No abstract

A preliminary study on the potential application of artificial neural networks in welded structures was expanded to metal inert gas welding of steel plates of grades D and DH 36. The main controllable variables were plate thickness, steel grade, plate cutting process, and heat input. A series of welded plates of each grade was manufactured, covering plate thicknesses of 6 and 8 mm. The topography of each welded plate was evaluated after tacking the plates together and after welding, allowing the actual distortion to be calculated. It was established that a multilayer perceptron network architecture configuration accurately represented the distortion for the 6 mm thickness plate, and for the 8 mm thickness plate after treatment of the data. The data generated were used to develop the PREDICTOR software package, which allows a distortion prediction to be produced, and to carry out a sensitivity analysis. Heat input was found to be the most sensitive factor related to distortion, with carbon content of the plates, yield/tensile strength ratio, carbon equivalent, and steel grade also having significant effects. Some test plates were modelled using finite element method software packages: the initially poor agreement was improved via the addition of significant detail, but the finite element model by its nature will normally predict symmetrical distortion from a symmetric weld, whereas the artificial neural network model developed was capable of predicting the asymmetric distortion observed in reality.

In computer-aided diagnosis, temporal change over time can be a key piece of information in treatment monitoring and disease tracking applications. Change detection depends on the abilit?, to align the images of the sequence to a common reference, and the abilit?/ to build up memory about the image scene over time. In this papel; we will present approaches for model supported image registration and warping developed for change detection in two computer-aided diagnosis applications. The first application is to develop image registration scheme for change detection in mamniographic sequence. A k q component of this scheme is the site model constructed based on a combination of image analvsis procedures. The site model supported multistep registration leads to a robust change detection derived @om the registered mammographic images which will be invaluable in computer-aided diagnosis. The second application is to develop volumetric image warping scheme aimed at lung desease detection and treatment monitoring using 3 0 images acquired at different breathing stages or dflerent time courses. The model we adopted in this of application is based on the theory of continuum mechanics in order to more accuratelv account for the non-rigid motion and deformation of the lung itself: In addition to the common feature of model-based approach, both applications require the reliable control points in order to obtain a robust registration and warping results. Experimental results on real image data sets show that these two model supported approaches are "er?/ promising in quantitatively characterizing the changes in mainniographic image sequences and lung CT image volumes. 180 0-7695-0978-9/00 $10.00 0 2000 IEEE

No abstract