Air Conditioning Abnormality Detection Using Trained Inference Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of detecting abnormalities in air conditioning systems is compromised when a common threshold value is used across varying operating environments, leading to inconsistent detection performance.
Innovation Solution
A system and method that utilizes a learning device to train an inference model using operation data from normal periods, allowing for the inference of normal values and subsequent determination of abnormalities based on specific parameters, adapting to the unique characteristics of each environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a common threshold value is used for abnormality detection regardless of operating environment, then the detection method is simple and easy to implement, but the accuracy of abnormality detection decreases
Solution Approach 1:
The patent changes the threshold parameter dynamically based on operating conditions. Instead of using a fixed threshold value, the system adjusts the threshold according to operating frequency and other environmental parameters, allowing accurate detection across varying operating environments while maintaining reasonable system complexity
Solution Approach 2:
The patent implements dynamic threshold adjustment by continuously monitoring operating conditions and adapting the threshold value accordingly. The determination threshold is made variable rather than fixed, enabling the system to respond to changing operating environments and maintain high detection accuracy throughout different operational phases
2Measurement precision
If environment-specific trained models are used for abnormality detection, then the detection accuracy is improved, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent performs preliminary training of the determination model using historical operation data before actual abnormality detection begins. By pre-training the model with normal operation patterns during the first N operation periods, the system establishes a baseline for comparison, reducing the need for extensive real-time data processing and enabling accurate detection from the (N+1)-th period onward
Solution Approach 2:
The patent uses a sufficient but not excessive amount of training data by limiting training to the first N operation periods. This partial action approach provides enough data to train an accurate model without requiring unlimited historical data, balancing detection accuracy with practical data availability and processing constraints
Data Source
AI summary
A learning device trains an inference model to be a trained inference model using training data, the inference model being a model that infers a normal value of a specific parameter of an air conditioning system from operation data of the air conditioning system acquired in an operation period for which the air conditioning system is normal, of continuous first to N-th operation periods (N is the natural number), the training data including the operation data of the air conditioning system. An inference device, using the inference model, infers the normal value from operation data of the air conditioning system acquired in a (N+1)-th operation period. A determination device determines whether the air conditioning system in the (N+1)-th operation period is abnormal, based on comparison between the normal value and the specific parameter in the (N+1)-th operation period.