Air-conditioner based on parameter learning using artificial intelligence, cloud server, and method of operating and controlling thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional air conditioner operation modes, such as rapid and comfortable modes, do not dynamically reflect changes in external temperature, humidity, and occupancy, leading to suboptimal performance and energy inefficiency.
Innovation Solution
An air conditioner system that includes a parameter generating unit, a learning unit, and an operation mode control unit, which use generated parameters to determine and adjust operation modes based on learning processes, either internally within the air conditioner or through a cloud server, to optimize energy usage and comfort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional operation modes (rapid and comfortable modes) are used, then the air conditioner can provide basic cooling functions, but the operation cannot dynamically reflect changes in external temperature, humidity, and occupancy, leading to suboptimal performance
Solution Approach 1:
The patent implements feedback mechanisms by collecting operational data from multiple indoor units and using learning algorithms to dynamically adjust operation modes. The system continuously monitors environmental parameters and occupancy changes, then feeds this information back to optimize cooling performance in real-time, resolving the contradiction between adaptability and system complexity.
Solution Approach 2:
The air conditioner system performs self-optimization through automated learning processes that analyze operational data and adjust modes without requiring manual intervention. The system serves itself by automatically adapting to environmental changes and occupancy patterns, improving versatility while maintaining manageable complexity through autonomous decision-making.
2Speed
If the air conditioner operates in rapid mode with maximum cooling capacity, then the cooling speed is fast, but the energy consumption is high
Solution Approach 1:
The patent applies dynamics by transitioning from static operation modes to dynamic mode switching based on real-time learning outcomes. The system dynamically adjusts between rapid and comfortable modes according to learned patterns of environmental changes and occupancy, optimizing the balance between cooling speed and energy consumption rather than relying on fixed modes.
Solution Approach 2:
The system changes operational parameters dynamically by adjusting cooling capacity, fan speeds, and mode selection based on learned environmental conditions. Rather than maintaining constant maximum capacity, the system modifies parameters in response to predicted occupancy and environmental changes, reducing energy consumption while maintaining effective cooling speed when needed.
3Use of energy by moving object
If the air conditioner operates in comfortable mode with reduced cooling output, then the energy consumption is lower, but the system cannot respond quickly to sudden environmental changes or occupancy increases
Solution Approach 1:
The patent implements preliminary action by using learning algorithms to predict future occupancy patterns and environmental changes before they occur. The system proactively adjusts operation modes in advance based on learned patterns, ensuring reliable response to upcoming changes while maintaining energy efficiency during stable periods. This predictive capability allows the system to switch to rapid mode before occupancy increases or environmental conditions deteriorate.
4Productivity
If operation information from multiple indoor units is collected and analyzed, then the overall system performance can be optimized, but the data processing complexity and communication overhead increase
Solution Approach 1:
The patent merges data from multiple indoor units into a centralized learning system that analyzes aggregated information to optimize overall performance. By combining operational data across multiple units and applying learning algorithms centrally, the system achieves improved productivity through coordinated optimization while managing data processing complexity through unified analysis rather than distributed processing.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system efficiently switches between operation modes to maintain target temperatures with reduced electrical power consumption, adapting to changing environmental conditions and occupancy levels, thereby enhancing comfort and energy efficiency.
Implementation Method 1
an outdoor unit configured to supply compressed refrigerant to the indoor unit, such that the supplied refrigerant exchanges heat with the air before the air is discharged from the blowing unit
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to an air conditioner based on parameter learning using artificial intelligence, a cloud server, and a method of driving and controlling the air conditioner. According to an embodiment of the present invention, the air conditioner includes a parameter generating unit that generates one or more parameters in a rapid operation mode, and an operation mode control unit that controls a blowing unit or an outdoor unit based on operation mode information that sets a comfortable operation mode after the period operating in the rapid operation mode, and the rapid operation mode operates only within a preset time range, and a central control unit instructs an operation of switching to the comfortable operation mode to the operation mode control unit after the rapid operation mode.