The phenomenon of using alternative sourcing has attracted the attention of researchers in the field of supply chain and operations management. Alternative sourcing refers to any method other than the status quo. When competition arises in the marketplace, firms tend to innovate by deviating from status quo approaches and take risks to gain advantages throughout their supply chains. One such alternative sourcing risk is using soft criteria primarily in the supplier selection process. While anecdotal evidence exists, the supplier selection literature stream fails to explain how alternative sourcing might impact operational performance. Such alternative approaches- evaluating tangibles versus intangibles- have come under scrutiny. Firms have used soft criteria, considered more difficult to quantify, mainly as a supplement to hard criteria- those status quo criteria based on operational performance metrics of cost, quality, timeliness of delivery, service level, etc. Researchers and practitioners alike have found empirical evidence to support a plethora of theories regarding the impact of hard criteria in supplier selection on the operational impact of buyer-supplier relationships. This research examines alternative sourcing by studying alternative supplier selection criteria, simulating the status quo versus alternative supplier selection methodologies, and studying alternative supplier evaluation techniques. First, the qualitative examination of sourcing teams provides case studies in private and public sector organizations to abductively establish boundaries of alternative supplier selection approaches. Second, a numerical experiment compares status quo supplier selection versus alternative methodologies to ultimately test long-held supplier selection assumptions. Lastly, a qualitative study of alternative supplier evaluation techniques establishes boundaries of alternative supplier evaluation approaches. This research makes theoretical contributions to sourcing and organization behavior literature streams.

Ramping up a semiconductor wafer fabrication facility is a challenging endeavor. One of the key components of this process is to schedule a large number of activities in installing and qualifying (Install/Qual) the capital intensive and sophisticated manufacturing equipment. Activities in the Install/Qual process share multiple types of expensive and scare resources and each activity might potentially have multiple processing options. In this dissertation, the semiconductor capital equipment Install/Qual scheduling problem is modeled as a multi-mode resource-constrained project scheduling problem (MRCPSP) with multiple special extensions. Three phases of research are carried out: the first phase studies the special problem characteristics of the Install/Qual process, including multiple activity processing options, time-varying resource availability levels, resource vacations, and activity splitting that does not allow preemption. A modified precedence tree-based branch-and-bound algorithm is proposed to solve small size academic problem instances to optimality. Heuristic-based methodologies are the main focus of phase 2. Modified priority rule-based simple heuristics and a modified random key-based genetic algorithm (RKGA) are proposed to search for Install/Qual schedules with short makespans but subject to resource constraints. Methodologies are tested on both small and large random academic problem instances and instances that are similar to the actual Install/Qual process of a major semiconductor manufacturer. In phase 3, a decision making framework is proposed to strategically plan the Install/Qual capacity ramp. Product market demand, product market price, resource consumption cost, as well as the payment of capital equipment, are considered. A modified simulated annealing (SA) algorithm-based optimization module is integrated with a Monte Carlo simulation-based simulation module to search for good capacity ramping strategies under uncertain market information. The decision making framework can be used during the Install/Qual schedule planning phase as well as the Install/Qual schedule execution phase when there is a portion of equipment that has already been installed or qualified. Computational experiments demonstrate the effectiveness of the decision making framework.

Nonregular screening designs can be an economical alternative to traditional resolution IV 2^(k-p) fractional factorials. Recently 16-run nonregular designs, referred to as no-confounding designs, were introduced in the literature. These designs have the property that no pair of main effect (ME) and two-factor interaction (2FI) estimates are completely confounded. In this dissertation, orthogonal arrays were evaluated with many popular design-ranking criteria in order to identify optimal 20-run and 24-run no-confounding designs. Monte Carlo simulation was used to empirically assess the model fitting effectiveness of the recommended no-confounding designs. The results of the simulation demonstrated that these new designs, particularly the 24-run designs, are successful at detecting active effects over 95% of the time given sufficient model effect sparsity. The final chapter presents a screening design selection methodology, based on decision trees, to aid in the selection of a screening design from a list of published options. The methodology determines which of a candidate set of screening designs has the lowest expected experimental cost.

This dissertation explores different methodologies for combining two popular design paradigms in the field of computer experiments. Space-filling designs are commonly used in order to ensure that there is good coverage of the design space, but they may not result in good properties when it comes to model fitting. Optimal designs traditionally perform very well in terms of model fitting, particularly when a polynomial is intended, but can result in problematic replication in the case of insignificant factors. By bringing these two design types together, positive properties of each can be retained while mitigating potential weaknesses. Hybrid space-filling designs, generated as Latin hypercubes augmented with I-optimal points, are compared to designs of each contributing component. A second design type called a bridge design is also evaluated, which further integrates the disparate design types. Bridge designs are the result of a Latin hypercube undergoing coordinate exchange to reach constrained D-optimality, ensuring that there is zero replication of factors in any one-dimensional projection. Lastly, bridge designs were augmented with I-optimal points with two goals in mind. Augmentation with candidate points generated assuming the same underlying analysis model serves to reduce the prediction variance without greatly compromising the space-filling property of the design, while augmentation with candidate points generated assuming a different underlying analysis model can greatly reduce the impact of model misspecification during the design phase. Each of these composite designs are compared to pure space-filling and optimal designs. They typically out-perform pure space-filling designs in terms of prediction variance and alphabetic efficiency, while maintaining comparability with pure optimal designs at small sample size. This justifies them as excellent candidates for initial experimentation.

This research is motivated by a deterministic scheduling problem that is fairly common in manufacturing environments, where there are certain processes that call for a machine working on multiple jobs at the same time. An example of such an environment is wafer fabrication in the semiconductor industry where some stages can be modeled as batch processes. There has been significant work done in the past in the field of a single stage of parallel machines which process jobs in batches. The primary motivation behind this research is to extend the research done in this area to a two-stage flow-shop where jobs arrive with unequal ready times and belong to incompatible job families with the goal of minimizing total weighted tardiness. As a first step to propose solutions, a mixed integer mathematical model is developed which tackles the problem at hand. The problem is NP-hard and thus the developed mathematical program can only solve problem instances of smaller sizes in a reasonable amount of time. The next step is to build heuristics which can provide feasible solutions in polynomial time for larger problem instances. The basic nature of the heuristics proposed is time window decomposition, where jobs within a moving time frame are considered for batching each time a machine becomes available on either stage. The Apparent Tardiness Cost (ATC) rule is used to build batches, and is modified to calculate ATC indices on a batch as well as a job level. An improvisation to the above heuristic is proposed, where the heuristic is run iteratively, each time assigning start times of jobs on the second stage as due dates for the jobs on the first stage. The underlying logic behind the iterative approach is to improve the way due dates are estimated for the first stage based on assigned due dates for jobs in the second stage. An important study carried out as part of this research is to analyze the bottleneck stage in terms of its location and how it affects the performance measure. Extensive experimentation is carried out to test how the quality of the solution varies when input parameters are varied between high and low values.

The ever-changing economic landscape has forced many companies to re-examine their supply chains. Global resourcing and outsourcing of processes has been a strategy many organizations have adopted to reduce cost and to increase their global footprint. This has, however, resulted in increased process complexity and reduced customer satisfaction. In order to meet and exceed customer expectations, many companies are forced to improve quality and on-time delivery, and have looked towards Lean Six Sigma as an approach to enable process improvement. The Lean Six Sigma literature is rich in deployment strategies; however, there is a general lack of a mathematical approach to deploy Lean Six Sigma in a global enterprise. This includes both project identification and prioritization. The research presented here is two-fold. Firstly, a process characterization framework is presented to evaluate processes based on eight characteristics. An unsupervised learning technique, using clustering algorithms, is then utilized to group processes that are Lean Six Sigma conducive. The approach helps Lean Six Sigma deployment champions to identify key areas within the business to focus a Lean Six Sigma deployment. A case study is presented and 33% of the processes were found to be Lean Six Sigma conducive. Secondly, having identified parts of the business that are lean Six Sigma conducive, the next steps are to formulate and prioritize a portfolio of projects. Very often the deployment champion is faced with the decision of selecting a portfolio of Lean Six Sigma projects that meet multiple objectives which could include: maximizing productivity, customer satisfaction or return on investment, while meeting certain budgetary constraints. A multi-period 0-1 knapsack problem is presented that maximizes the expected net savings of the Lean Six Sigma portfolio over the life cycle of the deployment. Finally, a case study is presented that demonstrates the application of the model in a large multinational company. Traditionally, Lean Six Sigma found its roots in manufacturing. The research presented in this dissertation also emphasizes the applicability of the methodology to the non-manufacturing space. Additionally, a comparison is conducted between manufacturing and non-manufacturing processes to highlight the challenges in deploying the methodology in both spaces.

A good production schedule in a semiconductor back-end facility is critical for the on time delivery of customer orders. Compared to the front-end process that is dominated by re-entrant product flows, the back-end process is linear and therefore more suitable for scheduling. However, the production scheduling of the back-end process is still very difficult due to the wide product mix, large number of parallel machines, product family related setups, machine-product qualification, and weekly demand consisting of thousands of lots. In this research, a novel mixed-integer-linear-programming (MILP) model is proposed for the batch production scheduling of a semiconductor back-end facility. In the MILP formulation, the manufacturing process is modeled as a flexible flow line with bottleneck stages, unrelated parallel machines, product family related sequence-independent setups, and product-machine qualification considerations. However, this MILP formulation is difficult to solve for real size problem instances. In a semiconductor back-end facility, production scheduling usually needs to be done every day while considering updated demand forecast for a medium term planning horizon. Due to the limitation on the solvable size of the MILP model, a deterministic scheduling system (DSS), consisting of an optimizer and a scheduler, is proposed to provide sub-optimal solutions in a short time for real size problem instances. The optimizer generates a tentative production plan. Then the scheduler sequences each lot on each individual machine according to the tentative production plan and scheduling rules. Customized factory rules and additional resource constraints are included in the DSS, such as preventive maintenance schedule, setup crew availability, and carrier limitations. Small problem instances are randomly generated to compare the performances of the MILP model and the deterministic scheduling system. Then experimental design is applied to understand the behavior of the DSS and identify the best configuration of the DSS under different demand scenarios. Product-machine qualification decisions have long-term and significant impact on production scheduling. A robust product-machine qualification matrix is critical for meeting demand when demand quantity or mix varies. In the second part of this research, a stochastic mixed integer programming model is proposed to balance the tradeoff between current machine qualification costs and future backorder costs with uncertain demand. The L-shaped method and acceleration techniques are proposed to solve the stochastic model. Computational results are provided to compare the performance of different solution methods.

Surgery is one of the most important functions in a hospital with respect to operational cost, patient flow, and resource utilization. Planning and scheduling the Operating Room (OR) is important for hospitals to improve efficiency and achieve high quality of service. At the same time, it is a complex task due to the conflicting objectives and the uncertain nature of surgeries. In this dissertation, three different methodologies are developed to address OR planning and scheduling problem. First, a simulation-based framework is constructed to analyze the factors that affect the utilization of a catheterization lab and provide decision support for improving the efficiency of operations in a hospital with different priorities of patients. Both operational costs and patient satisfaction metrics are considered. Detailed parametric analysis is performed to provide generic recommendations. Overall it is found the 75th percentile of process duration is always on the efficient frontier and is a good compromise of both objectives. Next, the general OR planning and scheduling problem is formulated with a mixed integer program. The objectives include reducing staff overtime, OR idle time and patient waiting time, as well as satisfying surgeon preferences and regulating patient flow from OR to the Post Anesthesia Care Unit (PACU). Exact solutions are obtained using real data. Heuristics and a random keys genetic algorithm (RKGA) are used in the scheduling phase and compared with the optimal solutions. Interacting effects between planning and scheduling are also investigated. Lastly, a multi-objective simulation optimization approach is developed, which relaxes the deterministic assumption in the second study by integrating an optimization module of a RKGA implementation of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to search for Pareto optimal solutions, and a simulation module to evaluate the performance of a given schedule. It is experimentally shown to be an effective technique for finding Pareto optimal solutions.