Search

Purpose This paper aims to propose a statistical method to measure the impacts of stockouts on demand, using a segmented linear regression model. Design/methodology/approach The proposed method is applied to data sets from large retail chains to measure the impacts of stockouts of an item on substitute items. The measured impacts of stockouts can be used to estimate the true demand of the sold-out item by recovering the lost demand (turned-away demand), as well as to estimate the true demand of the substitute item by reducing the extra demand. Findings This study found that estimated true demand by the proposed method improves sales forecasting and calculation of the annual expected revenue. Originality/value A new method to measure the impacts of stockouts on the demand of substitute items was proposed. The proposed method is practical, in that, it is conceptually simple, computationally efficient and applicable in general scenarios. Also, the proposed method is scalable for larger data sets.

Smart grids are an effective solution for the rapidly increasing power demand. This study attempts to solve the sustainable smart grid design problem, where three indispensable sustainability dimensions, economy, environment, and society, are considered simultaneously. A multiobjective robust fuzzy stochastic programming approach is presented to minimize the economic, environmental and social costs of the network under uncertain scenarios and parameters. The objective is to determine the optimal number, location and capacity of renewable distributed generation units as well as the dynamic electricity pricing and energy resources scheduling in a sustainable smart grid. The proposed method is applied to a Vietnamese power company in the residential sector. The results indicate that demand response with dynamic pricing reduces environmental and social costs by 3%. Moreover, the proposed model efficiently tackles both uncertainties in scenarios and parameters with a total cost lower than other models.

Research has been conducted on approaches using social media information to improve demand forecasting accuracy in business-to-customer industries. However, such social media information is not applicable to business-to-business (B2B) industries, as a result of a lack of end-consumer evaluations. This raises a few interesting questions, including whether there may be any external information that could be used to improve B2B demand forecasting, and whether practical approaches may be possible to collect and utilize useful external business information. In this study, we develop an innovative and intelligent demand forecasting approach and apply it to a B2B server company based in the United States. We first implemented time series and machine learning models based on sales data and selected the best-fitting model as a baseline, and then used a web crawler and Google Trends to collect related market signals as external information indices for the server industry, which were finally incorporated into the selected baseline model to adjust forecasting results to account for demand fluctuations. Experimental results demonstrate that the baseline model achieved an out‐of‐sample mean squared error (MSE) of 19.77 without considering the collected external information indices, and 11.87 when external information was incorporated. Therefore, our proposed approach significantly improved forecasting accuracy, demonstrating an improvement of 63.1% in terms of MSE, 44.1% in terms of mean absolute error, and 61.2% in terms of root mean square percentage error. Thus, this study sheds light on the value of external information in demand forecasting for B2B industries.

Rising penetrations of renewable distributed generations (RDG) units at the demand side in residential power markets imply a reduction in the revenue of a power plant. In addition, the intermittent nature of RDG units requires the power plant to maintain the generation capacity to meet the demand during the intermittent periods. This paper derived two resilient three-part tariff (TPT) pricing policies based on either the time-of-use (ToU) pricing or the increasing-block pricing (IBP) schemes. The proposed pricing policies aim to maximize the power plant profit and the social welfare of users (consumers and prosumers) and recover the losses related to the uncertainties in energy supply and demand. To handle hybrid uncertainties in demand and capacity, a novel mixed type-2 fuzzy stochastic approach based on the integration of a type-2 fuzzy set and scenario-based stochastic programming is proposed. The application of the proposed model was examined using an empirical case study. Our results indicated that the resilient TPT with ToU could help power plants improve their profits by approximately 41.14% compared to those earned through the traditional two-part tariff. Furthermore, a decision matrix is proposed to allow the power plant to visualize an appropriate tariff plan amongst various options accurately.

Sustainable supply chain networks have attracted considerable attention in recent years as a means of dealing with a broad range of environmental and social issues. This paper reports a multi-objective mathematical programming model for use in the design of a sustainable supply chain network under uncertain conditions. The proposed model is aimed at maximizing social benefits while minimizing economic costs and environmental impacts. The objective assists in making decisions concerning the selection of production technologies and materials and determining the number and locations of production and distribution centers and the quantity of product to be transported between facilities. Uncertainty related to customer demand is dealt by using stochastic variables, whereas overall costs, carbon emissions, job opportunities, and the detrimental effects of the resulting solutions are handled using fuzzy numbers. An interactive method based on two-phase stochastic programming and fuzzy probabilistic multi-objective programing is used to overcome problems related to uncertainty. Finally, numerical analysis demonstrates the efficacy and efficiency of the proposed model.

The costs of renewable energy technologies are highly sensitive to financing terms. Power companies are willing to invest in renewable energy generation because of clean and sustainability concerns. However, renewable energy generation poses a potentially high risk, both in generation and consumption. In this study, we consider how a power company makes its decisions if a credit bank willing to lend to it for renewable energy generation. The repayment ability of the company depends on sales revenue under demand uncertainty. We formulate a mathematical model to help the company determine the optimal electricity price, renewable energy capacity, and amount of loan while maximizing the total expected profit. A searching algorithm is proposed to solve the problem. Several numerical examples are provided to illustrate the proposed model and solution approach. Managerially, our study suggests that increasing renewable energy investments through financing institutions requires careful attention to pricing, capacity, and financing policies.

This paper reports on a closed-loop supply chain network for the remanufacturing of products under RFID technology. RFID technology can be used in a closed-loop supply chain to improve the efficiency of ordering and the operation of a just-in-time remanufacturing system; however, this invariably incurs costs. Companies must carefully consider the opportunities and challenges posed by RFID technology to ensure that such an investment is worthwhile. This study contributes to the body of existing closed loop supply chain literature through formulating the problems as continuous functions to reduce the complexity of the problems and decrease the amount of data required which greatly facilitates development and implementation. The objective of this study was to determine the number of distribution centers, the number of remanufacturing centers, the joint replenishment cycle time, and the investment in RFID required to minimize total network costs. This paper applies a continuous approximation (CA) approach to model the network. Nonlinear programming techniques are developed to solve the optimization problems. The results of numerical analysis demonstrate that the adoption of RFID could be highly beneficial to companies. We also investigate the effects of parameter values on costs and decisions to gain managerial insight.

Growing awareness of environmental issues is prompting the development of sustainable supply chain management. Closed-loop supply chains in which used products can be returned for remanufacture are becoming increasingly popular. This paper introduces a two-phase approach to the design of supply chain networks taking into account carbon emission and remanufacturing. In the first phase, a continuous approximation model is used to design the forward supply chain network. The objective is to minimize the total forward network cost by simultaneously determining the number and the service areas of distribution centers (DCs) and the replenishment cycle time for DCs. A nonlinear optimization technique is used to solve the forward supply chain network design problem. In the second phase, a reverse supply chain network is formulated based on the results of the first phase to determine the optimal number and service areas of remanufacturing centers (RCs) and the replenishment cycle time for RCs. Finally, numerical analyses are conducted to show the solution approach and provide some managerial insights.

Process modelling is the foundation of developing process controllers for monitoring and improving process/system health. Modelling process behaviours using a pure empirical approach might not be feasible due to limitation in collecting large amount of data. Engineering models provide valuable information about processes’ general behaviours but they might not capture distinct characteristics in the particular process studied. Many recent publications presented various ideas of using limited experimental data to adjust engineering models for making them suitable for certain applications. However, the focuses there are global adjustments, where modification of engineering models impacts the entire model-application region. In practice, some engineering models are only valid in a part of experimental data domain. Moreover, many discrepancies between engineering models and experimental data are in local regions. For example, in a chemical vapour deposition process, at high temperatures a process may be descri...

Experiments related to nanofabrication often face challenges of resource-limited experimental budgets, highly demanding tolerance requirements, and complicated response surfaces. Therefore, wisely selecting design points is crucial in order to minimize ..

This study considers a manufacturer-retailer supply chain in which the manufacturer provides trade promotions the retailer. We compare with four trade promotions (off-invoice, scan-back, unsold-discount and target rebate). Consider the linear price sensitive and uncertain demand, the results indicate that both manufacturer and retailer benefit from the unsold-discount policy; only manufacturer benefits from the target rebate policy. However, target rebate can benefit both manufacturer and retailer when the wholesale price is determined within the appropriate range of an agreement. Consider the price-elasticity and uncertain demand, both manufacturer and retailer can only benefit from the target rebate policy.

Conducting experiments to understand and model a complex process or system is usually costly and time-consuming due to multistages, multivariables, and multidisciplinary issues involved in the complex process. To reduce the complexity, for a single experiment, experimenters often fix some variables and investigate the effects of a smaller subset of variables. If then, it is possible to build individual models for each subset of variables, but this only allows partial understanding of the whole process. In this paper, we propose a method for building a holistic model of a complex process using multiple partial models that are learned from multiple sub-experiments that focus on different variables or the same variables but with different variable ranges. Using the proposed holistic model, it should be possible to provide an initial understanding of the complex process involving all variables. The effectiveness of the proposed method is demonstrated using a real example from a buckypaper process.

An accelerated degradation test (ADT) can be used to assess the reliability of highly reliable products by using degradation information. In this study, to exhibit a monotone increasing pattern, the gamma process is used to model the degradation of a product subject to a constant-stress ADT of two loadings. Maximum likelihood estimates (MLEs) of the parameters of the ADT model were obtained. Given a budget for the total cost, an optimal ADT procedure was established to minimize the asymptotic variance of the MLE of the mean time to failure of a product, and the sample size and termination time of each run of the ADT at a constant measurement frequency were determined. An algorithm is provided to achieve an optimal ADT plan. An extensive Monte Carlo simulation was implemented to evaluate the sensitivity of the MLE variations to the sample size. A lumen degradation data set of light emitting diodes is presented to illustrate the proposed method.

Manufacturing quality and lifetime testing conditions may affect product reliability measurements. The literature for the design of experiments (DOE) and robust product optimization considering both quality and reliability issues is scarce. This article develops a model to include both manufacturing variables and accelerated degradation test (ADT) conditions. A simple algorithm provides calculations of the maximum likelihood estimates (MLEs) of these model parameters and percentile lifetimes. Variances of these estimates are derived based on large sample theory. Our DOE plans focus on deciding replication sizes and proportions of the test-units allocated at three stress levels for various manufacturing and ADT conditions. This work also explores robust parameter design (RPD) optimizations for selected controllable manufacturing variables to achieve the longest product lifetime and smallest variation in lifetime distributions.

In the beginning of sequential experimentation, space-filling designs are more appropriate for exploring process behaviour since they do not require any assumptions about the underlying model. In the latter stages of sequential experimentation, however, when data are collected and more knowledge about the process behaviour is gathered, model-based optimal designs may be more appropriate. This article proposes an adaptive combined design (ACD) balancing the characteristics of both design criteria at different stages of the sequential experiments. The tuning parameter associated with the ACD adaptively gauges the amount of process knowledge gain, which is used to improve the estimation of model parameters while still allowing for the exploration of model uncertainties. Rather than employing the weighted-sum method, an -constraint method is proposed to balance the two design criteria. Property investigation shows that the ACD provides better estimation of parameters over the space-filling design, and yet is ...

In the field of nanofabrication, engineers often face unique challenges in resource-limited experimental budgets, the sensitive nature of process behavior with respect to controllable variables, and highly demanding tolerance requirements. To effectively overcome these challenges, this article proposes a methodology for a sequential design of experiments through batches of experimental runs, aptly named Layers of Experiments with Adaptive Combined Design (LoE/ACD). In higher layers, where process behavior is less understood, experimental regions cover more design space and data points are more spread out. In lower layers, experimental regions are more focused to improve understanding of process sensitivities in a local, data-rich environment. The experimental design is a combination of a space-filling and an optimal design with a tuning parameter that is dependent on the amount of information accumulated over the various layers. The proposed LoE/ACD method is applied to optimize a carbon dioxide (epet-CO2) assisted deposition process for fabricating silver nanoparticles with pressure and temperature variables. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 127–142, 2015

Motivated by the significant influence of trade allowance on store operation and the efficiency of shelf-space allocation, this article develops a model for optimizing category-level shelf-space management. A category shelf-space allocation framework with trade allowance is presented and a multi-player Retailer Stackelberg game is introduced to model the interaction between retailer and manufacturers. With this framework, a retailer maximizes profit by taking the manufacturers' trade allowance response into account, which provides a realistic approach of simultaneously determining the shelf-space and trade promotion decisions under the consideration of interactions among products. A piecewise linearization method is employed to reformulate the Mixed Integer Nonlinear Programming (MINLP) problem into a linear MIP problem for optimal solutions. Numerical examples demonstrate significant advantage of the proposed framework and quantitative analysis leads to a variety of managerial insights.

This article studies a container drayage problem with flexible orders defined by using requiring and releasing attributes as a unified formulation of various order types. A determined-activities-on-vertex (DAOV) graph introduces a temporary vertex set to formulate different truck statuses. The problem is formulated as a mixed-integer nonlinear programming model based on the DAOV graph. Four strategies including a window partition based (WPB) strategy are presented and evaluated extensively to solve the problem. Results indicate that the WPB method could solve the problem effectively and efficiently. Furthermore, this method is robust considering the operating time biases compared to other algorithms.

An initial experimental design criteria is proposed for optimization problems by combining multiple, potentially competing, sources of prior information on similar, nonidentical systems.

The study and optimization of nanofabrication techniques in nanotechnology research is often challenging because experiments are costly to conduct in terms of time and money. In particular, for a new system that has not been previously studied at length, it is a challenge to efficiently plan the first round of experiments in the region of interest near the process optimum, and there may be multiple process inputs that must be optimized simultaneously. A purely statistical approach to this challenge would apply a space-filling experimental design, or, alternatively, domain knowledge could be applied to guide the experimental design. However, both of these approaches may waste precious resources by failing to sample efficiently near the desired process output. In this work, a novel technique termed “initial experimental design” (IED) is applied to combine the statistical and experimental approaches for planning the initial round of experiments for a new system that is related to a similar but nonidentical e...

We propose a novel likelihood method for analyzing time-to-event data when multiple events and multiple missing data intervals are possible prior to the first observed event for a given subject. This research is motivated by data obtained from a heart monitor used to track the recovery process of subjects experiencing an acute myocardial infarction. The time to first recovery, T1, is defined as the time when the ST-segment deviation first falls below 50% of the previous peak level. Estimation of T1 is complicated by data gaps during monitoring and the possibility that subjects can experience more than one recovery. If gaps occur prior to the first observed event, T, the first observed recovery may not be the subject’s first recovery. We propose a parametric gap likelihood function conditional on the gap locations to estimate T1. Standard failure time methods that do not fully utilize the data are compared to the gap likelihood method by analyzing data from an actual study and by simulation. The proposed gap likelihood method is shown to be more efficient and less biased than interval censoring and more efficient than right censoring if data gaps occur early in the monitoring process or are short in duration.

In today’s retail business many companies have a complex distribution network with several national and regional distribution centers. This article studies an integrated facility location and inventory allocation problem for designing a distribution network with multiple distribution centers and retailers. The key decisions are where to locate the regional distribution centers (RDCs), how to assign retail stores to RDCs and what should be the inventory policy at the different locations such that the total network cost is minimized. Due to the complexity of the problem, a continuous approximation (CA) model is used to represent the network. Nonlinear programming techniques are developed to solve the optimization problems. The main contribution of this work lies in developing a new CA modeling technique when the discrete data cannot be modeled by a continuous function and applying this technique to solve an integrated facility location-allocation and inventory-management problem. Our methodology is illustrated with the network from a leading US retailer. Numerical analysis suggests that the total cost is significantly lower in the case of the integrated model as compared with the non-integrated model, where the location-allocation and inventory-management problems are considered separately. This paper also studies the effects of changing parameter values on the optimal solutions and to point out some management implications.

Managing shelf space is critical for retailers to attract customers and optimize profits. This article develops a shelf-space allocation optimization model that explicitly incorporates essential in-store costs and considers space- and cross-elasticities. A piecewise linearization technique is used to approximate the complicated nonlinear space-allocation model. The approximation reformulates the non-convex optimization problem into a linear mixed integer programming (MIP) problem. The MIP solution not only generates near-optimal solutions for large scale optimization problems, but also provides an error bound to evaluate the solution quality. Consequently, the proposed approach can solve single category-shelf space management problems with as many products as are typically encountered in practice and with more complicated cost and profit structures than currently possible by existing methods. Numerical experiments show the competitive accuracy of the proposed method compared with the mixed integer nonlinear programming shelf-space model. Several extensions of the main model are discussed to illustrate the flexibility of the proposed methodology.

This research investigates how the experience learned in repeated transactions by consumers and manufacturers would affect supply-chain partners' strategic decisions such as price, order quantity and service level. Consumer demand depends on two factors: (1) retailer price and (2) service level provided by the manufacturer in the past and current transaction periods. Game theory is used to understand interactions between the horizontally competitive suppliers and their vertical interactions to the common retailer in the one-period looking-ahead decision environment. Dynamic-system concepts are integrated into the game-theoretic model for understanding the evolution of the strategic decisions over multiple time periods. The research shows that the manufacturer with any type of cost-advantage for providing more services to its customers will capture a larger market than its competitor. Comparison of our model to the myopic model indicates that the myopic suppliers, who ignore the customer learning effect on future periods, shrink their market sizes and earn less profit over time. The manufacturers who use the learning experience to plan future investment can prevent this phenomenon from happening and enhance their competitiveness.

This study addresses an integrated facility location and inventory allocation problem considering transportation cost discounts. Specifically, this article considers two types of transportation discounts simultaneously: quantity discounts for inbound transportation cost and distance discounts for outbound transportation cost. This study uses an approximation procedure to simplify DC distance calculation details, and develops an algorithm to solve the aforementioned supply chain management (SCM) problems using nonlinear optimization techniques. Numerical studies illustrate the solution procedures and the effects of the model parameters on the SCM decisions and total costs. Results of this study serve as a reference for business managers and administrators.

A sequential design of experiments methodology with an adaptive design space is proposed and implemented to optimize a nanofabrication technique that possesses significant uncertainty in terms of design region and model structure along with an engineering tolerance requirement. This method is termed Layers of Experiment (LoE) with Adaptive Combined Design (ACD) and is developed specifically for advanced technology processes where there is little or no foreknowledge of the design region and/or model structure from either mechanistic understanding or empirical studies. This technique was applied to optimize an elevated pressure, elevated temperature carbon dioxide (epet-CO2) nanoparticle deposition process where silver nanoparticles were deposited directly from an organometallic precursor in the fluid phase onto a silicon wafer surface. A target mean nanoparticle size of 40 nm was chosen, with surface enhanced Raman spectroscopy (SERS) as the motivating application. Using the LoE/ACD method, it was possible...

This research seeks to determine the optimal order amount for a retailer given uncertainty in a supply-chain's logistics network due to unforeseeable disruption or various types of defects (e.g., shipping damage, missing parts and misplacing products). Mixture distribution models characterize problems from solitary failures and contingent events causing network to function ineffectively. The uncertainty in the number of good products successfully reaching distribution centers (DCs) and retail stores poses a challenge in deciding product-order amounts. Because the commonly used ordering plan developed for maximizing expected profits does not allow retailers to address concerns about contingencies; this research proposes two improved procedures with risk-averse characteristics towards low probability and high impact events. Several examples illustrate the impact of a DC's operation policies and model assumptions on a retailer's product-ordering plan and resulting sales profit.

Shelf management is a crucial task in retailing. Because of the large number of products found in most retail stores (sometimes more than 60 000), current shelf space management models can only solve sub-problems of the overall store optimization problem, since the size of the complete optimization problem would be prohibitively large. Consequently, an optimal allocation of store shelf space to products has not yet been achieved. We show that a hierarchical decomposition technique, consisting of two interwoven models, is suitable to overcome this limitation and, thus, is capable of finding accurate solutions to very large and complex shelf space management problems. We further conclude that other important variables (such as product-price) can be included into the methodology and their optimal values can be determined using the same solution technique. Our methodology is illustrated on a real-life application where we predict a 22.33% increase in store profits if our model's solution is implemented.

This research highlights the importance of service from manufacturers in the interactions between two competing manufacturers and their common retailer, facing end consumers who are sensitive to both retail price and manufacturer service. A game-theoretic framework is applied to obtain the equilibrium solutions for every entity. This article studies and compares results from three possible supply chain scenarios, (1) Manufacturer Stackelberg, (2) Retailer Stackelberg, and (3) Vertical Nash. This research concludes that consumers receive higher service level when every channel member possesses equal bargaining power (e.g., Vertical Nash). An interesting result shows that as the market base of one product increases, the competitor also benefits but at a lesser amount than the manufacturer of the first product. Furthermore, when one manufacturer has some economic advantage in providing service, the retailer will act to separate market segment by selling the product with low-cost/lower-quality service at a low price and selling the product with high-cost/high-quality service at a high price. The results and the modeling approach are useful references for managerial decisions and administrations.

This article proposes an adjusted empirical likelihood estimation (AMELE) method to model and analyze accelerated life testing data. This approach flexibly and rigorously incorporates distribution assumptions and regression structures by estimating equations within a semiparametric estimation framework. An efficient method is provided to compute the empirical likelihood estimates, and asymptotic properties are studied. Real-life examples and numerical studies demonstrate the advantage of the proposed methodology.

The increasing use of standard machines in manufacturing processes provides opportunities for sharing information from similar operations to improve the accuracy of process model characterization for supporting root cause analysis and process monitoring activities. This article investigates how to integrate data from parallel sites that are alike in some ways but dissimilar in others. The parallel sites could be several machines that accomplish the same process step, several industrial locations that produce the same product or even several different time windows for the same machine. The proposed Bayesian parallel site model flexibly allows for a compromise between pooling the data completely and treating sites as completely unrelated. One of the key features in the hierarchical model is the quasi-common parameters that are different from site to site, but have some commonality between sites. The similarities between the individual quasi-common parameters are modeled through common global hyperparameters...

Nanotechnology has become a multidisciplinary subject that will affect every sector of the economy and daily life in the near future. Science-based technologies and the use of statistical methods have helped the advancement of nanotechnology. Some insta..

This article introduces game theory commonly used in supply-chain analyses to solve potential conflicts between manufacturing partners at various process stages. Through our methods, the partners collaboratively decide settings of controllable variables to make product less sensitive to process noises, especially variations propagated from upstream processes. Modelling and solution strategies of this new research topic are provided along with illustrated examples and comparison studies.

Recent advances in sensor instrumentation have provided opportunities for process engineers to collect data at various process steps in order to detect process problems and develop remedial procedures. This article presents a structured wavelet model for the reduction of two-dimensional data having distinct structures. The wavelet component of our model can handle irregular data patterns exhibiting many peaks and valleys, while the existence of a distinct data structure prompts the use of polynomial functions on wavelet coefficients. The two-dimensional antenna data is reduced with a structured wavelet model followed by some procedures for the detection of process defects based on the reduced-size data. A real-life example is presented to illustrate the usefulness of the proposed tools in detecting process problems from a potentially large volume of data exhibiting many peaks and valleys.

The power law process has been shown to be a useful tool in characterizing the failure process of repairable systems. In this study, a procedure is proposed for detecting and estimating a mixture of reliable and unreliable systems. Using a simple likeli..

We decide on the time intervals between two replenishments first.We make the forecasts for time intervals.We propose grouping ATMs into nearby-location clusters, to improve forecast accuracy.Group forecast results are loaded to the ATMs.Example studies show that the proposed framework result in lower costs. In ATM cash replenishment banks want to use less resources (e.g., cash kept in ATMs, trucks for loading cash) for meeting fluctuated customer demands. Traditionally, forecasting procedures such as exponentially weighted moving average are applied to daily cash withdraws for individual ATMs. Then, the forecasted results are provided to optimization models for deciding the amount of cash and the trucking logistics schedules for replenishing cash to all ATMs. For some situations where individual ATM withdraws have so much variations (e.g., data collected from Istanbul ATMs) the traditional approaches do not work well. This article proposes grouping ATMs into nearby-location clusters and also optimizing the aggregates of daily cash withdraws (e.g., replenish every week instead of every day) in the forecasting process. Example studies show that this integrated forecasting and optimization procedure performs better for an objective in minimizing costs of replenishing cash, cash-interest charge and potential customer dissatisfaction.

Distributed sensing, a system-wide deployment of sensing devices, has resulted in both temporally and spatially dense data-rich environments. This new technology provides unprecedented opportunities for quality and productivity improvement. This paper discusses the state-of-the-art practice, research challenges, and future directions related to distributed sensing. The discussion includes the optimal design of distributed sensor systems, information criteria, and processing for distributed sensing and optimal decision making in distributed sensing. The discussion also provides applications based on the authors' research experiences. Note to Practitioners-This paper is based on a panel discussion on the topic of the emerging technology of distributed sensing and the associated challenges and opportunities. The panel, constituted by a group of leading researchers and practitioners with expertise in operations and statistics, convened during the Institute for Operations Research and the Management Sciences (INFORMS) 2003 annual meeting in Atlanta, GA. This panel focused its discussion on the information layer technology of distributed sensing for quality and productivity improvements, which differentiates this panel from other similar panels that were formed in a different society. The panelists provided their visions about the state-of-the-art practice, research challenges, and future research directions, and also discussed potential applications based on their own experiences

The term ‘functional data’ (or ‘curve’) refers to an analog or digital signal measured during each operational cycle of a manufacturing process. Functional data contain rich information concerning the process condition and product quality for quality improvement. We propose a vertical group-wise threshold (VGWT) procedure for the reduction of multiple high-dimensional functional data containing class information. The proposed method selects important wavelet coefficients for the whole set of multiple curves by a comparison between every vertical energy metric and a threshold (VGWT). The VGWT increases the class separability with a reasonably small loss in data-reduction efficiency. A real-life example is presented to illustrate the proposed method, and a Monte Carlo simulation is performed to study the impact of different levels of class variation and noise.

In modeling defect counts collected from an established manufacturing processes, there are usually a relatively large number of zeros (non-defects). The commonly used models such as Poisson or Geometric distributions can underestimate the zero-defect probability and hence make it difficult to identify significant covariate effects to improve production quality. This article introduces a flexible class of zero inflated models which includes other familiar models such as the Zero Inflated Poisson (ZIP) models, as special cases. A Bayesian estimation method is developed as an alternative to traditionally used maximum likelihood based methods to analyze such data. Simulation studies show that the proposed method has better finite sample performance than the classical method with tighter interval estimates and better coverage probabilities. A real-life data set is analyzed to illustrate the practicability of the proposed method easily implemented using WinBUGS.

Functional data characterize the quality or reliability performance of many manufacturing processes. As can be seen in the literature, such data are informative in process monitoring and control for nanomachining, for ultra-thin semiconductor fabrication, and for antenna, steel-stamping, or chemical manufacturing processes. Many functional data in manufacturing applications show complicated transient patterns such as peaks representing important process characteristics. Wavelet transforms are popular in the computing and engineering fields for handling these types of complicated functional data. This article develops a wavelet-based statistical process control (SPC) procedure for detecting ‘out-of-control’ events that signal process abnormalities. Simulation-based evaluations of average run length indicate that our new procedure performs better than extensions from well-known methods in the literature. More importantly, unlike recent SPC research on linear profile data for monitoring global changes of dat...

This paper uses random scales similar to random effects used in the generalized linear mixed models to describe “inter-location” population variation in variance components for modeling complicated data obtained from applications such as antenna manufacturing. Our distribution studies lead to a complicated integrated extended quasi-likelihood (IEQL) for parameter estimations and large sample inference derivations. Laplace's expansion and several approximation methods are employed to simplify the IEQL estimation procedures. Asymptotic properties of the approximate IEQL estimates are derived for general structures of the covariance matrix of random scales. Focusing on a few special covariance structures in simpler forms, the authors further simplify IEQL estimates such that typically used software tools such as weighted regression can compute the estimates easily. Moreover, these special cases allow us to derive interesting asymptotic results in much more compact expressions. Finally, numerical simulation results show that IEQL estimates perform very well in several special cases studied.

This article presents new data reduction methods based on the discrete wavelet transform to handle potentially large and complicated nonstationary data curves. The methods minimize objective functions to balance the trade-off between data reduction and modeling accuracy. Theoretic investigations provide the optimality of the methods and the large-sample distribution of a closed-form estimate of the thresholding parameter. An upper bound of errors in signal approximation (or estimation) is derived. Based on evaluation studies with popular testing curves and real-life datasets, the proposed methods demonstrate their competitiveness with the existing engineering data compression and statistical data denoising methods for achieving the data reduction goals. Further experimentation with a tree-based classification procedure for identifying process fault classes illustrates the potential of the data reduction tools. Extension of the engineering scalogram to the reduced-size semiconductor fabrication data leads ...

Summary Semiparametric maximum likelihood estimation with estimating equations (SMLE) is more flexible than traditional methods; it has fewer restrictions on distributions and regression models. The required information about distribution and regression structures is incorporated in estimating equations of the SMLE to improve the estimation quality of non-parametric methods. The likelihood of SMLE for censored data involves complicated implicit functions without closed-form expressions, and the first derivatives of the log-profile-likelihood cannot be expressed as summations of independent and identically distributed random variables; it is challenging to derive asymptotic properties of the SMLE for censored data. For group-censored data, the paper shows that all the implicit functions are well defined and obtains the asymptotic distributions of the SMLE for model parameters and lifetime distributions. With several examples the paper compares the SMLE, the regular non-parametric likelihood estimation method and the parametric MLEs in terms of their asymptotic efficiencies, and illustrates application of SMLE. Various asymptotic distributions of the likelihood ratio statistics are derived for testing the adequacy of estimating equations and a partial set of parameters equal to some known values.

This work reports on a novel in situ sensing technique for monitoring the thickness of selectively grown Si epitaxial layers. The technique can be extended to detect selectivity loss when Si nuclei begin to appear on the insulator surface. In this technique, a quadruple mass spectrometer (QMS) monitors the ionized molecular hydrogen (H/sub 2//sup +/) signal, which is a by-product of the chemical-vapor deposition process. The thickness of the epitaxial layer is determined by evaluating the area under the hydrogen signal. We have deliberately used silane (SiH/sub 4/) without HCl or Cl/sub 2/ to achieve both nonselective and selective depositions. We also show that the amount of hydrogen produced by the deposition process is a strong function of the exposed Si area on the wafer and the effect can be accurately monitored by QMS. This finding was exploited to develop an in situ sensing method to detect the selectivity loss. When selectivity is lost, Si nuclei begin to form on the insulator surface increasing the effective Si area on the wafer. Consequently, the rate of hydrogen production increases rapidly as nuclei coalesce, resulting in a distinct change in the functional form of the hydrogen signal. The hydrogen signal was analyzed using an automatic edge detection procedure based on the wavelet transform modulus maxima representation. The technique facilitated the determination of selective film thickness from the time-integrated hydrogen (H/sub 2//sup +/) signal. To the authors' knowledge, This work represents one of the first applications of wavelets to in situ process monitoring and fault detection in semiconductor manufacturing. The authors expect the methodology presented in This work to be readily transferable to other selective deposition processes, including those that utilize dichlorosilane and disilane since hydrogen is a by-product of those processes as well.