Innovative Production Machines and Systems Conference - Decision Support

Wecome to IPROMS2006 - Decision Support

charles — Mon, 03 Jul 2006 12:00:24 +0100

Dear authors and participants,

I am Charles Eugene, on behalf of the co-chairs welcome you to the session Decision Support, IPROMS 2006!

Authors, thank you very much for your contribution to this session and to the conference. I am kindly expecting you to be active and participate in the discussions.

Engineering applications of clustering techniques

ashraf_afify — Thu, 13 Jul 2006 20:33:08 +0100

The amount of data being collected in engineering is increasing exponentially and it is no longer practical to rely on traditional manual methods to analyse these data. Clustering, which automatically finds natural groups in the data, is an important data exploration technique. It has many applications in different areas of engineering, including engineering design, manufacturing system design, quality assurance, production planning and process control. Many clustering algorithms have been proposed from different research disciplines. However, efforts to perform effective and efficient clustering on large data sets only started in recent years with the emergence of data mining. This paper provides a review of various clustering algorithms in data mining and describes a number of important engineering applications of these algorithms.

Control Chart Pattern Recognition Using Spiking Neural Networks

scess6 — Tue, 04 Jul 2006 19:31:55 +0100

Author : D.T. Pham and S. Shahnorbanun

Keywords : Control charts, Pattern recognition, Spiking neural networks

Statistical process control (SPC) is a method for improving the quality of products. Control charting plays the most important role in SPC. A control chart can be used to indicate whether a manufacturing process is under control. Unnatural patterns in control charts mean that there are some unnatural causes for variations. Control chart pattern recognition is therefore important in SPC. In recent years, neural network techniques have increasingly been applied to pattern recognition. Spiking Neural Networks (SNNs) are the third generation of artificial neural networks, with spiking neurons as processing elements. In SNNs, time is an important feature for information representation and processing. Latest research has shown SNNs to be computationally more powerful than other types of artificial neural networks. This paper proposes the application of SNN techniques to control chart pattern recognition. The paper focuses on the architecture and the learning procedure of the network. Experiments show that the proposed architecture and the learning procedure give high pattern recognition accuracies.

Statistical approach to numerical databases:clustering using normalised Minkowski metrics

mariasuarez — Fri, 30 Jun 2006 13:19:40 +0100

Pre-processing or normalisation of data sets is widely used in a number of fields of machine intelligence. Contrary to the overwhelming majority of other normalisation procedures, when data is scaled to a unit range, it is argued in the paper that after normalisation of a data set, the average contributions of all features to the measure employed to assess the similarity of the data have to be equal to one another.

Prediction of workpiece surface roughness using soft computing

ashraf_afify — Thu, 29 Jun 2006 11:27:23 +0100

A study is presented to model surface roughness in end milling using adaptive neuro-fuzzy inference system (ANFIS).The machining parameters, namely, the spindle speed, feed rate and depth of cut have been used as inputs to model the workpiece surface roughness. The parameters of membership functions (MFs) have been tuned using the training data in ANFIS maximizing the modeling accuracy. The trained ANFIS are tested using the set of validation data. The effects of different machining parameters and number of MFs on the prediction accuracy have been studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminum alloy. Results are compared with artificial neural network (ANN) and previously published results. The results show the effectiveness of the proposed approach in modeling the surface roughness.

Technology Readiness Model for Enterprises

ashraf_afify — Thu, 29 Jun 2006 11:22:21 +0100

This paper presents an innovative technology management model for the enterprises. It provides an overview of existing technology assessment models and introduces TRM (Technology Readiness Model). The proposed model assesses the technology from operational, tactical, and strategic aspects.

A Novel Self-Organised Learning Model with Temporal Coding for Spiking Neural Networks

charles — Tue, 27 Jun 2006 10:40:57 +0100

In this paper, a novel self-organised learning model with temporal coding is proposed for a network of spiking neurons which encode information through the timing of action potentials. The development of this learning model is based on recent findings in biological neural systems. The Hebbian-type learning equation for the proposed model utilises the time difference between the input and output spikes. The proposed spiking neural network learning model was tested on two sets of benchmark data. Clusters were formed in the output space based on the position of the output neurons and their firing time. The results show that networks trained using action potential timings are capable of learning complex tasks.

Service Orientation in Production Control

charles — Tue, 27 Jun 2006 10:35:47 +0100

Service orientation is one of the most discussed topics in the world of application integration. It seems to be the new paradigm for application integration infrastructures and directly bridges between the process-oriented business world and the application-oriented world of IT. However, the benefits of service orientation are not limited to largescaled service enterprises such as insurance companies. It has the potential of enabling other major developments in production control as the rise of intelligent decision support systems that allow for advanced maintenance, failure prediction and machinery protection.

Fusing neural networks, genetic algorithms and fuzzy logic for diagnosis of cracks in shafts

Dentsoras — Tue, 27 Jun 2006 10:32:41 +0100

During the last decades, the engineering community has extensively studied crack identification in rotating machine elements. Although the proposed analytical models may be capable of identifying cracks on the basis of modal analysis, response easurements or other techniques, the required time for performing the underlying computations is restrictive in real-time diagnosis applications. This paper introduces a framework for implementing soft-computing techniques, namely artificial neural networks (ANN), fuzzy logic (FL) and genetic algorithms (GA), for identifying cracks in rotating shafts while diminishing the required computational time. In the context of the current approach the cracks are considered to lie on arbitrary angular positions around the longitudinal axis of the shaft at any distance from the clamped end and characterized by three measures: position, depth and relative angle. The reduction in computational time is achieved by approximating the analytical model with a neural network and by replacing the exhaustive search of the solution space with a genetic algorithm whose objective function relies on a fuzzy logic representation. Results concerning the efficiency of the proposed framework in terms of accuracy and computational time are also presented.

Optimization of Assembly Lines with Transportation Delay Using IPA

charles — Tue, 27 Jun 2006 10:28:05 +0100

This paper addresses the optimization of assembly lines with important transportation delays and with constant demand. Machines are subject to time-dependent failures and times to failure and times to repair are random variable with general distribution. In the continuous flow model proposed in this paper, material flowing out a machine waits a period of time called delay for material transfer before arriving at its downstream buffer. A simulation-based optimization method is used for determining optimal buffer levels in order to minimize the long run average cost. The optimization algorithm is based on the Infinitesimal Perturbation Analysis (IPA) technique for estimation of gradients along the simulation.