Ultrasonic distance scanning techniques for mobile robots
Authors: D.T. Pham, Ze Ji, Anthony Soroka
Abstract
This paper discusses about the usage of ultrasound in the application of mobile robot navigation. Two methods using an array of transducers are described with theoretical analyses and practical experiments, namely the phased array and the Maximum Likelihood Estimation (MLE) method. These two methods are also compared with the conventional Time of Flight (ToF) method. Analyses show that the phased array of ultrasound has a number of advantages, including narrowing the beam width and efficient beam steering.
MATLAB-Based 3D Dynamic Model of a Powered Wheelchair
Authors: Anas Fattouh, YEHYA DADAM, D. T PAHM
Abstract
In this paper, a detailed dynamic model of a powered wheelchair is obtained. This model not only takes in consideration the kinematics equations of a powered wheelchair but also includes all other parts of a powered wheelchair such as the power module and the DC motors. Then a 3D model of the powered wheelchair is designed using virtual reality modeling language (VRML). This 3D model can be integrated in any 3D VRML environment including a domestic environment. Finally, the dynamic model is used with the 3D model of the powered wheelchair in a simulation system.
Association rules discovery in manufacturing: A case study in the metal industry
Authors: Ashraf Afify
Abstract
Manufacturing activities generate large quantities of data and it is no longer practical to rely on traditional manual methods to analyse this data. Data mining offers tools for extracting knowledge from data, leading to significant improvement in the decision-making process. Association rule mining is one of the most important data mining techniques and has received considerable attention from researchers and practitioners. It aims to identify interesting relationships among a large set of data items. To date, little has been done to exploit the potentially viable association rule mining tools in manufacturing.
Fit Manufacturing: A Strategy for Achieving Economic Sustainability
Authors: D. T. Pham, O. Adebayo-Williams, Z. Ebrahim, R. Barton, A.J. Thomas
Abstract
Achieving economic sustainability is a major focus for managers in manufacturing firms. The implementation of lean and agile initiatives has not really facilitated an organisation’s long-term economic sustainability. The industrial landscape is littered with the carcasses of manufacturing companies who have tried to improve their productivity, competitiveness and hence economic sustainability using these initiatives.
Design of an expert system for decision-making in the textile industry
Authors: itziar goicoechea castaño
Abstract
The overarching goal of this study is to create an expert information system for decision-making in the textile
industry. Based on “Knowledge Engineeringâ€:
- Knowledge of the design of a new product,
- Knowledge of the current manufacturing process,
- Knowledge of how the machinery currently operates,
- Knowledge of the machinery’s flexibility,
- Knowledge of machine times
With this expert system prototype we can provide a useful information tool for the designer who wants to introduce
Generating Branded Product Concepts: Comparing the Bees Algorithm and an Evolutionary Algorithm
Authors: D.T. Pham, M.C. Ang, K.W. Ng, Sameh Otri, Ahmed Haj Darwish
Abstract
The task to generate product design concepts to maintain a particular brand identity whilst meeting functional requirements is challenging to designers. Shape grammars have been shown to be able formally to describe the creation of branded product shapes using a set of shape rules. These shape rules are applied manually to generate a family of new design concepts that maintain the brand identity of the product. However, shape grammars are not meant to evaluate whether the generated product concepts can meet specified functional requirements.
Application of the Bees Algorithm to Fuzzy Clustering
Authors: D.T Pham, H AL-Jabbouli, M Mahmuddin, S Otri , Ahmed Haj Darwish
Abstract
This paper discusses the application of the Bees Algorithm to fuzzy clustering. The Bees Algorithm is used to optimise the performance of the fuzzy C-Means (FCM) algorithm and improve its clustering results. Computational experiments show that the Bees Algorithm gives a significant improvement over the FCM algorithm on its own and better results compared to the FCM algorithm combined with a Genetic Algorithm.
Neuro fuzzy network for composites manufacturing time estimation
Authors: ANTONIA DE SIMONE, LUIGI NELE
Abstract
Composite materials offer great promise to all future air vehicles by allowing engineers to design and build aircrafts that weigh less, have better performance and lower lifecycle cost.
However even though these materials have been used by the industry for over a decade, there still does not exist an accurate means to estimate their cost. The primary aim of this study is to develop a cost estimation system in manufacture of advanced composite materials for aeronautic use.
The result of this study is the development of a predictive model that relates cost in direct labor hours. An artificial intelligence system has been successfully developed with the ANFIS Editor GUI of the Matlab Fuzzy Logic Toolbox.
read more | login or register to post comments | 1 attachment |
Fuzzy Selection of Local Search Sites in the Bees Algorithm
Authors: D.T Pham, Ahmed Haj Darwish
Abstract
The Bees Algorithm is a swarm-based algorithm that mimics the natural food foraging behaviour of honey bees. The algorithm essentially involves both random exploration of the solution space and more focused exploitation of promising local search sites. A basic version of the Bees Algorithm has been applied to function optimisation and a variety of other practical problems. This paper describes an enhanced version implementing fuzzy greedy selection of local search sites. The paper presents the results obtained for a number of benchmark problems to demonstrate the robustness and self-organising ability of the new Bees Algorithm.









