Ebook: The Management of Transshipment Terminals: Decision Support for Terminal Operations in Finished Vehicle Supply Chains

1.1 Freight Transshipment We observe an ongoing trend towards globalized industrial produc­ tion. Multinational companies aim at strategic competitive advantages by distributing their activities around the globe. As a result, the in­ dividual supply chains become longer and more complex. Next to the supply chain reliability, companies try to keep supply chains cost effi­ cient and responsive, i.e. warrant short order fulfillment lead times (Siirie and Wagner, 2005). The above goals dictate low inventory levels at the stages of a supply chain as well as a high frequency of transports between the partners involved. Supply Chain Requirements. Detailed performance measures for a supply chain are provided by the Supply Chain Operations Refer­ ence (SCOR) model (Supply-Chain Council, 2002). The SCOR model provides four levels with increasing detail of process modeling. In accor­ dance to the process detail depicted SCOR metrics are defined for each level. Level 1 distinguishes metrics addressing the reliability of supply chains, their responsiveness, flexibility, cost and optionally their assets. On levels 2-4 these metrics are operationalized with respect to the pro­ cess types source, make and deliver. Thus, as substantial activities of the deliver process, transport and transshipment are evaluated as an integral part of the supply chain.

Artificial neural networks (ANNs) offer a general framework for representing non-linear mappings from several input variables to several output variables, and they can be considered as an extension of the many conventional mapping techniques. In addition to many considerations on their biological foundations and their really wide spectrum of applications, constructing appropriate ANNs can be seen as a really hard problem. A distinguished task in building ANNs is the tuning of a set of parameters known as weights. This will be the main focus of the present book. The trained ANNs can be later used in classification (or recognition) problems, where the ANN outputs represent categories, or in prediction (approximation) problems, where the outputs represent continuous variables.

METAHEURISTIC PROCEDURES FOR TRAINING NEURAL NETWORKS provides successful implementations of metaheuristic methods for neural network training. Moreover, the basic principles and fundamental ideas given in the book will allow the readers to create successful training methods on their own. Apart from Chapter 1, in which classical training methods are reviewed for the sake of the book’s completeness, we have classified the chapters in three main categories. The first one is devoted to local search based methods, in which we include Simulated Annealing, Tabu Search, and Variable Neighborhood Search. The second part of the book presents the most effective population based methods, such as Estimation Distribution algorithms, Scatter Search, and Genetic Algorithms. Finally, the third part includes other advanced techniques, such as Ant Colony Optimization, Co-evolutionary methods, GRASP, and Memetic algorithms. All these methods have been shown to work out high quality solutions in a wide range of hard optimization problems. However, the book's objective is engineered to provide a broad coverage of the concepts, methods, and tools of this important area of ANNs within the realm of continuous optimization.