Hidden Switch Fuzzy Inference Correction for Input Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hidden switches with pressure-sensing architecture face issues with poor functionality and failure due to changes in input conditions over time, as the fuzzy interval between maximum and minimum input values narrows, affecting the supervised algorithm's ability to accurately determine intentional presses.
Innovation Solution
A correction control method that dynamically adjusts the fuzzy inference system by rebuilding the membership function, setting maximum and minimum correction values, and adjusting the fuzzy intervals based on output values to maintain effective control, even as input conditions change, and notifies users when functionality fails.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a traditional fuzzy inference system with fixed membership function is used in a hidden switch, then the initial control functionality is established, but the fuzzy interval narrows over time due to input condition changes, leading to poor functionality and failure
Solution Approach 1:
The patent implements dynamic adjustment of the membership function parameters (a and b values) in the fuzzy inference system. Instead of using fixed initial values, the system continuously updates these parameters based on actual input data, allowing the fuzzy intervals to adapt to changing input conditions over time and preventing the narrowing issue that leads to failure
Solution Approach 2:
The patent employs feedback mechanisms where the system monitors the actual input values and usage patterns, then uses this information to correct and update the membership function parameters. This feedback loop ensures the fuzzy inference system maintains accurate fuzzy intervals despite drift in input conditions, thereby preserving reliability
2Adaptability or versatility
If the fuzzy interval range is increased to accommodate input variations, then adaptability improves, but the precision of distinguishing intentional presses from improper touches decreases
Solution Approach 1:
The patent dynamically adjusts the parameters (a and b) of the membership function based on actual input conditions. By changing these parameters adaptively, the system maintains optimal fuzzy interval ranges that balance adaptability and precision, rather than using fixed wide or narrow intervals
3Device complexity
If the supervised algorithm uses fixed initial fuzzy intervals, then the algorithm complexity is low, but the system fails when input conditions change over time
Solution Approach 1:
The patent implements a self-updating mechanism where the fuzzy inference system automatically adjusts its own membership function parameters based on observed input patterns. This self-service capability allows the system to maintain reliability without requiring complex external recalibration procedures or increasing overall algorithm complexity
Data Source
AI summary
A correction control method includes steps of rebuilding a fuzzy inference system, setting a maximum correction value and a minimum correction value, determining whether there is an output value to be outputted, deciding a intermediate correction value and determining whether a range of an interval between the maximum correction value and the intermediate correction value is enough to constitute the fuzzy interval of the membership function, allowing the correction unit to output the maximum correction value, the minimum correction value and the intermediate correction value, adjusting the fuzzy inference system, allowing the fuzzification unit to constitute the minimum correction value according to the output value, determining whether a range of an interval between the maximum correction value and the minimum correction value is enough to constitute the fuzzy interval, and notifying that functions of the fuzzy inference system are failed. The functionality of supervised algorithm of hidden switch is enhanced.