The application of artificial neural networks to the interpretation and classification of freshwater benthic invertebrate communities

This thesis presents a thorough and principled investigation into the application of artificial neural networks to the biological monitoring of freshwater. It contains original ideas on the classification and interpretation of benthic macroinvertebrates, and aims to demonstrate their superiority over the biotic systems currently used in the UK to report river water quality. The conceptual basis of a new biological classification system is described, and a full review and analysis of a number of river data sets is presented. The biological classification is compared to the common biotic systems using data from the Upper Trent catchment. This data contained 292 expertly classified invertebrate samples identified to mixed taxonomic levels. The neural network experimental work concentrates on the classification of the invertebrate samples into biological class, where only a subset of the sample is used to form the classification. Other experimentation is conducted into the identification of novel input samples, the classification of samples from different biotopes and the use of prior information in the neural network models. The biological classification is shown to provide an intuitive interpretation of a graphical representation, generated without reference to the class labels, of the Upper Trent data. The selection of key indicator taxa is considered using three different approaches; one novel, one from information theory and one from classical statistical methods. Good indicators of quality class based on these analyses are found to be in good agreement with those chosen by a domain expert. The change in information associated with different levels of identification and enumeration of taxa is quantified. The feasibility of using neural network classifiers and predictors to develop numeric criteria for the biological assessment of sediment contamination in the Great Lakes is also investigated.

Growth of short fatigue cracks in titanium alloys

The initiation and early propagation of short fatigue cracks has been studied in detail in two alpha / beta titanium alloys as a function of microstructure. Detailed metallography is presented relating short crack growth rates to the microstructural features present. The work shows the significant differences in short crack propagation rates which can be achieved by microstructural changes within a single alloy.

Relevance of microstructural influences in the short crack regime to overall fatigue resistance

The behaviour of short fatigue cracks is shown to be relevant only to a limited number of engineering situations. Within these situations, further restrictions on the extent to which metallurgical control can be exerted to improve fatigue crack growth behaviour are identified. The degree of control remaining is discussed in terms of two separate regimes which are described as intrinsic and extrinsic crack growth resistance. These separate effects are highlighted by comparisons both within and between a wide range of alloy systems. The implications of such an analysis are discussed in terms of aerospace applications.