Robust optimization of multistage process: response surface and multi-response optimization approaches

Author(s):  
Amir Moslemi ◽  
Mirmehdi Seyyed-Esfahani

Abstract A multistage system refers to a system contains multiple components or stages which are necessary to finish the final product or service. To analyze these problems, the first step is model building and the other is optimization. Response surfaces are used to model multistage problem as an efficient procedure. One regular approach to estimate a response surface using experimental results is the ordinary least squares (OLS) method. OLS method is very sensitive to outliers, so some multivariate robust estimation methods have been discussed in the literature in order to estimate the response surfaces accurately such as multivariate M-estimators. In optimization phase, multi-response optimization methods such as global criterion (GC) method and ε-constraints approaches are different methods to optimize the multi-objective-multistage problems. An example of the multistage problem had been estimated considering multivariate robust approaches, besides applying multi-response optimization approaches. The results show the efficiency of the proposed approaches.

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Amir Moslemi ◽  
Mahmood Shafiee

PurposeIn a multistage process, the final quality in the last stage not only depends on the quality of the task performed in that stage but is also dependent on the quality of the products and services in intermediate stages as well as the design parameters in each stage. One of the most efficient statistical approaches used to model the multistage problems is the response surface method (RSM). However, it is necessary to optimize each response in all stages so to achieve the best solution for the whole problem. Robust optimization can produce very accurate solutions in this case.Design/methodology/approachIn order to model a multistage problem, the RSM is often used by the researchers. A classical approach to estimate response surfaces is the ordinary least squares (OLS) method. However, this method is very sensitive to outliers. To overcome this drawback, some robust estimation methods have been presented in the literature. In optimization phase, the global criterion (GC) method is used to optimize the response surfaces estimated by the robust approach in a multistage problem.FindingsThe results of a numerical study show that our proposed robust optimization approach, considering both the sum of square error (SSE) index in model estimation and also GC index in optimization phase, will perform better than the classical full information maximum likelihood (FIML) estimation method.Originality/valueTo the best of the authors’ knowledge, there are few papers focusing on quality-oriented designs in the multistage problem by means of RSM. Development of robust approaches for the response surface estimation and also optimization of the estimated response surfaces are the main novelties in this study. The proposed approach will produce more robust and accurate solutions for multistage problems rather than classical approaches.


2018 ◽  
Vol 52 (4-5) ◽  
pp. 1233-1243
Author(s):  
Amir Moslemi ◽  
Mirmehdi Seyyed-Esfahani

Response surface methodology involves relationships between different variables, specifically experimental inputs as controllable factors, and a response or responses by incorporating uncontrollable factors named nuisance. In order to optimize these response surfaces, we should have accurate response models. A common approach to estimate a response surface is the ordinary least squares (OLS) method. Since OLS is very sensitive to outliers, some robust approaches have been discussed in the literature. Most problems face with more than one response which are mostly correlated, that are called multi-response problem. This paper presents a new approach which takes the benefits of robust multivariate regression to cope with the mentioned difficulties. After estimating accurate response surfaces, optimization phase should be applied in order to have proper combination of variables and optimum solutions. Global criterion method of multi-objective optimization has also been used to reach a compromise solution which improves all response variables simultaneously. Finally, the proposed approach is described analytically by a numerical example.


2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
◽  

Abstract A Burden of Disease (BoD) approach can be used to summarise the debilitating effects of morbidity and premature mortality in a population in a consistent and comparable manner. Summary measures of population health such as the Disability-Adjusted Life Year (DALY) have become key metrics for quantifying burden of disease. DALYs quantify the health gap between a life lived in perfect health and current health status, as the number of healthy life years lost due to illness (Years Lived with Disability, YLDs) and premature death (Years of Life Lost, YLLs). DALYs combine the effects of morbidity and mortality in an equitable way, and can therefore be used to identify the leading causes of disease or injury that cause BoD and to quantify the relative importance of specific risk factors. BoD studies are becoming an increasingly popular way to assess national and local population health as a means to influence national and local policy decisions. The increasing prominence of the burden of disease approach, however, comes at a cost. Calculations of DALYs involve multiple components and as such can be difficult for people to interpret. Burden of disease methodology is complex and highly data intensive, which has led to major disparities across researchers and nations in their capacity to perform studies, to interpret the soundness of available estimates, or to evidence and advocate for the use of particular methodological choices. In this skills-building seminar, we will give an overview of the methodology of calculating the DALY. It will outline the single steps to be undertaken, and the necessary assumptions that have to be taken, on the way to the calculation of the DALYs. This workshop will be supported by technical presentations from burden of disease experts about different choices of estimation methods to calculate both the fatal burden (YLL) and the non-fatal burden (YLD). Throughout the presentations, cerebrovascular disease will be used as a case study, giving a complete, real-life example of how DALYs are calculated. Overall, the aim is to demonstrate the importance of the choices researchers make when designing and interpreting BoD studies as a means of supporting evidence-based decision making. The workshop will foresee ample time for interaction with the audience and discussion of the implications of the different methodological choices. Key messages Although burden of disease methodology is complex, with calculations of DALYs involving multiple components, simple roadmaps can be created to enhance methodological knowledge. The choices and assumptions researchers make are important when designing and interpreting burden of disease studies.


1988 ◽  
Vol 7 (7) ◽  
pp. 1013-1030 ◽  
Author(s):  
C. Gennings ◽  
R. A. Carchman ◽  
W. H. Carter ◽  
E. D. Campbell ◽  
R. M. Boyle ◽  
...  

The therapeutic efficacy of atropine sulfate/pralidoxime chloride (ATR/2-PAM) treatment therapy and physostigmine (PHY) pretreatment therapy was evaluated in soman-challenged guinea pigs. Response surface analysis (RSM) of treatment efficacy indicated that the optimal ATR/2-PAM dose combination varied as a function of both the soman (GD) challenge level and the PHY pretreatment dose. Efficacy was, therefore, evaluated for varying PHY pretreatment doses in combination with the appropriate optimal ATR/2-PAM treatment (as determined by RSM for each soman challenge dose and PHY dose evaluated). The response surfaces depicting the effects (i.e., probability of survival) of ATR/2-PAM combinations at fixed levels of PHY and GD are presented, and confidence regions and point estimates for optimal ATR/2-PAM treatment combination are included. It was estimated that with optimal therapy a protective ratio (PR) of 6 can be observed. Comparisons were made between the use of PHY/ATR/2-PAM as presented here and the use of PYR/ATR/2-PAM, as discussed by Jones et al.(1) Both studies showed a strong positive (r ≥ 0.98) relationship between dose and the PR. However, the estimated slope parameter for PHY was significantly larger ( P < 0.001) than the slope parameter for pyridostigmine (PYR). This difference in slopes may indicate different mechanisms of action for PYR and PHY.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ömer Esen ◽  
Gamze Yıldız Seren

PurposeThis study aims to empirically examine the impact of gender-based inequalities in both education and employment on economic performance using the dataset of Turkey for the period 1975–2018.Design/methodology/approachThis study employs Johansen cointegration tests to analyze the existence of a long-term relation among variables. Furthermore, dynamic ordinary least squares (DOLS) and fully modified ordinary least squares (FMOLS) estimation methods are performed to determine the long-run coefficients.FindingsThe findings from the Johansen cointegration analysis confirm that there is a long-term cointegration relation between variables. Moreover, DOLS and FMOLS results reveal that improvements in gender equality in both education and employment have a strong and significant impact on real gross domestic product (GDP) per capita in the long term.Originality/valueThe authors expect that this study will make remarkable contributions to the future academic studies and policy implementation, as it examines the relation among the variables by including the school life expectancy from primary to tertiary based on the gender parity index (GPI), the gross enrollment ratio from primary to tertiary based on GPI and the ratio of female to male labor force participation (FMLFP) rate.


Sign in / Sign up

Export Citation Format

Share Document