Method for predicting filter purifying efficiency and exchange time using machine learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is no effective method to predict the lifespan of air cleaner filters, leading to uncertain purifying efficiency and increased power consumption, as users lack information on when to exchange filters.
Innovation Solution
A method using machine learning, specifically an artificial neural network model, that predicts filter lifespan by combining indoor and outdoor fine dust concentration data with user history, determining exchange time and purifying efficiency, and transmitting this information to other devices for user notification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If filter exchange is performed based on fixed time intervals, then device complexity is reduced, but purifying efficiency deteriorates due to inaccurate lifespan prediction
Solution Approach 1:
The patent changes the parameter basis for filter exchange from fixed time intervals to dynamic predictions based on multiple factors including indoor/outdoor dust concentrations, user behavior patterns, and operational history. The machine learning model processes these varying parameters to determine optimal exchange timing, thereby maintaining purifying efficiency while providing actionable guidance to users.
2Loss of time
If filter exchange is delayed to extend usage time, then loss of time is reduced, but purifying efficiency deteriorates due to filter degradation
Solution Approach 1:
The system performs preliminary analysis by continuously monitoring dust concentrations, user behaviors, and filter performance metrics to predict the optimal exchange time in advance. This allows users to replace filters proactively before performance degradation occurs, maximizing usage time while maintaining purifying efficiency through data-driven timing.
3Measurement precision
If machine learning model uses multiple data sources including indoor and outdoor dust concentrations, then measurement precision of lifespan prediction is improved, but device complexity increases due to additional sensors and data processing
Solution Approach 1:
The patent merges multiple data sources including indoor dust concentration from onboard sensors, outdoor dust concentration from external APIs, user behavior patterns, and operational history into a unified machine learning model. This integration allows the system to comprehensively assess filter lifespan while leveraging existing smartphone sensors and free external services, thereby improving prediction accuracy without proportionally increasing complexity.
4Reliability
If filter exchange timing is precisely determined using machine learning, then purifying efficiency is improved, but loss of energy increases due to continued operation of air cleaner with degraded filter
Solution Approach 1:
The system implements feedback by continuously monitoring filter performance metrics and comparing them against predicted lifespan thresholds. When the filter approaches its optimal exchange point, the system provides timely notifications to users, enabling them to replace the filter before significant energy waste occurs due to degraded performance, thus balancing purifying efficiency with energy conservation.
Data Source
AI summary
Disclosed is a method of predicting the lifespan of a filter in an air cleaner based on machine learning. According to an embodiment of the present disclosure, a machine learning-based filter lifespan prediction method may more precisely predict the lifespan of a filter in an air cleaner by inputting fine dust concentration data and a history related to use of the air cleaner to a lifespan prediction model and determining the purifying efficiency and exchange time of the filter according to an output value. Intelligent air cleaner of the present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.