Artificial intelligence air-conditioning control system and method using interpolation method
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional artificial intelligence air conditioning control systems face challenges in reducing learning time and convergence due to the need for extensive training data across a wide range of environmental conditions, leading to lengthy and costly data preparation and processing.
Innovation Solution
An AI air conditioning control system using interpolation, which includes input units for target and current performance factor information, an AI learning model unit trained on different environmental conditions, and an interpolation unit that generates final control values by applying real-time environmental conditions to an interpolation function, allowing for quick estimation of optimal control values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If training data is generated for all possible environmental conditions and target air conditioning settings, then output accuracy is improved, but learning time and data preparation cost increase significantly
Solution Approach 1:
The patent segments the continuous range of environmental conditions and target settings into discrete intervals (e.g., temperature ranges from -10°C to 30°C divided into multiple segments). Training data is generated only for these segmented intervals rather than all possible continuous values, reducing data volume while maintaining coverage of the full operating range.
Solution Approach 2:
The patent applies partial action by generating training data for only certain representative environmental conditions and target settings rather than exhaustively covering all possible scenarios. The system selectively trains on key intervals and uses interpolation to estimate outputs for intermediate values, avoiding the need to prepare data for every possible condition.
2Measurement precision
If training data is generated for all possible environmental conditions and target air conditioning settings, then output accuracy is improved, but data preparation cost increases significantly
Solution Approach 1:
The patent segments the continuous range of environmental conditions and target settings into discrete intervals (e.g., temperature ranges from -10°C to 30°C divided into multiple segments). Training data is generated only for these segmented intervals rather than all possible continuous values, reducing data volume while maintaining coverage of the full operating range.
Solution Approach 2:
The patent uses interpolation to create estimated output values for conditions not explicitly present in the training data. By copying and extrapolating patterns from trained intervals to untrained intervals, the system generates accurate predictions without requiring expensive data collection and processing for every possible scenario.
3Loss of time
If the AI model is trained with minimal data using interpolation, then learning time is reduced, but the ability to handle all environmental conditions may be compromised
Solution Approach 1:
The patent creates a universal AI model that can handle all environmental conditions through interpolation. The model trained on minimal representative data learns general patterns that can be universally applied across the entire range of environmental conditions and target settings, enabling the system to adapt to any condition within the defined intervals without requiring condition-specific training.
Solution Approach 2:
The patent introduces interpolation as an intermediary mechanism between the minimal training data and the full range of environmental conditions. The interpolation function acts as a mediator that bridges gaps in the training data, allowing the model to generate accurate predictions for conditions not explicitly present in the training set while maintaining versatility across all environmental scenarios.
Data Source
AI summary
The present invention relates to an artificial intelligence air conditioning control system and method using interpolation. The present invention provides an artificial intelligence air conditioning control system and method using interpolation that is capable of driving an optimal control value by estimating the desired air conditioning target value through interpolation on the output values resulted from training on only minimal air conditioning data.