AI-based heating ventilation air conditioner energy-saving control method and system

Abstract

The invention discloses an AI-based heating ventilation air conditioner energy-saving control method and system, and the system employs an intelligent sensor network to collect environment and equipment operation data in real time, carries out the primary processing through an edge calculation node, and guarantees the accuracy and real-time performance of the data. Local and cloud computing resources are combined, a multi-dimensional optimization algorithm is applied, the optimal efficiency point and control parameters are generated, the running state of the central air-conditioning system is dynamically adjusted, and the optimal energy-saving effect is achieved. Meanwhile, the system has a real-time fault detection and diagnosis function, the timeliness and accuracy of fault processing are improved by utilizing a machine learning algorithm, and the maintenance cost is reduced. Through a data-driven optimization strategy and a remote monitoring and maintenance function, the energy efficiency, the response speed and the reliability of the heating, ventilation and air conditioning system are remarkably improved, the maintenance cost is reduced, and an effective solution is provided for intelligent energy-saving control of the heating, ventilation and air conditioning system.

Description

Technical Field

[0001] The present invention relates to the field of heating, ventilation and air conditioning (HVAC) systems, and specifically to an artificial intelligence (AI)-based HVAC energy-saving control method and system, which aims to optimize the operating efficiency of a refrigeration room and a central air-conditioning system through multi-dimensional optimization and adaptive control technology to achieve the best energy-saving effect. Background Art

[0002] Traditional HVAC systems mainly rely on preset control strategies and manual adjustments, which makes it difficult to respond to environmental changes and user needs in real time. This control method has the following problems:

[0003] (1) Low energy efficiency: Traditional systems cannot dynamically adjust operating parameters and are difficult to maintain optimal operating conditions under different environmental conditions, resulting in energy waste.

[0004] (2) Slow response: When faced with environmental changes and user needs, traditional systems respond slowly and cannot be adjusted in time, affecting user comfort.

[0005] (3) High maintenance cost: Fault detection and diagnosis of traditional systems mainly rely on manual work, which cannot achieve real-time monitoring and automatic fault prevention, increasing maintenance costs and downtime.

[0006] In order to improve the energy efficiency and reliability of the system, an intelligent energy-saving control method that can perform real-time monitoring, dynamic optimization and adaptive control is needed. Summary of the invention

[0007] The present invention provides an AI-based HVAC energy-saving control method and system to solve the problem of how to optimize the operating parameters of the refrigeration room and central air-conditioning system in real time through multi-dimensional optimization and adaptive control algorithms, ensure that the system achieves the best energy-saving effect under different environmental conditions, and improve the system's response speed, reliability and maintenance efficiency.

[0008] In order to solve the above problems, the present invention provides an AI-based HVAC energy-saving control method and system, including:

[0009] An AI-based HVAC energy-saving control method, characterized by comprising:

[0010] S100 collects environmental data and operating parameters of the refrigeration room and central air-conditioning system through the intelligent sensor network, and performs preliminary processing locally to ensure the accuracy and real-time nature of the data;

[0011] S200, combining local and cloud computing resources, applying multi-dimensional optimization algorithms to generate the best efficiency point and control parameters;

[0012] S300, adjust the operating status of the central air-conditioning system in real time according to the control parameters to achieve the best energy-saving effect;

[0013] S400, monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control.

[0014] As a preferred solution, step S100 includes:

[0015] S110, through the deployment of intelligent sensors around the refrigeration room and central air conditioning system, real-time collection of ambient temperature, humidity, air flow speed, light intensity and other data;

[0016] S120, collect operating parameters of the refrigeration room and central air-conditioning system, such as cooling water temperature, compressor operating status, refrigerant pressure, current and voltage, etc.;

[0017] S130: Perform preliminary processing on the collected data to ensure the accuracy and real-time nature of the data.

[0018] As a preferred solution, in step S200, the multi-dimensional optimization algorithm comprehensively considers multiple variables such as temperature, humidity, energy consumption and equipment life, and performs global optimization to ensure that the system maintains the best operating state under different environmental conditions.

[0019] As a preferred solution, in step S300, the cooling water temperature, compressor operating time and fan speed are adjusted in real time according to the control parameters to ensure that the system can achieve optimal energy efficiency under various environments.

[0020] As a preferred solution, in step S400, a machine learning algorithm is used to monitor and analyze system operation data in real time, automatically detect and diagnose faults, and provide solutions and processing suggestions.

[0021] As a preferred solution, it also includes remote monitoring and maintenance functions to achieve remote monitoring and control of the system, facilitating system maintenance and management.

[0022] As a preferred solution, the method also uses historical data management and data mining technology to analyze the laws and trends in system operation, provide a reference for optimizing calculation and control parameter generation, and improve the robustness and reliability of the system.

[0023] As a preferred solution, it also includes:

[0024] Data collection and preprocessing module, used to collect environmental data and operating parameters of the refrigeration room and central air-conditioning system, and perform preliminary processing;

[0025] The optimization calculation and control parameter generation module is used to combine local and cloud computing resources, apply multi-dimensional optimization algorithms, and generate the best efficiency point and control parameters;

[0026] Real-time control and adjustment module, used to adjust the operating status of the central air-conditioning system in real time according to the control parameters to achieve the best energy-saving effect;

[0027] The fault detection and diagnosis module is used to monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control.

[0028] As a preferred solution, it also includes a data storage and management module for storing and managing the collected data and calculation results to ensure the integrity and traceability of the data.

[0029] As a preferred solution, the system dynamically adjusts system parameters by applying an adaptive control algorithm, so that the system can achieve the best energy-saving effect under different environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flow chart of an AI-based HVAC energy-saving control method and system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0033] Reference Figure 1 , is a flow chart of an AI-based HVAC energy-saving control method and system according to an embodiment of the present invention. The AI-based HVAC energy-saving control method and system may at least include steps S100-S400:

[0034] S100 collects data through a smart sensor network and performs preliminary processing locally to ensure the accuracy and real-time nature of the data.

[0035] S200 combines local and cloud computing resources and applies multi-dimensional optimization algorithms to generate the best efficiency point and control parameters.

[0036] S300, according to the control parameters, real-time adjustment of the operating status of the central air-conditioning system to achieve the best energy-saving effect.

[0037] S400, monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control.

[0038] An AI-based HVAC energy-saving control method and system provided in an embodiment of the present invention is mainly used to solve the technical problem solved by the present invention, which is "how to optimize the operating parameters of the refrigeration room and central air-conditioning system in real time through multi-dimensional optimization and adaptive control algorithms, to ensure that the system achieves the best energy-saving effect under different environmental conditions, and to improve the system's response speed, reliability and maintenance efficiency."

[0039] The present invention discloses an AI-based HVAC energy-saving control method and system, which utilizes an intelligent sensor network to collect environmental and equipment operation data in real time, and performs preliminary processing through edge computing nodes to ensure the accuracy and real-time nature of the data. By combining local and cloud computing resources, a multi-dimensional optimization algorithm is applied to generate the optimal efficiency point and control parameters, dynamically adjust the operating state of the central air-conditioning system, and achieve the best energy-saving effect. At the same time, the system has real-time fault detection and diagnosis functions, and uses machine learning algorithms to improve the timeliness and accuracy of fault handling and reduce maintenance costs. Through data-driven optimization strategies and remote monitoring and maintenance functions, the present invention significantly improves the energy efficiency, response speed, and reliability of the HVAC system, reduces maintenance costs, and provides an effective solution for intelligent energy-saving control of the HVAC system.

[0040] S100, collect data through the intelligent sensor network and perform preliminary processing locally to ensure the accuracy and real-time nature of the data. Step S100 includes steps S110-S140:

[0041] S110, by deploying smart sensors around the refrigeration room and the central air conditioning system, real-time data such as ambient temperature, humidity, air flow speed, and light intensity are collected. Step S111 includes steps S111-S113:

[0042] S111. By deploying smart sensors, operating parameter sensors, user behavior sensors, etc. around the refrigeration room and central air-conditioning system, real-time data such as ambient temperature, equipment operation data, and user behavior are collected.

[0043] (1) Deploy smart sensors at key locations in the refrigeration room and central air-conditioning system. These sensors include temperature sensors, humidity sensors, wind speed sensors, and light sensors.

[0044] Temperature sensor: deployed inside and outside the refrigeration room to monitor the ambient temperature (℃) in real time.

[0045] Humidity sensor: deployed in refrigeration rooms and around central air conditioning systems to monitor ambient humidity (%RH) in real time.

[0046] Wind speed sensor: installed at the air outlet and return air outlet of the air conditioner to monitor the air flow speed (m / s) in real time.

[0047] Light sensor: deployed in the refrigeration room to monitor light intensity (l ux) and help assess environmental impact.

[0048] (2) Sensors collect environmental data in real time and transmit the data to edge computing nodes wirelessly or wiredly.

[0049] Temperature data collection: The sensor collects temperature data at regular intervals (such as every second) and sends the data to the edge computing node.

[0050] Humidity data collection: The sensor continuously monitors the ambient humidity, collects humidity data in real time, and transmits the data to the edge computing node.

[0051] Wind speed data collection: The sensor measures the air flow speed in real time, collects wind speed data, and transmits it to the edge computing node through the network.

[0052] Light data collection: The sensor regularly measures light intensity, collects light data, and transmits it to the edge computing node.

[0053] Input data and processing:

[0054] Temperature data: The ambient temperature (°C) is collected through the temperature sensor to ensure that the system operates within the appropriate temperature range.

[0055] Humidity data: The humidity sensor collects the ambient humidity (%RH) and regulates the humidity in the refrigeration room and central air-conditioning system.

[0056] Wind speed data: The wind speed sensor collects air flow speed (m / s) to ensure air circulation and heat dissipation of the system.

[0057] Light data: Light intensity (lux) is collected through light sensors to assess environmental impact and adjust system operating parameters.

[0058] S112, collect operating parameters of the refrigeration room and central air conditioning system, such as cooling water temperature, compressor operating status, refrigerant pressure, current and voltage, etc. Specifically:

[0059] (1) Deploy operating status sensors on key equipment in the refrigeration room and central air-conditioning system. These sensors include temperature sensors, pressure sensors, current sensors, and voltage sensors.

[0060] Cooling water temperature sensor: installed at the cooling water inlet and outlet to monitor the cooling water temperature (℃) in real time.

[0061] Compressor status sensor: Installed on the compressor to monitor the compressor's operating status (ON / OFF) and operating time.

[0062] Refrigerant pressure sensor: Installed in the refrigerant circuit to monitor the refrigerant pressure (MPa).

[0063] Current and voltage sensors: Installed on the main power lines and equipment power supplies to monitor the system current (A) and voltage (V).

[0064] (2) Sensors collect equipment operation data in real time and transmit the data to edge computing nodes wirelessly or wiredly.

[0065] Cooling water temperature data collection: The sensor collects cooling water temperature data at regular intervals (such as every second) and sends the data to the edge computing node.

[0066] Compressor operating status data collection: The sensor continuously monitors the operating status of the compressor, collects the switch status and operating time in real time, and transmits the data to the edge computing node.

[0067] Refrigerant pressure data collection: The sensor measures the refrigerant pressure in real time, collects pressure data, and transmits it to the edge computing node through the network.

[0068] Current and voltage data collection: The sensor regularly measures the current and voltage, collects the current and voltage data, and transmits it to the edge computing node.

[0069] Input data and processing:

[0070] Cooling water temperature data: The cooling water temperature (°C) is collected through the cooling water temperature sensor to ensure that the system operates within the appropriate temperature range.

[0071] Compressor operating status data: The compressor operating status (ON / OFF) and operating time are collected through the compressor status sensor to adjust the operating efficiency of the compressor.

[0072] Refrigerant pressure data: The refrigerant pressure (MPa) is collected through the refrigerant pressure sensor to ensure the stable and efficient operation of the refrigerant circuit.

[0073] Current and voltage data: The current (A) and voltage (V) of the system are collected through current and voltage sensors to monitor the power consumption of the system and the operating status of the equipment.

[0074] S113, using user behavior sensors to collect user activity data in the air-conditioned environment, so as to personalize the control system. Specifically:

[0075] (1) Deploy user behavior sensors at key locations and user activity areas in the air-conditioned environment. These sensors include position sensors, motion sensors, infrared sensors, and cameras.

[0076] Position sensors: installed throughout the room to detect the user's real-time position (coordinates).

[0077] Motion sensors: deployed at doors, windows and main passages to monitor user activity frequency and behavior patterns.

[0078] Infrared sensor: Mounted on the ceiling or wall to detect the presence and movement of the user.

[0079] Cameras: Installed in hidden corners of the room to capture user behavior and activities.

[0080] (2) Sensors collect user behavior data in real time and transmit the data to edge computing nodes via wireless or wired means.

[0081] Location data collection: The sensor collects user location data at regular intervals (such as every second) and sends the data to the edge computing node.

[0082] Motion data collection: Sensors continuously monitor the user's activity frequency and behavior patterns, collect motion data in real time, and transmit the data to edge computing nodes.

[0083] Presence data collection: Infrared sensors detect the presence and movement of users in real time, collect presence data, and transmit it to edge computing nodes through the network.

[0084] Behavioral data collection: The camera captures the user's behavior and activities in real time, collects video data, and transmits it to the edge computing node through the network.

[0085] Input data and processing:

[0086] Location data: The user's real-time location (coordinates) is collected through location sensors to help the system understand the user's activity areas and habits.

[0087] Motion data: Motion sensors are used to collect user activity frequencies and behavior patterns, making it easier for the system to identify user behavior habits and needs.

[0088] Presence data: The presence and movement of users are collected through infrared sensors to ensure that the system can sense the user's presence status in real time.

[0089] Behavioral data: The user's behavior and activities are collected through the camera to provide more comprehensive user behavior data and provide a basis for personalized regulation.

[0090] S120, remove noise and outliers in sensor data, fuse data from different sensors, generate a unified data set, compress the data, reduce the pressure of data transmission and storage, and improve the response speed of the system, specifically:

[0091] (1) After the data collection arrives at the edge computing node, data cleaning is performed first. The specific steps are as follows:

[0092] A. Noise filtering: Use filters and statistical methods to remove noise from sensor data. For example, low-pass filtering is performed on data such as ambient temperature, humidity, air flow speed, and light intensity to smooth out transient noise.

[0093] B. Outlier detection: Use machine learning algorithms and rule detection methods to identify and remove outliers. For example, if the cooling water temperature exceeds the allowed range of the equipment or changes suddenly, the system will identify the data as an outlier and remove it.

[0094] C. Data calibration: According to the calibration parameters of the sensor, the collected data is calibrated to ensure the accuracy of the data. For example, the compressor operating status, current and voltage parameters are calibrated to eliminate sensor drift and errors.

[0095] (2) After data cleaning, the data from different sensors are fused to generate a unified data set. The specific steps are as follows:

[0096] A. Time synchronization: All sensor data are synchronized to ensure the consistency of data at the same time point. For example, the ambient temperature, humidity, air flow speed, and light intensity data collected at the same time are synchronized.

[0097] B. Spatial fusion: Based on the spatial arrangement of sensors, multiple sensor data in the same spatial area are fused. For example, data such as cooling water temperature, compressor operating status, and refrigerant pressure at the same location are fused.

[0098] C. Data alignment: Align different types of data to generate a unified data format and structure. For example, align environmental data, equipment operation data, and user behavior data to form a multidimensional data set.

[0099] (3) In order to reduce the pressure of data transmission and storage, the cleaned and fused data is compressed. The specific steps are as follows:

[0100] A. Lossless compression: Use lossless compression algorithms (such as Huffman coding, LZW compression) to compress data to ensure that the data remains consistent after compression and decompression. For example, lossless compression is performed on key data such as cooling water temperature and compressor operating status.

[0101] B. Lossy compression: For data that does not require high accuracy, use lossy compression algorithms (such as wavelet transform and DCT compression) to reduce the amount of data stored. For example, lossy compression is performed on the activity frequency and behavior pattern in user behavior data.

[0102] C. Block processing: Divide large data sets into small blocks for compression and transmission to improve the system's response speed and processing efficiency. For example, divide environmental data, equipment operation data, and user behavior data within an hour into several small blocks for compression processing.

[0103] Input data and processing:

[0104] Environmental data: temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (l ux)

[0105] Equipment operation data: cooling water temperature (℃), compressor operation status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V)

[0106] User behavior data: user location (coordinates), activity frequency (times / minute), behavior pattern (classification label)

[0107] S130: Use edge computing nodes to perform preliminary analysis and processing on the collected data, reduce data transmission delays, improve real-time performance, and adjust some simple control strategies in real time based on the preliminary analysis results, such as wind speed adjustment, temperature setting, etc., to ensure the initial response of the system. Specifically:

[0108] (1) Perform preliminary analysis and processing of the collected data at the edge computing node to reduce data transmission delays and improve real-time performance. The specific steps are as follows:

[0109] A. Data reception: Edge computing nodes receive data from smart sensor networks, including environmental data, device operation data, and user behavior data.

[0110] B. Data preprocessing: Clean, fuse and compress the received data to ensure the accuracy, uniformity and efficiency of the data.

[0111] C. Analysis and processing: Use the computing power of edge computing nodes to perform preliminary analysis on preprocessed data. For example:

[0112] Environmental data: Analyzes current temperature, humidity, airflow speed, and light intensity to determine whether they are within the set safety range.

[0113] Equipment operation data: monitor cooling water temperature, compressor operating status, refrigerant pressure, and current and voltage to determine whether the equipment is operating normally.

[0114] User behavior data: Analyze the user's location, activity frequency, and behavior patterns to determine whether the current environment meets user needs.

[0115] (2) Based on the preliminary analysis results, some simple control strategies are adjusted in real time, such as wind speed adjustment, temperature setting, etc., to ensure the initial response of the system. The specific steps are as follows:

[0116] A. Data analysis results: The edge computing node generates preliminary analysis results, such as whether the current environmental data exceeds the set range, whether the equipment operation status is normal, and whether the user behavior meets expectations.

[0117] B. Control strategy adjustment:

[0118] Environmental data adjustment: According to the analysis results of ambient temperature, humidity, air flow speed and light intensity, the wind speed, temperature setting, etc. are adjusted in real time. For example, if the ambient temperature is too high, the system automatically increases the wind speed or lowers the temperature set point.

[0119] Equipment operation adjustment: According to the analysis results of cooling water temperature, compressor operation status, refrigerant pressure and current and voltage, the equipment operation status is adjusted in real time. For example, if the cooling water temperature is too high, the system automatically adjusts the compressor operation time or power.

[0120] User behavior adjustment: Based on the analysis results of user location, activity frequency and behavior patterns, the operation mode of the air conditioning system is adjusted in real time. For example, if it detects that the user is away, the system automatically reduces the fan speed or adjusts the temperature set point to save energy.

[0121] Input data and processing:

[0122] Environmental data: temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (l ux)

[0123] Equipment operation data: cooling water temperature (℃), compressor operation status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V)

[0124] User behavior data: user location (coordinates), activity frequency (times / minute), behavior pattern (classification label)

[0125] S140, the pre-processed and preliminarily analyzed data is transmitted to the cloud computing platform for more complex optimization calculations, and encryption technology is used to protect data privacy and security. Specifically:

[0126] (1) The preprocessed and preliminarily analyzed data is transferred from the edge computing node to the cloud computing platform for more complex optimization calculations. The specific steps are as follows:

[0127] A. Data preparation: After completing data cleaning, fusion, compression, and preliminary analysis, the edge computing node packages the processed data for transmission.

[0128] B. Data transmission protocol: Choose an efficient data transmission protocol (such as MQTT, HTTP / 2, CoAP) to ensure fast and reliable data transmission.

[0129] C. Data upload: Upload the packaged data to the cloud computing platform through a secure transmission channel. The transmitted data includes the pre-processing and preliminary analysis results of environmental data, equipment operation data and user behavior data.

[0130] D. Cloud reception: The cloud computing platform receives the uploaded data for storage and further complex optimization calculations.

[0131] (2) To ensure the security of data during transmission, encryption technology is used to protect data privacy and security. The specific steps are as follows:

[0132] A. Data encryption: Before data transmission, encryption algorithms (such as AES, RSA) are used to encrypt data to ensure the confidentiality of data during transmission. For example, environmental data, equipment operation data, and user behavior data are encrypted before transmission.

[0133] B. Secure channel: Use secure transmission protocols (such as TLS / SSL) to establish an encrypted channel to ensure the integrity and security of data transmission. For example, the TLS protocol can be used to ensure that data is not stolen or tampered with during transmission.

[0134] C. Key management: Use a reliable key management mechanism to ensure the security and ease of management of encryption keys. For example, use a key management system based on public key infrastructure (PKI) to generate, distribute and manage encryption keys.

[0135] D. Data decryption: After the data reaches the cloud computing platform, it is decrypted by the corresponding decryption algorithm to ensure that the cloud can correctly read and process the transmitted data. For example, the cloud computing platform decrypts the encrypted data received through RSA.

[0136] S200, combining local and cloud computing resources, applying a multi-dimensional optimization algorithm, and generating the best efficiency point and control parameters. Step S200 includes steps S210-S240:

[0137] S210, applying genetic algorithms, particle swarm optimization, reinforcement learning and other multi-dimensional optimization algorithms, and dynamically adjusting the optimization strategy based on real-time data and historical data to ensure that the system always runs at the optimal efficiency point. Step S210 includes steps S211-S212, specifically:

[0138] S211. Original algorithmic formulas based on topology, geometry, mathematical logic and set theory, numerical analysis and scientific computing.

[0139] (1) Multi-dimensional optimization objective function: Define the optimization objective function F(x) to comprehensively consider multiple variables such as temperature, humidity, energy consumption, and equipment life:

[0140]

[0141] Where x is the control parameter vector, T(x) is temperature, H(x) is humidity, E(x) is energy consumption, L(x) is equipment life, and w i is the weight factor, T opt and H opt are the optimized temperature and humidity values.

[0142] (2) Topological constraints: Define topological constraints C(x) to ensure that the system operates in a valid area:

[0143]

[0144] Among them, g i (x) represents various constraints, such as the safe range of equipment operation and user comfort conditions.

[0145] (3) Dynamic optimization equation: Using topological deformation methods and geometric principles, dynamically adjust the optimization strategy:

[0146]

[0147] Among them, t is the time variable, is the gradient of the objective function, λ i is the Lagrange multiplier.

[0148] (4) Numerical solution method: Use the asymptotic expansion method in numerical analysis to solve the optimization equation:

[0149]

[0150] Among them, x kis the control parameter of the kth iteration and α is the learning rate.

[0151] S212: Use the algorithm formula in S211 to implement the operation process of the optimization calculation module. Specifically:

[0152] (I) Optimization calculation

[0153] Description of the multi-dimensional optimization process: Apply multi-dimensional optimization algorithms such as genetic algorithm, particle swarm optimization, and reinforcement learning to comprehensively consider environmental data, equipment operation data, and user behavior data for global optimization. The specific steps are as follows:

[0154] A. Data input: Receive environmental data, equipment operation data and user behavior data from the intelligent data acquisition and preprocessing module. After preprocessing and preliminary analysis, these data have high accuracy and real-time performance.

[0155] Environmental data: temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (l ux)

[0156] Equipment operation data: cooling water temperature (℃), compressor operation status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V)

[0157] User behavior data: user location (coordinates), activity frequency (times / minute), behavior pattern (classification label)

[0158] B. Variable definition: Define temperature, humidity, energy consumption, equipment life, etc. as optimization variables. These variables are key factors in the optimization calculation.

[0159] C. Optimization objective: Set the optimization objective function F(x) with the main goals of minimizing energy consumption and maximizing equipment life, while ensuring that the ambient temperature and humidity are within a comfortable range.

[0160] D. Genetic algorithm: Initialization: Generate an initial population, each individual represents a set of control parameters.

[0161] Fitness evaluation: Calculate the fitness of each individual based on its performance in terms of temperature, humidity, energy consumption, and equipment life.

[0162] Selection, crossover and mutation: Generate a new generation of population through selection, crossover and mutation operations.

[0163] Iteration: Repeat the above steps until the stopping condition is met (such as reaching the maximum number of generations or the fitness no longer improves significantly).

[0164] E. Particle Swarm Optimization: Initialization: Initialize the particle swarm, where each particle represents a set of control parameters.

[0165] Fitness evaluation: Calculate the fitness of each particle based on its performance in terms of temperature, humidity, energy consumption, and device life.

[0166] Speed ​​and position update: Update the speed and position of each particle according to the particle swarm optimization algorithm.

[0167] Iteration: Repeat the above steps until the stopping condition is met (such as reaching the maximum number of iterations or the fitness no longer improves significantly).

[0168] F. Reinforcement Learning: Environmental Modeling: Model the HVAC system as a reinforcement learning environment, with states including temperature, humidity, energy consumption, equipment operating status, etc.

[0169] Policy training: Train the intelligent agent through algorithms such as Qlearning or Deep Q Network (DQN) to learn the optimal control strategy under different states.

[0170] Policy Evaluation: Evaluate the performance of the trained policy and apply and adjust it in real-world environments.

[0171] (II) Dynamic optimization: Based on real-time data and historical data, dynamically adjust the optimization strategy to ensure that the system always runs at the optimal efficiency point. The specific steps are as follows:

[0172] A. Real-time data update: Continuously receive and process the latest environmental data, equipment operation data and user behavior data from the intelligent data acquisition and preprocessing module.

[0173] B. Historical data analysis: Analyze and store historical data to identify long-term trends and patterns to provide a basis for dynamic optimization.

[0174] C. Optimization model update: Use real-time data and historical data to dynamically update the optimization model. Adjust the optimization objectives and constraints to adapt to the current environment and demand changes.

[0175] D. Real-time optimization calculation: Based on the latest data and the updated optimization model, real-time optimization calculation is performed to generate new control parameters:

[0176]

[0177] E. Feedback adjustment: Based on the real-time feedback from the feedback and fault diagnosis module, further fine-tune the optimization strategy to ensure the stability and reliability of the system.

[0178] S220. Use deep learning algorithms to train prediction models, predict future environmental changes and system operating status, and use reinforcement learning algorithms to continuously adjust and optimize control strategies so that the system can adapt to environmental changes and achieve the best control effect.

[0179] Step S220 includes steps S221-S222:

[0180] S221. An original deep learning objective function and its reinforcement learning reward function, etc., specifically:

[0181] (1) Deep learning objective function: Define the loss function L(θ) of the prediction model to comprehensively consider multiple variables such as temperature, humidity, energy consumption, and equipment life:

[0182]

[0183] Among them, θ is the model parameter, are the predicted temperature, humidity, energy consumption and equipment life, respectively, i is the weight factor and N is the number of samples.

[0184] (2) Reinforcement learning reward function: Define the reward function R(s,a), comprehensively considering the impact of system state and control strategy on the system:

[0185]

[0186] Where s is the system state, a is the control action, T opt and H opt are the optimized temperature and humidity values.

[0187] (3) Topological constraints: Define topological constraints C(θ) to ensure that the system operates in a valid area:

[0188]

[0189] Among them, g i (θ) represents various constraints, such as the safe range of equipment operation and user comfort conditions.

[0190] (4) Dynamic optimization equation for model training: Using topological deformation methods and geometric principles, dynamically adjust the model training strategy:

[0191]

[0192] Among them, t is the time variable, is the gradient of the loss function, λ i is the Lagrange multiplier.

[0193] S222: Use the algorithm formula of S221 to perform deep learning and reinforcement learning. Specifically:

[0194] (I) Model training: Use deep learning algorithms to train prediction models, predict future environmental changes and system operating status, and improve the accuracy and efficiency of optimization calculations. The specific steps are as follows:

[0195] A. Data input: Receive environmental data, equipment operation data and user behavior data from the intelligent data acquisition and preprocessing module. After preprocessing and preliminary analysis, these data have high accuracy and real-time performance.

[0196] Environmental data: temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (l ux)

[0197] Equipment operation data: cooling water temperature (℃), compressor operation status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V)

[0198] User behavior data: user location (coordinates), activity frequency (times / minute), behavior pattern (classification label)

[0199] B. Data preprocessing: Standardize and normalize the input data to meet the requirements of the deep learning model.

[0200] C. Model selection: Select appropriate deep learning models, such as long short-term memory network (LSTM), convolutional neural network (CNN), etc., to predict future environmental changes and system operation status.

[0201] D. Training data preparation: Divide the processed historical data and real-time data into training sets and validation sets to train the deep learning model.

[0202] E. Model training: Use the training set data to train the deep learning model and adjust the model parameters (such as weights and biases) so that the model can accurately predict changes in the environment and system state. The loss function is:

[0203]

[0204] F. Model validation: Use validation set data to validate the model’s predictive ability, evaluate the model’s performance through loss functions (such as mean square error), and make necessary adjustments and optimizations.

[0205] G. Model update: Continuously update and optimize the model based on real-time data and feedback to ensure the model's predictive ability and accuracy.

[0206] (II) Reinforcement learning: Through the reinforcement learning algorithm, the control strategy is continuously adjusted and optimized so that the system can adapt to environmental changes and achieve the best control effect. The specific steps are as follows:

[0207] A. Environmental modeling: Model the HVAC system as a reinforcement learning environment and define the state, action, and reward function. The state includes environmental data and equipment operation data, the action is the control strategy of the system, and the reward function measures the effect of the action (such as energy saving effect, user comfort).

[0208] B. State representation: Environmental data and equipment operation data are represented as a state vector S t :

[0209] S t =[T(t),H(t),E(t),L(t)]

[0210] Among them, T(t) is temperature, H(t) is humidity, E(t) is energy consumption, and L(t) is equipment life.

[0211] C. Action selection: define action A t To adjust the control parameters, such as temperature setting, wind speed adjustment, etc.

[0212] D. Reward function: Define the reward function R(s,a) to measure the effect of the control strategy, for example:

[0213]

[0214] Among them, T opt and H opt are the optimized temperature and humidity values.

[0215] E. Policy training: Use reinforcement learning algorithms (such as Qlearning, Deep Q Network (DQN)) to train intelligent agents to learn optimal control strategies under different states.

[0216] F. Strategy Evaluation: Evaluate the performance of the training strategy and verify the effectiveness of the strategy through application in simulation and actual environments.

[0217] G. Strategy adjustment: Based on actual operation data and feedback, continuously adjust and optimize the control strategy to ensure that the system can achieve the best control effect under different environments and requirements.

[0218] Input data and processing:

[0219] Environmental data: temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (lux)

[0220] Equipment operation data: cooling water temperature (℃), compressor operation status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V)

[0221] User behavior data: user location (coordinates), activity frequency (times / minute), behavior pattern (classification label)

[0222] S230: Generate specific control parameters based on the optimization calculation results, such as cooling water temperature setting value, compressor start time, fan speed, etc. Verify and adjust the generated control parameters to ensure their effectiveness and reliability in actual application. Specifically:

[0223] (I) Parameter calculation: Generate specific control parameters based on the optimization calculation results, such as cooling water temperature setting value, compressor start time, fan speed, etc. The specific steps are as follows:

[0224] A. Data input: Receive optimization results from the optimization calculation module, including comprehensive analysis of environmental data, equipment operation data, and user behavior data, and output of optimization calculations.

[0225] B. Analysis of optimization results: Analyze the optimization calculation results into specific control objectives and parameter requirements, such as temperature setting range, humidity adjustment requirements, energy consumption optimization targets, etc.

[0226] C. Control parameter calculation: Calculate specific control parameters based on the optimization objectives and system model, for example:

[0227] Cooling water temperature setting value T set :Based on the optimization calculation results and the current ambient temperature T env , set the optimal temperature of cooling water.

[0228] T set =T env -ΔT opt

[0229] Where, ΔT opt is the temperature difference obtained by optimization calculation.

[0230] Compressor start time t on :Calculate the start and stop time of the compressor based on the optimization results and current load demand.

[0231] t on =f(L current , L opt )

[0232] Among them, L current is the current load, L opt is the target load for optimization calculation.

[0233] Fan speed V fan :Set the fan speed according to the optimization calculation results and the current air flow rate requirements.

[0234] V fan =V opt +ΔV

[0235] Among them, V opt is the optimal wind speed obtained by optimization calculation, and ΔV is the adjustment amount.

[0236] (II) Parameter verification: Verify and adjust the generated control parameters to ensure their effectiveness and reliability in practical applications. The specific steps are as follows:

[0237] A. Simulation verification: Simulate the application effect of control parameters in a virtual environment to evaluate their impact on system performance. For example, use a simulation model to verify the impact of cooling water temperature setpoints on system energy consumption and equipment life.

[0238] B. Field test: Apply control parameters in the actual system and observe their actual impact on system operation. For example, adjust the fan speed and compressor start time, and monitor the temperature, humidity and energy consumption changes of the system.

[0239] C. Feedback adjustment: According to the results of simulation verification and field test, make necessary parameter adjustments. For example, if the field test shows that the frequent start and stop of the compressor leads to increased energy consumption, the start time t is appropriately adjusted. on .

[0240] D. Robustness evaluation: Evaluate the robustness of control parameters under different environmental and load conditions to ensure that the system can operate stably under various conditions. For example, test the effectiveness of cooling water temperature setpoints under extreme temperature conditions.

[0241] S240, using the powerful computing power of the cloud computing platform to perform complex optimization calculations and model training to improve the computing efficiency and accuracy of the system. The collected data and calculation results are stored and managed to ensure the integrity and traceability of the data.

[0242] (I) Use the powerful computing power of the cloud computing platform to perform complex optimization calculations and model training to improve the computing efficiency and accuracy of the system. The specific steps are as follows:

[0243] A. Data input: Receive data from the intelligent data collection and preprocessing module and edge computing nodes, including environmental data, equipment operation data, and user behavior data. After preprocessing and preliminary analysis, these data have high accuracy and real-time performance.

[0244] B. Data upload: Upload the pre-processed and initially analyzed data from the edge computing node to the cloud computing platform through a secure transmission protocol (such as TLS / SSL).

[0245] C. Complex optimization calculation: Use the high-performance computing resources of the cloud computing platform to perform complex optimization calculation tasks. For example, apply multi-dimensional optimization algorithms, deep learning, and reinforcement learning methods, and combine input data for global optimization.

[0246] Multi-dimensional optimization: Apply topological and geometric principles to solve complex multi-dimensional optimization problems and ensure that the refrigeration room always operates at the optimal efficiency point under different environmental conditions.

[0247] Deep learning training: Use historical data and real-time data to train deep learning models, predict future environmental changes and system operating status, and improve the accuracy of optimization calculations.

[0248] Reinforcement learning training: Through the reinforcement learning algorithm, the control strategy is continuously adjusted and optimized, so that the system can adapt to environmental changes and achieve the best control effect.

[0249] D. Calculation result output: The results of complex optimization calculations and model training are used as input for control parameter generation to provide the system with efficient and accurate control parameters.

[0250] (ii) Store and manage the collected data and calculation results to ensure the integrity and traceability of the data. The specific steps are as follows:

[0251] A. Data storage: Establish a distributed database on the cloud computing platform to store all collected environmental data, equipment operation data, user behavior data, and the results of optimization calculations and model training.

[0252] Optimization result storage: such as the storage of control parameters generated by optimization calculations and model training results.

[0253] B. Data Management: Implement data management strategies to ensure data integrity, consistency and security.

[0254] Data integrity: Ensure the integrity of stored data through verification and redundancy mechanisms to prevent data loss or damage.

[0255] Data consistency: Use a consistency algorithm (such as Paxos or Raft) to ensure data consistency across different nodes.

[0256] Data security: Use access control, encryption, and audit mechanisms to protect data security and privacy.

[0257] C. Data retrieval and query: Provide efficient data retrieval and query functions to support users and systems to quickly access and analyze data when needed.

[0258] Index and query optimization: Improve the speed and efficiency of data retrieval by establishing indexes and optimizing query strategies.

[0259] Data analysis and reporting: Support data analysis and reporting functions to provide a basis for system optimization and decision-making.

[0260] S300, according to the control parameters, real-time adjustment of the operating state of the central air-conditioning system to achieve the best energy-saving effect, step S300 includes steps S310-S340:

[0261] S310, applying the control parameters generated by the optimization calculation to the central air-conditioning system, and adjusting the operating status of the system in real time. And according to the real-time data, automatically adjust various parameters of the refrigeration room and the central air-conditioning system, such as temperature setting, wind speed adjustment, compressor operation, etc., to ensure that the system operates at the best efficiency point.

[0262] (I) Apply the control parameters generated by the optimization calculation to the central air conditioning system and adjust the operating status of the system in real time. The specific steps are as follows:

[0263] A. Data input: Receive control parameters from the optimization calculation and control parameter generation module. These parameters are generated through optimization calculation based on environmental data, equipment operation data and user behavior data.

[0264] B. Parameter application: Apply control parameters to each subsystem of the central air conditioning system. For example:

[0265] Cooling water temperature setting: According to the optimization calculation results, the cooling water temperature setting value T set Input to the control unit of the cooling water system to adjust the cooling water temperature in real time.

[0266] Compressor running time: Set the compressor start and stop time t according to load demand on , ensuring operation during peak demand periods and shutdown during low demand periods.

[0267] Fan speed: Set the fan speed V fan The adjustment parameters are input into the fan control unit, and the wind speed is adjusted in real time to achieve the best air flow effect.

[0268] (ii) Based on real-time data, automatically adjust various parameters of the refrigeration room and central air-conditioning system, such as temperature setting, wind speed adjustment, compressor operation, etc., to ensure that the system operates at the optimal efficiency point. The specific steps are as follows:

[0269] A. Real-time monitoring: Use smart sensor networks to monitor environmental data, equipment operation data, and user behavior data in real time. For example, sensors collect data such as current ambient temperature, humidity, and air flow speed, and transmit these data to the control system.

[0270] B. Data analysis: The control system analyzes real-time data to determine the gap between the current system operating status and the optimization target. For example, it analyzes whether the current ambient temperature reaches the set temperature, whether the compressor operating status meets expectations, whether the wind speed needs to be adjusted, etc.

[0271] C. Control strategy adjustment: Automatically adjust control parameters based on data analysis results. For example:

[0272] Temperature setting adjustment: If the ambient temperature is too high, the system automatically lowers the cooling water temperature setting value T set ; If the ambient temperature is low, the system automatically increases the cooling water temperature set point.

[0273] Wind speed adjustment: Automatically adjust the fan speed V according to the real-time monitored air flow speed and user behavior data fan , ensuring optimal air flow.

[0274] Compressor operation adjustment: Automatically adjust the compressor operation time t according to the current load demand on and downtime, ensuring optimal energy efficiency.

[0275] D. Feedback control: Through real-time monitoring and analysis of feedback, the control strategy is continuously adjusted and optimized to ensure that the system always operates at the optimal efficiency point. For example, the system continuously adjusts the cooling water temperature, wind speed and compressor operating status through feedback data to dynamically respond to environmental changes and user needs.

[0276] S320, adjust the control strategy in real time according to the feedback data to ensure that the system can quickly respond to changes in the environment and demand. And apply adaptive control algorithms to dynamically adjust system parameters so that the system can achieve the best energy-saving effect under different environmental conditions.

[0277] (i) Adjust control strategies in real time based on feedback data to ensure that the system can respond quickly to changes in the environment and demand.

[0278] The specific steps are as follows:

[0279] A. Data input: Receive real-time feedback from environmental data, equipment operation data, and user behavior data. These data are initially processed by the intelligent data acquisition and preprocessing module and edge computing nodes, and have high accuracy and real-time performance.

[0280] B. Data analysis: Real-time analysis of feedback data to determine the gap between the current system operating status and the optimization target. For example, by analyzing changes in ambient temperature and humidity, determine whether the cooling water temperature or wind speed needs to be adjusted.

[0281] C. Strategy adjustment: adjust the control strategy in real time according to the data analysis results. For example:

[0282] Temperature adjustment: If the ambient temperature is too high, the system automatically lowers the cooling water temperature setting value T set ; If the ambient temperature is low, the system automatically increases the cooling water temperature set point.

[0283] Wind speed adjustment: If insufficient air flow speed is detected, the system automatically increases the fan speed V fan ; If the airflow is too strong, the system automatically reduces the fan speed.

[0284] Compressor operation adjustment: adjust the compressor start and stop time according to real-time load demand on and t off , ensuring optimal energy efficiency.

[0285] (II) Apply adaptive control algorithms to dynamically adjust system parameters so that the system can achieve optimal energy-saving effects under different environmental conditions. The specific steps are as follows:

[0286] A. Adaptive control algorithm: Adopt adaptive control algorithm (such as model reference adaptive control, LMS algorithm, etc.) to dynamically adjust system parameters according to real-time data and system model. The algorithm can self-learn and adjust to environmental changes and demand fluctuations.

[0287] B. State space representation: The current environment data and equipment operation data are represented as a state vector S t :

[0288] S t =[T(t),H(t),E(t),L(t)]

[0289] Among them, T(t) is temperature, H(t) is humidity, E(t) is energy consumption, and L(t) is equipment life.

[0290] C. Parameter optimization: According to the state vector S t And adaptive control algorithm, calculate the optimal control parameters:

[0291] Temperature setting value T set :Dynamically adjust the cooling water temperature setting value T according to the current temperature T(t) and humidity H(t) set .

[0292] Wind speed V fan :Dynamically adjust the fan speed V according to the current air flow speed V(t) and user needs fan .

[0293] Compressor operation: Optimize the running time and downtime of the compressor based on the current energy consumption E(t) and equipment life L(t).

[0294] D. Real-time application: Apply the optimized control parameters to the central air conditioning system in real time, and perform parameter adjustments through the automatic control unit to ensure that the system operates at the optimal efficiency point. For example, the cooling water temperature setting value, fan speed and compressor operating time are adjusted in real time through the automatic control unit.

[0295] E. Feedback loop: Continuously monitor the system operating status, continuously adjust and optimize the control strategy through feedback data, form a closed-loop control, and ensure that the system always operates in the best energy-saving state.

[0296] S330 coordinates with the intelligent data acquisition and preprocessing module, the optimization calculation and control parameter generation module, and the feedback and fault diagnosis module to achieve overall optimization of the system. And according to the fault prediction results of the feedback and fault diagnosis module, adjust the control strategy in advance to prevent possible faults and improve the stability and reliability of the system. Specifically:

[0297] (I) Module coordination: coordinate with the intelligent data acquisition and preprocessing module, the optimization calculation and control parameter generation module, and the feedback and fault diagnosis module to achieve overall optimization of the system. The specific steps are as follows:

[0298] A. Data input: Integrate input data from each module, including environmental data, equipment operation data, and user behavior data, to ensure the consistency and synchronization of data between different modules.

[0299] B. Coordination of intelligent data acquisition and preprocessing modules: Receive and process environmental data, equipment operation data and user behavior data in real time, and transmit the preprocessed data to the optimization calculation and control parameter generation module.

[0300] Data collection: Ensure that the data collected by sensors is accurate and reliable, and eliminate noise and outliers.

[0301] Data preprocessing: Clean, merge and compress data to ensure data quality and transmission efficiency.

[0302] C. Coordination between optimization calculation and control parameter generation module: Generate specific control parameters based on the optimization calculation results and transmit them to the intelligent control execution module for application.

[0303] Optimization calculation: Calculate the optimal control strategy through multi-dimensional optimization, deep learning, reinforcement learning and other methods.

[0304] Control parameter generation: Convert the optimization calculation results into specific control parameters, such as temperature setpoint, wind speed and compressor running time.

[0305] D. Feedback and fault diagnosis module coordination: real-time monitoring of system operation status, detection and prediction of faults, and feedback of fault information to the intelligent control execution module.

[0306] Fault detection: Use machine learning algorithms and rules to detect anomalies in the equipment's operating status in real time.

[0307] Fault diagnosis: Based on the test results, diagnose the cause of the fault and the scope of impact, and provide solutions and handling suggestions.

[0308] E. System integration: coordinate data and control information between modules to ensure the overall optimization of the system.

[0309] Data synchronization: Ensure data synchronization and consistency between modules to avoid data conflicts and redundancy.

[0310] Control collaboration: Based on the optimization calculations and feedback information of each module, the control strategy is collaboratively adjusted to achieve overall optimization of the system.

[0311] (ii) According to the fault prediction results of the feedback and fault diagnosis module, adjust the control strategy in advance to prevent possible faults and improve the stability and reliability of the system. The specific steps are as follows:

[0312] A. Fault prediction: Use machine learning and data analysis techniques to predict possible equipment failures.

[0313] Data analysis: Analyze environmental data, equipment operation data, and historical failure data to identify failure modes and characteristics.

[0314] Machine learning models: Train and apply fault prediction models to predict the probability and time of equipment failure.

[0315] B. Early warning: Based on the fault prediction results, early warning information is issued to remind operation and maintenance personnel to pay attention to potential faults.

[0316] Warning information: Generate detailed warning reports, including fault type, possible causes and recommended treatment measures.

[0317] Operation and maintenance notification: Through the intelligent control system, early warning information is transmitted to the operation and maintenance personnel to ensure timely response and processing.

[0318] C. Control strategy adjustment: Adjust the control strategy based on the fault prediction results to prevent possible faults.

[0319] Parameter adjustment: Adjust relevant control parameters based on the predicted fault type and cause, for example, adjust the compressor running time and reduce equipment load.

[0320] Maintenance plan: Based on the failure prediction results, formulate and implement preventive maintenance plans to avoid equipment failure and downtime.

[0321] D. Real-time monitoring: Continuously monitor the operating status of the equipment, verify the effect of the adjusted control strategy, and ensure the stability and reliability of the system.

[0322] Monitoring data: Real-time monitoring of environmental data, equipment operation data, and user behavior data to ensure the normal operation of the system.

[0323] Feedback adjustment: Based on real-time monitoring data, continuously adjust and optimize control strategies to ensure that the system always operates in the best condition.

[0324] S340, through the Internet of Things technology, realizes remote monitoring and control of the system, which is convenient for system maintenance and management. In addition, when a failure occurs, it can be handled promptly through remote control, reducing system downtime and maintenance costs.

[0325] (I) Remote control: Through the Internet of Things technology, the system can be remotely monitored and controlled, which is convenient for system maintenance and management. The specific steps are as follows:

[0326] A. Data input: Integrate data from the intelligent data acquisition and preprocessing module and edge computing nodes, including environmental data, equipment operation data, and user behavior data.

[0327] B. Remote data transmission: Through the Internet of Things technology, the collected data is transmitted to the remote monitoring center in real time. Use secure transmission protocols (such as MQTT, HTTPS) to ensure the reliability and security of data transmission.

[0328] C. Remote monitoring platform: In the remote monitoring center, the operating status of the central air conditioning system is monitored in real time using the monitoring platform. The platform includes a visual dashboard, data analysis tools, and an alarm system.

[0329] Visual dashboard: Real-time display of key parameters such as temperature, humidity, air flow velocity, cooling water temperature, compressor operating status, etc., allowing operation and maintenance personnel to fully understand the system operating status.

[0330] Data analysis tools: Analyze historical and real-time data, identify operating trends and potential problems, and provide optimization suggestions.

[0331] Alarm system: Set alarm rules. When system parameters exceed the preset range, the alarm will be automatically triggered to notify the operation and maintenance personnel for timely processing.

[0332] D. Remote control: Operation and maintenance personnel can remotely control the central air-conditioning system through the monitoring platform. For example, they can adjust the cooling water temperature setting value, fan speed, compressor operation time, etc. to ensure that the system always operates at the optimal efficiency point.

[0333] (ii) When a fault occurs, it can be handled promptly through remote control, reducing system downtime and maintenance costs. The specific steps are as follows:

[0334] a. Fault detection: Real-time monitoring of system operating status, detection and prediction of faults through feedback and fault diagnosis modules. For example, abnormal conditions can be identified by monitoring parameters such as cooling water temperature, compressor operating status, and current and voltage. Fault detection data: Real-time monitoring of temperature (℃), humidity (%RH), air flow velocity (m / s), light intensity (l ux), cooling water temperature (℃), compressor operating status (ON / OFF), refrigerant pressure (MPa), current and voltage (A / V).

[0335] B. Fault Alarm: When a fault is detected, the alarm system is automatically triggered to notify the operation and maintenance personnel. For example, when the compressor operates abnormally, the system sends an alarm notification to the operation and maintenance personnel's mobile device.

[0336] C. Remote diagnosis: Operation and maintenance personnel conduct remote diagnosis through the monitoring platform to analyze the cause of the fault and the scope of impact. For example, by viewing real-time data and historical data, the fault type and specific location can be confirmed.

[0337] D. Remote processing: Based on the diagnosis results, the operation and maintenance personnel can handle the fault through the remote control platform. For example, they can remotely restart the compressor, adjust the control parameters, switch to backup equipment, etc., to quickly restore the normal operation of the system.

[0338] Parameter adjustment: Remotely adjust relevant control parameters according to the fault type and cause to ensure that the fault is handled and repaired in a timely manner.

[0339] Equipment switching: When a fault cannot be repaired immediately, remotely switch to a backup device to ensure continuous system operation.

[0340] E. Maintenance records: record the fault handling process and results, update the maintenance log, and provide reference for subsequent optimization and improvement. For example, record the fault type, handling measures, handling time and results, and form a detailed fault handling report.

[0341] F. Preventive maintenance: Based on the fault records and analysis results, formulate a preventive maintenance plan to reduce the occurrence of future faults. For example, regularly inspect and maintain key equipment, optimize control strategies, and improve system reliability.

[0342] S400, monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control. Step S400 includes steps S410-S440:

[0343] S410, monitor the operating status of the refrigeration room and central air conditioning system in real time, collect various parameters and data, and analyze the collected data to identify abnormal conditions and trends in system operation.

[0344] (I) Status monitoring: Real-time monitoring of the operating status of the refrigeration room and central air-conditioning system, and collection of various parameters and data. The specific steps are as follows:

[0345] A. Data input: Receive environmental data, equipment operation data and user behavior data from the intelligent data acquisition and preprocessing module. These data have been preliminarily processed and have high accuracy and real-time performance.

[0346] B. Sensor network: Smart sensors are deployed at key locations in the refrigeration room and central air conditioning system to collect various operating parameters and data in real time. For example, temperature sensors collect cooling water temperature, humidity sensors monitor ambient humidity, and current sensors measure the current and voltage of the compressor.

[0347] C. Data transmission: Through the Internet of Things technology, the collected real-time data is transmitted to the edge computing nodes and cloud computing platforms. Use secure and reliable transmission protocols (such as MQTT, HTTPS) to ensure the integrity and timeliness of data transmission.

[0348] D. Real-time monitoring platform: On the real-time monitoring platform, various operating parameters and data are displayed, and the operation and maintenance personnel can understand the current status of the system through the visual interface. For example, the platform displays key parameters such as cooling water temperature, compressor operating status, air flow speed and user activities, which makes it easier for the operation and maintenance personnel to fully understand the system operation status.

[0349] (II) Data analysis: Analyze the collected data to identify abnormal conditions and trends in system operation. The specific steps are as follows:

[0350] A. Data processing: On the cloud computing platform and edge computing nodes, the collected real-time data is cleaned and preprocessed to remove noise and outliers to ensure data quality.

[0351] B. Data analysis tools: Use data analysis tools and machine learning algorithms to conduct in-depth analysis of processed data and identify abnormal conditions and trends in system operation. For example, use time series analysis and statistical methods to identify abnormal fluctuations and changing trends in cooling water temperature.

[0352] Anomaly detection: By setting parameter thresholds and rules, abnormal conditions in system operation can be detected. For example, when the cooling water temperature exceeds the preset range, the system automatically generates an alarm.

[0353] Trend analysis: Use historical data and real-time data to analyze the long-term trends of system operation.

[0354] C. Visual analysis: On the real-time monitoring platform, the analysis results are displayed through charts and dashboards, which makes it easier for operation and maintenance personnel to quickly understand and respond. For example, a line chart can be used to display the changing trend of cooling water temperature, and a pie chart can be used to display the distribution of compressor operating status.

[0355] D. Alarm and notification: According to the data analysis results, set the alarm rules. When the system parameters exceed the preset range, the alarm will be automatically triggered and the operation and maintenance personnel will be notified to handle it in time. For example, when the compressor current and voltage are abnormal, the system will send an alarm notification to the mobile device of the operation and maintenance personnel.

[0356] S420: Use machine learning algorithms to analyze system operation data and detect possible faults and abnormal conditions. Perform fault diagnosis based on the detection results, determine the cause of the fault and the scope of impact, and provide solutions and processing suggestions.

[0357] (I) Fault detection: Use machine learning algorithms to analyze system operation data and detect possible faults and abnormal conditions. The specific steps are as follows:

[0358] A. Data input: Receive environmental data, equipment operation data and user behavior data from the intelligent data acquisition and preprocessing module. These data have been preprocessed and have high accuracy and real-time performance.

[0359] B. Feature extraction: Extract relevant features from input data and construct feature vectors for training and prediction of machine learning models. For example, extract average temperature and temperature change rate from temperature data, and extract start frequency and operating time from compressor operation data.

[0360] C. Model training: Use historical fault data and normal operation data to train machine learning models (such as support vector machines, random forests, neural networks, etc.) so that they can identify normal operating conditions and fault conditions.

[0361] Data labeling: Label historical data to distinguish normal data from faulty data, and use them as training sets and test sets.

[0362] Model selection: Select an appropriate machine learning algorithm, train a fault detection model, and evaluate model performance through cross-validation.

[0363] D. Real-time detection: Input the real-time monitoring data into the trained fault detection model to detect possible faults and abnormal conditions. For example, when the cooling water temperature fluctuates violently in a short period of time, the model identifies it as a possible fault state and triggers an alarm.

[0364] (II) Fault diagnosis: Based on the test results, perform fault diagnosis, determine the cause of the fault and the scope of impact, and provide solutions and handling suggestions. The specific steps are as follows:

[0365] A. Fault classification: Based on the output of the fault detection model, classify and identify different types of faults. For example, classify faults into temperature anomalies, humidity anomalies, compressor failures, fan failures, etc.

[0366] B. Fault location: Based on the classification results and input data, further analyze the specific location and cause of the fault. For example, by analyzing the cooling water temperature and compressor operating status, determine whether the fault occurs in the compressor or cooling system.

[0367] C. Impact scope analysis: Evaluate the scope of the fault's impact on system operation. For example, a compressor failure may result in reduced cooling efficiency, thus affecting the operation of the entire air conditioning system.

[0368] D. Solution provision: Provide corresponding solutions and handling suggestions based on the cause of the failure and the scope of impact. For example:

[0369] Abnormal temperature: It is recommended to check and adjust the cooling water temperature setting value, clean the cooling water pipes, and ensure smooth water flow.

[0370] Compressor failure: It is recommended to check the electrical connections of the compressor, clean the dust inside the compressor, and replace aging parts.

[0371] Fan failure: It is recommended to check the operating status of the fan motor, adjust the fan speed, and clean the fan blades.

[0372] E. Feedback and Recording: Feedback fault detection and diagnosis results to the real-time monitoring platform, generate fault reports, record the processing process and results, and provide reference for subsequent optimization.

[0373] S430: According to the fault detection and diagnosis results, adjust the system operating parameters, prevent and handle faults, and ensure stable operation of the system. Feedback the fault information to the optimization calculation and control parameter generation module to further optimize the control strategy and improve the robustness and reliability of the system.

[0374] (I) Parameter adjustment: According to the fault detection and diagnosis results, adjust the system operating parameters to prevent and handle faults and ensure stable system operation. The specific steps are as follows:

[0375] A. Data input: Receive the fault detection and diagnosis results from the fault detection and diagnosis module, including the fault type, fault cause and impact range. These data are obtained by analyzing environmental data, equipment operation data and user behavior data.

[0376] B. Parameter adjustment: Adjust the system control parameters according to the fault detection and diagnosis results.

[0377] C. Real-time response: The system responds to faults in real time based on the adjusted parameters to ensure that the system resumes normal operation in the shortest possible time. For example, the cooling water temperature, fan speed and compressor operating status are adjusted in real time through the automatic control unit.

[0378] (II) Strategy optimization: Feedback fault information to the optimization calculation and control parameter generation module to further optimize the control strategy and improve the robustness and reliability of the system. The specific steps are as follows:

[0379] A. Fault information feedback: The fault detection and diagnosis results are transmitted as feedback information to the optimization calculation and control parameter generation module. This information includes the fault type, fault cause, impact range and treatment measures.

[0380] B. Optimization model update: The optimization calculation and control parameter generation module updates the optimization model based on feedback information. Fault information is used to improve multi-dimensional optimization algorithms, deep learning, and reinforcement learning models so that they can better predict and respond to faults. For example, the optimization calculation model will adjust the optimization objectives and constraints of the control parameters based on fault data to improve the model's sensitivity to faults and its ability to respond.

[0381] C. Control strategy optimization: Generate new control strategies based on the updated optimization model. These strategies can better prevent and handle faults and improve the robustness and reliability of the system. For example, the optimized control strategy will pay more attention to the health of the compressor, avoid frequent start and stop, and extend the life of the equipment.

[0382] D. Application of optimization results: Apply the optimized control strategy to the intelligent control execution module, adjust the system operating parameters in real time, and ensure that the system can maintain the best operating state before and after the failure occurs. For example, the system will adjust the cooling water temperature and fan speed in advance according to the optimized control strategy to prevent failures.

[0383] S440, store and manage system operation data and fault records, establish system operation history archives. And through data mining technology, analyze historical data, discover the rules and trends in system operation, and provide reference for future optimization.

[0384] (I) Data storage: Store and manage the system's operating data and fault records, and establish the system's operating history archives.

[0385] The specific steps are as follows:

[0386] A. Data input: Receive data from the intelligent data acquisition and preprocessing module, optimization calculation and control parameter generation module, intelligent control execution module and feedback and fault diagnosis module. These data include environmental data, equipment operation data, user behavior data and fault records.

[0387] Fault record: fault type, fault cause, impact range, and treatment measures

[0388] B. Data storage system: Establish a distributed database system to store and manage various types of data, ensuring the integrity, security and traceability of the data.

[0389] Data integrity: Ensure the integrity of stored data and prevent data loss or damage through data verification and redundancy mechanisms.

[0390] Data security: Access control, encryption technology and backup mechanisms are used to ensure data security and privacy protection.

[0391] Data traceability: Record the source, processing and modification records of data to ensure data traceability.

[0392] C. Data classification storage: Different types of data are classified and stored to facilitate subsequent retrieval and analysis. For example, environmental data, equipment operation data, user behavior data, and fault records are stored in different database tables.

[0393] (II) Data mining: Through data mining technology, historical data is analyzed to discover the laws and trends in system operation and provide reference for future optimization. The specific steps are as follows:

[0394] A. Data preparation: Extract historical data from the database, including environmental data, equipment operation data, user behavior data, and fault records. These data have been cleaned and preprocessed to have high quality.

[0395] B. Data mining algorithms: Apply various data mining algorithms (such as association rule mining, cluster analysis, classification algorithms, time series analysis, etc.) to analyze historical data and discover the patterns and trends in system operation.

[0396] Association rule mining: Identify the associations between different variables, for example, the impact of changes in temperature and humidity on the operating status of a compressor.

[0397] Cluster analysis: Cluster similar data to identify different modes and states in system operation, for example, the operation mode of equipment under different environmental conditions.

[0398] Classification algorithm: Based on historical fault records, a classification model is established to predict the probability of occurrence and impact range of different types of faults.

[0399] Time series analysis: Analyze the time series data of system operating parameters to discover long-term trends and periodic changes, and provide reference for future optimization.

[0400] C. Visual analysis: Display the results of data mining through visual charts to facilitate operation and maintenance personnel to understand and apply. For example, trend charts can be used to display the long-term changes in cooling water temperature and compressor operating status, and correlation charts can be used to display the correlation between different variables.

[0401] D. Optimization reference: Based on the results of data mining, provide reference for optimization calculation and control parameter generation modules, and improve optimization models and control strategies. For example, based on the rules found in historical data, optimize the cooling water temperature setting value and fan speed to improve the energy efficiency and reliability of the system.

[0402] The key innovations of this patent:

[0403] (1) Multi-dimensional optimization algorithm: The multi-dimensional optimization algorithm is used to comprehensively consider multiple variables such as temperature, humidity, energy consumption, and equipment life, and perform global optimization to ensure that the system maintains the best operating state under different environmental conditions.

[0404] (2) Adaptive control algorithm: Adaptive control algorithm is used to dynamically adjust system parameters according to real-time data, so that the system can quickly respond to environmental changes and user needs, improving user comfort and system energy efficiency.

[0405] (3) Intelligent fault detection and diagnosis: Through machine learning algorithms, real-time monitoring and analysis of system operation data, automatic detection and diagnosis of faults, and provision of solutions and processing suggestions can be achieved, thus reducing system downtime and maintenance costs.

[0406] (4) Data-driven optimization strategy: Through historical data management and data mining technology, the laws and trends in system operation are analyzed to provide reference for optimization calculation and control parameter generation, continuously improve the optimization model and control strategy, and enhance the robustness and reliability of the system.

[0407] (5) Remote monitoring and maintenance: Remote monitoring and control of the system is realized to facilitate system maintenance and management. When a failure occurs, it can be handled promptly through remote control, reducing system downtime and maintenance costs.

[0408] The present invention "A HVAC energy-saving control method and system based on AI" has the following beneficial effects:

[0409] (1) Improve system energy efficiency: Through multi-dimensional optimization algorithms and deep learning technology, the optimal operating parameters are calculated and generated in real time, so that the refrigeration room and central air-conditioning system can always maintain the best operating state under different environmental conditions and save energy to the maximum extent. The system dynamically adjusts the cooling water temperature, compressor operating time and fan speed according to real-time data to ensure that the best energy efficiency can be achieved in various environments and reduce energy waste.

[0410] (2) Rapid response to environmental changes: Using adaptive control algorithms and real-time data feedback, the system can quickly respond to environmental changes and user needs. By real-time monitoring of temperature, humidity, air flow speed and other parameters, the system automatically adjusts operating parameters to ensure user comfort. When environmental conditions change, the system can quickly adjust the cooling water temperature set point, fan speed and compressor operating status to maintain a stable and comfortable indoor environment.

[0411] (3) Intelligent fault detection and diagnosis: Machine learning algorithms are used to analyze system operation data, automatically detect and diagnose faults, and improve the timeliness and accuracy of fault handling. The system can predict faults before they occur and take preventive measures in advance to reduce system downtime and maintenance costs. It monitors various operating parameters in real time, quickly identifies abnormal situations, and provides specific fault causes and handling suggestions through fault diagnosis, thereby improving system reliability and stability.

[0412] (4) Data-driven optimization strategy: Through historical data management and data mining technology, the laws and trends in system operation are analyzed to provide reference for optimizing calculation and control parameter generation, further improving the robustness and reliability of the system. The system can continuously optimize the control strategy based on historical operation data, improve multi-dimensional optimization and adaptive control algorithms, and keep the system in an efficient and energy-saving state in long-term operation.

[0413] (5) Reduce maintenance costs: The system can monitor the operating status in real time, automatically detect and diagnose faults, reduce reliance on manual inspections and maintenance, and reduce maintenance costs. Through remote monitoring and maintenance functions, operation and maintenance personnel can monitor the system operating status at any time and handle faults remotely in a timely manner when they occur, reducing the time and cost of on-site maintenance.

[0414] In summary, the present invention realizes intelligent energy-saving control of the HVAC system by introducing advanced artificial intelligence technology, overcomes the shortcomings of traditional control methods, significantly improves the energy efficiency, response speed and reliability of the system, reduces maintenance costs, and provides an effective technical solution for the optimized operation of the HVAC system.

[0415] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0416] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0417] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0418] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0419] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0420] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0421] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An AI-based HVAC energy-saving control method, characterized in that: include: S100 collects environmental data and operating parameters of the refrigeration room and central air-conditioning system through the intelligent sensor network, and performs preliminary processing locally to ensure the accuracy and real-time nature of the data; S200, combining local and cloud computing resources, applying multi-dimensional optimization algorithms to generate the best efficiency point and control parameters; S300, adjust the operating status of the central air-conditioning system in real time according to the control parameters to achieve the best energy-saving effect; S400, monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control.

2. The method according to claim 1, characterized in that Step S100 includes: S110, through the deployment of intelligent sensors around the refrigeration room and central air conditioning system, real-time collection of ambient temperature, humidity, air flow speed, light intensity and other data; S120, collect operating parameters of the refrigeration room and central air-conditioning system, such as cooling water temperature, compressor operating status, refrigerant pressure, current and voltage, etc.; S130: Perform preliminary processing on the collected data to ensure the accuracy and real-time nature of the data.

3. The method according to claim 1, characterized in that: In step S200, the multi-dimensional optimization algorithm comprehensively considers multiple variables such as temperature, humidity, energy consumption and equipment life, performs global optimization, and ensures that the system maintains the best operating state under different environmental conditions.

4. The method according to claim 1, characterized in that In step S300, the cooling water temperature, compressor operation time and fan speed are adjusted in real time according to the control parameters to ensure that the system can achieve optimal energy efficiency under various environments.

5. The method according to claim 1, characterized in that: In step S400, a machine learning algorithm is used to monitor and analyze system operation data in real time, automatically detect and diagnose faults, and provide solutions and processing suggestions.

6. The method according to claim 1, characterized in that It also includes remote monitoring and maintenance functions to realize remote monitoring and control of the system, facilitating the maintenance and management of the system.

7. The method according to any one of claims 1 to 6, characterized in that: The method also uses historical data management and data mining technology to analyze the laws and trends in system operation, provide reference for optimizing calculation and control parameter generation, and improve the robustness and reliability of the system.

8. An AI-based HVAC energy-saving control system, characterized in that: include: Data collection and preprocessing module, used to collect environmental data and operating parameters of the refrigeration room and central air-conditioning system, and perform preliminary processing; The optimization calculation and control parameter generation module is used to combine local and cloud computing resources, apply multi-dimensional optimization algorithms, and generate the best efficiency point and control parameters; Real-time control and adjustment module, used to adjust the operating status of the central air-conditioning system in real time according to the control parameters to achieve the best energy-saving effect; The fault detection and diagnosis module is used to monitor the system operation status, perform real-time fault detection and diagnosis, and feed back to the data acquisition and preprocessing module to achieve closed-loop control.

9. The system according to claim 8, characterized in that It also includes a data storage and management module for storing and managing collected data and calculation results to ensure data integrity and traceability.

10. The system according to claims 8 and 9, characterized in that The system dynamically adjusts system parameters by applying an adaptive control algorithm, so that the system can achieve the best energy-saving effect under different environmental conditions.

Images