Serial MT Discriminators for Low-Load State Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
State identification devices using the Mahalanobis-Taguchi Method (MT method) face high computational load, requiring high-performance hardware resources, limiting the degree of freedom in designing hardware resources while maintaining high identification accuracy.
Innovation Solution
A state identification device employing a first and a second discriminator using the MT method, where the first discriminator determines a condition and either terminates the process or loops, and the second discriminator is connected in series, reducing computational load by avoiding high-load computations in subsequent stages, and allowing for flexible handling of extensive branching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple discriminators using MT method are connected in series to identify multiple abnormal states stepwise, then identification accuracy is improved, but computational load increases and hardware resources are consumed
Solution Approach 1:
The patent divides the identification process into multiple discriminators connected in series, where each discriminator handles a specific abnormal state. This segmentation allows the system to process different states independently, improving identification accuracy while enabling selective computation based on detected conditions
Solution Approach 2:
The patent implements conditional execution where discriminators are only activated when their specific conditions are met. This partial action approach avoids unnecessary computational load by not executing all discriminators in every cycle, while still maintaining the capability to identify multiple abnormal states when needed
2Measurement precision
If multiple discriminators using MT method are connected in series to identify multiple abnormal states stepwise, then identification accuracy is improved, but device complexity increases
Solution Approach 1:
The identification system is segmented into multiple independent discriminators, each responsible for a specific abnormal state. This modular architecture improves identification accuracy for different states while keeping each individual discriminator relatively simple, thus managing overall device complexity
Solution Approach 2:
Each discriminator is designed to be a universal module that can identify a specific abnormal state using the MT method. This multi-functionality approach allows the same basic discriminator structure to be reused for different states, reducing the need for completely separate hardware for each state and thereby managing device complexity
Data Source
AI summary
A state identification device, including a storage device coupled with a processor, the storage device storing a program executable by the processor to cause the state identification device to: obtain physical parameters from at least one detector monitoring a monitoring target; perform determination by a plurality of discriminators using the obtained physical parameters; and output an identification signal indicating whether the monitoring target is at a predetermined state based on the determination result. The discriminators includes: a first discriminator that terminates a process of the state identification device without starting the other discriminators and without outputting the identification signal, or causes an operation of the first discriminator to restart; and a second discriminator that is connected in series with the first discriminator and starts to operate after the first discriminator, and/or, terminates the process of the state identification device or cause an operation of the second discriminator to restart.