Artificial intelligence-based combined air conditioning unit power control system and method

Abstract

The application relates to the technical field of intelligent building systems, in particular to an electric control system and method for a combined air conditioning unit based on artificial intelligence, which comprises an environment monitoring module, a data analysis module, a prediction and control module, an energy management module, a user behavior recognition module, a maintenance optimization module and a context perception adjustment module; in the application, cognitive computing technology is introduced, complex environment data can be deeply analyzed and understood, the prediction and adaptation capability for subtle environment differences and sudden demand changes is improved, the air conditioning system can more accurately adjust its operation to meet the real-time environment and specific needs of users, through data analysis and machine learning technology, fault prediction and preventive maintenance can be more effectively carried out, thereby reducing system failure and maintenance costs, and better real-time reaction and automatic adjustment capability is exhibited under rapidly changing environmental conditions, ensuring that the operation of the air conditioning system is always in the optimal state.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent building systems, and in particular to an electric control system and method for combined air conditioning units based on artificial intelligence. BACKGROUND

[0002] The technical field of intelligent building systems focuses on using information technology and automation control technology to improve the energy efficiency, comfort and safety of buildings. In this field, artificial intelligence plays a crucial role, especially in optimizing the energy use of buildings. Intelligent building systems achieve efficient management of building environments by integrating sensors, controllers and user interfaces, which not only include air conditioning systems but also cover lighting, security and energy management.

[0003] The electric control system for combined air conditioning units based on artificial intelligence is a system that uses artificial intelligence technology to optimize the electricity efficiency of air conditioning systems. Its purpose is to achieve energy saving, energy efficiency improvement and user comfort by intelligently analyzing and adjusting the operation of air conditioning units. This system can automatically adapt to different environmental conditions and user needs, thereby reducing unnecessary energy consumption and costs. The system usually achieves its goal by integrating various technical means. First, sensors are used to monitor environmental conditions and user behavior. Using artificial intelligence algorithms such as machine learning and data analysis, the system can predict and adjust the operation mode of the air conditioner to adapt to real-time needs.

[0004] Although the existing electric control system for combined air conditioning units based on artificial intelligence has made progress in optimizing energy use of air conditioners and improving environmental comfort, it still has the following limitations. The system can adjust according to basic environmental conditions and user behavior, but it is difficult to fully identify and adapt to more subtle environmental differences or sudden changes in demand. At the same time, there are limitations in real-time response and automatic adjustment under rapidly changing environmental conditions. Therefore, although the system uses artificial intelligence technology, there is still room for improvement in integrating cognitive computing technology and environmental perception. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to provide an electric control system and method for combined air conditioning units based on artificial intelligence.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solution: the electric control system for combined air conditioning units based on artificial intelligence includes an environment monitoring module, a data analysis module, a prediction and control module, an energy management module, a user behavior recognition module, a maintenance optimization module and a context perception adjustment module.

[0007] The environment monitoring module performs real-time monitoring and analysis of environment parameters based on sensor data using a Kalman filtering algorithm, and performs data aggregation to generate an environment data report;

[0008] The data analysis module performs data pattern recognition and anomaly analysis based on the environment data report using a support vector machine algorithm to generate an anomaly pattern analysis report;

[0009] The prediction and control module performs environment prediction based on the anomaly pattern analysis report using a long short-term memory network algorithm, and formulates adjustment strategies through a genetic algorithm to generate an air conditioner adjustment strategy;

[0010] The energy management module optimizes energy use based on the air conditioner adjustment strategy using a dynamic programming algorithm, and performs energy consumption evaluation to generate an energy management plan;

[0011] The user behavior recognition module evaluates user habits and predicts demand based on the energy management plan and environment data report using a decision tree algorithm to generate a user behavior analysis report;

[0012] The maintenance optimization module performs fault prediction analysis and maintenance plan formulation based on the user behavior analysis report using an artificial neural network to generate a maintenance plan;

[0013] The context-aware adjustment module performs environment adaptability analysis and adjusts air conditioner settings based on the maintenance plan and air conditioner adjustment strategy using cognitive computing technology to generate a context adjustment result;

[0014] The environment data report is specifically temperature, humidity, light intensity, and air quality index report, the anomaly pattern analysis report includes environmental change trend and anomaly pattern recognition, the air conditioner adjustment strategy is specifically adaptive adjustment instructions for air conditioner temperature and humidity, the energy management plan includes energy distribution, efficiency improvement, and cost control scheme, the user behavior analysis report is specifically user activity pattern, temperature and humidity preference, and energy use habit report, and the maintenance plan includes fault warning, maintenance time planning, and performance monitoring scheme, and the context adjustment result is specifically air conditioner settings automatically adjusted according to environmental changes and user demand.

[0015] As a further scheme of the present application, the environment monitoring module includes a temperature monitoring submodule, a humidity monitoring submodule, a light monitoring submodule, and an air quality monitoring submodule;

[0016] The temperature monitoring submodule performs real-time temperature monitoring based on sensor data using a Kalman filtering algorithm to generate a temperature monitoring report;

[0017] The humidity monitoring submodule generates a humidity monitoring report based on the temperature monitoring report, using a dew point measurement method to analyze the relationship between temperature and humidity.

[0018] The light monitoring submodule generates a light intensity report based on the humidity monitoring report, using a photoelectric sensing technology to evaluate the ambient light conditions.

[0019] The air quality monitoring submodule generates an environmental data report based on the light intensity report, using a gas component analysis technology to evaluate the air quality.

[0020] As a further aspect of the application, the data analysis module includes a trend analysis submodule, an anomaly detection submodule, a data fusion submodule, and a report generation submodule.

[0021] The trend analysis submodule generates a trend analysis report based on the environmental data report, using a moving average method and linear regression analysis to analyze the long-term trend of the data.

[0022] The anomaly detection submodule generates an anomaly pattern recognition report based on the trend analysis report, using a support vector machine algorithm to identify data outliers.

[0023] The data fusion submodule generates a comprehensive data report based on the anomaly pattern recognition report, using principal component analysis and ensemble learning methods to fuse multi-dimensional data.

[0024] The report generation submodule generates an anomaly pattern analysis report based on the comprehensive data report, using an automatic report generation tool to integrate the analysis results.

[0025] As a further aspect of the application, the prediction and control module includes an environmental prediction submodule, a strategy formulation submodule, a temperature control optimization submodule, and a humidity adjustment submodule.

[0026] The environmental prediction submodule generates an environmental trend prediction report based on the anomaly pattern analysis report, using a long short-term memory network algorithm to analyze future environmental trends.

[0027] The strategy formulation submodule generates a regulation strategy planning report based on the environmental trend prediction report, using a genetic optimization algorithm to formulate adjustment strategies.

[0028] The temperature control optimization submodule generates a temperature control optimization report based on the regulation strategy planning report, using intelligent temperature control technology to optimize temperature adjustment logic.

[0029] The humidity adjustment submodule generates an air conditioner adjustment strategy based on the temperature control optimization report, using an adaptive feedback control method to adjust humidity settings.

[0030] As a further scheme of the present application, the energy management module comprises an energy monitoring submodule, a resource allocation submodule, an efficiency optimization submodule, and a cost analysis submodule;

[0031] The energy monitoring submodule monitors energy flow and consumption based on air conditioning adjustment strategies using real-time data monitoring technology and generates an energy use analysis report;

[0032] The resource allocation submodule generates a resource allocation optimization report based on the energy use analysis report using linear programming and constraint optimization techniques;

[0033] The efficiency optimization submodule generates an energy efficiency optimization report based on the resource optimization allocation report using system dynamic simulation and performance analysis methods;

[0034] The cost analysis submodule evaluates the economic effects of energy-saving measures based on the energy efficiency optimization report using cost-benefit analysis and generates an energy management plan.

[0035] As a further scheme of the present application, the user behavior recognition module comprises an activity recognition submodule, a habit analysis submodule, a demand prediction submodule, and a personalized recommendation submodule;

[0036] The activity recognition submodule performs activity pattern recognition based on the energy management plan and environmental data report using time series analysis and generates a user activity pattern report;

[0037] The habit analysis submodule analyzes user habits based on the user activity pattern report using clustering algorithms and generates a user habit analysis report;

[0038] The demand prediction submodule predicts future demands and preferences of users based on the user habit analysis report using a logistic regression model and generates a user demand prediction report;

[0039] The personalized recommendation submodule provides energy-saving recommendations based on the user demand prediction report using a collaborative filtering recommendation algorithm and generates a user behavior analysis report.

[0040] As a further scheme of the present application, the maintenance optimization module comprises a fault prediction submodule, a maintenance plan submodule, a performance monitoring submodule, and a maintenance log submodule;

[0041] The fault prediction submodule performs fault trend analysis on data based on the user behavior analysis report using a multilayer perceptron neural network and generates a fault prediction report;

[0042] The maintenance plan submodule formulates maintenance strategies and plans based on the fault prediction report using linear programming methods and generates a maintenance strategy and plan report;

[0043] The performance monitoring submodule generates a performance monitoring report based on the maintenance strategy plan, uses data analysis techniques, and performs operation state monitoring.

[0044] The maintenance log submodule generates a maintenance plan based on the performance monitoring report, uses log analysis techniques, and records operation and maintenance activities.

[0045] As a further aspect of the application, the context-aware adjustment module includes an environment adaptation submodule, a user preference submodule, an intelligent adjustment submodule, and a comfort monitoring submodule.

[0046] The environment adaptation submodule generates an environment adaptability adjustment report based on the maintenance plan and air conditioner adjustment strategy, using an adaptive neuro-fuzzy inference system to analyze environmental data and adjust air conditioner parameters.

[0047] The user preference submodule generates a user preference analysis report based on the environment adaptability adjustment report, using a K-means clustering algorithm to refine user behavior patterns.

[0048] The intelligent adjustment submodule generates an intelligent adjustment strategy report based on the user preference analysis report, using a particle swarm optimization algorithm to optimize air conditioner settings.

[0049] The comfort monitoring submodule generates a context adjustment result based on the intelligent adjustment strategy report, using an environmental quality evaluation model to continuously monitor and evaluate air conditioner adjustment effects.

[0050] The power control method for the combined air conditioning unit based on artificial intelligence is executed based on the above-mentioned power control system for the combined air conditioning unit based on artificial intelligence, and includes the following steps:

[0051] S1: Based on environmental sensor data, use Kalman filtering algorithm for real-time monitoring and analysis to generate an environmental data report.

[0052] S2: Based on the environmental data report, use support vector machine algorithm for pattern recognition and anomaly analysis to generate an anomaly pattern analysis report.

[0053] S3: Based on the anomaly pattern analysis report, use long short-term memory network algorithm to predict environmental change trends and generate an environmental trend prediction report.

[0054] S4: Based on the environmental trend prediction report, use genetic optimization algorithm to develop air conditioner adjustment strategies and generate air conditioner adjustment strategies.

[0055] S5: Based on the air conditioner adjustment strategy, use dynamic programming algorithm to optimize energy use and generate an energy management plan.

[0056] S6: Based on the energy management plan and environmental data report, a decision tree algorithm is used to analyze user behavior, generating a user behavior analysis report;

[0057] S7: Based on the user behavior analysis report, a multi-layer perceptron neural network is used for fault trend analysis and maintenance planning, generating a maintenance plan;

[0058] S8: Based on the maintenance plan and air conditioning adjustment strategy, an adaptive neuro-fuzzy inference system is used for environmental adaptability analysis and adjustment of air conditioning settings, generating an environmental adaptability adjustment scheme;

[0059] S9: Based on the environmental adaptability adjustment scheme, an environmental quality evaluation model is used for system performance monitoring, generating a system performance report.

[0060] As a further scheme of the present application, the environmental adaptability adjustment scheme specifically refers to the automatic adjustment of air conditioning settings according to environmental changes and user needs, and the system performance report specifically refers to a comprehensive evaluation report of air conditioning adjustment effect and environmental comfort.

[0061] Compared with the prior art, the present application has the following advantages and positive effects:

[0062] In the present application, by introducing cognitive computing technology, complex environmental data can be deeply analyzed and understood, thereby improving the prediction and adaptation ability to subtle environmental differences and sudden demand changes, so that the air conditioning system can more accurately adjust its operation to meet the real-time environment and specific needs of users, and through data analysis and machine learning technology, more effective fault prediction and preventive maintenance can be performed, thereby reducing system failure and maintenance costs, and better real-time response and automatic adjustment capabilities are demonstrated under rapidly changing environmental conditions, ensuring that the operation of the air conditioning system is always in the best state, improving energy use efficiency and user comfort, and enhancing the stability and reliability of system power control. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 The system flowchart of the present application;

[0064] Figure 2 The system framework diagram of the present application;

[0065] Figure 3 The flowchart of the environmental monitoring module of the present application;

[0066] Figure 4 The flowchart of the data analysis module of the present application;

[0067] Figure 5 The flowchart of the prediction and control module of the present application;

[0068] Figure 6Flow chart of the energy management module of the present application;

[0069] Figure 7 Flow chart of the user behavior identification module of the present application;

[0070] Figure 8 Flow chart of the maintenance optimization module of the present application;

[0071] Figure 9 Flow chart of the context-aware adjustment module of the present application;

[0072] Figure 10 Schematic diagram of the method steps of the present application. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0074] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0075] Example one

[0076] Please refer to Figures 1-2 The present application provides a technical solution: an electric control system for a combined air conditioning unit based on artificial intelligence, which includes an environment monitoring module, a data analysis module, a prediction and control module, an energy management module, a user behavior identification module, a maintenance optimization module and a context-aware adjustment module.

[0077] The environment monitoring module performs real-time monitoring and analysis of environmental parameters based on sensor data using Kalman filtering algorithm, and performs data aggregation to generate an environmental data report.

[0078] The data analysis module performs data pattern recognition and anomaly analysis based on the environmental data report using a support vector machine algorithm to generate an anomaly pattern analysis report.

[0079] The prediction and control module performs environmental prediction based on the anomaly pattern analysis report using a long short-term memory network algorithm, and formulates an adjustment strategy through a genetic algorithm to generate an air conditioning adjustment strategy.

[0080] The energy management module optimizes energy use based on the air conditioner adjustment strategy using dynamic programming algorithm and conducts energy consumption evaluation to generate an energy management plan;

[0081] The user behavior recognition module assesses user habits and predicts demand based on the energy management plan and environmental data report using decision tree algorithm to generate a user behavior analysis report;

[0082] The maintenance optimization module conducts fault prediction analysis and maintenance plan formulation based on the user behavior analysis report using artificial neural network to generate a maintenance plan;

[0083] The context-aware adjustment module conducts environmental adaptability analysis and adjusts air conditioner settings based on the maintenance plan and air conditioner adjustment strategy using cognitive computing technology to generate a context adjustment result;

[0084] The environmental data report specifically refers to temperature, humidity, light intensity, and air quality index report, the abnormal pattern analysis report includes environmental change trend and abnormal pattern recognition, the air conditioner adjustment strategy specifically refers to self-adaptive adjustment instructions for air conditioner temperature and humidity, the energy management plan includes energy distribution, efficiency improvement, and cost control scheme, the user behavior analysis report specifically refers to user activity pattern, temperature and humidity preference, and energy use habit report, the maintenance plan includes fault warning, maintenance time planning, and performance monitoring scheme, and the context adjustment result specifically refers to automatic adjustment of air conditioner settings according to environmental changes and user demand.

[0085] The environmental monitoring module monitors and analyzes environmental parameters in real time to ensure that the air conditioning system can adaptively adjust under different environmental conditions and reduce unnecessary energy consumption. The predictive control module uses abnormal pattern analysis and genetic algorithm to develop adjustment strategies, improving user experience. The user behavior recognition module assesses user habits and demand, predicts user demand, and automatically adjusts air conditioner settings, improving comfort and reducing user operation burden. The context-aware adjustment module ensures appropriate temperature and humidity settings in different situations through cognitive computing technology, enhancing user satisfaction. The maintenance optimization module reduces maintenance costs and downtime through fault prediction analysis and maintenance plan formulation. The context-aware adjustment module can also automatically adjust air conditioner settings to extend equipment life. In terms of data analysis and reporting, the system provides support vector machine algorithm for data pattern recognition and anomaly analysis, and user behavior analysis report and energy management plan provide important information for management personnel to develop more effective management strategies. In terms of real-time monitoring and feedback, the environmental monitoring module provides real-time environmental data report, and the context-aware adjustment module can adjust air conditioner settings in real time to ensure that the system always maintains appropriate conditions.

[0086] Please refer to Figure 3The environmental monitoring module includes a temperature monitoring submodule, a humidity monitoring submodule, an illumination monitoring submodule, and an air quality monitoring submodule.

[0087] The temperature monitoring submodule uses a Kalman filter algorithm to monitor temperature in real time based on sensor data and generates a temperature monitoring report.

[0088] The humidity monitoring submodule analyzes the relationship between temperature and humidity using a dew point measurement method based on the temperature monitoring report and generates a humidity monitoring report.

[0089] The illumination monitoring submodule uses photoelectric sensing technology to evaluate environmental lighting conditions based on the humidity monitoring report and generates an illumination intensity report.

[0090] The air quality monitoring submodule uses gas component analysis technology to evaluate air quality based on the illumination intensity report and generates an environmental data report.

[0091] The temperature monitoring submodule collects data through a temperature sensor and uses a Kalman filter algorithm for real-time monitoring to generate a temperature monitoring report. The humidity monitoring submodule calculates humidity using a dew point measurement method based on the temperature monitoring report to generate a humidity monitoring report. The illumination monitoring submodule uses photoelectric sensing technology to evaluate environmental lighting conditions based on the humidity monitoring report to generate an illumination intensity report. The air quality monitoring submodule uses gas component analysis technology to evaluate air quality based on the illumination intensity report to generate an environmental data report, ensuring accurate monitoring and report generation of various environmental parameters and providing necessary environmental information for the intelligent combined air conditioning unit to support subsequent data analysis and intelligent control decisions.

[0092] Please refer to Figure 4 The data analysis module includes a trend analysis submodule, an anomaly detection submodule, a data fusion submodule, and a report generation submodule.

[0093] The trend analysis submodule uses moving average and linear regression analysis to analyze long-term trends in data based on the environmental data report and generates a trend analysis report.

[0094] The anomaly detection submodule uses a support vector machine algorithm to identify data outliers based on the trend analysis report and generates an anomaly pattern recognition report.

[0095] The data fusion submodule uses principal component analysis and ensemble learning methods to fuse multi-dimensional data based on the anomaly pattern recognition report and generates a comprehensive data report.

[0096] The report generation submodule uses an automatic report generation tool to integrate analysis results based on the comprehensive data report and generates an anomaly pattern analysis report.

[0097] The trend analysis submodule extracts data from the environmental data reports, analyzes long-term trends using moving average and linear regression analysis, and generates a trend analysis report. The anomaly detection submodule detects data outliers based on the trend analysis report using a support vector machine algorithm and generates an anomaly pattern recognition report describing the abnormal data points. The data fusion submodule uses the abnormal data points in the anomaly pattern recognition report to fuse multi-dimensional data using principal component analysis and ensemble learning methods, generating a comprehensive data report that provides a comprehensive data view. The report generation submodule uses the comprehensive data report as a basis to integrate analysis results using an automatic report generation tool to create an anomaly pattern analysis report that includes data visualization, trend description, outlier identification, and fused data analysis, which helps improve the stability and performance of the system to ensure efficient operation of the air conditioning system in various situations.

[0098] Please refer to Figure 5 , the prediction and control module includes an environmental prediction submodule, a strategy formulation submodule, a temperature control optimization submodule, and a humidity adjustment submodule.

[0099] The environmental prediction submodule analyzes future environmental trends based on the anomaly pattern analysis report using a long short-term memory network algorithm and generates an environmental trend prediction report.

[0100] The strategy formulation submodule formulates adjustment strategies based on the environmental trend prediction report using a genetic optimization algorithm and generates an adjustment strategy planning report.

[0101] The temperature control optimization submodule optimizes temperature adjustment logic based on the adjustment strategy planning report using intelligent temperature control technology and generates a temperature control optimization report.

[0102] The humidity adjustment submodule adjusts humidity settings based on the temperature control optimization report using an adaptive feedback control method and generates an air conditioner adjustment strategy.

[0103] The environmental prediction submodule analyzes future environmental trends based on historical environmental data and trend information using a long short-term memory network algorithm and generates an environmental trend prediction report. The strategy formulation submodule considers multiple factors, including energy consumption, user demand, and environmental changes, and uses a genetic optimization algorithm to formulate adjustment strategies and generate an adjustment strategy planning report. The temperature control optimization submodule optimizes temperature control logic based on the adjustment strategy planning report using intelligent temperature control technology and generates a temperature control optimization report, including temperature set values and optimization results of adjustment logic. The humidity adjustment submodule adjusts humidity settings based on the temperature control optimization report using an adaptive feedback control method and generates an air conditioner adjustment strategy, ensuring that the air conditioning system can automatically adjust according to environmental prediction, strategy formulation, and intelligent control logic in different situations to provide appropriate temperature and humidity control while considering energy efficiency and user demand, achieving intelligent air conditioning management.

[0104] Referring to Figure 6 , the energy management module includes an energy monitoring submodule, a resource allocation submodule, an efficiency optimization submodule, and a cost analysis submodule;

[0105] The energy monitoring submodule monitors the flow and consumption of various energies based on the air conditioning adjustment strategy using real-time data monitoring technology, and generates an energy usage analysis report describing the energy consumption patterns and trends.

[0106] The resource allocation submodule determines the appropriate allocation of resources based on the energy usage analysis report using linear programming and constraint optimization techniques to meet system demands and ensure efficient use of resources.

[0107] The efficiency optimization submodule evaluates the efficiency of energy usage based on the resource allocation optimization report using system dynamic simulation and performance analysis methods, and proposes improvement measures to generate an energy efficiency optimization report describing efficiency improvement opportunities and expected effects.

[0108] The cost analysis submodule conducts cost-benefit analysis based on the energy efficiency optimization report to evaluate the economic effects of energy-saving measures, including the trade-off between costs and energy-saving benefits, to generate an energy management plan.

[0109] The energy monitoring submodule monitors the flow and consumption of various energies based on the air conditioning adjustment strategy using real-time data monitoring technology, and generates an energy usage analysis report describing the energy consumption patterns and trends.

[0110] Referring to Figure 7 , the user behavior recognition module includes an activity recognition submodule, a habit analysis submodule, a demand prediction submodule, and a personalized recommendation submodule.

[0111] The activity recognition submodule identifies activity patterns based on the energy management plan and environmental data report using time series analysis to generate a user activity pattern report.

[0112] The habit analysis submodule analyzes user habits based on the user activity pattern report using clustering algorithms to generate a user habit analysis report.

[0113] The demand prediction submodule predicts future user demands and preferences based on the user habit analysis report using a logistic regression model to generate a user demand prediction report.

[0114] The personalized recommendation submodule provides energy-saving recommendations based on user demand prediction reports using collaborative filtering recommendation algorithms and generates user behavior analysis reports.

[0115] The activity recognition submodule identifies user activity patterns based on energy management plans and environmental data reports using time series analysis methods to understand the types of activities users engage in during different time periods. The habit analysis submodule analyzes user habits based on user activity pattern reports using clustering algorithms to divide users into different habit groups and identify their similar behavior patterns. The demand prediction submodule predicts future user needs and preferences based on user habit analysis reports using logistic regression models, taking into account user activity patterns, habits, and environmental changes. The personalized recommendation submodule provides personalized energy-saving recommendations based on user demand prediction reports using collaborative filtering recommendation algorithms, combining user needs and preferences to generate personalized energy-saving recommendations to improve user comfort and reduce energy consumption. This process helps achieve intelligent energy management, provides personalized user experiences, and supports other modules with important user behavior data, promoting system collaboration and optimization.

[0116] Please refer to Figure 8 , the maintenance optimization module includes a fault prediction submodule, a maintenance plan submodule, a performance monitoring submodule, and a maintenance log submodule.

[0117] The fault prediction submodule analyzes data for fault trends based on user behavior analysis reports using multilayer perceptron neural networks and generates fault prediction reports.

[0118] The maintenance plan submodule develops maintenance strategies and plans based on fault prediction reports using linear programming methods and generates maintenance strategy and plan reports.

[0119] The performance monitoring submodule monitors running states based on maintenance strategy and plan reports using data analysis techniques and generates performance monitoring reports.

[0120] The maintenance log submodule records running and maintenance activities based on performance monitoring reports using log analysis techniques and generates maintenance plans.

[0121] The fault prediction submodule uses a multi-layer perceptron neural network to analyze system operation data based on user behavior analysis reports to identify fault types and occurrence times. The maintenance planning submodule uses linear programming to develop maintenance strategies and plans, including task and time scheduling, based on fault prediction reports. The performance monitoring submodule uses data analysis techniques to continuously monitor system performance based on maintenance strategy and plan reports, generating performance monitoring reports including performance data and anomaly alerts. The maintenance log submodule uses log analysis techniques to record information about operation and maintenance activities, including maintenance activities, fault repairs, and component replacement records, to provide a basis for subsequent audits and analyses, helping to improve system reliability and maintainability, reduce maintenance costs and system downtime, and ensure system stability and long-term performance. This also provides important historical records and experience accumulation for future maintenance activities.

[0122] Please refer to Figure 9 The context-aware adjustment module includes an environment adaptation submodule, a user preference submodule, an intelligent adjustment submodule, and a comfort monitoring submodule.

[0123] The environment adaptation submodule uses an adaptive neuro-fuzzy inference system to analyze environmental data and adjust air conditioning parameters based on maintenance plans and air conditioning adjustment strategies, generating an environment adaptability adjustment report.

[0124] The user preference submodule uses a K-means clustering algorithm to refine user behavior patterns based on the environment adaptability adjustment report, generating a user preference analysis report.

[0125] The intelligent adjustment submodule uses a particle swarm optimization algorithm to optimize air conditioning settings based on the user preference analysis report, generating an intelligent adjustment strategy report.

[0126] The comfort monitoring submodule uses an environmental quality evaluation model to continuously monitor and evaluate air conditioning adjustment effects based on the intelligent adjustment strategy report, generating context adjustment results.

[0127] The environment adaptation submodule analyzes environmental data and intelligently adjusts air conditioning parameters based on the maintenance plan and air conditioning adjustment strategy using an adaptive neuro-fuzzy inference system, generates an environment adaptation adjustment report to adapt to different situational needs, and the user preference submodule analyzes user behavior patterns based on the environment adaptation adjustment report using a K-means clustering algorithm, identifies the behavior characteristics and preferences of user groups, generates a user preference analysis report, and the intelligent adjustment submodule optimizes air conditioning settings based on the user preference analysis report using a particle swarm optimization algorithm, generates an intelligent adjustment strategy report to meet user needs and improve comfort, and the comfort monitoring submodule continuously monitors and evaluates air conditioning adjustment effects based on the intelligent adjustment strategy report using an environmental quality evaluation model, generates a situational adjustment result report to ensure that the system provides appropriate temperature and humidity settings in different situations, enhances user satisfaction, helps achieve intelligent environmental adjustment, improves user comfort, and reduces energy consumption to achieve the goal of intelligent environmental management.

[0128] Please refer to Figure 10 The power control method for the combined air conditioning unit based on artificial intelligence is executed based on the above-mentioned power control system for the combined air conditioning unit based on artificial intelligence, including the following steps:

[0129] S1: Based on environmental sensor data, real-time monitoring and analysis are performed using a Kalman filter algorithm to generate an environmental data report;

[0130] S2: Based on the environmental data report, a support vector machine algorithm is used for pattern recognition and anomaly analysis to generate an anomaly pattern analysis report;

[0131] S3: Based on the anomaly pattern analysis report, a long short-term memory network algorithm is used to predict environmental change trends to generate an environmental trend prediction report;

[0132] S4: Based on the environmental trend prediction report, a genetic optimization algorithm is used to develop an air conditioning adjustment strategy to generate an air conditioning adjustment strategy;

[0133] S5: Based on the air conditioning adjustment strategy, a dynamic programming algorithm is used to optimize energy use to generate an energy management plan;

[0134] S6: Based on the energy management plan and environmental data report, a decision tree algorithm is used to analyze user behavior to generate a user behavior analysis report;

[0135] S7: Based on the user behavior analysis report, a multilayer perceptron neural network is used for fault trend analysis and maintenance plan development to generate a maintenance plan;

[0136] S8: Based on the maintenance plan and air conditioning adjustment strategy, an adaptive neuro-fuzzy inference system is used for environmental adaptability analysis and adjustment of air conditioning settings, and an environmental adaptability adjustment scheme is generated.

[0137] S9: Based on the environmental adaptability adjustment scheme, an environmental quality evaluation model is used for system performance monitoring, and a system performance report is generated.

[0138] The environmental adaptability adjustment scheme specifically refers to the automatic adjustment of air conditioning settings according to environmental changes and user needs, and the system performance report specifically refers to a comprehensive evaluation report of air conditioning adjustment effects and environmental comfort.

[0139] This method ensures that the system can adaptively adjust according to the current environmental conditions through real-time monitoring of environmental parameters and the use of Kalman filtering algorithm, which makes the system more effective in controlling temperature and humidity, reduces energy costs, and reduces carbon emissions. Based on the support vector machine algorithm for data pattern recognition and anomaly analysis, the system can quickly identify and solve problems, improving the stability and reliability of the system, which helps to reduce system failures and downtime, improve system efficiency, and reduce maintenance costs. The long short-term memory network algorithm is used for environmental prediction, and the genetic algorithm is used to develop adjustment strategies, further optimizing energy use. The system can achieve appropriate performance under different environmental conditions, improving overall efficiency. By analyzing user behavior through the decision tree algorithm, the system can evaluate user habits and predict needs, reducing user operation burden and improving user experience. The maintenance optimization module performs fault trend analysis and maintenance plan development based on user behavior analysis reports and artificial neural networks, which enables the system to more accurately predict faults, plan maintenance time, and reduce maintenance costs and system downtime. The context-aware adjustment module ensures that the air conditioning system provides appropriate temperature and humidity settings in different contexts through adaptive neuro-fuzzy inference system for environmental adaptability analysis, improving user satisfaction.

[0140] The above is only a preferred embodiment of the present application, and does not limit the form of the present application. Any skilled person in the art can modify or change the above disclosed technical content to equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification of the above embodiments without departing from the technical solution content of the present application, according to the technical essence of the present application, still belongs to the protection scope of the technical solution of the present application.

Claims

1. An air conditioning unit power control system based on artificial intelligence, characterized in that: The system comprises an environment monitoring module, a data analysis module, a prediction and regulation module, an energy management module, a user behavior recognition module, a maintenance optimization module, and a context-aware adjustment module; The environment monitoring module performs real-time monitoring and analysis of environmental parameters based on sensor data using a Kalman filtering algorithm, and performs data aggregation to generate an environmental data report; The data analysis module performs data pattern recognition and anomaly analysis based on the environmental data report using a support vector machine algorithm, and generates an anomaly pattern analysis report; The prediction and regulation module performs environmental prediction based on the anomaly pattern analysis report using a long short-term memory network algorithm, and formulates adjustment strategies through a genetic algorithm to generate an air conditioner adjustment strategy; The energy management module optimizes energy use based on the air conditioner adjustment strategy using a dynamic programming algorithm, and performs energy consumption evaluation to generate an energy management plan; The user behavior recognition module evaluates user habits and predicts demand based on the energy management plan and environmental data report using a decision tree algorithm to generate a user behavior analysis report; The maintenance optimization module performs fault prediction analysis and maintenance plan formulation using an artificial neural network based on the user behavior analysis report to generate a maintenance plan; The context-aware adjustment module performs environmental adaptability analysis and adjusts air conditioner settings using cognitive computing technology based on the maintenance plan and air conditioner adjustment strategy to generate a context adjustment result; The environmental data report is specifically a temperature, humidity, light intensity, and air quality index report, the anomaly pattern analysis report includes environmental change trends and anomaly pattern recognition, the air conditioner adjustment strategy is specifically adaptive adjustment instructions for air conditioner temperature and humidity, the energy management plan includes energy distribution, efficiency improvement, and cost control solutions, the user behavior analysis report is specifically a user activity pattern, temperature and humidity preference, and energy use habit report, and the maintenance plan includes fault warning, maintenance time planning, and performance monitoring solutions, and the context adjustment result is specifically air conditioner settings automatically adjusted according to environmental changes and user demand. 2.The AI-based combined air conditioning package unit power consumption control system of claim 1, wherein: The environment monitoring module comprises a temperature monitoring submodule, a humidity monitoring submodule, a light monitoring submodule, and an air quality monitoring submodule; The temperature monitoring submodule performs real-time temperature monitoring using a Kalman filtering algorithm based on sensor data to generate a temperature monitoring report; The humidity monitoring submodule analyzes the relationship between temperature and humidity using a dew point measurement method based on the temperature monitoring report to generate a humidity monitoring report; The light monitoring submodule evaluates environmental light conditions using photoelectric sensing technology based on the humidity monitoring report to generate a light intensity report; The air quality monitoring submodule evaluates air quality using gas component analysis technology based on the light intensity report to generate an environmental data report. 3.The AI-based combined air conditioning package unit power consumption control system of claim 2, wherein: The data analysis module comprises a trend analysis submodule, an anomaly detection submodule, a data fusion submodule, and a report generation submodule; The trend analysis submodule analyzes long-term trends in data using a moving average method and linear regression analysis based on the environmental data report to generate a trend analysis report; The anomaly detection submodule generates an anomaly pattern recognition report by using a support vector machine algorithm based on a trend analysis report to identify data outliers. The data fusion submodule generates a comprehensive data report by using principal component analysis and ensemble learning methods to fuse multi-dimensional data based on the anomaly pattern recognition report. The report generation submodule generates an anomaly pattern analysis report by using an automatic report generation tool to integrate analysis results based on the comprehensive data report. 4.The AI-based combined air conditioning package unit power consumption control system of claim 3, wherein: The prediction control module includes an environment prediction submodule, a policy formulation submodule, a temperature control optimization submodule, and a humidity adjustment submodule. The environment prediction submodule generates an environment trend prediction report by using a long short-term memory network algorithm to analyze future environmental trends based on the anomaly pattern analysis report. The policy formulation submodule generates an adjustment strategy planning report by using a genetic optimization algorithm to formulate adjustment strategies based on the environment trend prediction report. The temperature control optimization submodule generates a temperature control optimization report by using intelligent temperature control technology to optimize temperature adjustment logic based on the adjustment strategy planning report. The humidity adjustment submodule generates an air conditioner adjustment strategy by using an adaptive feedback control method to adjust humidity settings based on the temperature control optimization report. 5.The AI-based combined air conditioning package unit power consumption control system of claim 4, wherein: The energy management module includes an energy monitoring submodule, a resource allocation submodule, an efficiency optimization submodule, and a cost analysis submodule. The energy monitoring submodule generates an energy use analysis report by using real-time data monitoring technology to monitor energy flow and consumption based on the air conditioner adjustment strategy. The resource allocation submodule generates a resource allocation optimization report by using linear programming and constraint optimization techniques based on the energy use analysis report. The efficiency optimization submodule generates an energy efficiency optimization report by using system dynamic simulation and performance analysis methods based on the resource optimization allocation report. The cost analysis submodule generates an energy management plan by using cost-benefit analysis to evaluate the economic effects of energy-saving measures based on the energy efficiency optimization report. 6.The AI-based combined air conditioning unit power consumption control system of claim 5, wherein: The user behavior recognition module includes an activity recognition submodule, a habit analysis submodule, a demand prediction submodule, and a personalized recommendation submodule. The activity recognition submodule generates a user activity pattern report by using time series analysis to identify activity patterns based on the energy management plan and environmental data report. The habit analysis submodule generates a user habit analysis report by using clustering algorithms to analyze user habits based on the user activity pattern report. The demand prediction submodule generates a user demand prediction report by using a logistic regression model to predict users' future needs and preferences based on the user habit analysis report. The personalized recommendation submodule generates a user behavior analysis report by using a collaborative filtering recommendation algorithm to provide energy-saving recommendations based on the user demand prediction report. 7.The AI-based combined air conditioning unit power consumption control system of claim 6, wherein: The maintenance optimization module includes a fault prediction submodule, a maintenance plan submodule, a performance monitoring submodule, and a maintenance log submodule. The fault prediction submodule generates a fault prediction report by using a multilayer perceptron neural network to analyze data for fault trends based on the user behavior analysis report. The maintenance plan submodule formulates maintenance strategies and plans based on the failure prediction report using a linear programming method, and generates a maintenance strategy plan report; The performance monitoring submodule performs operational status monitoring based on the maintenance strategy plan report using data analysis techniques, and generates a performance monitoring report; The maintenance log submodule records running and maintenance activities based on the performance monitoring report using log analysis techniques, and generates a maintenance plan. 8.The AI-based combined air conditioning unit power consumption control system of claim 7, wherein: The context-aware adjustment module includes an environmental adaptation submodule, a user preference submodule, an intelligent adjustment submodule, and a comfort level monitoring submodule; The environmental adaptation submodule analyzes environmental data and adjusts air conditioner parameters based on the maintenance plan and air conditioner adjustment strategies using an adaptive neuro-fuzzy inference system, and generates an environmental adaptability adjustment report; The user preference submodule refines user behavior patterns based on the environmental adaptability adjustment report using a K-means clustering algorithm, and generates a user preference analysis report; The intelligent adjustment submodule optimizes air conditioner settings based on the user preference analysis report using a particle swarm optimization algorithm, and generates an intelligent adjustment strategy report; The comfort level monitoring submodule continuously monitors and evaluates air conditioner adjustment effects based on the intelligent adjustment strategy report using an environmental quality evaluation model, and generates a context adjustment result.

9. The method for controlling the power consumption of an air conditioning unit based on artificial intelligence, characterized in that, The artificial intelligence-based combined air conditioning unit power control system according to any one of claims 1-8, comprising the following steps: Based on environmental sensor data, real-time monitoring and analysis are performed using a Kalman filter algorithm to generate an environmental data report; Based on the environmental data report, pattern recognition and anomaly analysis are performed using a support vector machine algorithm to generate an abnormal pattern analysis report; Based on the abnormal pattern analysis report, environmental change trends are predicted using a long short-term memory network algorithm to generate an environmental trend prediction report; Based on the environmental trend prediction report, air conditioner adjustment strategies are formulated using a genetic optimization algorithm to generate an air conditioner adjustment strategy; Based on the air conditioner adjustment strategy, energy use is optimized using a dynamic programming algorithm to generate an energy management plan; Based on the energy management plan and environmental data report, user behavior is analyzed using a decision tree algorithm to generate a user behavior analysis report; Based on the user behavior analysis report, fault trend analysis and maintenance planning are performed using a multilayer perceptron neural network to generate a maintenance plan; Based on the maintenance plan and air conditioner adjustment strategy, environmental adaptability analysis and air conditioner setting adjustment are performed using an adaptive neuro-fuzzy inference system to generate an environmental adaptability adjustment scheme; Based on the environmental adaptability adjustment scheme, system performance monitoring is performed using an environmental quality evaluation model to generate a system performance report. 10.The AI-based electric power control method for a packaged air conditioning unit according to claim 9, characterized by: The environmental adaptability adjustment scheme specifically refers to automatic adjustment of air conditioner settings according to environmental changes and user needs, and the system performance report specifically refers to a comprehensive evaluation report of air conditioner adjustment effects and environmental comfort levels.

Images