Modeling and Control Techniques for Microstructure Development

2014 ◽  
Vol 541-542 ◽  
pp. 317-323
Author(s):  
R. Karthikeyan ◽  
R.K. Ganesh Ram ◽  
V. Kalaichelvi
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Logic Controller ◽  
True Stress ◽  
Microstructure Development ◽  
Modeling And Control ◽  
Control Techniques ◽  
Hot Compression Test ◽  
Strain Data ◽  
Sic Composites ◽  
And Control

True stress-strain data is obtained for 6061Al/ 10% SiC composites by hot compression test. Mathematical models for % volume of recrystallization and diameter of the recrystallized grains are developed with process parameters such as strain, strain rate and temperature. These models are applied for optimization of the grain size and % volume of recrystallization. An attempt has been made to control microstructure evolution during hot deformation using fuzzy logic controller through simulation in MATLAB software. The fuzzy logic controller parameters are tuned using genetic algorithm.

Fuzzy Logic in Hole Drilling of Composites

1994 ◽  
Author(s):  
Aditya Thadani ◽  
Athamaram H. Soni
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Logic Controller ◽  
Thrust Force ◽  
Cutting Speed ◽  
Research Data ◽  
Theoretical Research ◽  
Hole Drilling ◽  
Tool Geometry ◽  
Drilling Process ◽  
And Control

Abstract Experimental and theoretical research data was utilized in building a Fuzzy Logic Controller model applied to simulate the drilling process of composite materials. The objective is to have a better understanding and control of delamination of composites during the drilling process and at the same time to improve the hole finish by controlling fraying and splintering. By controlling the main issues in the drilling process such as feed rate, cutting speed, thrust force, and torque generated in addition to the tool geometry, it is possible to optimize the drilling process avoiding the conventionally encountered problems.

Artificial Neural Networks Used As a Rule Selector for Fuzzy Logic Controllers

1993 ◽  
Author(s):  
Shou-Heng Huang ◽  
Ron M. Nelson
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Logic Controller ◽  
Absolute Error ◽  
Operating Conditions ◽  
Delta Rule ◽  
Rule Sets ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Set Up ◽  
And Control

Abstract A feedforward, three-layer, partially-connected artificial neural network (ANN) is proposed to be used as a rule selector for a rule-based fuzzy logic controller. This will allow the controller to adapt to various control modes and operating conditions for different plants. A principal advantage of an ANN over a look up table is that the ANN can make good estimates to fill in for missing data. The control modes, operating conditions, and control rule sets are encoded into binary numbers as the inputs and outputs for the ANN. The General Delta Rule is used in the backpropagation learning process to update the ANN weights. The proposed ANN has a simple topological structure and results in a simple analysis and relatively easy implementation. The average square error and the maximal absolute error are used to judge if the correct connections between neurons are set up. Computer simulations are used to demonstrate the effectiveness of this ANN as a rule selector.

Sign in / Sign up

Export Citation Format

Share Document