Development of complex products and large systems is a highly interactive social process involving hundreds of people designing thousands of interrelated components and making millions of coupled decisions. Nevertheless, in the research summarized by this paper, we have created methods to study the development process, identify its underlying structures, and critique its operation. In this article, we introduce three views of product development complexity: a process view, a product view, and an organization view. We are able to learn about the complex social phenomenon of product development by studying the patterns of interaction across the decomposed elements within each view. We also compare the alignment of the interaction patterns between the product, process, and organization domains. We then propose metrics of product development complexity by studying and comparing these interaction patterns. Finally, we develop hypotheses regarding the patterns of product development interactions, which will be helpful to guide future research. / Singapore-MIT Alliance (SMA)

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

Report covers June 1, 1976-July 31, 1978. / Each v. has also a distinctive title. / National Science Foundation. Grant NSF/RANN APR76-12036 National Science Foundation. Grant DAR78-17826

The first primary objective of this dissertation is to develop a framework that can quantitatively measure complexity of manufacturing systems in various configurations, including conjoined and disjoined systems. In this dissertation, an analytical model for manufacturing systems complexity that employs information entropy theory is proposed and verified. The model uses probability distribution of information regarding resource allocations that are described in terms of interactions among resources for part processing and part processing requirements. In the proposed framework, both direct and indirect interactions among resources are modeled using a matrix, called interaction matrix, which accounts for part processing and waiting times. The proposed complexity model identifies a manufacturing system that has evenly distributed interactions among resources as being more complex, because under disruption situation more information is required to identify source of the disruption. In addition, implicit relationships between the system complexity and performance in terms of resource utilizations, waiting time, cycle time and throughput of the system are studied in this dissertation by developing a computer program for simulating general job shop environment. The second primary objective of this dissertation is to develop a mathematical model for measuring the vulnerability of the supply chain systems. Global supply chains are exposed to different kinds of disruptions. This has promoted the issue of supply chain resilience higher than ever before in business as well as supporting agendas. In this dissertation, an extension of the proposed measure for manufacturing system complexity is used to measure the vulnerability of the supply chain systems using information entropy theory and influence matrix. We define the vulnerability of supply chain systems based on required information that describes the system in terms of topology and interrelationship among components. The proposed framework for vulnerability modeling in this dissertation focus on disruptive events such as natural disasters, terrorist attacks, or industrial disputes, rather than deviations such as variations in demand, procurement and transportation.

In statistical data mining research, datasets often have nonlinearity and high-dimensionality. It has become difficult to analyze such datasets in a comprehensive manner using traditional statistical methodologies. Kernel-based data mining is one of the most effective statistical methodologies to investigate a variety of problems in areas including pattern recognition, machine learning, bioinformatics, chemometrics, and statistics. In particular, statistically-sophisticated procedures that emphasize the reliability of results and computational efficiency are required for the analysis of high-dimensional data. In this dissertation, first, a novel wrapper method called SVM-ICOMP-RFE based on hybridized support vector machine (SVM) and recursive feature elimination (RFE) with information-theoretic measure of complexity (ICOMP) is introduced and developed to classify high-dimensional data sets and to carry out subset selection of the variables in the original data space for finding the best for discriminating between groups. Recursive feature elimination (RFE) ranks variables based on the information-theoretic measure of complexity (ICOMP) criterion. Second, a dual variables functional support vector machine approach is proposed. The proposed approach uses both the first and second derivatives of the degradation profiles. The modified floating search algorithm for the repeated variable selection, with newly-added degradation path points, is presented to find a few good variables while reducing the computation time for on-line implementation. Third, a two-stage scheme for the classification of near infrared (NIR) spectral data is proposed. In the first stage, the proposed multi-scale vertical energy thresholding (MSVET) procedure is used to reduce the dimension of the high-dimensional spectral data. In the second stage, a few important wavelet coefficients are selected using the proposed SVM gradient-recursive feature elimination (RFE). Fourth, a novel methodology based on a human decision making process for discriminant analysis called PDCM is proposed. The proposed methodology consists of three basic steps emulating the thinking process: perception, decision, and cognition. In these steps two concepts known as support vector machines for classification and information complexity are integrated to evaluate learning models.