Machine learning-based air handler and control method thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional air handlers using HEPA filters face reduced efficiency due to clogged pores, while electrostatic precipitators generate ozone and require high voltage, leading to increased costs and safety risks, and fail to optimize operation based on varying air characteristics in different spaces.
Innovation Solution
A machine learning-based air handler that ionizes pollutants using low-energy electromagnetic waves, allowing for efficient collection of both positively and negatively charged particles without generating ozone, and adjusts its operation based on real-time air quality data to minimize power consumption and optimize performance for specific environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If electrostatic precipitation method is used to remove pollutants without differential pressure, then dust collection efficiency is improved, but ozone is generated as a harmful byproduct
Solution Approach 1:
The patent replaces the traditional electrostatic precipitation method (which uses high voltage to generate plasma and ions) with a mechanical filtration system using HEPA filters. This substitution eliminates ozone generation while maintaining dust collection efficiency through physical filtration rather than electrical charging.
Solution Approach 2:
The patent employs replaceable HEPA filters that can be periodically replaced. These filters are designed to be cost-effective and disposable, allowing the system to maintain high dust collection efficiency without the harmful byproducts of electrostatic precipitation, as the filters are replaced before becoming clogged and ineffective.
2Productivity
If high voltage is applied to the charging part to generate plasma, then pollutant particles are charged and collected efficiently, but facility and operating costs increase
Solution Approach 1:
The patent replaces the high-voltage electrostatic charging system with a low-energy mechanical filtration system using HEPA filters. This eliminates the need for high voltage application, thereby reducing facility and operating costs while maintaining pollutant collection efficiency through physical filtration mechanisms.
Solution Approach 2:
The patent uses affordable, replaceable HEPA filters instead of expensive high-voltage electrostatic precipitation systems. The filters are designed to be cost-effective replacements that maintain collection efficiency without the high energy costs associated with generating and maintaining high voltage plasma.
3Device complexity
If the air handler operates on the same basis regardless of space characteristics, then device complexity is reduced, but power consumption increases due to unnecessary operation
Solution Approach 1:
The patent implements dynamic operation control where the air handler adjusts its operation based on real-time air quality conditions and space characteristics. Sensors detect pollutants and trigger air handler operation only when needed, and the system adapts its runtime and intensity based on the specific environment, optimizing power consumption without increasing operational complexity.
Solution Approach 2:
The patent incorporates feedback mechanisms through air quality sensors that continuously monitor the environment and provide information to the control system. This feedback enables the air handler to operate selectively based on actual air quality conditions rather than continuous operation, reducing unnecessary power consumption while maintaining simple user-facing operation.
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 solution achieves high dust collection efficiency with minimal power consumption, maintains ion balance, and prevents ozone generation, optimizing air purification based on the characteristics of the space it is installed in.
Implementation Method 1
ionizes pollutants using low-energy electromagnetic waves
Implementation Method 2
The negatively charged dust particles may be removed by moving and clinging to a positively charged dust collecting plate by electrostatic attraction
Data Source
AI summary
Disclosed is a machine learning-based air handler and a control method thereof, the control method including collecting first data on an air quality of air flowing into the air handler, controlling a purification part based on the first data, collecting second data on an air quality of air passing through the purification part, and controlling the purification part according to a machine-learning model generated based on a setting value related to a control of the purification part, the first data, and the second data.