Journal of Quality Engineering and Management

Abstract application of Reliability can be seen in many industrial, communication, In the early stages of system design, many system features such as reliability, weight, cost, and etc are associated with uncertainty due to various reasons such as lifespan, operational conditions, etc. Since the use of the probabilistic approach in solving reliability problems has limitations and can only be used in quantitative analysis of information and in many cases does not produce useful and sufficient results for experts, therefore the use of the approach Fuzzy is much more efficient for solving reliability optimization problems. One of the ways to optimize the reliability is to allocate redundancy. When using redundant components in a subsystem, how the redundant components are used is particular importance. In reliability-redundancy allocation problems, the reliability of components is not known in advance and is considered as a decision variable. In the current research, the reliability-redundancy allocation problem has been investigated with two active and cold-standby redundancy strategies and the triangular fuzzy number approach has been used in using the parameters of probability functions and reliability calculation in two model problems and an industrial system. Genetic algorithm has been used to solve the problem. In the implementation of the genetic algorithm, the the random, tournament and roulette wheel methods has been used to select parents and different types of mutation and crossover operators have been used to produce children. The results are more efficient than the results obtained from solving the deterministic model.

Abstract Purpose: In statistical data analysis and modeling, assessing the similarity or divergence between two probability distributions is of great importance. One of the most widely used metrics for this purpose is the Kullback-Leibler (KL) divergence, which quantifies the informational distance between distributions. This study aims to analyze the KL divergence between two normal distributions with equal variance and to compare the performance of different estimation methods for this measure.
Methodology: In this study, the exact value of the Kullback–Leibler divergence between two normal distributions with equal variance is first analytically derived, and then three estimation methods (maximum likelihood, Bayesian, and shrinkage) are proposed to estimate this measure. The performance of each estimator is evaluated via Monte Carlo simulations using the Mean Squared Error (MSE) criterion.
Findings: The simulation results indicate that the Bayesian estimator outperforms the MLE in terms of estimation accuracy. Furthermore, the shrinkage estimator performs best, achieving the lowest MSE among the three methods. This argument suggests that incorporating prior information or penalization techniques can significantly improve estimation quality.
Originality/Value: This study contributes to the literature by providing a detailed comparison of classical and modern estimation techniques for KL divergence in the context of normal distributions with equal variance. The novelty lies in integrating shrinkage methodology and demonstrating its superior performance, which is quantitatively validated through simulations. The findings have practical implications across fields such as machine learning, signal processing, and information theory.

Abstract One of the common approaches in system reliability optimization is the use of redundant components. It has been proven that the redundant component allocation problem is NP-hard and involves selecting redundant components to optimize system reliability based on pre-defined constraints. In this paper, the maximization of reliability in series-parallel systems is addressed by adding redundant components subject to weight and cost constraints. In the allocation of redundant components, the existence of multiple types for each component is considered, meaning that in addition to determining the number of components, it is also necessary to select the appropriate type from the available options. This problem is modeled as a three-level graph, and an Ant Colony Optimization (ACO) algorithm is employed to solve it. The search capability of the proposed algorithm is enhanced by a local search method in the neighborhood of feasible points, and a dynamic penalty function is used to guide solutions toward feasible regions. The application of this algorithm is demonstrated in optimizing the reliability of a mechanical gearbox system. Numerical results obtained from solving sample problems indicate the considerable efficiency of the proposed algorithm compared to previous approaches, achieving not only the maximization of reliability but also minimizing the required weight and cost.




 

 




 

Abstract Profile monitoring is one of the emerging research areas in the field of statistical process control. A profile describes the relationship between a response variable and one or more independent variables. This relationship, which is typically modeled using a regression equation, may be simple linear, multiple linear, polynomial, or in some cases nonlinear. In order to monitor the quality of a process or product whose quality characteristic is expressed as a profile, multivariate control charts must be used due to the correlation among the regression model parameters. Various types of multivariate control charts can be applied to detect small and large shifts in the process.
A major limitation of multivariate control charts is their inability to identify the specific parameter that goes out of control once a change is detected. In this study, after a multivariate MCUSUM control chart in the MCUSUM–Chi-square method signals a shift in a polynomial profile, a multilayer perceptron neural network is employed to identify the out-of-control parameter. The designed network is trained and then tested, and the results demonstrate its strong performance in identifying the parameter that has shifted out of control.

Abstract The sign chart is one of the most common nonparametric charts used to control the centrality of processes with unknown or non-normal distributions. Considering the effect of measurement error on the performance of control charts, this paper examines the effect of measurement error on the performance of the sign chart using an additive model. For this purpose, a simulation program has been developed that calculates the average length of the sign chart sequence for three different distributions and in two states of awareness or ignorance of the existence of measurement error. The simulation results show that the performance of the sign chart for all three distributions and in both states is weakened by the effect of measurement error, and with an increase in the variance of the measurement error, the effect of the error on the performance of the chart increases. Also, the effect of increasing the number of measurements on reducing the effect of measurement error in the sign chart has been investigated. The results show that although using this method when aware of the existence of measurement error has a positive effect on the performance of the chart, if unaware of the existence of the error, this method weakens the performance of the sign chart.

Abstract Purpose: The purpose of this paper is to address one of the most critical challenges faced by organizations today: controlling carbon dioxide emissions. This study aims to provide a model for designing a green supply chain network that minimizes total network costs while incorporating environmental considerations. The research seeks to achieve a balanced optimization of costs, carbon emissions, and service levels in supply chain management.
Methodology: This study proposes a novel integrated optimization model that considers economic, environmental, and customer satisfaction aspects within the supply chain network. The mathematical model is formulated as a Mixed-Integer Nonlinear Programming (MINLP) problem. An exact method is employed to solve the model, which is coded and implemented using GAMS optimization software. The efficiency and effectiveness of the model are validated through numerical examples and data analysis.
Findings: The results demonstrate the model's ability to optimize both economic and environmental dimensions while maintaining high service levels and customer satisfaction. The numerical examples, solved for problems of varying dimensions, confirm the practicality and effectiveness of the proposed approach. The findings highlight the trade-offs between cost minimization, carbon emission reduction, and service quality in supply chain networks.
Originality/Value: This research contributes to the field by presenting a new integrated optimization model that simultaneously addresses cost efficiency, environmental sustainability, and customer satisfaction in green supply chain design. The use of a mixed-integer nonlinear programming approach and its implementation in GAMS provides a robust framework for solving complex supply chain problems. The study offers valuable insights for organizations aiming to achieve sustainability goals while maintaining economic viability and customer-centric operations.

Abstract Traditional control charts are based on the basic assumption that process data are sequentially independent of each other and have a normal distribution. However, in many real-world cases, including chemical and continuous processes, this basic assumption does not exist and there is a kind of autocorrelation between the data collected from the process. The use of traditional control charts in autocorrelated processes is unreliable and increases false alarms. One of the methods developed to control autocorrelated processes is to identify the structure of the process time series and use the residual values ​​to control the process. In this paper, a model based on neuro-fuzzy adaptive systems is designed to identify the structure of the time series and use the prediction. Finally, it is AR(2). Also, residual control charts based on this system for second-order autoregressive data using simulated data, the efficiency of the proposed method in the weighted moving average chart and for different degrees of correlation are evaluated, and it is shown that the proposed method has very good efficiency for data with high correlation.

Abstract The growth of activity and investment of startups in the field of financial technology has provided a good opportunity to increase the quality management system. The application and implementation of quality management system requires a codified and indigenous model, so the present study was conducted with the aim of identifying the effective components and providing a model of quality management system in Fintech startups. This study is a fundamental research in terms of purpose and has been done with a cross-sectional survey approach. Also, because both quantitative and qualitative methods have been used, a research is mixed. The statistical population includes theoretical experts (university professors) and experimental experts (managers of Fintech startups). Purposeful method was used for sampling and continued until theoretical saturation was achieved. Finally, the views of 17 experts were used. The content quality analysis method and MaxQDA software were used to identify the basic categories of quality management system. Structural-interpretive method and MicMac software were used to present the model. Findings show that leadership and management and customer orientation affect the decision-making method, systematic approach to management and employee participation. These factors also affect the continuous improvement of the process and process management. Finally, they lead to improved quality. Level four elements, namely leadership and management and customer-orientation, have the greatest impact on the continuous improvement of the process of public institutions.
 
 

Abstract The change point is a useful concept in the control of statistical process that assists quality engineers in finding assignable causes and improving the quality of a product or process. It also reduces the time and cost of detecting assignable causes. In this paper, an artificial neural network approach is used to estimate the step change point in phase II monitoring of the mean of multiple linear profiles. the performance of the probabilistic neural network is evaluated in order to estimate the change point utilizing Monte Carlo Simulation. The results of simulations show the fact that the network recommended in estimating the change point has entirely better performance than maximum likelihood estimator in small shifts, considering mean square error criteria, but maximum likelihood estimator method owns better performance in medium to large shifts. In general, in all shift types, maximum likelihood estimator has a better performance in terms of precision, and the proposed probabilistic neural network performs better in terms of accuracy. In addition, another advantage of the proposed approach is the fact that contrary to the maximum likelihood estimator approach, it does not require any knowledge about the change type and can appropriately estimate any kind of change point as well. 
 

Abstract The importance of software is increasing day by day, and with this growing importance, continuous efforts are being made to develop technologies that lead to the creation of high-quality software. Software metrics are essential tools for project and quality management. In addition to selecting appropriate metrics for monitoring, detecting meaningful behaviors and changes or deviations in the process, analyzing them, and determining whether process shifts are statistically significant are also crucial.
Since statistical quality control is one of the well-established approaches for addressing these issues, this paper aims, for the first time, to identify and categorize all techniques used in the existing literature related to Statistical Process Control (SPC) in software processes. This classification helps researchers recognize practical topics and research directions and supports them in conducting useful and statistically sound studies based on the compiled material.

Abstract Control charts are among the most important tools in statistical process control, used to monitor the extent of variation in a process. When a assignable cause deviation is observed in a control chart, identifying the root causes of the change and determining the time at which the deviation began—referred to as the change point—is crucial and impactful. In some statistical process control problems, the quality of a product or the performance of a process is described by the relationship between a response variable and one or more independent variables, known as a profile. In many applications, such as calibration, this relationship is described by a linear profile, while in other situations more complex models, such as Poisson regression profiles, are required. In this paper, the maximum likelihood estimation method is employed to detect change points in Phase II monitoring of Poisson regression profiles, and its performance is evaluated through simulation.




 

 




 

Abstract Curve fitting is an important tool in data analysis, geometric modeling, and other engineering applications. When the shape of the measured data function is complex, estimating the curve using a polynomial function becomes difficult. In such cases, spline functions are generally preferred due to their higher accuracy and smoother approximation compared to other approximation functions. Often, for proper spline fitting, the number and locations of knots are unknown. Therefore, this paper presents a genetic algorithm to simultaneously determine the number and positions of knots based on a minimum error objective function without any restrictive assumptions. The proposed algorithm employs both the maximum likelihood estimation and least squares error methods for curve fitting. The performance of the proposed algorithm is evaluated using numerical examples with both methods. Simulation results indicate that when observations follow a normal distribution, the least squares method performs better. However, the main advantage of the maximum likelihood-based approach is its applicability to all statistical distributions. Finally, the effectiveness of the proposed approach is demonstrated through a practical case study.

Abstract Reliability is one of the most important issues in the engineering design process. When we use a system, we often want to determine the reliability of this system. Clearly, higher reliability systems are more valuable. On the other hand, the reliability of each system depends on the structure and reliability of its components. Therefore, to increase the reliability of the system, the reliability of its components can be improved. In addition, to increase the reliability of the components of a system, it is necessary to consider its costs. This study, by considering a series-parallel system, determines the amount of increase required for the reliability of system components so that the reliability of the whole system is maximized and the cost of this increase does not exceed a predetermined value. The following is a numerical example for reviewing the results. Finally, a summary of the results of the article is given.

Abstract Purpose: This study aims to develop a durable closed-loop supply chain network capable of simultaneously addressing sustainability, resilience, agility, and digitalization while incorporating fuzzy–stochastic uncertainties. The significance of this research lies in the limitations of traditional supply chains, which often fail to perform effectively under severe environmental fluctuations, operational disruptions, and demand variability, thereby highlighting the need for intelligent and multidimensional decision-making frameworks.
Methodology: To achieve the research objectives, a structured three-phase framework was designed. In the first phase, demand subject to considerable uncertainty was forecast using the SARIMA time-series model to capture market volatility and seasonal patterns. In the second phase, supplier evaluation criteria were identified through a systematic literature review and expert judgment, and subsequently weighted via the Stochastic–Fuzzy Best–Worst Method (SFBWM). Supplier ranking was then performed using the Stochastic–Fuzzy TOPSIS (SFTOPSIS) technique. In the final phase, a multi-objective fuzzy–stochastic mathematical model was developed to design and optimize the supply chain network, while fuzzy–stochastic robust optimization was employed to address data uncertainty. The multi-objective problem was solved using a modified version of the Lexicographic–Chebyshev Multi-Choice Goal Programming Method (LCRMCGP).
Findings: A case study conducted in “Ebtakar Tajhiz Teb Yekta,” a company operating in the medical equipment industry, demonstrated that the proposed model effectively supports key strategic decisions, including the selection of primary and backup suppliers, the optimal location of collection and recycling centers, excess capacity allocation, and the choice of information-exchange technologies (traditional systems vs. blockchain-based platforms). The integration of IoT and blockchain technologies increased product return rates, reduced recycling costs, and enhanced transparency and sustainability across the network. Overall, the results confirm that the proposed framework can successfully balance economic, environmental, and social objectives while improving flexibility and resilience under uncertainty.
Originality/Value: The novelty of the present study lies in developing an integrated framework for designing a viable closed-loop supply chain under hybrid fuzzy–stochastic uncertainty. Unlike previous studies that mainly focused on isolated dimensions of supply chain management, this research simultaneously incorporates sustainability, resilience, agility, and digitalization within a multi-objective optimization model. Furthermore, the integration of SARIMA, SFBWM, SFTOPSIS, and LCRMCGP methods provides a more accurate and comprehensive decision-making process. Comparative results also demonstrate that the proposed model outperforms conventional approaches in reducing deviations, improving decision consistency, and enhancing overall network sustainability.

Abstract The Permasin engine is a critical mission-oriented system, the failure of which will cause the failure of the main mission. Comprehensive studies on its reliability can be a step towards improving the performance of this system. The aim of the article is to analyze the reliability of the Permasin engine in the specified scenarios. In this article, first of all, the structure of Permasin engine as the studied system is described and the breakdown structure of the product is drawn for this system, and according to the mission-oriented nature of this system, there are 2 time scenarios, the basis of floating performance, definition and failure rate for sensitive parts from the standard. MilHDB-217 and NPRD-95 will be calculated in two optimistic and pessimistic modes. By using the breakdown structure, the connection of specific system components and the reliability block diagram are drawn in the Reliability Workbench software. Finally, the reliability of the subsystems and the studied system is calculated separately for both working scenarios. The results show that drive and motor subsystem has the lowest level of reliability compared to other subsystems in rated power.

Abstract Statistical process control is a powerful method for establishing stability and improving process performance by reducing variability. Control charts are among the most widely used tools in statistical process control and play a significant role in enhancing process quality. Recent studies have shown that adaptive control charts—such as those with variable sample sizes, variable sampling intervals, and variable parameters—detect mean shifts faster than standard Shewhart xˉ\bar{x}xˉ control charts. One common assumption in designing a control chart is that observations follow a normal distribution; however, this assumption may not hold in some processes. In this paper, the performance of adaptive control charts under non-normal data is investigated using a simulation approach in MATLAB. It is demonstrated that the variable-parameter control chart outperforms other adaptive xˉ\bar{x}xˉ control charts in detecting small mean shifts under non-normal data, and, most importantly, it reduces the risk of false alarms.

Abstract In this research, a Multi-Objective model for reliability-centered preventive maintenance planning for a production system with parallel series components is developed. In this model, maintenance costs and cost of failures; including the cost of lost production, due to system shutdown are considered. In this way, this model plans preventive maintenance operations with the aim of increasing the system reliability level, with the lowest total cost. A binary nonlinear program is developed and a numerical example is solved for it and the results are discussed. To solve the proposed model, the Augmented Epsilon Constraint Method (AUGMECON) by GAMS software is used and the results are discussed. The results show the effect of preventive service planning on system failure rate and reliability. The proposed approach can be used to plan maintenance of industrial systems by considering the reliability related costs
 
 
 

Abstract Reliability is an integral part of the planning, design, and operation of engineering systems, ranging from the smallest and simplest to the largest and most complex. The failure of any system can disrupt the ongoing processes of people and equipment associated with it, which in some cases is considered a serious threat to the community. Therefore, this study first aims to identify all industrial engineering techniques that can be effective in improving reliability and to prioritize these techniques across all phases of the product life cycle using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). Subsequently, using the Interpretive Structural Modeling (ISM), the cause-and-effect relationships among the techniques in each phase are determined, providing a systematic framework to enhance equipment reliability and to understand and develop the relationships between reliability and other industrial engineering techniques.

Abstract Many engineers and researchers base their reliability models on the hypothesis that the components of a system work statistically independently and fail. This assumption is often violated in practice because, specific environmental and systemic factors affect the performance of components and thus contribute to correlated failures, which can reduce the reliability of a system. Determining the component correlation index and its effect on system reliability is necessary to be able to require models to explicitly combine and coordinate continuous failures and provide an accurate estimate of system reliability. Previous approaches to correlation modeling are limited to systems that consist of two or three components or assume that the operation of the components is statistically independent. In this study, while considering the dependence between component functions, a model is presented to consider this dependence and calculate the reliability of series, parallel, k-out of-n, parallel-series and series-parallel systems. To better understand the problem, examples are provided with sensitivity analysis in which the components are functionally interdependent. These examples show how the correlation between the components has affected their performance.

Abstract Nowadays, most manufactured products are produced through multiple interdependent process stages. Due to the cascading nature of many such processes, monitoring them using conventional control charts often leads to unavoidable errors and incorrect decisions. One of the useful charts for monitoring multistage processes is the deviation-based control chart. These types of charts have mostly been applied to normally distributed quality characteristics.
In this paper, a two-stage process is examined in which the quality characteristic in the second stage follows a gamma distribution, and the deviation-based control chart is employed for monitoring this process. The test statistic of the deviation-based control chart is derived from combining the inverse NORTA method with a generalized linear model.
To evaluate the performance of the proposed method, the Average Run Length (ARL) index is used, and the results are compared with the best existing method in the literature. The findings indicate that the proposed approach performs better in detecting both upward and downward shifts.

Abstract Purpose: Reliability is one of the most critical quality characteristics of components, products, and systems. Unlike other attributes, it cannot be directly measured and is usually evaluated only after significant operational time under real conditions. However, waiting for long-term field data may reduce market competitiveness in commercial industries and pose serious safety risks in sensitive systems such as military equipment. Therefore, reliability prediction plays a vital role in key decision-making areas such as product release timing, warranty policies, and maintenance planning. This study aims to present an integrated model based on accelerated degradation testing and accelerated life testing to predict the lifetime of a turbine engine nozzle under operational conditions.
Methodology: Initially, the ADT was designed and conducted to monitor the degradation trend of the nozzle's critical feature at various temperature and time levels. Using the power-law and Arrhenius acceleration models, acceleration parameters and the activation energy were estimated. Subsequently, the ALT was performed under high-stress thermal conditions using the extracted parameters, and the corresponding failure times were recorded. Finally, by integrating the results of both tests and applying statistical methods such as maximum likelihood estimation and degradation path modeling, the system's lifetime distribution was modeled.
Findings: The implementation of the proposed model on a turbine engine nozzle demonstrated its ability to predict lifetime accurately and to reduce testing time and cost significantly.
Originality/Value: This model introduces a novel analytical framework that systematically combines two testing methods (ADT and ALT), with the output of one serving as input to the other. The proposed approach can be generalized and applied to other critical industrial and defense-related products.

Abstract The purpose of the current research is to design a structure so that it can be used to investigate the drivers of the appropriate implementation of quality 4.0 in the country's steel industry. In order to carry out this research, ten stimuli were initially identified using research literature. Then, using the interpretative structural modeling technique, these stimuli were structured using the opinions of 13 experts. , in order to fit the obtained structure, the structural equation modeling of the tools related to it, including measurement model fitting, structural and general model fitting, were used. For this purpose, a questionnaire containing 33 questions with a five-point Likert scale was designed and in order to complete it, opinions were sought from 214 managers and employees of the country's steel industry. The findings of the research on the high effectiveness of reward stimuli and control of big data in proper implementation have quality 4.0.

Abstract As is well known, data obtained from real-world processes are typically autocorrelated, and monitoring such processes requires accounting for this autocorrelation. The control charts developed so far for monitoring the defective proportion (p) are generally based on the assumption that binary observations are independent, which ignores the inherent correlation in the data.
In this paper, a cumulative sum (CUSUM) control chart is proposed that incorporates the autocorrelation between binary observations using a first-order two-state Markov chain model. Furthermore, using the Average Number of Observations to Signal (ANOS) index, it is shown that under 100% inspection conditions, the proposed chart performs better than the Bernoulli CUSUM chart—which assumes independent observations—and, in other words, detects increases in p more quickly.

Abstract Guiding the engineering process in systems has created an interdisciplinary approach called system engineering. The concept of guidance in the first step means choosing the best path among the existing paths and then guiding, directing and managing the process in the selected path. In this context, requirements management is one of the first stages of the product development process, which can engineer the requirements with a comprehensive and accurate view and produce a product that meets the needs of users.
The purpose of preparing this research, which was carried out in the period of 1402-1401, is to implement all requirements management activities in a marine system. For this purpose, at first, the basic requirements related to this product were extracted from different sources, categorized and then the metadata of the requirements was prepared, and one or more confirmation methods were provided for each of them. Finally, the relationship between the requirements has been determined and after resolving the conflicts between them, the metadata of the requirements has been updated. According to the results of this process, 106 requirements have been identified. These requirements will be considered as the basis for starting the product development and design process.

Abstract The purpose of this paper is to investigate the reliability parameter R = P (X <Y) based on samples with type 2 incremental censorship in which X and Y are independent random variables with generalized inverse exponential distribution with different shape parameters and the same scale parameter. The maximum likelihood estimator (MLE) and the nonlinear estimator with uniform uniform variance (UMVUE) of the parameter R are obtained and different confidence intervals are provided. Also, Bayesian R estimator and HPD confidence interval using Gibbs sampling method are proposed. Monte Carlo simulations have been performed to compare the performance of different methods.