Indrajit Mukherjee

A review of optimization techniques in metal cutting processes

In todays rapidly changing scenario in manufacturing industries, applications of optimization techniques in metal cutting processes is essential for a manufacturing unit to respond effectively to severe competitiveness and increasing demand of quality product in the market. Optimization methods in metal cutting processes, considered to be a vital tool for continual improvement of output quality in products and processes include modelling of input-output and in-process parameters relationship and determination of optimal cutting conditions. However, determination of optimal cutting conditions through cost-effective mathematical models is a complex research endeavour, and over the years, the techniques of modelling and optimization have undergone substantial development and expansion. In this paper, the application potential of several modelling and optimization techniques in metal cutting processes, classified under several criteria, has been critically appraised, and a generic framework for parameter optimization in metal cutting processes is suggested for the benefits of selection of an appropriate approach.

Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process

Highlights? Levenberg-Marquardt (L-M) and Boyden, Fletcher, Goldfarb and Shanno (BFGS) update Quasi-Newton (Q-N)-based BPNN networks are equally efficient as adaptive learning (A-L) algorithm-based BPNN network. ? L-M algorithm has fastest network convergence rate, followed by BFGS update Q-N and A-L algorithm. ? A-L -based BPNN learns faster than BFGS update Q-N, and L-M takes maximum time for network training. ? A-L algorithm is relatively easy-to-understand and implement, as compared to L-M or BFGS update Q-N algorithm, for online process control. Monitoring and control of multiple process quality characteristics (responses) in grinding plays a critical role in precision parts manufacturing industries. Precise and accurate mathematical modelling of multiple response process behaviour holds the key for a better quality product with minimum variability in the process. Artificial neural network (ANN)-based nonlinear grinding process model using backpropagation weight adjustment algorithm (BPNN) is used extensively by researchers and practitioners. However, suitability and systematic approach to implement Levenberg-Marquardt (L-M) and Boyden, Fletcher, Goldfarb and Shanno (BFGS) update Quasi-Newton (Q-N) algorithm for modelling and control of grinding process is seldom explored. This paper provides L-M and BFGS algorithm-based BPNN models for grinding process, and verified their effectiveness by using a real life industrial situation. Based on the real life data, the performance of L-M and BFGS update Q-N are compared with an adaptive learning (A-L) and gradient descent algorithm-based BPNN model. The results clearly indicate that L-M and BFGS-based networks converge faster and can predict the nonlinear behaviour of multiple response grinding process with same level of accuracy as A-L based network.

Quality improvement of multistage and multi-response grinding processes: an insight into two different methodologies for parameter optimisation

Process quality improvement using appropriate optimisation methodology has been a continual research endeavour. However, search for optimal path conditions for multi-stage and multi-response grinding in mass-scale manufacturing still remains a critical and difficult task for researchers. In this context, two different methodologies may be adopted to determine optimal process setting conditions. The first methodology (Methodology-1) is to assume each stage as independent, and thereby determine optimal setting conditions for the individual stages. Based on individual stage optimal process conditions, overall optimal path conditions are selected. Another possible methodology (Methodology-2) for optimisation is to consider all the stages as a single system, with their interdependency, and thereby determine the overall optimal path conditions. In this paper, an attempt has been made to compare and contrast the solution quality, as determined by genetic algorithm, and tabu search for both the methodology. The computational results show the relative superiority of tabu search.

A Holistic Framework for Multiple Response Optimization of Hot Strip Rolling Process

The hot strip rolling (HSR) process typically depends on setting of its various process parameters. Controlling these parameters to obtain optimal response is always a critical and difficult task for researchers and practitioners. The complexity of the problem is compounded for multiple response (multiobjective) situations. This article critically reviews the various approaches proposed for modelling and optimization of HSR process in single and multiple response situations. Based on the research scope, a holistic framework for modelling and optimization of HSR process is proposed in this article. The proposed framework is expected to facilitate the researchers and industry practitioners to select the appropriate approach and its intrinsic technique(s) for any typical HSR optimization problem.

An ellipsoidal distance-based search strategy of ants for nonlinear single and multiple response optimization problems

Various continuous ant colony optimization (CACO) strategies are proposed by researchers to resolve continuous single response optimization problems. However, no such work is reported which also verifies suitability of CACO in case of both single and multiple response situations. In addition, as per literature survey, no variant of CACO can balance simultaneously all the three important aspects of an efficient search strategy, viz. escaping local optima, balancing between intensification and diversification scheme, and handling correlated variable search space structure. In this paper, a variant of CACO, so-called ‘CACO-MDS’ is proposed, which attempts to address all these three aspects. CACO-MDS strategy is based on a Mahalanobis distance-based diversification, and Nelder–Mead simplex-based intensification search scheme. Mahalanobis distance-based diversification search ensures exact measure of multivariate distance for correlated structured search space. The proposed CACO-MDS strategy is verified using fourteen single and multiple response multimodal function optimization test problems. A comparative analysis of CACO-MDS, with three different metaheuristic strategies, viz. ant colony optimization in real space (ACOR), a variant of local-best particle swarm optimization (SPSO) and simplex-simulated annealing (SIMPSA), also indicates its superiority in most of the test situations.

An Integrated Approach Based on Principal Component and Multivariate Process Capability for Simultaneous Optimization of Location and Dispersion for Correlated Multiple Response Problems

ABSTRACT Product quality is generally defined by a family of critical characteristics, or so-called responses. In this article, a new integrated approach is proposed that has the ability to reduce the response space dimensionality and also considers both location and dispersion effects in a correlated multiple response optimization problem. The proposed approach uses a principal component (PC)-based multivariate process capability index (MCpmk;PC) as an objective function for optimization. In addition, the nonlinear search algorithm can efficiently determine the best trade-off solution in the orthogonal PC space. Three different cases are selected to illustrate the effectiveness of the new proposed approach compared to a few selected existing approaches.

A multistage and multiple response optimization approach for serial manufacturing system

A serial manufacturing system generally consists of multiple and different dedicated processing stages that are aligned sequentially to produce a specific end product. In such a system, the intermediate and end product quality generally varies due to setting of in-process variables at a specific stage and also due to interdependency between the stages. In addition, the output quality at each individual stage may be judged by multiple correlated end product characteristics (so-called ‘multiple responses’). Thus, achieving the optimal product quality, considering the setting conditions at multiple stages with multiple correlated responses at individual stage is a critical and difficult task for practitioners. The solution to such a problem necessitates building data driven empirical response function(s) at individual stage. These response function(s) may be nonlinear and multimodal in nature. Although extensive research works are reported for single-stage multiple response optimization (MRO) problems, there exist little evidence on work addressing multistage MRO problem with more than two sequential stages. This paper attempts to develop an efficient and simplified solution approach for a typical serial multistage MRO problem. The proposed approach integrates a modified desirability function and an ant colony-based metaheuristic search strategy to determine the best process setting conditions in serial multistage system. Usefulness of the approach is verified by using a real life case on serial multistage rolled aluminum sheet manufacturing process.

A modified tabu search strategy for multiple-response grinding process optimisation

Multiple-response grinding process is usually too complex to optimise, requiring a large number of interacting process variables and responses. Experimentation techniques, such as factorial design, fractional factorial design and Response Surface Methodology (RSM) that may be used for this process are too difficult to implement for production lines involving grinding and other necessary operations. For grinding process involving continuous variable, non-linear and multiple-response optimisation problem, the potential of Tabu Search (TS) strategy needs to be explored either in its original form or its variant. In this paper, integrating Artificial Neural Network (ANN) and composite desirability function with a Modified Tabu Search (MTS) strategy, based on Mahalanobis multivariate distance approach to identify tabu move, with scatter search intensification scheme is proposed for the above-mentioned problem. Computational results show that MTS provides better consistency in terms of sample mean and standard deviation of composite desirability measures than that of real-coded GA.

A Synergistic Approach of Desirability Functions and Metaheuristic Strategy to Solve Multiple Response Optimization Problems

Ensuring quality of a product is rarely based on observations of a single quality characteristic. Generally, it is based on observations of family of properties, so‐called ‘multiple responses’. These multiple responses are often interacting and are measured in variety of units. Due to presence of interaction(s), overall optimal conditions for all the responses rarely result from isolated optimal condition of individual response. Conventional optimization techniques, such as design of experiment, linear and nonlinear programmings are generally recommended for single response optimization problems. Applying any of these techniques for multiple response optimization problem may lead to unnecessary simplification of the real problem with several restrictive model assumptions. In addition, engineering judgements or subjective ways of decision making may play an important role to apply some of these conventional techniques. In this context, a synergistic approach of desirability functions and metaheuristic tech...

Multi-response grinding process functional approximation and its influence on solution quality of a modified tabu search

In this paper, the solution quality of a modified tabu search (MTS) strategy for a constrained, two- stage, multi-response, and continuous variable grinding process optimization problem is studied for varied degree of process functional approximations. Multivariate regression (MR) and artificial neural network (ANN) is selected, and found to be suitable for process functional approximation or modelling at each stage of grinding. Integrating these functional approximations or process models (MR or ANN- based) with desirability functions, near-optimal solutions (expressed in terms of mean and standard deviation of a single primary objective measure or a composite desirability at the final stage) is determined using MTS strategy. The computational run results show that MTS is efficient and suitable to determine near optimal acceptable solutions for varied degree of functional approximation for the two-stage constrained optimization problem. However, the results also indicate that MTS provide inferior or sub-optimal solutions for higher order nonlinear approximation (based on ANN models) as compared to MR-based classical linear models.