Neuro-Fuzzy Controller Using Genetic Programming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing control systems require substantial training data and expert tuning, are complex, and cannot effectively combine decision-making methodologies to improve performance.
Innovation Solution
A neuro-fuzzy controller that uses a predictor, a fuzzy cluster module with a neural network-based fuzzifier and defuzzifier, and genetic programming to determine rules quickly without expert intervention, allowing for autonomous tuning and improved performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If neural networks and fuzzy logic are used to make decisions, then decision-making performance is improved, but system complexity and training requirements increase
Solution Approach 1:
The patent merges neural networks, fuzzy logic, and genetic programming into a unified neuro-fuzzy controller. This combination allows the system to leverage the strengths of each methodology (neural networks for learning, fuzzy logic for decision-making under uncertainty, genetic programming for rule generation) while providing a comprehensive solution that addresses the limitations of individual approaches.
Solution Approach 2:
The system employs genetic programming to automatically generate and tune fuzzy rules without requiring expert intervention. The neural network components self-adjust their parameters through learning from data, reducing the need for manual configuration and expert tuning while maintaining system performance.
2Reliability
If expert tuning is used to establish the system, then system performance is improved, but ease of operation deteriorates
Solution Approach 1:
The neuro-fuzzy controller performs self-tuning through genetic programming and neural network learning mechanisms. The system automatically generates fuzzy rules and adjusts parameters based on input data without requiring expert knowledge for configuration, making the system easier to operate while maintaining performance.
Solution Approach 2:
The system pre-generates fuzzy rules using genetic programming before operation begins. This preliminary rule generation allows the system to be ready for immediate use without requiring expert tuning during deployment, improving ease of operation while maintaining performance through pre-established rule sets.
3Reliability
If multiple decision-making methodologies are combined, then performance is improved, but device complexity increases
Solution Approach 1:
The patent integrates neural networks, fuzzy logic, and genetic programming into a cohesive neuro-fuzzy controller architecture. This merging allows multiple decision-making methodologies to work together synergistically, improving performance while managing complexity through a unified framework that leverages the complementary strengths of each approach.
Data Source
AI summary
A neuro-fuzzy controller is provided. The neuro-fuzzy controller includes a predictor that receives inputs and makes prediction inputs. The prediction inputs are passed to a fuzzy cluster module that includes a neural network fuzzifing said prediction inputs and passing the result to an inference engine. The output of the inference engine is defuzzified and provided as an output of the controller. The fuzzifier and defuzzifier preferably represent a neural network employing a trigonometrical series. The inference engine preferably employs rules that are determined using genetic programming.