Design and degradation modelling through artificial neural networks

Automotive is one of the major manufacturing industries in Australia that requires extensive reliability test for the components used in vehicles. To achieve a shorter time-to-market and a highly reliable product while reducing the amount of physical prototyping, there is a growing need for better understanding on the effect that the design parameters have on the degradation of the product. This paper presents comprehensive descriptions of applying Artificial Neural Network (ANN) to capture the relationships between design and degradation. Consequently, two models of different practical significance are created as the result of the work. The vision of the models is to be used by the testers and designers as a guideline in design evaluation, so that time-consuming and expensive iterations of the product developmental cycle can be reduced substantially. The degradation of the folding force of a mechanical system is used to illustrate our approach.

Identification and classification of animal fibres using artificial neural networks

It has been an important and challenging task to classify and evaluate the contents in wool blends. Quantitative characterisation of animal fibre scale patterns has attracted considerable attention, since it is the major evidence for identification and subsequent classification purpose. Although techniques such as imaging processing and linear demarcation functions have been used to identify unknown fibre type with some success, a more comprehensive approach is required to perform this task. In this paper, a new approach is presented, which employs non-linear demarcation functions by using an artificial neural network (ANN). Based on scale pattern features extracted by using image processing techniques the artificial neural network (ANN) model is to classify mohair and merino fibres. It is observed that the techniques developed in this work are very effective and have the potential to be applied to other animal fibres.

Nutritional related aspects of the artificial propagation and larval rearing of Macquarie perch, Macquaria Australasica (Cuvier, 1830)

Studies the underlying role of nutrition in the lack of response of captive fish to hypophysation. Aspects studied include morphological characteristics, histology of ovaries, proximate analysis, fatty and amino acid profiles of oocytes, muscle, liver and diets of wild and tank-reared fish, egg and larval quality, amino acid composition of eggs and larvae at different developmental stages, larval feeding and hormone treatments.

Managing alternative stable states in constructed wetlands using artificial substrates

Algal blooms are a management concern in shallow water bodies. This project investigated the use of artificial substrates to enhance biofilm growth and shift primary production from the open water to artificial surfaces. This resulted in a shift from algal dominated wetland back to a clear water macrophyte dominated wetland.

An artificial intelligence examination of the influence of geological conditions and changes in climate on damage to light structures in Victoria

Damage to light structures in the state of Victoria can be caused by movements of expansive soils. The presentation will present the results of an examination of reports of increasing complaints of house damage in Victoria and particularly in the Melbourne area. The examination analyses the influence of geology and change in climate using Neural Network and Genetic Algorithm approaches and assesses their relative importance in contributing to the cause of the damage.

Designing adaptive artificial agents for an economic production and conflict model

Production and conflict models have been used over the past 30 years to represent the effects of unproductive resource allocation in economics. Their major applications are in modelling the assignment of property rights, rentseeking and defense economics. This paper describes the process of designing an agent used in a production and conflict model. Using the capabilities of an agent-based approach to economic modelling, we have enriched a simple decision-maker of the kind used in classic general equilibrium economic models, to build an adaptive and interactive agent which uses its own attributes, its neighbors’ parameters and information from its environment to make resource allocation decisions. Our model presents emergent and adaptive behaviors than cannot be captured using classic production and conflict agents. Some possible extensions for future applications are also recommended.

Provision of artificial shelter on beaches is associated with improved shorebird fledging success

Artificial chick shelters might improve productivity of beach-nesting birds threatened by anthropogenic disturbance. We investigated the efficacy of three different chick shelter designs against four criteria: accessibility to chicks over time, thermal insulation, conspicuousness to beach-goers, and practicality (cost and ease of transport). One design (‘A-frame’) was selected because it offered the greatest thermal insulation, was the least conspicuous, most cost effective, and performed equally well in terms of accessibility. We deployed these artificial shelters on Hooded Plover Thinornis rubricollis territories where broods were present (n 5 11), and compared the behaviour and survival rate of chicks to that at control sites (n 5 10). We were unable to discern any difference in the behaviour of broods when artificial shelters were available. However, the survival rate of chicks to fledging was 71.8% higher where an artificial shelter was provided (n 5 21 broods). This was validated by analysing data from a larger sample of broods monitored as part of an active volunteer-based management programme; shelters conferred a 42.8%increase in survival to fledging (n 5 81 broods). Thus, artificial shelters have the potential to increase survival rates of threatened shorebird chicks, though the mechanisms through which survival is increased require further investigation.