Intelligent building automatic control system based on artificial intelligence

Abstract

The invention discloses an intelligent building automatic control system based on artificial intelligence, relates to the technical field of artificial intelligence, and aims to solve the problems that an existing system lacks predictive maintenance, energy efficiency optimization, integration and data sharing, so that intelligence and decision-making efficiency are insufficient. The system comprises an intelligent decision-making layer, an intelligent sensing layer, a control decision-making layer, an execution layer and a user interaction layer.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent building automatic control system based on artificial intelligence. Background Art

[0002] The intelligent building automatic control system realizes intelligent management and monitoring of various equipment inside the building.

[0003] Environmental parameters and equipment status information are collected in real time through various sensors and smart meters installed inside the building.

[0004] The collected data is transmitted to the central processing unit or cloud platform using wired or wireless communication technology.

[0005] On the cloud platform or central processing unit, data processing and artificial intelligence technologies are used to deeply mine and analyze the collected data to identify potential problems and optimization space.

[0006] Based on the processing results, the equipment inside the building can be intelligently controlled through preset algorithms or user instructions.

[0007] User interaction: Provides user interaction methods such as mobile applications, web interfaces, and human-computer interaction interfaces, allowing users to view environmental parameters, equipment status, and other information inside the building in real time and send control instructions.

[0008] Existing systems are often composed of multiple independent subsystems, and there is a lack of effective integration and collaboration between the subsystems, resulting in low overall system efficiency. Although these subsystems perform their respective functions, they often lack tight integration and coordination mechanisms. This decentralized architecture makes it impossible for the entire system to maximize its efficiency during operation, affecting overall performance and response speed.

[0009] It is difficult to share and communicate data between different subsystems, forming data silos and limiting the ability to deeply mine and analyze data. Data silos not only hinder the flow of information across systems, but also limit the integrated analysis and deep mining of data, affecting the quality and efficiency of decision-making. This problem is particularly prominent in today's data-driven business environment because it limits the ability of organizations to gain insights and value from big data.

[0010] In addition, although the existing systems have certain intelligent functions, the degree of intelligence in some aspects is still limited and cannot meet the growing needs of users. In particular, in key intelligent applications such as predictive maintenance and energy efficiency optimization, the capabilities of existing systems are limited and it is difficult to accurately predict and optimize complex situations. This makes it difficult to meet users' needs for efficient and forward-looking solutions in a rapidly changing technology and business environment. Summary of the invention

[0011] In view of the shortcomings of the prior art, the present invention proposes an intelligent building automatic control system based on artificial intelligence, including an intelligent decision-making layer, an intelligent perception layer, a control decision-making layer, an execution layer and a user interaction layer; The intelligent decision layer is used to pre-process the system data received from the control decision layer; use big data analysis and artificial intelligence technology to deeply mine and analyze the pre-processed system data, identify opportunities in the system status as the basis for subsequent decision-making; propose multiple alternative plans based on the identified opportunities; use predetermined decision criteria and the expected cost, uncertainty and risk indicators of various plans to evaluate and rank the alternative plans; based on the evaluation, select the best plan and implement it, and transmit it to the control decision layer; track changes in system status through real-time monitoring and early warning functions; detect potential problems, adjust strategies in a timely manner, and propose new decision suggestions; receive equipment status information transmitted by the execution layer, analyze and optimize decisions; The intelligent sensing layer selects appropriate intelligent devices to be deployed at the locations to be tested in the building according to the specific environment and requirements inside the building; the intelligent devices can collect various parameters inside the building in real time according to the preset sampling frequency and measurement range, and transmit them to the control decision layer in a specific communication protocol and data format; The control decision layer receives the control instructions transmitted by the user interaction layer and transmits them to the execution layer; receives various parameters transmitted by the intelligent perception layer; monitors various parameters of the system in real time through sensors and transmits them to the control decision layer; cleans, organizes and analyzes the various parameters; uses algorithms to mine hidden laws and patterns from processed data; based on these laws, it can make predictions and optimization decisions to find energy efficiency points: adjust equipment operation strategies and optimize system parameters; based on the results of data mining and prediction optimization, generate corresponding control instructions and transmit them to the execution layer; feed back the current state of the system and operation results to the user interaction layer; receive decisions transmitted by the intelligent decision layer; convert the feelings into specific control instructions and transmit them to the execution layer; The execution layer receives various control instructions transmitted by the intelligent decision layer, responds quickly, and automatically adjusts various parameters inside the building; it is used to feed back the equipment status information inside the building to the intelligent decision layer in real time; The user interaction layer receives the system status and operation results transmitted by the control decision layer, and displays the latest status information of the building's internal environmental parameters and equipment operation on the user interface in real time; and allows the user to send control instructions through the user interface and transmit them to the control decision layer.

[0012] As a further limitation of the system of the present invention, the various parameters include equipment and environmental parameters within the building.

[0013] As a further limitation of the system of the present invention, the identification of energy efficiency points in the control decision layer is specifically as follows: relying on the computing resources and AI algorithm library of the cloud computing platform or the central processing unit, the parameters are cleaned, sorted and analyzed; the parameters are processed using statistical analysis methods, including descriptive statistics, inferential statistics and multivariate statistics, so as to obtain the distribution and change trend information of the data and provide a basis for decision-making; using AI algorithms and deep learning algorithms, hidden laws and patterns are mined from the processed data, and predictions and optimization decisions are made based on these laws as energy efficiency points.

[0014] Beneficial effects of the present invention: 1. Significantly improve energy efficiency and energy saving effects: Through advanced AI algorithms, the system can accurately predict and optimize the internal environmental parameters of the building. It can automatically adjust the operating status of the equipment to avoid energy waste. Compared with traditional intelligent building automatic control systems, this system improves energy-saving efficiency and effectively reduces building operating costs.

[0015] 2. Enhance environmental comfort and user experience: Real-time perception and response to changes in the building's internal environment ensures that the indoor environment is always kept in the most suitable state. This intelligent environmental management not only improves the user's comfort, but also enhances the user's satisfaction and trust in building facilities.

[0016] 3. Improve system stability and reliability: Adopting highly integrated system architecture, stable and reliable data transmission technology, and efficient system solutions, we can ensure seamless connection between various components of the system and improve the overall stability and reliability of the system.

[0017] 4. User-friendly interactive interface: It provides a variety of user interaction methods, such as mobile applications, Web management platform, human-computer interaction interface, etc. The user interaction interface is intuitive and easy to use, allowing users to view internal building information in real time, send control commands, and receive system feedback, simplifying the operation process and reducing maintenance costs.

[0018] 5. Improve data processing and analysis capabilities: Using data processing technology, the system can process massive amounts of data in real time, provide decision-making support for building managers, and provide a data foundation for subsequent system optimization and upgrades.

[0019] 6. Enhance system scalability and flexibility: The design fully considers the needs of future expansion and supports the access of various sensors, actuators and devices.

[0020] 7. The system adopts a highly integrated architecture, which closely connects various links such as intelligent perception, data transmission, intelligent decision-making, control execution and user interaction to form an efficient and coordinated whole. This integrated design improves the stability and response speed of the system.

[0021] 8. Advanced AI algorithms and data processing technology: The core technology lies in the application of AI algorithms, which enable in-depth mining and analysis of massive data through optimization algorithms and deep learning to achieve accurate prediction and optimized control. At the same time, data processing technology ensures the real-time and accuracy of data.

[0022] 9. Improve system integration: Through unified interfaces and protocols, achieve seamless integration and collaborative work among subsystems to improve the overall efficiency of the system.

[0023] 10. Break the data silos: Establish a data sharing mechanism to achieve interoperability and sharing of data between subsystems and improve data utilization and value.

[0024] 11. Intelligent control strategy: The system can introduce artificial intelligence algorithms and models according to changes in environmental parameters and equipment status, improve the system's intelligence level in predictive maintenance, energy efficiency optimization, etc., automatically adjust the control strategy, and realize intelligent management of the building's internal environment. This intelligent control not only improves energy efficiency, but also improves user comfort, and improves the level of building intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a summary system block diagram of an intelligent building automatic control system based on artificial intelligence of the present invention.

[0026] Figure 2 The present invention is a flowchart of an intelligent building automatic control system method based on artificial intelligence. DETAILED DESCRIPTION

[0027] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. The embodiments described are given in the drawings. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thoroughly and comprehensively understood.

[0028] In this implementation, the various layers of the system are transmitted through stable and reliable data transmission technology to ensure that data can be transmitted between different layers in real time and efficiently. In addition, an efficient storage solution is implemented to ensure long-term storage and ready availability of data. In order to further enhance data security, data encryption and regular backup measures are also taken.

[0029] In this implementation, each layer achieves seamless integration and collaborative work through a unified interface and protocol, thereby improving the overall efficiency of the system.

[0030] like Figure 1 As shown, an intelligent building automatic control system based on artificial intelligence includes an intelligent decision-making layer, an intelligent perception layer, an intelligent decision-making layer, an execution layer and a user interaction layer; The intelligent decision-making layer first receives system data from the control decision-making layer. These data include temperature, humidity, pressure, flow and other sensor data, as well as information from other systems. After data collection, the intelligent decision-making layer will perform preprocessing, including data cleaning, standardization and formatting, to ensure the accuracy and consistency of the data. The preprocessed data will be sent to the data analysis module. This layer uses big data analysis and artificial intelligence technologies, such as machine learning and deep learning, to conduct in-depth mining and analysis of system data. Through data analysis, the intelligent decision-making layer can identify opportunities in the system status, including energy-saving potential and equipment operation efficiency improvement. These opportunities will become the basis for subsequent decision-making. For the identified opportunities, the intelligent decision-making layer will propose a variety of alternative solutions. These solutions involve adjusting system parameters and optimizing equipment operation strategies. In order to evaluate the pros and cons of these solutions, the intelligent decision-making layer uses predetermined decision criteria and the expected costs, uncertainties and risk indicators of various solutions for quantitative analysis. These criteria include economic benefits, environmental impacts and technical feasibility. Based on the evaluation of alternative solutions, the intelligent decision-making layer uses decision optimization algorithms (multi-objective optimization, random optimization) to further optimize and sort the solutions. These algorithms comprehensively consider the trade-offs between multiple decision-making objectives, as well as the uncertainties and risks in the implementation process. Ultimately, the intelligent decision layer selects the optimal solution and transmits it to the control decision layer for implementation. In the process of implementing the optimal solution, the intelligent decision layer also tracks changes in system status through real-time monitoring and early warning functions. This includes monitoring the changing trends of key parameters, identifying abnormal situations, and issuing early warning signals. Once potential problems or risks are detected, the intelligent decision layer will promptly adjust the strategy or make new decision suggestions to ensure the stability and security of system operation.

[0031] The intelligent perception layer selects appropriate intelligent devices, including temperature sensors, humidity sensors, light sensors, and air quality sensors, according to the specific environment and needs inside the building. These devices are deployed at the locations to be tested in the building to ensure that the required parameters can be collected comprehensively and accurately. Intelligent devices collect various parameters inside the building in real time according to the preset sampling frequency and measurement range. These parameters include temperature, humidity, light intensity, air quality (PM2.5, CO2 concentration), and sound intensity. The collected data will be transmitted to the control decision layer via wireless or wired means. During the transmission process, the intelligent perception layer will follow specific communication protocols and data formats to ensure the accuracy and integrity of the data.

[0032] The control decision layer receives control instructions from the user interaction layer, including temperature setting, humidity adjustment, and device switching. The intelligent perception layer uses sensors to monitor various system parameters in real time, such as temperature, humidity, pressure, and flow. These parameters are transmitted to the control decision layer for subsequent data cleaning, sorting, and analysis. The control decision layer uses machine learning algorithms to mine hidden laws and patterns from processed data. Based on these laws, the control decision layer can make predictions and optimization decisions to find energy efficiency points, such as adjusting equipment operation strategies and optimizing system parameters. According to the results of data mining and prediction optimization, the control decision layer will generate corresponding control instructions. These instructions are designed to optimize the energy efficiency of the system, improve the operating efficiency of the equipment, and reduce energy consumption. The generated control instructions will be transmitted to the execution layer, which will be responsible for the specific execution of the operation. The control decision layer will also feed back the current status of the system and the operation results to the user interaction layer. This information can be used to display the real-time status of the system on the user interface, and provide operation feedback and error prompts to the user. The control decision layer also receives decisions from the intelligent decision layer, which involve higher-level system optimization and strategy adjustment. The control decision layer converts these decisions into specific control instructions and transmits them to the execution layer for implementation.

[0033] Among them, energy efficiency points are identified; Relying on the computing resources and AI algorithm library of the cloud computing platform or central processing unit, the parameters are cleaned, sorted and analyzed. Statistical analysis methods are used to process the parameters, including descriptive statistics, inferential statistics and multivariate statistics, to obtain the distribution and trend information of the data and provide a basis for decision-making. AI algorithms and deep learning algorithms are used to dig out hidden laws and patterns from the processed data, and predictions and optimization decisions are made based on these laws as energy efficiency points.

[0034] In smart building automation systems, energy efficiency optimization is a key goal, aiming to minimize energy consumption and maximize user comfort. To achieve this goal, algorithms and deep learning techniques can be combined to optimize the performance of the control system.

[0035] Genetic algorithm is a search heuristic algorithm that simulates natural selection and genetics. It does not rely on specific mathematical formulas to directly solve problems, but instead simulates operations such as selection, crossover (hybridization) and mutation in the biological evolution process to find the optimal solution or approximate optimal solution. In intelligent building automatic control systems, genetic algorithms can be used to optimize energy consumption patterns and improve solutions through operations such as selection, crossover, mutation and iteration.

[0036] Combine genetic algorithms with computing resources and AI algorithms from cloud computing platforms or central processing units to achieve energy efficiency optimization.

[0037] Calculate energy efficiency points by combining genetic algorithms and deep learning; The selection operation in genetic algorithms is usually based on the fitness function. textFitness = textObjective function value The solution space of the problem is mapped to the search space of the genetic algorithm, usually using binary coding, Gray code coding or real number coding, etc. Then based on the fitness, operations such as selection, crossover, mutation and iteration are performed to find the optimal solution.

[0038] In intelligent building control systems, deep learning algorithms, especially those based on neural networks, can be used in data processing, pattern recognition, and predictive control. Deep learning algorithms automatically learn complex features in input data through a multi-layer neural network structure and use them for subsequent control decisions.

[0039] Take the feedforward neural network in deep learning as an example: Forward propagation, computing the output of the network given the input data:

[0040] In the formula, y is the output, f is the activation function (such as ReLU, Sigmoid), W is the weight matrix, x is the input, b is the bias vector.

[0041] Backpropagation is used to train the network and adjust weights and biases: Weight updates are usually done using gradient descent or a variant of it, such as the Adam optimizer. The exact formula depends on the optimization algorithm chosen.

[0042] A feedforward neural network is a commonly used deep learning model that calculates outputs through forward propagation and adjusts network weights through backpropagation to improve prediction accuracy.

[0043] Through this process, the genetic artificial intelligence algorithm and the deep learning model work together to gradually improve the solution and eventually find the optimal control strategy, that is, the energy efficiency point.

[0044] The core function of the execution layer is to automatically adjust various parameters inside the building. This includes adjusting the working status of the air conditioning system, lighting system, and fresh air system equipment to achieve precise control of temperature, humidity, and lighting environment parameters. The execution layer will adjust the operating mode and parameter settings of these devices according to the instructions of the control decision layer and the intelligent decision layer to achieve the adjustment effect. While performing the adjustment task, the execution layer will also provide real-time feedback on the status of the equipment inside the building. And feed this data back to the intelligent decision layer. This data can be used by the intelligent decision layer for subsequent analysis and optimization decisions.

[0045] The user interaction layer receives the system status and operation results transmitted by the control decision layer, and displays the latest status information of the building's internal environmental parameters and equipment operation on the user interface in real time; it allows users to send control instructions through the user interface and transmit them to the control decision layer. It provides a variety of user interaction methods, such as mobile applications, Web management platforms, and human-computer interaction interfaces. The interface design is intuitive and easy to use, which facilitates users to view the internal information of the building in real time; it is used to feedback the system status and execution results through the user interface.

[0046] The above description is relatively specific, and of course it cannot be used to limit the scope of the rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. An intelligent building automatic control system based on artificial intelligence, characterized in that: It includes intelligent decision-making layer, intelligent perception layer, control decision-making layer, execution layer and user interaction layer; The intelligent decision layer is used to pre-process the system data received from the control decision layer; use big data analysis and artificial intelligence technology to deeply mine and analyze the pre-processed system data, identify opportunities in the system status as the basis for subsequent decision-making; propose multiple alternative plans based on the identified opportunities; use predetermined decision criteria and the expected cost, uncertainty and risk indicators of various plans to evaluate and rank the alternative plans; based on the evaluation, select the best plan and implement it; track changes in system status through real-time monitoring and early warning functions; detect potential problems, adjust strategies in a timely manner, propose new decision suggestions, and transmit them to the control decision layer; receive equipment status information transmitted by the execution layer, analyze and optimize decisions; The intelligent sensing layer selects appropriate intelligent devices to be deployed at the locations to be tested in the building according to the specific environment and requirements inside the building; the intelligent devices can collect various parameters inside the building in real time according to the preset sampling frequency and measurement range, and transmit them to the control decision layer in a specific communication protocol and data format; The control decision layer receives the control instructions transmitted by the user interaction layer and transmits them to the execution layer; receives various parameters transmitted by the intelligent perception layer; monitors various parameters of the system in real time through sensors and transmits them to the control decision layer; cleans, organizes and analyzes the various parameters; uses algorithms to mine hidden laws and patterns from processed data; based on these laws, it can make predictions and optimization decisions to find energy efficiency points: adjust equipment operation strategies and optimize system parameters; based on the results of data mining and prediction optimization, generate corresponding control instructions and transmit them to the execution layer; feed back the current state of the system and operation results to the user interaction layer; receive decisions transmitted by the intelligent decision layer; convert the feelings into specific control instructions and transmit them to the execution layer; The execution layer receives various control instructions transmitted by the intelligent decision layer, responds quickly, and automatically adjusts various parameters inside the building; Used to provide real-time feedback of equipment status information inside the building to the intelligent decision-making layer; The user interaction layer receives the system status and operation results transmitted by the control decision layer, and displays the latest status information of the building's internal environmental parameters and equipment operation on the user interface in real time; and allows the user to send control instructions through the user interface and transmit them to the control decision layer.

2. The intelligent building automatic control system based on artificial intelligence according to claim 1 is characterized in that: The various parameters include equipment status and environmental parameters in the building.

3. The intelligent building automatic control system based on artificial intelligence according to claim 1 is characterized in that: The specific steps of identifying energy efficiency points in the control decision layer are as follows: relying on the computing resources and AI algorithm library of the cloud computing platform or the central processing unit, the parameters are cleaned, sorted and analyzed; statistical analysis methods are used to process the parameters, including descriptive statistics, inferential statistics and multivariate statistics, so as to obtain the distribution and trend information of the data and provide a basis for decision-making; AI algorithms and deep learning algorithms are used to mine hidden laws and patterns from the processed data, and predictions and optimization decisions are made based on these laws as energy efficiency points.

Images