نشریه مهندسی و مدیریت کیفیت
سال دوازدهم شماره 2 (تابستان 1401)

One of the basic issues in Ultrahigh-dimensional data analysis is fitting the optimal model and estimating its unknown quality parameters in such a way that it can correctly interpret the structure of the investigated data. In this article, we compare two non-local hyper priors: hyper product moment and hyper product inverse moment priors in determining the optimal model at the same time as estimating the parameters in variable selection using Bayesian Shrinkage in ultrahigh-dimensional generalized linear models. In order to compute the posterior probabilities, the Laplace approximation method was used, and to select the optimal model in the model space of posterior probabilities, Simplified shotgun stochastic search algorithm with screening (S5) for GLMs was used along with screening. Finally, through the study of simulation and real data analysis, the effectiveness of the above Bayesian Shrinkage methods has been evaluated with the ISIS-LASSO and ISIS-SCAD method. The advantage of the model is shown.

Dependency in systems is one of the problems that reliability faces. Dependence increases the probability of failure and can affect the performance of a system; Therefore, it is very important to study and understand the consequences when designing, operating and maintaining the system. Regardless of the dependency, reliability is optimistically estimated and the system fails sooner than expected. In the rail industry, subsystems show a high level of dependence due to their high dynamics and complexity. Failure of any of the subsystems can affect the performance of the entire network and sometimes have irreparable consequences. Identifying dependencies and dependent failures based on the block diagram of reliability and the structure of the rail system can affect the more accurate prediction of reliability and reduce the subsequent consequences. This paper presents a new mathematical model for predicting reliability in the rail industry by considering common cause failure. Various methods have been introduced to estimate the common cause failure coefficient. The results show an increase in accuracy in predicting reliability.

In this article with title "Economic-statistical design of Bayesian control chart based on the predictive distribution for individual observations with an exponential qualitative characteristic distribution" the economic-statistical design of the Bayesian control chart based on the predictive distribution for individual observations of the exponential qualitative characteristic distribution is presented. In doing this, two types of the conjugate prior distribution and Jeffrey’s distribution are considered, and based on the distribution of observations in phase I, the predictive distribution is determined. Then, using the economic model of Lorenzen and Vance, an economic-statistical design was obtained for the data. Optimal design parameters (sampling distance, sample size, and control limits) were determined using a genetic algorithm and sensitivity analysis was performed for different values of model parameters. The results of this approach have been compared with the results of the classical model. The results show that this method is more effective than the classical method

Since the development of a strong platform architecture is considered a competitive advantage for companies and is effective in improving the future generations of the product, therefore there is a need for a kind of diversified product design that simultaneously manages the costs and supply chain process and thus help to develop the architecture of the product platform. In this research, the design for vareity (DFV) method and two generational variety index (GVI) and coupling index (CI) are used to measure a product architecture and by using the quality improvement function (QFD) and the design structure matrix ( DSM), design indicators for variety are identified and ranked. Also, the DFV approach is simultaneously modeled with the categories of design for cost (DFC) and design for supply chain (DFSC) and a mathematical model applied to the development of the product platform architecture is obtained, which seeks to diversify the product and reduce costs and Supply chain process management. The case study of the current research is the phased array antenna system, in which the problem is solved using one of the new optimization techniques (LP metric) and GAMS software. After the implementation of the model, its validation was carried out and considering three objectives including the total cost and the evaluation score (competence) of the suppliers and the objective of variety and the seven main parameters of the model, sensitivity analysis and other comparisons and results. A review is provided. Regarding the comparison of the goals with each other, the findings show the inverse relationship of the total cost goal with the variety and the evaluation score goals and the direct relationship between the two variety and the evaluation score goals. Also, the results of the sensitivity analysis showed the higher effectiveness of the goal of variety among the investigated parameters, and the evaluation score (competence) of suppliers and the total cost were ranked next.

Iran's steel industry chain is very important as one of the key industries which is the driving force of many other industries. The purpose of this research is to prepare the companies of this industrial chain for the optimal establishment of the organizational performance management system (PMS) by identifying the barriers investigating the relationship between them and also determining the priorities for removing the barriers in this chain. In this regard, barriers to the optimal implementation of PMS were extracted from the literature review. Validation of identified barriers to PMS optimization was conducted through semi-structured interviews with industries experts. BY Using IMS method, the relationship between barriers and the priority of removing the final barriers was identified. The results show that the government's involvement in policy-making is the main barrier. The existence of many resources in the country (Iran) and the costs of performance control are also among the root factors. Therefore, it seems that removing these three barriers are the first priority to optimize the performance management system.

Emphasizing the importance of competition and cooperation in supply chains caused a resurgence of game theory ‎as a tool for the analysis of interactions in a supply chain. The development of the business and the ‎complexity of retailing requires a change in the advertising approaches. Affiliate advertising is one of the ways that ‎manufacturers and distributors can jointly participate in advertising programs. Therefore, a variable is defined as ‎the participation rate, which is a percentage of local advertising costs that the producer agrees to pay. In this ‎research, we consider cooperation in advertising during two different advertising function models along with pricing ‎decisions, warranty period and quality level, in a two-level supply chain. Therefore, demand will be affected by ‎price, advertising, warranty period and quality level. Manufacturer and retailer can have cooperative advertising. ‎The theory of non-cooperative and cooperative games is the tool used to solve this problem. Due to the complexity ‎of the model, a meta-heuristic algorithm, the optics inspired optimization, which is a population-based search ‎algorithm, is used to solve the problem. In this research, it was observed that the sum of the profits claimed by both ‎parties in the non-cooperative game is smaller than the profit of the whole system in the cooperative game, and the ‎profit of each individual is also lower in the non-cooperative state than in the cooperative state. Therefore, ‎cooperation between two players increases their profits. Also, sensitivity analysis has been done on some ‎parameters, including parameters related to product quality.‎