Process Optimization using Taguchi Technique

Download Full-Text PDF Cite this Publication

Text Only Version

Process Optimization using Taguchi Technique


1Scholar, MDU, UIET, Rohtak

Abstract: The aim of this sub method paper is to see the process by applying the Taguchi method with orthogonal array robust design. Taguchi method Design is a truly magnificent and efficient rule for optimization the route and quality and recital required outcome of mechanized processes, hence a prevailing instrument for scheming high quality system. Off-line eminence control is measured to be an of use approach to get better quality of artifact at comparatively low cost. The Taguchi method is one of the predictable approach for this principle. Optimization of procedure parameters is done to have immense control over quality, efficiency and cost aspects of the process. The approach is based on Taguchis signal-to-noise (S/N) ratio and the analysis of variance (ANOVA).Analysis of variance (ANOVA) is used to study the effect of process parameters and confirm the experiment.(132 words)

Keywords: Taguchi method, Process optimization, orthogonal arrays, S/N ratio, design of experiments, ANOVA


    After devastating second world war , the Japanese manufacturer were besieged and having been very distressed to endure with very low possessions of stock and resources. Taguchi revolutionize the industrialized development in Japan by heavy financial savings. He implicit, same as many other technocrat or engineers, that all the process of supply chain and manufacturing techniques are affected by the outside manipulation, noise. But , Taguchi realized that of those abrupt noise source, which have the furthermost belongings on product unpredictability. His own had have been taken by unbeaten developers approximately the earth for the reason that of their consequences in create better-quality invention steps at a great deal .

    Taguchi techniques is different type of methods industrially coined by Genichi Taguchi to advance the superiority of the feigned things and more freshly also practical to manufacturing (Rosa et al. 2009), biotechnology (Rao et al. 2008, Rao et al. 2004), promotional and advertise (Selden 1997). specialized statisticians have welcome the goals and good amplification bring on the subject of by Taguchi methods, principally by Taguchi's improvement of designs for cramming discrepancy.


    There is defined phenomenon of the industrial output increasing technique and depend upon the process used for it and revolutionized the area (Shoemakers et al.1991, Thornton, et al. 1999, Gremyaret al. 2003 and Taguchi et al. 2005). Some of the author insist that the enemy of the mass output or the production is the phenomenon requirement. triumph in plummeting it will customarily simplify process, decrease morsel, and subordinate costs

    Characterization of eminence is the loss as the quantity of serviceable discrepancy of products in addition all possible

    unconstructive effects, Like environmental indemnity and equipped in the costs ropes this view (Taguchis 1993).

    The most important intent in the Taguchi method is to drawing vigorous system that are trustworthy under irrepressible conditions (Taguchi1978, Byrne1987 and Phadke1989).The method aim to fiddle with the design parameter (known as the control factors) to their most advantageous levels, is, tactless to noise factors, which are inflexible or unworkable to organize (Phadke1989).


    It refers to the procedure or procedures used to make a system or design as effective or functional as possible, especially the mathematical techniques involved.

    Also optimization is putting mutually a assortment in such a way that return is maximize for a prearranged risk level, or peril is minimize for a given probable return level. Process optimization is the compliance of adjusting a evolution to optimize some particular set of parameters without violate some restriction. The most widespread aim are minimize cost, maximizing all through, and/or value. This is one of the major quantitative tools in industrial conclusion-assembly.

      1. Process Optimization Tools

        Many narrate course optimization in a immediately line to use of arithmetic techniques to identify the optimum solution. This is not true. Statistical techniques are undeniably looked- for. However, a thorough understanding of the process is required prior to commit time to optimize it. Over the years, many methodologies have been urbanized for course of action optimization including Taguchi method, six sigma, slant computerized and others.


Taguchi's techniques have been used widely in production design (Ross1996 & Phadke1989). The Taguchi technique contain system drawing, factor devise, and forbearance design procedures to achieve a robust process and result for the best product quality (Taguchi1987& 1993). The main trust of Taguchi's techniques is the use of parameter design (Ealey Lance A.1994), which is an manufacturing method for artifact or process design that focus on seminal the factor settings producing the finest levels of a feature attribute (piece measure) with smallest variation. Taguchi designs grant a potent and proficient routine for deceitful process that operates constantly and optimally over a array of situation. To confirm the best blueprint, it require the use of a tactically planned research, which exposes the process to various levels of depiction parameter.

Taguchi particular three situations:

      1. Larger the enhanced (for example, agricultural capitulate);

      2. Minor the improved (for example, carbon dioxide emissions); and

      3. On-target, smallest-discrepancy (for example, a mating part in an gathering).

        4.1 Route Optimization Tools

        1. Key rudiments of his feature thinking comprise the subsequent:

          • Taguchi loss utility (Ross 1996), used to calculate monetary loss to culture ensuing from pitiable feature;

          • The philosophy of off-line feature direct (Logothetis and Wynn1989), conniving harvest and process so that they are unfeeling ("robust") to parameter exterior the blueprint engineer's control.

          • Innovations in the arithmetical drawing of experiment Atkinson, Donev, and Tobias, (2007), notably the use of an external array for factor that are unmanageable in existent life, but are haphazardly different in the testing. Taguchi proposed a standard 8-step procedure for applying his method for optimizing any course of action.

          1. Process Optimization Tools

            Taguchi realize that the best chance to purge gap is in the portrayal of a product and its manufacturing enlargement. as a result, he industrial a dodge for eminence engineering that can be worn in both milieu. The observe has following three stage:

            Stage I: System design

            1. This is design at the conceptual level, connecting creativity and discoveries .

            2. Stage II: Parameter Devise

            3. Once the conception is recognized, the ostensible values of the assorted dimensions and plan parameter need to be set, the detail design phase of conformist engineering. This is sometimes stated robustification.

            4. Stage III: Lenience design


          Standard S/N ratio:


          where 'i' is the number of a tryout; 'Yij' is the calculated value of value attribute for the ith trial and jth experiment, 'n' is the number of repetitions fo the untried amalgamation.

          Larger the better characteristic:

          Using OAs appreciably reduces the amount of tentative configurations to be considered (Montgomery1991). The outcome of many unlike parameter on the act characteristic in a process can be examined by using the orthogonal array experimental blueprint planned by Taguchi.

          Once the parameters affect a process that can be controlled have been firm, the levels at which these parameters should be diverse must be indomitable. Determining what levels of a capricious to test require an in- depth understanding of the process, including the minimum, maximum, and current value of the parameter. If the difference between the minimum and maximum value of a parameter is large, the ethics being tested can be more apart or more values can be experienced.

          If the variety of a parameter is tiny, then less significance can be tested or the values tested can be closer collectively.

          The Taguchi method is a dominant device for deceitful high feature system. Knowing the number of parameters and the number of levels, the proper orthogonal array can be


          Step-1: Identify the main function, and failure mode

          Step-2: Identify the noise factors, testing conditions,

          Step-3: Identify the and quality characteristics Step-4:

          Identify the control factors and their levels

          Step-5: Select the orthogonal array matrix experiment

          Step-6: Conduct the matrix experiment

          Step-7: Analyze the data,

          predict the finest levels and recital


  1. Determine the standered gist (ANOVA)-Analysis of variance (Hafeezetal.2002)

  2. Conduct a focal achieves plot analysis to determine the finest level of the control factor.

  3. Execute a factor involvement rate examination.

  4. Confirm experimentation and plan future appliance.


Taguchi started to develop new methods to optimize the method of manufacturing testing. He believed that the best way to improve quality was to design and build it into the product. He developed the techniques which are now known as the associated philosophy. His perceptions produced a unique and powerful quality progress technique that differs from conventional practices. He developed mechanized system that was robust or insensitive to daily and seasonal variations of atmosphere, instrument wear and other external factor.

The Taguchi approach to quality engineering places a great deal of emphasis on minimizing variation as the main means of improving quality. The idea is to design products and processes whose feat is not affected by outside conditions and to build this in during the development and design stage through the use of experimental design. The method includes a set of tables that facilitate main variables and interactions to be investigated in a minimum number of trials.


  1. U. S. Choi, Nano fluids: from vision to reality through research,

    Journal of Heat Transfer, vol. 131,no. 3, pp. 19, (2010).

  2. Mu-Jung Kao, Chen-Ching Ting Aqueous Aluminium Nano fuid Combustion in Diesel Fuel, Journal of Testing and Evaluation, vol. 36, no.2, pp. 432460, (2008).

  3. Calvin Hong Li, Proceedings of the ASME International Mechanical Engineering Congress &Exposition, IMECE 2011, Denver, Colorado, USA, (2011)

  4. Mu-Jung Aqueous aluminum nano fluid combustion in Diesel Fuel Journal of Testing and Evaluation, Vol. 36, No. 2 Paper ID JTE100579 ;( 2010)

  5. Matthew Jones1, Calvin H Li1,2*, Abdollah Afjep, GP Experimental study of combustion characteristics of nanoscale metal and metal oxide additives in biofuel (ethanol) Peterson3Jones et al. Nanoscale Research Letters ,6:246;(2011)

  6. K. Ilunga, O. del Fabbro, L. Yapi, W.W. Focke, Powder Technol. 205; 97102. (2011)

  7. D. Wen Nanofuel as a potential secondary energy carrier, Energy& Environmental Science,3 (5), p 591-600,(2010)

  8. S.H. Fischer and M.C. Grubelich, Theoretical energy release of thermite, intermetallic, and combustible metals, International Pyrotechnics Seminar, SAND98-1176C.(1998)

  9. W. Miziolek, Nanoenergetics: An emerging technology area of national importance, The AMPTIAC Newsletter, Vol. 6(1) 43- 48.(2001)

  10. Y. Gan, and L. Qiao, Combustion characteristics of fuel droplets with addition of nano and micron-sized aluminium particles,. Combustion and Flame Volume 158, Issue 2, Pages 354-368; (2011)

  11. G. A. Risha, T. L. Connell Jr., R. A. Yetter, V. Yang, T. D. Wood, M. A. Pfeil, T. L. Pour point, and S.F. Son,Aluminium- Ice (ALICE) Propellants for Hydrogen Generation & Propulsion 45th AIAA/ASME/SAE/ASEE;(2010)

  12. L. Meda, G. Marra, Nano-aluminium as energetic material for rocket propellants Materials Science and Engineering C 27 ; 13931396,( 2007)

Leave a Reply

Your email address will not be published. Required fields are marked *