Response surface optimization of an artificial neural network for predicting the size of re-assembled casein micelles

2009 ◽  
Vol 68 (2) ◽  
pp. 216-221 ◽  
Author(s):  
Ashkan Madadlou ◽  
Zahra Emam-Djomeh ◽  
Mohamad Ebrahimzadeh Mousavi ◽  
Mohamadreza Ehsani ◽  
Majid Javanmard ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface ◽  
Casein Micelles ◽  
Response Surface Optimization ◽  
Artificial Neural ◽  
Surface Optimization

Artificial Neural Network and Metaheuristic Strategies

2011 ◽  
pp. 366-397 ◽  
Author(s):  
Indrajit Mukherjee ◽  
Pradip Kumar Ray
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface ◽  
Nonlinear Response ◽  
Metal Cutting ◽  
Surface Model ◽  
Response Surface Optimization ◽  
Artificial Neural ◽  
Cutting Processes ◽  
Solution Methodology

Application of optimization tools and techniques is necessary and an essential requirement for any metal cutting-based manufacturing unit to respond effectively to severe competitiveness and increasing demand of quality product in the global market. However, both problem types and techniques employed are diverse. Often the context of the problem involves building nonlinear inferential response surface model(s) of the process(s), and then determine levels of inputs and in-process parameters that result in best (or significantly improved than existing) measures of process quality improvement and effectiveness. Selecting the appropriate levels or settings of inputs and in-process variables is a typical example of desired process effectiveness. However, determination of optimal process conditions, using appropriate solution methodology through cost-effective inferential nonlinear response surface model(s) is a challenging and continual research endeavour for researchers and practitioners. In this context, artificial neural network (ANN) and metaheuristic strategies, such as genetic algorithm (GA), simulated annealing (SA), and tabu search (TS), either in its original form or its variant, has been shown to yield promising outcomes for solving nonlinear response surface optimization problems in metal cutting process(s). The goal of this chapter is to assess the status and scope of artificial neural network-based inferential model, GA, SA, and TS-based metaheuristic search stategies in metal cutting processes. Subsequently, a solution methodology for nonlinear response surface optimization in metal cutting processes is proposed for the benefits of selection of an appropriate technique. Specific application in a multiple response grinding process optimization problem using ANN, realvalued genetic algorithm, simulated annealing, and a modified tabu search is also provided for a clearer understanding of the settings, where the proposed methodology is being used.

Wear volume prediction of AISI H13 die steel using response surface methodology and artificial neural network

2020 ◽  
Vol 14 (2) ◽  
pp. 6789-6800
Author(s):  
Vishal Jagota ◽  
Rajesh Kumar Sharma
Keyword(s):  
Neural Network ◽  
Heat Treatment ◽  
Artificial Neural Network ◽  
Response Surface ◽  
Sliding Wear ◽  
Austenitizing Temperature ◽  
Tempering Temperature ◽  
Die Steel ◽  
Artificial Neural ◽  
Tempering Time

Resistance to wear of hot die steel is dependent on its mechanical properties governed by the microstructure. The required properties for given application of hot die steel can be obtained with control the microstructure by heat treatment parameters. In the present paper impact of different heat treatment parameters like austenitizing temperature, tempering time, tempering temperature is studied using response surface methodology (RSM) and artificial neural network (ANN) to predict sliding wear of H13 hot die steel. After heat treating samples at austenitizing temperature of 1020°C, 1040°C and 1060°C; tempering temperature 540°C, 560°C and 580°C; tempering time 1hour, 2hours and 3hours, experimentation on pin-on-disc tribo-tester is done to measure the sliding wear of H13 die steel. Box-Behnken design is used to develop a regression model and analysis of variance technique is used to verify the adequacy of developed model in case of RSM. Whereas, multi-layer feed-forward backpropagation architecture with input layer, single hidden layer and an output layer is used in ANN. It was found that ANN proves to be a better tool to predict sliding wear with more accuracy. Correlation coefficient R2 of the artificial neural network model is 0.986 compared to R2 of 0.957 for RSM. However, impact of input parameter interactions can only be analysed using response surface method. In addition, sensitivity analysis is done to determine the heat treatment parameter exerting most influence on the wear resistance of H13 hot die steel and it showed that tempering time has maximum influence on wear volume, followed by tempering temperature and austenitizing temperature. The prediction models will help to estimate the variation in die lifetime by finding the amount of wear that will occur during use of hot die steel, if the heat treatment parameters are varied to achieve different properties.

Sign in / Sign up

Export Citation Format

Share Document