Programmable Fuzzy Controller Automatic Knowledge Base Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fuzzy controllers require expert knowledge for configuration and maintenance, limiting their adoption in industrial applications due to the need for manual development of membership functions and fuzzy rules, which is time-consuming and costly, and previous automation methods failed to fully address this issue.

Innovation Solution

A programmable fuzzy controller that uses an artificial potential field approach to automatically generate a fuzzy knowledge base, allowing for the direct interaction with processes through A/D and D/A converters, eliminating the need for expert knowledge by creating membership functions and fuzzy rules based on minimal input parameters such as minimum, maximum, equilibrium point, non-linearity, and control direction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual development of membership functions and fuzzy rules by experts is used, then the fuzzy controller can be configured with precise control logic, but the time consumption and cost increase significantly

Engineering Contradiction:

Improvecontrol logic precisionVSAvoidconfiguration time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs self-configuration by automatically generating membership functions and fuzzy rules from process data without requiring expert intervention. The controller analyzes historical process data, identifies patterns, and autonomously creates the fuzzy knowledge base, eliminating the time-consuming manual configuration while maintaining control precision.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual expert system is replaced with an automated data-driven system. Instead of relying on human experts to manually create fuzzy rules, the system uses computational algorithms to automatically generate the fuzzy knowledge base from process data, substituting human cognitive work with automated computational processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual configuration by fuzzy logic experts is required, then the fuzzy controller can be properly tuned, but the scarcity and high cost of trained professionals limits adoption

Engineering Contradiction:

Improvecontroller tuning qualityVSAvoiddeployment accessibility

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The controller performs self-tuning by automatically generating its own fuzzy knowledge base from process data. This eliminates the dependency on external experts for controller configuration and deployment, making the technology accessible to organizations without access to trained fuzzy logic professionals while maintaining tuning quality through data-driven optimization.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

Process data serves as an intermediary between the physical process and the fuzzy controller configuration. Instead of requiring expert knowledge as the intermediary, the system uses actual process data to automatically generate appropriate fuzzy rules and membership functions, bridging the gap between process behavior and control logic without human intervention.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If automatic learning systems like Neural Networks are used instead of fuzzy controllers, then expert knowledge is not required, but the interpretability and adaptability of the control system decreases

Engineering Contradiction:

Improveconfiguration automationVSAvoidsystem interpretability

Core Design Contradiction:

Extent of automationVSAdaptability or versatility

Solution Approach 1:

The system generates different types of membership functions for different variables based on their specific characteristics. Each variable receives a customized membership function structure optimized for its local requirements while maintaining overall system interpretability. This localized optimization allows automatic generation to achieve both automation and adaptability.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system automatically adjusts membership function parameters such as width, shape, and position based on process data analysis. This dynamic parameter optimization enables the controller to adapt to different process conditions and requirements while maintaining interpretability through the use of standard fuzzy logic structures that can be understood and modified if needed.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10838376B2Method of generating fuzzy knowledge base for a programmable fuzzy controller

Publication Date: 2020.11.17 I SYST AUTOMACAO IND SA

AI summary

A method of generating the knowledge base used for a programmable fuzzy controller comprising the steps of determining the relevant input and output variables to be controlled; creating artificial potential fields for each of said variables; sampling each of said potential fields in order to generate fuzzy membership functions; compiling said fuzzy membership functions into fuzzy sets; and mapping inputs fuzzy set to output fuzzy sets through a rule base. The relevant input and output variables are including: minimum, maximum, and equilibrium values; an importance weight; a non-linearity value; a control direction; and information as to whether said variable is an input or output variable. Further provided is a programmable fuzzy controller whose fuzzy knowledge base is obtained by the method described.