DCINCO 2014 Abstracts

Short Papers
Short Papers
Paper Nr: 3
Title:

Effective Ways on How to Develop Best Practices for Visualizing Supply Chain Dashboards KPI’s
Authors:

Johannes Mapokgole
Abstract: The benefits of Supply Chain Visibility (SCV) have been known for over a decade. Supply Chain Visibility can be accomplished through data visualization, referred to as supply chain dashboards in this paper. Organizations have been deploying Supply Chain Visibility solutions in their environment to reduce costs and improve services but often remain dissatisfied as the existing solutions fail to deliver in today’s highly dynamic business environment. As a result Supply Chain Visibility projects to support agile supply networks are at high risk for failure. Achieving Supply Change Visibility excellence has become a major concern for supply chain leaders. Some of the major challenges faced by supply chain companies among others are: • Collapsing demand, unreliable forecasts • Increasing complexity of global sourcing and aggressive global competition leading to longer lead times and more pipeline inventory; and • The immediate need to control downstream and upstream logistics To address the above-mentioned challenges organizations need a dynamic and robust SCV framework that can enable quick response to change as well as improve and strengthen the organizational supply chain by making data readily available at a glance to all stakeholders, including the customer. The need for Supply Chain Visibility framework is especially great for manufacturing companies who are moving from a push supply chain model to a demand-driven supply chain model. This paper presents a generic concept of developing a supply chain dashboard coupled with practical case studies. The concept is developed based on a methodology for mapping, modeling, analyzing and redesigning the value chains for extended enterprise, the control and monitoring model. The supply chain dashboard supports the monitoring, analysis, control and management of the supply chain performance. It supports decision making by visually displaying in true time leading and lagging indicators in a supply chain process perspective. The dashboard offers support for three areas: monitoring, analysis and management, and it contains three indicators; performance, diagnostic and control. The supply chain dashboard concept serves as basis for a supply chain studio that will allow rapid decision making based on real-time information at an aggregate level along the entire value chain. An old management adage that say "you cannot manage what you do not measure" and "to measure is to know".
Paper Nr: 5
Title:

Nonlinear Dynamics Based Sensors - A New Class of Devices for System Monitoring
Authors:

Carlo Famoso, Mattia Frasca and Luigi Fortuna
Abstract: Post-silicon materials like polymers and solution-based devices allow to design new types of sensors. On the other hand, the nonlinear dynamic behavior of a class of nonlinear circuits offers the possibility of conceiving devices where the nonlinearity of the circuit is exploited to realize new mechanisms or improve classical ones. In this PhD work we discuss the possibility of coupling a new class of materials with nonlinear dynamic circuits to design a new class of sensors. The results that are included are preliminary and cover a wide range of applications. In particular advanced sensors based equipment has been studied on an electromechanical system, in order to monitorize its vibrating behaviour to establish self organizing phenomenon to control the system.
Download
Paper Nr: 7
Title:

Building Poker Agent Using Reinforcement Learning with Neural Networks

Authors:

Annija Rupeneite
Abstract: Poker is a game with incomplete and imperfect information. The ability to estimate opponent and interpret its actions makes a player as a world class player. Finding optimal game strategy is not enough to win poker game. As in real life as in online poker game, the most time of it consists of opponent analysis. This paper illustrates a development of poker agent using reinforcement learning with neural networks.
Download
Paper Nr: 8
Title:

An Insect Inspired Object Tracking Mechanism for Autonomous Vehicles
Authors:

Zahra Bagheri, Benjamin S. Cazzolato, Steven D. Wiederman, Steven Grainger and David C. O'Carroll
Abstract: Target tracking is a complicated task from an engineering perspective, especially where targets are seen against complex natural scenery. Due to the high demand for robust target tracking algorithms much research has focused in this area. However most engineering solutions developed for this purpose are either unreliable in real world conditions or too computationally expensive to be used in many real-time applications. Insects, such as the dragonfly, solve this task when chasing tiny prey, despite their low spatial resolution eye and small brain suggesting that nature has evolved an efficient solution for target detection and tracking problem. This project aims to develop a robust, closed-loop model inspired by the physiology of insect neurons that solves this problem, and to integrate this into an autonomous robot. This system is tested in software simulations using MATLAB/Simulink. In near future this system will be integrated with a robotic platform to examine its performance in real world environments to demonstrate the usefulness of this approach for applications such as wildlife monitoring.
Download
Paper Nr: 10
Title:

Intelligent Path Panning Towards Collision-free Cooperating Industrial Robots
Authors:

L. Larsen, J. Kim and M. Kupke
Abstract: Due to rising energy cost aircraft are intended to have a lower kerosine consumption. To achieve that aircraft manufacturers increase the usage of high performance, lightweight materials like carbon fibre reinforced plastics (CFRP). These materials pose new challenges to manufacturing processes concerning cost-effectiveness and quality requirements. The Institute of Structures and Design within the German Aerospace Center (DLR) designed a large (30m x 15m x 7m) robotic cell which is adequate to produce large airplane structures like fuselages. In this cell multiple robots share the same workspace. New methods are needed to program these robots to work cooperative on CFRP structures. The aim of these thesis is to develop path planning strategies for a CFRP process with cooperating robots using computational intelligence.
Download
Paper Nr: 13
Title:

Self-reorganizing Dynamic Formations of Mobile Autonomous Robots for Communication Network Optimization
Authors:

Philip Necsulescu and Klaus Schilling
Abstract: This doctoral research intends to study a method to autonomously self reorganize a formation of mobile robots to optimize network performance. Currently, a program has already been developed that allows the robots to retrieve the received signal strength of their neighbours along with positional information of themselves and their neighbours. A routing protocol has also been developed and tested that uses the signal strength. It is intended to improve this protocol with the addition of positional data of each robot. Further studies will be conducted in uncommon environments, such as underground mines, to further its applications. Control algorithms have been developed and simulated to autonomously reorganize a small formation of car like robots to optimize communication links. These algorithms will also be used to automatically set up communication networks using droppable, non-moving routing nodes. Along with being simulated, experiments will be conducted in physical environments.
Download