Network modelling for Townsville distribution system

Drinking water quality guidelines are becoming increasingly stringent. To comply with these guidelines and to manage water quality in a distribution system, improved understanding of the movement and fate of drinking water constituents within the system is required. This study illustrates the construction and calibration of an electronic model of the Townsville drinking water distribution system. Being in the tropics, the temperature of the water in the distribution system changes little throughout the year (usually between 20 and 25&deg;C); also, water is supplied to the system from two sources, the location of the blending of these waters is varies with demand.<br />

Prediction interval-based neural network modelling of polystyrene polymerization reactor - a new perspective of data-based modelling

In this paper, prediction interval (PI)-based modelling techniques are introduced and applied to capture the nonlinear dynamics of a polystyrene batch reactor system. Traditional NN models are developed using experimental datasets with and without disturbances. Simulation results indicate that traditional NNs cannot properly handle disturbances in reactor data and demonstrate a poor forecasting performance, with an average MAPE of 22% in the presence of disturbances. The lower upper bound estimation (LUBE) method is applied for the construction of PIs to quantify uncertainties associated with forecasts. The simulated annealing optimization technique is employed to adjust NN parameters for minimization of an innovative PI-based cost function. The simulation results reveal that the LUBE method generates quality PIs without requiring prohibitive computations. As both calibration and sharpness of PIs are practically and theoretically satisfactory, the constructed PIs can be used as part of the decision-making and control process of polymerization reactors. &copy; 2014 The Institution of Chemical Engineers.

Measuring the influence of fibre-to-fabric properties on the pilling of wool fabrics

This study ranks the contribution of various fibre, yarn and fabric attributes to the pilling of wool knitwear. On the basis of an artificial neural network modelling, a combination of sensitivity analysis, forwards/backwards search and genetic algorithms was used to identify the importance of various fibre/yarn/fabric input parameters. The three different techniques show broad similarities in their assessment of which input parameters are important or are not important in affecting fabric pilling. The ranking shows that fabric cover factor has the most effect on pilling, followed by yarn count and thin places, fibre length, yarn twist, etc. It is further illustrated that the directional trend of the predicted pilling outputs for a selection of inputs was in line with the expected behaviour. To verify the findings of input feature selection, input factors deemed to have a small effect on the predicted pilling output, such as fibre length and diameter variations and curvature, were removed and the subsequent performance statistically compared to the original multi-layer perceptron. Differences between the outputs predicted by the original and pruned models are found not to be statistically significant at the 5% significance level. Results from this study may help manufacturers and knitwear designers in choosing the most appropriate materials and structures to reduce the pilling propensity of wool knitwear. <br />

Controlling and predicting the pilling propensity of knitted wool fabrics

This thesis tackles an important quality issue in the wool industry - the pilling of wool knitwear. Through artificial neural network modelling, the important fibre, yarn and fabric attributes that affect fabric pilling have been identified. A predictive model on fabric pilling has been developed, which will assist the wool industry in the management and control of fabric pilling.

Modelling of porosity defects in high pressure die casting with a neural network

High Pressure Die Casting (HPDC) is a complex process that results in casting defects if configured improperly. However, finding out the optimal configuration is a non-trivial task as eliminating one of the casting defects (for example, porosity) can result in occurrence of other casting defects. The industry generally tries to eliminate the defects by trial and error which is an expensive and error -prone process. This paper aims to improve current modelling and understanding of defects formation in HPDC machines. We have conducted conventional die casting tests with a neural network model of HPDC machine and compared the obtained results with the current understanding of formation of porosity. While most of our findings correspond well to established knowledge in the field, some of our findings are in conflict with the previous studies of die casting.<br />

Controller area network (CAN) modelling for automotive body control applications

This research details methods to improve upon current worst-case message response time analysis of CAN networks. Also, through the development of a CAN network model, and using modern simulation software, methods were shown to provide more realistic analyses of both sporadic and periodic messages on CAN networks prior to implementation.

Statistical modelling of artificial neural network for sorting temporally synchronous spikes

Artificial neural network (ANN) models are able to predict future events based on current data. The usefulness of an ANN lies in the capacity of the model to learn and adjust the weights following previous errors during training. In this study, we carefully analyse the existing methods in neuronal spike sorting algorithms. The current methods use clustering as a basis to establish the ground truths, which requires tedious procedures pertaining to feature selection and evaluation of the selected features. Even so, the accuracy of clusters is still questionable. Here, we develop an ANN model to specially address the present drawbacks and major challenges in neuronal spike sorting. New enhancements are introduced into the conventional backpropagation ANN for determining the network weights, input nodes, target node, and error calculation. Coiflet modelling of noise is employed to enhance the spike shape features and overshadow noise. The ANN is used in conjunction with a special spiking event detection technique to prioritize the targets. The proposed enhancements are able to bolster the training concept, and on the whole, contributing to sorting neuronal spikes with close approximations.

Methodological shifts in ratio-based modelling of corporate collapse

The year 1968 saw a major shift from univariate to multivariate methodological approaches to ratio-based modelling of corporate collapse. This was facilitated by the introduction of a new statistical tool called Multiple Discriminant Analysis (MDA). However, it did not take long before other statistical tools were developed. The primary objective for developing these tools was to enable deriving models that would at least do as good a job asMDA, but rely on fewer assumptions. With the introduction of new statistical tools, researchers became pre-occupied with testing them in signalling collapse. lLTUong the ratio-based approaches were Logit analysis, Neural Network analysis, Probit analysis, ID3, Recursive Partitioning Algorithm, Rough Sets analysis, Decomposition analysis, Going Concern Advisor, Koundinya and Purl judgmental approach, Tabu Search and Mixed Logit analysis. Regardless of which methodological approach was chosen, most were compared to MDA. This paper reviews these various approaches. Emphasis is placed on how they fared against MDA in signalling corporate collapse.<br />

Mobility modelling and trajectory prediction for cellular networks with mobile base stations

This paper provides mobility estimation and prediction for a variant of GSM network which resembles an adhoc wireless mobile network where base stations and users are both mobile. We propose using Robust Extended Kalman Filter (REKF)as a location heading altitude estimator of mobile user for next node (mobile-base station)in order to improve the connection reliability and bandwidth efficiency of the underlying system. Through analysis we demonstrate that our algorithm can successfully track the mobile users with less system complexity as it requires either one or two closest mobile-basestation measurements. Further, the technique is robust against system uncertainties due to inherent deterministic nature in the mobility model. Through simulation, we show the accuracy and simplicity in implementation of our prediction algorithm.<br />

Application of neural networks as an auxiliary technique in the modelling of power station

Artificial neural network (NN) is an alternative way (to conventional physical or chemical based modeling technique) to solve complex ill-defined problems. Neural networks trained from historical data are able to handle nonlinear problems and to find the relationship between input data and output data when there is no obvious one between them. Neural Networks has been successfully used in control, robotic, pattern recognition, forecasting areas. This paper presents an application of neural networks in finding some key factors eg. heat loss factor in power station modeling process. In the conventional modeling of power station, these factors such as heat loss are normally determined by experience or &ldquo;rule of thumb&rdquo;. To get an accurate estimation of these factors special experiment needs to be carried out and is a very time consuming process. In this paper the neural networks (technique) is used to assist this difficult conventional modeling process. The historical data from a real running brown coal power station in Victoria has been used to train the neural network model and the outcomes of the trained NN model will be used to determine the factors in the conventional energy modeling of the power stations that is under the development as a part of an on-going ARC Linkage project aiming to detail modeling the internal energy flows in the power station.<br />

Location based power control for mobile devices in a cellular network

This paper provides location estimation based power control strategy for cellular radio systems via a location based interference management scheme. Our approach considers the carrier-to-interference as dependent on the transmitter and receiver separation distance and therefore an accurate estimation of the precise locations can provide the power critical mobile user to control the transition power accordingly. In this fully<br />distributed algorithms, we propose using a Robust Extended Kalman Filter (REKF) to derive an estimate of the mobile user&rsquo;s closest mobile base station from the user&rsquo;s location, heading and altitude. Our analysis demonstrates that this algorithm can successfully track the mobile users with less system complexity, as it requires measurements from only one or two closest mobile base stations and hence enable the user to transmit at the rate that is sufficient for the interference management. Our power control<br />algorithms based on this estimation converges to the desired power trajectory. Further, the technique is robust against system uncertainties caused by the inherent deterministic nature of the mobility model. Through simulation, we show the accuracy of our prediction algorithm and the simplicity of its implementation.<br />