An integrated approach to optimise parameter design of multi-response processes based on Taguchi method and artificial intelligence

Šibalija, Tatjana V.; Majstorovic, Vidosav D.

doi:10.1007/s10845-010-0451-y

Cited by 67 publications

(37 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This was further improved by the previously presented method based on GA [38]. The proposed SA-based method found equal solution (SPM=0.88120) as the GA-based method for M1, but for M2, all the tested SA algorithms found significantly better solution than the best GA.…”

Section: Discussionmentioning

confidence: 79%

“…In this paper, we propose an integrated and generic approach for robust multiresponse process optimisation based on SA algorithm that extends our previous research [36][37][38][39] in terms of the improvement of the quality of a final solution obtained by the method, the robustness of the method and a feasibility of its practical application. The intention was to develop a generic framework that could be applied to various static multiresponse optimisation problems, disregarding the type of process, its parameters and/or responses and their mutual interrelations.…”

Section: Introductionmentioning

confidence: 70%

“…Hence, in this case, SA showed a slightly slower convergence than GA. For M2, GAs with roulette wheel and single-or two-point crossover found the best solution (SPM=0.71280); the other tested function types performed worse. Also, it was noticed that GAs converged to the best solution in later generations, so the speed of GA convergence was relatively low [38]. For M2, the best SA found the maximal SPM of 0.78501 in the third generation, showing very fast convergence, in contrast to the best GA that found the maximal SPM of 0.71280 in the 710th generation (Table 6).…”

Section: Case Studymentioning

confidence: 97%

See 2 more Smart Citations

An integrated simulated annealing-based method for robust multiresponse process optimisation

Šibalija

Majstorovic

2011

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

This paper presents a generic optimisation methodology for the selection of optimal process parameters in multiresponse processes that consists of two stages: The first stage is based on a quality loss function and multivariate statistical methods in order to adequately present responses, uncorrelate and synthesise them into a single process performance measure; the second stage uses artificial neural networks to build a process model and a simulated annealing (SA) algorithm to find the optimal process parameter conditions. The initial point of the SA algorithm is generated in such a way as to improve the convergence to the actual global optimum. The most important SA algorithm parameters are varied to assess the algorithm's robustness in terms of the effect of the algorithm setting on the quality of the final solution (optimal process parameters and the corresponding process performance measure). The results are benchmarked to genetic algorithm (GA) performance within the proposed methodology, and the quality of a final solution, the robustness of the optimisation algorithm, the speed of a convergence to the optimum and the computational time are evaluated. Four case studies are presented to illustrate the effectiveness of the proposed methodology in comparison to several commonly used approaches from the literature and also to the GA-based performance.

show abstract

Section: Discussionmentioning

confidence: 79%

Section: Introductionmentioning

confidence: 70%

Section: Case Studymentioning

confidence: 97%

See 1 more Smart Citation

An integrated simulated annealing-based method for robust multiresponse process optimisation

Šibalija

Majstorovic

2011

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the first stage, a statistical factor effects approach was developed, based on Taguchi's quality loss function, principal component analysis and grey relational analysis, to uncorrelated and synthesis responses into a single measure. Since this approach could not provide the overall global optimum, in the second stage the intelligent approach was developed using neural networks (to model the process behaviour) and a genetic algorithm (GA) (to perform search in a continual space), to ensure that the actual global optimum is found [11]. The method was further improved using simulated annealing (SA) as the optimisation tool, instead of GA [12].…”

Section: Discussionmentioning

confidence: 99%

Application of the Advanced Quality Improvement Techniques: Case Study

Majstorovic

Šibalija

2012

Advances in Production Management Systems. Value Networks: Innovation, Technologies, and Management

View full text Add to dashboard Cite

Abstract. Implementation of the advanced cost-effective methodologies for product and/or process quality improvement is an effective mean to fulfil or exceeds customer's expectations. This paper presents the analysis of a performance of automatic enamelling process for a non-normal data distribution, conducted within the six sigma project implemented in a production system. Drawing on the process analysis results, process optimisation was performed using location and dispersion modelling. It proved its effectiveness in determining the significant effects of process factors on the response mean and variation, and in obtaining the optimal factors setting of the observed single-response process.

show abstract

“…Of relevant interest are also the combinations of ANN with other soft computing techniques such as GA together with Taguchi experimental design; see for example Refs. [24][25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Machinability in Turning of Engineering Alloys by Applying Artificial Neural Networks

Vaxevanidis¹,

Kechagias²,

Fountas³

et al. 2014

TOBCTJ

View full text Add to dashboard Cite

Abstract:The present paper investigates the influence of main cutting parameters on the machinability during turning process for three typical materials namely AISI D6 tool steel, Ti6Al4V ELI and CuZn39Pb3 brass, all three under dry cutting environment. Spindle speed, feed rate and depth of cut were selected for study whilst arithmetic surface roughness average (R a ) and main cutting force component (F C ) were treated as quality objectives characterizing machinability. For the aforementioned materials a full factorial design of experiments was conducted to exploit main effects and interactions among parameters it terms of quality objectives. The results obtained from dry turning experiments were utilized as a data set to test, train and validate a feed-forward back propagation artificial neural network for machinability prediction regarding all three materials. The work presents the results obtained from the aforementioned experimental effort under an extensive state-of-the-art survey concerning neural network technology and implementation to machining optimization problems.

show abstract

An integrated approach to optimise parameter design of multi-response processes based on Taguchi method and artificial intelligence

Cited by 67 publications

References 23 publications

An integrated simulated annealing-based method for robust multiresponse process optimisation

An integrated simulated annealing-based method for robust multiresponse process optimisation

Application of the Advanced Quality Improvement Techniques: Case Study

Evaluation of Machinability in Turning of Engineering Alloys by Applying Artificial Neural Networks

Contact Info

Product

Resources

About