Engineering Commons^™

A Neural Network-Based Vision System For Automated Separation Of Onion From Clod Using Mechanical Harvester, Demian Morquin

Theses and Dissertations - UTB/UTPA

A neural network classifier for separating clods from onions during harvesting has been developed. The separator consists of a multi-layer feedforward network that maps textural features computed from gray-scale images of onions and clods into the correct object. Texture features were computed from co-occurrence matrices that specify the spatial relationship of pixel values in an image. The textural features selected for this application consist of homogeneity, contrast, variance, and energy. The network was trained using the back-propagation algorithm. Based on the textural features classification, the effect of changing the network configuration on separation effectiveness was investigated. Factors including network topology …

Mathematical Modeling For Fabricating A Microstructure With A Pre-Specified Geometry Using Laser -Induced Chemical Vapor Deposition, Chaoyang Zhang

Doctoral Dissertations

Laser-induced chemical vapor deposition (LCVD) is an emerging new technique with many practical applications. To optimize the system for fabricating a microstructure with a pre-specified geometry in pyrolytic LCVD, a three-dimensional mathematical model is developed for predicting temperature distributions and laser dwell times across the substrate scanned by the laser beam. A microstructure is fabricated layer by layer, and for each layer the laser beam moves from one pixel to the next. The complicated correlations among temperature distribution, deposit growth rate, and laser dwell time are investigated. A purely heterogeneous reaction is assumed and any gas-phase transport is ignored.

A …