achieved; and the indoor comfort is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor temperature control, and specifically to an intelligent indoor temperature control system. Background Art

[0002] "HVAC" is a classification of trades in building equipment, including heating, ventilation, and air conditioning (abbreviated as HVAC). Heating supplies load to a building as needed to ensure that the indoor temperature is higher than the external environment. Ventilation is the process of sending air into or exhausting air from a room, which is divided into natural ventilation and mechanical ventilation. Air conditioning is a building environment control system that regulates the temperature, humidity, cleanliness, and air flow rate in a room or space and provides a sufficient amount of fresh air.

[0003] With the progress of technology and the improvement of living standards, people's requirements for the comfort of the indoor environment are getting higher and higher. Most traditional indoor temperature control systems adopt centralized control, collecting indoor temperature through a single temperature sensor, and then performing on-off control on actuators such as air conditioners and floor heating according to a preset temperature threshold. This method has many deficiencies, such as inaccurate temperature collection, slow regulation response, high energy consumption, etc. Therefore, there is an urgent need for an intelligent indoor temperature control system. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent indoor temperature control system to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solution: An intelligent indoor temperature control system, comprising:

[0006] A distributed temperature sensor array, deployed in multiple indoor areas and configured to collect three-dimensional space temperature data in real time;

[0007] A multi-modal environment perception module, integrating a temperature and humidity sensor, a human infrared sensor, and a door and window status detector;

[0008] An intelligent control center, including a machine learning processor and a knowledge graph database;

[0009] An adaptive actuator group, including a variable frequency air conditioner, a floor heating control valve, and a fresh air adjustment device;

[0010] An edge computing gateway, having a local decision-making engine and a cloud collaboration interface;

[0011] A user interaction terminal, supporting voice, gesture, and biometric recognition input.

[0012] Preferably, the temperature sensor array adopts a self-organizing wireless mesh network topology, each node is equipped with a self-calibration module and an abnormal data filtering algorithm, and the deployment density is dynamically adjusted according to the room functional partition.

[0013] Preferably, the intelligent control center includes:

[0014] a) A deep reinforcement learning model that optimizes strategies based on historical regulation records and energy consumption data;

[0015] b) A digital twin engine that constructs a virtual building thermodynamics model and real-time simulates the regulation effect;

[0016] c) A swarm intelligence algorithm that coordinates the collaborative optimization of multi-region temperature fields.

[0017] Preferably, the deep reinforcement learning model adopts a hierarchical architecture:

[0018] The upper decision-making network processes the multi-objective optimization of long-term energy-saving goals and user comfort;

[0019] The lower execution network generates a combined optimization scheme for device control parameters;

[0020] Introduce a transfer learning mechanism to adapt to different building structure characteristics.

[0021] Preferably, the adaptive actuator group includes:

[0022] A variable-frequency air conditioner drive circuit based on model predictive control (MPC);

[0023] An intelligent water distributor with pressure compensation to achieve dynamic hydraulic balance of the floor heating pipeline;

[0024] A fresh air volume fuzzy controller with PM2.5 detection.

[0025] Preferably, the user interaction terminal includes:

[0026] An augmented reality (AR) spatial temperature field visualization interface;

[0027] A non-intrusive comfort perception module that analyzes the user's micro-expressions and body postures through a camera;

[0028] An adaptive recommendation engine that dynamically adjusts the control strategy preference weights according to the user's response.

[0029] Preferably, the edge computing gateway realizes:

[0030] Aggregation of energy consumption data with local differential privacy protection;

[0031] A distributed model update mechanism based on federated learning;

[0032] An autonomous fault-tolerant control strategy in the case of network disconnection.

[0033] Preferably, it further includes:

[0034] Building Energy Router, integrating the collaborative optimization of photovoltaic power generation, energy storage systems and grid power supply;

[0035] Dynamic electricity price response module, combined with real-time power market data for demand-side management;

[0036] Carbon footprint tracker, calculating and optimizing the environmental impact indicators of system operation.

[0037] Preferably, the system passes through:

[0038] a) Establishing a digital passport for equipment to record full-life cycle maintenance data;

[0039] b) Deploying blockchain verification nodes to ensure the immutability of regulation records;

[0040] c) Using homomorphic encryption for cross-system data exchange;

[0041] To achieve trustworthy traceability and secure collaboration in building energy management.

[0042] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0043] First, in the present invention, three-dimensional space temperature data is collected in real time through a distributed temperature sensor array. The multi-modal environment perception module integrates multiple sensors, and the intelligent control center includes a machine learning processor and a knowledge graph database, etc., which can achieve precise control and optimized adjustment of the indoor temperature, improve indoor comfort. The temperature sensor array adopts a self-organizing wireless mesh network topology, each node is equipped with a self-calibration module and an abnormal data filtering algorithm, and the deployment density is dynamically adjusted according to the room functional partition, improving the accuracy and reliability of temperature data. The deep reinforcement learning model of the intelligent control center optimizes strategies based on historical regulation records and energy consumption data, the digital twin engine constructs a building thermodynamics virtual model and simulates the regulation effect in real time, and the swarm intelligence algorithm coordinates the collaborative optimization of multi-region temperature fields, achieving multi-objective optimization of energy conservation and improving user comfort.

[0044] Second, in the present invention, the adaptive actuator group includes a variable-frequency air conditioner drive circuit based on model predictive control, an intelligent water distributor with pressure compensation, a fresh air volume fuzzy controller with PM2.5 detection, etc., which can perform precise adjustment according to actual needs and improve energy utilization efficiency. The user interaction terminal supports voice, gesture and biometric recognition input, including an augmented reality space temperature field visualization interface, a non-intrusive comfort perception module, an adaptive recommendation engine, etc., providing a more convenient and personalized user experience. The edge computing gateway realizes local differential privacy protection of energy consumption data aggregation, a distributed model update mechanism based on federated learning, and an autonomous fault-tolerant control strategy in the case of network disconnection, improving the security and reliability of the system.

[0045] Thirdly, the present invention further includes a building energy router, a dynamic electricity price response module, a carbon footprint tracker, etc., which can integrate the collaborative optimization of multiple energies, conduct demand-side management by combining real-time data in the electricity market, calculate and optimize the environmental impact indicators of system operation, and achieve trustworthy traceability and secure collaboration in building energy management, having beneficial effects in aspects such as energy conservation and emission reduction, improving energy utilization efficiency, and optimizing the indoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a block diagram of an intelligent indoor temperature control system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] The present invention provides the following technical solutions:

[0049] Embodiment

[0050] Please refer to Figure 1 , an intelligent indoor temperature control system, including:

[0051] A distributed temperature sensor array, deployed in multiple indoor areas and configured to collect three-dimensional space temperature data in real time;

[0052] A multimodal environment perception module, integrating a temperature and humidity sensor, a human infrared sensor, and a door and window status detector;

[0053] An intelligent control center, including a machine learning processor and a knowledge graph database;

[0054] An adaptive actuator group, including a variable-frequency air conditioner, a floor heating control valve, and a fresh air regulating device;

[0055] An edge computing gateway, having a local decision-making engine and a cloud collaboration interface;

[0056] A user interaction terminal, supporting voice, gesture, and biometric recognition inputs.

[0057] Through the above technical solutions, multiple sensor nodes distributed indoors can comprehensively and accurately obtain the indoor temperature distribution, providing basic data for intelligent control. The temperature and humidity sensors monitor the indoor temperature and humidity, the passive infrared sensors detect whether there are people moving indoors, and the door and window status detectors monitor the opening and closing status of the doors and windows. These sensors work together to provide rich environmental information for the system. The intelligent control center includes a machine learning processor and a knowledge graph database. The machine learning processor uses historical data and real-time data to optimize control strategies through algorithm models; the knowledge graph database stores relevant knowledge such as buildings, equipment, and user preferences to support intelligent decision-making. The devices of the actuator group include variable-frequency air conditioners, floor heating control valves, and fresh air regulating devices. These devices can automatically adjust their working states according to the instructions of the intelligent control center to achieve stable and comfortable indoor temperature. For example, the variable-frequency air conditioner can automatically adjust its power according to the indoor temperature change, the floor heating control valve can control the heating intensity of the floor heating system, and the fresh air regulating device can adjust the indoor fresh air volume. The edge computing gateway has a local decision-making engine, which can process part of the data locally and make preliminary decisions to reduce the burden on the cloud. At the same time, it also has a cloud collaboration interface, which can perform data transmission and collaborative work with the cloud to achieve a higher level of intelligent control. The user interaction terminal supports multiple input methods (voice, gesture, biometric recognition), enabling users to conveniently interact with the system. For example, users can control the working state of the system through voice commands or perform interface operations through gesture recognition. The biometric recognition function can improve the security of the system. These components together constitute a complete intelligent indoor temperature control system. The distributed temperature sensor array and the multi-modal environmental perception module provide real-time data input, the intelligent control center processes this data and formulates control strategies, the adaptive actuator group adjusts the indoor temperature according to the control strategies, the edge computing gateway realizes local decision-making and cloud collaboration, and the user interaction terminal provides an interaction interface between the user and the system. Through the collaborative work of these components, the system can achieve precise control of the indoor temperature and efficient utilization of energy, providing users with a comfortable and intelligent indoor environment.

[0058] The temperature sensor array adopts a self-organizing wireless mesh network topology. Each node is equipped with a self-calibration module and an abnormal data filtering algorithm, and the deployment density is dynamically adjusted according to the room functional partition.

[0059] Through the above technical solutions, each node (i.e., sensor) in the temperature sensor array can automatically organize into a wireless mesh network. In this network, each node can communicate with other nodes, forming a data transmission network with multiple paths, improving the reliability and transmission efficiency of data, making the deployment and maintenance of the system more flexible and simple, without relying on wired connections or complex network configurations. Moreover, each temperature sensor node is built-in with a self-calibration module, enabling it to automatically calibrate its measurement data to ensure the accuracy and consistency of the data. At the same time, the self-calibration module can achieve calibration by comparing data with other nodes, using known reference points, or through interaction with the environment. Each node is also equipped with an abnormal data filtering algorithm for identifying and filtering out abnormal or unreliable data. These algorithms can determine the rationality of the data based on the statistical characteristics of the data, the trend of change, comparison with data from other nodes, etc., thus ensuring that only accurate data is used for subsequent analysis and control. The deployment density of the temperature sensor array is dynamically adjusted according to the functional zoning of the room. Different rooms may have different temperature control requirements. For example, the bedroom requires more precise temperature control, while the corridor or storage room may only need approximate temperature monitoring. Therefore, the system can dynamically adjust the deployment density of the temperature sensors according to the functional zoning of the room and the user's temperature control requirements. In areas where more precise control is needed, more sensors can be deployed, while in areas with lower requirements, the number of sensors can be reduced, enabling the indoor temperature intelligent control system to more accurately and reliably obtain indoor temperature data and dynamically adjust the deployment density of the sensors according to the functional zoning of the room and the user's control requirements, which helps to improve the control accuracy and energy utilization efficiency of the system.

[0060] The intelligent control center includes:

[0061] a) A deep reinforcement learning model for policy optimization based on historical regulation records and energy consumption data;

[0062] b) A digital twin engine for building a virtual model of building thermodynamics and real-time simulating the regulation effect;

[0063] c) A swarm intelligence algorithm for coordinating the collaborative optimization of multi-region temperature fields.

[0064] Through the above technical solutions, there are three core components of the intelligent control center. Among them, a) the deep reinforcement learning model can extract effective control strategies from historical regulation records through continuous trial and error and learning, and optimize these strategies in combination with energy consumption data. It can automatically find a way to meet the user's comfort requirements in a complex temperature regulation environment and continuously adjust and optimize the control strategies as time and the environment change. b) The digital twin engine uses advanced modeling and simulation technologies to create a virtual thermodynamic model for the actual building, which can real-time reflect information such as the temperature distribution and energy consumption inside the building, and can simulate and predict different control strategies. Through the digital twin engine, the system can pre-test and evaluate different control strategies without actually changing the indoor temperature, so as to select the optimal control plan. This greatly improves the regulation efficiency and accuracy of the system. c) The swarm intelligence algorithm draws on the cooperative optimization mechanism of group behaviors in nature (such as ant colonies, bird flocks, etc.), coordinates the optimization problems between multiple temperature regulation areas by simulating the behaviors of these groups, can consider the mutual influence and restrictive relationships between different areas, and thus find a globally optimal control plan. The swarm intelligence algorithm has the characteristics of being distributed, self-organizing and adaptive, and can achieve efficient cooperative optimization in a complex multi-area temperature regulation environment. Generally speaking, the intelligent control center realizes the intelligent, refined and cooperative optimization of the indoor temperature control strategy by integrating the deep reinforcement learning model, the digital twin engine and the swarm intelligence algorithm.

[0065] The deep reinforcement learning model adopts a hierarchical architecture:

[0066] The upper-layer decision-making network processes the multi-objective optimization of long-term energy-saving goals and user comfort;

[0067] The lower-layer execution network generates a combined optimization plan for device control parameters;

[0068] Introduce a transfer learning mechanism to adapt to different building structure characteristics.

[0069] Through the above technical solution, the deep reinforcement learning model adopts a hierarchical architecture. This architecture decomposes the complex decision-making process into multiple levels, with each level responsible for different tasks, thereby improving the efficiency and accuracy of the model. Among them, the upper-level decision-making network is responsible for starting from a global perspective, considering long-term energy-saving goals and the comfort requirements of users. By learning historical data and the current state, it formulates a long-term regulation strategy. This strategy aims to minimize energy consumption while meeting the comfort requirements of users. Through the upper-level decision-making network, the system can optimize long-term goals and avoid increased energy consumption or decreased user comfort caused by short-term fluctuations. Among them, the lower-level execution network is responsible for generating specific combinations of device control parameters according to the strategy formulated by the upper-level decision-making network. These parameters include the temperature setting, wind speed, working mode, etc. of the air conditioner, as well as the opening degree of the control valve of the floor heating and the air supply volume of the fresh air system. The lower-level execution network continuously learns and adjusts these parameters to achieve the long-term goals formulated by the upper-level decision-making network. The lower-level execution network can achieve fine-tuning of device control parameters, thereby improving the regulation accuracy and response speed of the system. Among them, the transfer learning mechanism allows the model to transfer the learned knowledge and experience between different building structures. When the system is deployed in a new building, the transfer learning mechanism can use the previously learned regulation strategy as a starting point to quickly adapt to the characteristic features of the new building structure. Through the transfer learning mechanism, the system can shorten the learning cycle in the new building and improve the deployment efficiency and adaptability of the system. The hierarchical architecture of the deep reinforcement learning model decomposes the complex decision-making process into two levels: the upper-level decision-making network and the lower-level execution network, which are responsible for formulating long-term goals and specific execution strategies respectively. At the same time, the introduction of the transfer learning mechanism improves the adaptability of the system to different building structures.

[0070] The adaptive actuator group includes:

[0071] A variable-frequency air conditioner drive circuit based on model predictive control (MPC);

[0072] An intelligent water distributor with pressure compensation to achieve dynamic hydraulic balance of the floor heating pipeline;

[0073] A fresh air volume fuzzy controller with PM2.5 detection.

[0074] Through the above technical solutions, the adaptive actuator group consists of three components, which jointly act on the intelligent indoor temperature control system to achieve precise and efficient temperature regulation and air quality optimization. Among them, the model predictive control (MPC) in the variable-frequency air conditioner drive circuit based on model predictive control (MPC) is an advanced control algorithm that uses a mathematical model to predict the future behavior of the system and formulates control strategies according to the prediction results. In the variable-frequency air conditioner drive circuit, the MPC algorithm can calculate and adjust the power output of the air conditioner in real time based on multiple factors such as indoor temperature, humidity, user settings, and outdoor environmental conditions to achieve indoor temperature stability and energy conservation. Among them, the intelligent water separator with pressure compensation can, through the built-in pressure sensor and flow controller, monitor the water pressure and flow changes in the floor heating pipeline in real time. When abnormal water pressure or flow is detected in a certain area, the intelligent water separator will automatically adjust the valve opening of that area to compensate for the pressure difference and achieve dynamic hydraulic balance of the floor heating pipeline. The intelligent water separator with pressure compensation can ensure the efficient and stable operation of the floor heating system, avoid local overheating or overcooling, and improve the comfort of users. Among them, the fresh air volume fuzzy controller with PM2.5 detection has a PM2.5 sensor and a temperature sensor, which can monitor the PM2.5 concentration and the temperature difference between indoor and outdoor in real time. Through the fuzzy control algorithm, the controller can intelligently adjust the air supply volume of the fresh air system according to the changes of these parameters to minimize energy consumption while ensuring indoor air quality. The fresh air volume fuzzy controller with PM2.5 detection can achieve precise control of the fresh air system, ensuring both fresh and comfortable indoor air and avoiding unnecessary energy consumption waste. These three components of the adaptive actuator group achieve precise and efficient control of the air conditioner, floor heating, and fresh air system.

[0075] The user interaction terminal includes:

[0076] An augmented reality (AR) spatial temperature field visualization interface;

[0077] A non-intrusive comfort perception module that analyzes the user's micro-expressions and body postures through a camera;

[0078] An adaptive recommendation engine that dynamically adjusts the preference weights of control strategies according to user responses.

[0079] Through the above technical solution, the user interaction terminal consists of an augmented reality (AR) spatial temperature field visualization interface, a non-invasive comfort perception module, and an adaptive recommendation engine. Among them, the augmented reality (AR) spatial temperature field visualization interface uses AR technology. Users can see the temperature distribution maps superimposed on the real scene through intelligent devices (such as mobile phones, tablets, or AR glasses). These temperature distribution maps can represent different temperature ranges according to different colors or patterns, enabling users to intuitively understand the temperature conditions in various indoor areas. The AR spatial temperature field visualization interface improves users' perception and understanding of the indoor temperature distribution, helps users more accurately judge and adjust the indoor temperature, and thus optimize the living or working environment. Among them, the non-invasive comfort perception module uses advanced image recognition and analysis technologies to monitor and analyze users' facial expressions (such as frowning, smiling, etc.) and body postures (such as sitting postures, standing postures, etc.) in real time. By analyzing these micro-expressions and body postures, the module can indirectly infer the comfort level of users, so as to provide more personalized temperature control suggestions for users. The non-invasive comfort perception module can evaluate the comfort level of users in real time without disturbing their normal activities and provide more considerate and personalized services for users. Among them, the adaptive recommendation engine collects and analyzes the feedback data (such as temperature setting adjustments, comfort evaluations, etc.) during the user's use process, continuously learns and optimizes the control strategy. When the user shows a preference for a certain temperature control scheme, the recommendation engine will automatically adjust the weight of this scheme so that it occupies a larger proportion in the future control strategy. The adaptive recommendation engine can dynamically adjust the control strategy according to the real-time needs and preferences of users and provide a more intelligent and personalized temperature control experience for users. The user interaction terminal provides a more intuitive, personalized, and intelligent temperature control experience for users through technical means such as augmented reality technology, non-invasive comfort perception, and adaptive recommendation engine.

[0080] Edge computing gateway implementation:

[0081] Energy consumption data aggregation with local differential privacy protection;

[0082] Distributed model update mechanism based on federated learning;

[0083] Autonomous fault tolerance control strategy in the case of network disconnection.

[0084] Through the above technical solutions, the edge computing gateway can execute local differential privacy protection policies to aggregate energy consumption data. Through local differential privacy technology, even if an attacker can access the aggregated data, they cannot accurately infer the original energy consumption data of individual users, thus effectively protecting user privacy. The edge computing gateway supports a distributed model update mechanism based on federated learning. Under the federated learning framework, the original data does not need to leave the local device, thus avoiding the risk of data leakage. Each device only uses its own data locally to train the model and sends the model update to the server instead of directly transmitting the original data. The edge computing gateway can achieve fault tolerance by deploying redundant backups, automatic fault recovery and other technologies. When a network failure or device failure is detected, the gateway can automatically switch to a standby device or recover the faulty device to ensure the continuity and stability of the system. In the case of a network outage, the edge computing gateway can rely on locally stored data and models for decision-making and control. For example, in a smart home scenario, the gateway can automatically adjust the status of devices such as indoor temperature and lighting according to locally stored user habits and energy consumption data.

[0085] It also includes:

[0086] A building energy router that integrates the collaborative optimization of photovoltaic power generation, energy storage systems, and grid power supply;

[0087] A dynamic electricity price response module that combines real-time data from the electricity market for demand-side management;

[0088] A carbon footprint tracker that calculates and optimizes the environmental impact indicators of system operation.

[0089] Through the above technical solutions, the system introduces three components: a building energy router, a dynamic electricity price response module, and a carbon footprint tracker. Among them, the building energy router, as the core device for intelligent building energy management, can monitor and regulate the output of the photovoltaic power generation system, the charge and discharge status of the energy storage system, and the power supply situation of the power grid in real time. Through advanced algorithms and control strategies, it can achieve the collaborative optimization of these energy systems to ensure the efficient and reliable utilization of building energy. Among them, the dynamic electricity price response module can obtain real-time electricity price information from the electricity market and adjust the building's electricity consumption strategy according to the change in electricity price. For example, increase electricity consumption when the electricity price is low and reduce electricity consumption or use the energy storage system to supply power when the electricity price is high. In this way, the module can help the building reduce electricity costs and at the same time relieve the load pressure on the power grid. Among them, the carbon footprint tracker calculates the carbon emissions and other environmental impact indicators of the building by collecting and analyzing information such as energy consumption data and emission data during the building operation process. At the same time, it can also propose optimization suggestions based on these data to help the building reduce carbon emissions and environmental impact, further enhancing the function and performance of the indoor temperature intelligent control system.

[0090] The system works through:

[0091] a) Establishing a digital passport for the equipment to record the maintenance data throughout its life cycle;

[0092] b) Deploying blockchain verification nodes to ensure that the regulation records cannot be tampered with;

[0093] c) Using homomorphic encryption for cross-system data exchange;

[0094] To achieve trustworthy traceability and secure collaboration in building energy management.

[0095] Through the above technical solutions, by establishing a digital passport for the equipment, deploying blockchain verification nodes, and using homomorphic encryption technology, trustworthy traceability and secure collaboration in building energy management are achieved, specifically including the following aspects: a) Establishing a digital passport for the equipment to record the maintenance data throughout its life cycle. Digital passports are established for various energy equipment in the building (such as air conditioners, lighting, heating systems, etc.). These digital passports detail the maintenance data of the entire life cycle, including the basic information of the equipment, installation date, operating parameters, historical maintenance records, and repair and replacement situations, etc. By establishing such digital files, the system can comprehensively track and precisely manage the equipment status. Once a fault or performance decline occurs in the equipment, the system can quickly locate the problem and provide targeted maintenance suggestions, thereby extending the service life of the equipment and improving energy utilization efficiency; b) Deploying blockchain verification nodes to ensure that the regulation records cannot be tampered with. By deploying blockchain verification nodes, the system can record and store relevant data on energy regulation in real time, including equipment operating status, energy consumption, regulation strategies, etc. The decentralized and non-tamperable characteristics of the blockchain ensure the authenticity and integrity of these records. Even in the case of network failures or malicious attacks, the security and traceability of the data can be guaranteed, providing strong legal evidence support for energy management and helping to resolve potential disputes and problems; c) Using homomorphic encryption for cross-system data exchange. To protect the privacy and security of the data, homomorphic encryption technology is adopted. Homomorphic encryption allows calculations and analyses to be performed on encrypted data without decrypting it, thereby achieving secure data transmission and collaborative processing. Even if the data is intercepted during transmission, attackers cannot decrypt or tamper with the data content, improving the efficiency and flexibility of data exchange and ensuring the integrity and privacy of the data.

[0096] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An indoor temperature intelligent control system, characterized in that: include: Distributed temperature sensor arrays, deployed in multiple areas indoors and configured to collect three-dimensional spatial temperature data in real time; Multimodal environmental perception module, integrating temperature and humidity sensors, human infrared sensors, and door and window status detectors; Intelligent control center, including machine learning processor and knowledge graph database; Adaptive actuator group, including variable frequency air conditioner, floor heating control valve and fresh air adjustment device; Edge computing gateway, with local decision engine and cloud collaboration interface; User interaction terminal, supporting voice, gesture and biometric recognition input.

2. An indoor temperature intelligent control system according to claim 1, characterized in that: The temperature sensor array adopts a self-organizing wireless mesh network topology, each node is equipped with a self-calibration module and an abnormal data filtering algorithm, and the deployment density is dynamically adjusted according to the functional zoning of the room.

3. The indoor temperature intelligent control system according to claim 1, characterized in that: The intelligent control center includes: a) Deep reinforcement learning model, which optimizes strategies based on historical control records and energy consumption data; b) Digital twin engine, which constructs a virtual model of building thermodynamics and simulates the control effect in real time; c) Swarm intelligence algorithm to coordinate the collaborative optimization of multi-region temperature fields.

4. An indoor temperature intelligent control system according to claim 3, characterized in that: The deep reinforcement learning model adopts a layered architecture: The upper decision network handles the multi-objective optimization of long-term energy saving goals and user comfort; The lower layer execution network generates a combinatorial optimization scheme for device control parameters; A transfer learning mechanism is introduced to adapt to different building structure characteristics.

5. The indoor temperature intelligent control system according to claim 1, characterized in that: The adaptive actuator group comprises: Variable frequency air conditioner drive circuit based on model predictive control (MPC); Intelligent water distributor with pressure compensation to achieve dynamic hydraulic balance of floor heating pipelines; Fresh air volume fuzzy controller with PM2.5 detection.

6. The indoor temperature intelligent control system according to claim 1, characterized in that: The user interaction terminal comprises: Augmented reality (AR) spatial temperature field visualization interface; Non-intrusive comfort perception module, which analyzes user micro-expressions and body posture through cameras; Adaptive recommendation engine that dynamically adjusts control strategy preference weights based on user responses.

7. The indoor temperature intelligent control system according to claim 1, characterized in that: The edge computing gateway implements: Energy consumption data aggregation with local differential privacy protection; Distributed model update mechanism based on federated learning; Autonomous fault-tolerant control strategy under network outage.

8. The indoor temperature intelligent control system according to claim 1, characterized in that: Also includes: Building energy routers integrate the coordinated optimization of photovoltaic power generation, energy storage systems and grid energy supply; Dynamic electricity price response module, combining real-time data from the electricity market to manage demand side; Carbon footprint tracker, calculates and optimizes the environmental impact of system operations.

9. The indoor temperature intelligent control system according to claim 1, characterized in that: The system is implemented by: a) Establish a digital passport for equipment to record maintenance data throughout its life cycle; b) Deploy blockchain verification nodes to ensure that regulatory records cannot be tampered with; c) Use homomorphic encryption for cross-system data exchange; Realize trusted traceability and secure coordination of building energy management.

Images