A New Evaluation Approach to Mechanical Kinematic Concept Using Fuzzy Neural Network

Jian De Wu

doi:10.4028/www.scientific.net/AMR.421.666

Paper Titles

Situation Analysis about Cold-Chain Logistics in China Based on SWOT Analysis
p.644

Hydrodynamic Integrated Optimization of Two-D Hydrofoil Based on Kriging Model
p.651

Reliability Research in Design Stage of CNC System
p.657

An Damping Analysis on Local Vibration in Foundation of ‘four in one’ Nitric Acid Plant
p.661

A New Evaluation Approach to Mechanical Kinematic Concept Using Fuzzy Neural Network
p.666

The Application of Car’s Parting Lines in Optimizing Car Styling & Assembly Process
p.670

Gas Analysis Based on Piezoelectric Sensor Array
p.674

Research on Concept System of Translation Symmetry in Mechanical Systems
p.679

An Intake Three-Pipeline Model Using Experimental Optimization for a Small Engine
p.683

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 421A New Evaluation Approach to Mechanical Kinematic...

A New Evaluation Approach to Mechanical Kinematic Concept Using Fuzzy Neural Network

Abstract:

In this paper, BP network is applied to structure multi-level evaluation model to implement evaluation for the kinematic concepts acquired by function analysis. Under this approach, the best concept can be selected once evaluation indicators of each candidate are fuzzily quantified, converted into evaluation attribute value, and fed into the trained network model. During the process, neural network is used to solve the bottle-neck problem of knowledge acquiring and expression, which can be viewed as knowledge base and reasoning engine for the evaluation. At the same time, it is effective in solving the problem of weight distribution in evaluation indicator system. Fuzzy logic is used to achieve the fuzzy quantization for the attribute value of evaluation indicator in evaluation system, which can be used as the I/O value for neural network.