Innovative Production Machines and Systems Conference - Intelligent Automation

An intelligent system for routing automation

chrisvdv — Fri, 22 Jun 2007 14:17:48 +0100

We present an outline of an intelligent routing environment developed for design automation of aircraft electrical wiring harness and pipe routing. The system interfaces with domain experts for capture of engineering knowledge and rules. System users specify only a few parameters to define individual routing problems. Geometry obstacles are specified using a discrete Finite Element (FE) mesh. Resultant paths are output in IGES form as CAD-readable geometry, and as a FE mesh consisting of geometry, routed path and knowledge layers. The knowledge layer provides detail of the rules and knowledge implemented throughout the routing process.

Forecasting SO2 air pollution in Salamanca, Mexico using an ADALINE.

gcortina — Fri, 22 Jun 2007 14:17:48 +0100

A comparison between a linear regression model and a Non-linear regression model is presented in this work for forecasting of pollution levels due to SO2 in Salamanca city, Gto. Prediction is performed by means of an Adaptive Linear Neural Network (ADALINE) and a Generalized Regression Neural Network (GRNN). Prediction experiments are realized for 1, 12 and 24 hours in advance, and the results for linear regression have been satisfactory. The performance estimation of both models are determined using the Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Obtained results are compared. The final results indicated that ADALINE outperforms the past approach using GRNN.

Modelling objects for skill-based reconfigurable machines

MBengel — Fri, 22 Jun 2007 14:17:46 +0100

Within the European SIARAS project, a SkillServer is developed which is supposed to support users to reconfigure existing production lines. It reasons about modified requirements on a given process.

This paper describes the fundamental knowledge representation used in the SkillServer. The skill-based approach is introduced before describing the deployed ontology with regards to production systems.

To enable the SkillServer to reason on configuration changes, models of the geometric representation of physical entities are required. This is described in chapter four.
Finally, a small demonstrator is explained where this system will be used first.

A Fractal-ANN approach for quality control

wang — Fri, 22 Jun 2007 14:17:46 +0100

The main problem with modern quality control of sound speakers is that the process is conducted manually. This manual checking of the quality of sound speakers is time consuming. In order to find an automated way of doing this, this paper presents an intelligent system for automated quality control in sound speaker manufacturing, which fuses Fractal Dimension (FD) into Artificial Neural Networks (ANNs) system. The Artificial Neural Networks is used to classify the levels of the quality of sound speakers from SEAS, a Norwegian manufacturing company for sound speakers. The Fractal Dimension is used for reducing the complexity of the sound signals.