Computational intelligence
Condition monitoring reduces defence maintenance costs
IISRI researchers and their collaborators have developed an intelligent decision support tool to monitor vehicle conditions through the engine lubrication oil. The tool avoids the time and cost burdens associated with laboratory-based oil testing for land vehicle fleets of the ADF. The research revealed the potentially useful correlations between VHUMS data from G-Wagons and laboratory test results for inferring engine oil conditions using machine learning models.
Constructing optimal prediction intervals for load forecasting problem
Short-term load forecasting is fundamental for the reliable and efficient operation of power systems. Application of artificial intelligence-based techniques and, in particular, neural networks has proliferated STLF (extend) within the last two decades. Despite this, NN (extend) models are deterministic and their application for predicting the future of stochastic systems, such as loads, is always in doubt and questionable. The objective of this research is to construct prediction intervals (PIs) for future loads instead of forecasting their exact values.
Safer roads through advanced driver awareness monitoring systems
Having alert drivers is fundamental for having safe road. The purpose of this research is to monitor the driver’s behaviour using multidimensional signals and advanced machine learning technique to detect the onset of performance degradation due to the lack of concentration.
Understanding complex systems
Sticke health and wellbeing project with VicHealth
IISRI has applied systems thinking to health promotion, with support of a grant awarded by VicHealth. IISRI’s new technology aids to assist with chronic disease prevention that helps to better understand and intervene the complex drivers of unhealthy diets.
Uncertainty quantification through construction of prediction intervals
As universal approximators, neural networks (NNs) have achieved great success in many regression problems in the last two decades. No matter how NNs are trained or used, they suffer from two basic deficiencies: they are susceptible to uncertainty and there is no indication of their accuracy. To cope with these deficiencies, construction of Prediction Intervals (PIs) for NN outputs has been proposed in literature. Although NN-based PIs have been investigated in literature for almost two decades, there are many issues left unarticulated relating to them including PI assessment, PI optimisation, and reducing the computational requirements. Motivated by these gaps in literature, this research attempts to develop practically useful measures for quantitative evaluation of PIs.
Development and application of hybrid soft computing models
Soft computing (SC) is an inter-disciplinary area that is well-suited for the design and development of computerised intelligent systems. The main SC models include artificial neural networks, fuzzy systems and evolutionary algorithms. Each SC model, however, has its own benefits and limitations. As a result, this research focuses on the design and development of hybrid SC models (e.g. neural-fuzzy, neural-evolutionary, fuzzy-evolutionary, neural-fuzzy-evolutionary paradigms) with the aim of capitalising on the strengths of each SC model and alleviating the associated shortcomings.
Video-driven traffic modelling
A video-driven modelling technique is used for traffic systems, where video processing is employed to estimate metrics such as traffic volumes. These metrics are used to update the traffic system model, which is then simulated using the Paramics traffic simulation platform. Video driven model tuning has widespread potential application in traffic systems due to the convenience and reduced costs of model development and maintenance.
Developing artificial intelligent-based metamodels for complex systems
Motivations for this research are the recent trends in both academia and industry towards the integration of simulation modelling techniques in system design and operation. Development of detailed 3D-discrete event simulation models has become the common practice for modelling and analysis of complex systems. These models, however, are expert-intensive throughout their life cycle and their computational requirement is huge, hindering their application for real-time operational planning and optimisation. This research aims to develop abstract metamodels for modelling operations within complex man-made systems.
Scheduling and optimisation
Multi-objective scheduling for joinery manufacturing
The Australian furniture industry represents 4% of Australia's manufacturing base, with an annual turnover of $9.5 billion. Australian furniture manufacturers are losing the battle against imports, due to high fixed costs and long delivery times. Improved scheduling of their constrained resources provides an opportunity to stay competitive. However, traditional scheduling methods cannot be easily implemented in practice, as they primarily consider a single objective and cannot deal with multi-objective dynamic processes. This project aims to propose and develop a novel multi-objective scheduling strategy to optimise the outputs and dramatically reduce delivery time.
Simulation-based learning for control of complex conveyor networks
The demands placed on material handling systems continues to grow with increasing design complexity and higher throughput requirements. In complex engineered environments, such as a baggage handling system, thousands of bags must be tracked through the system and delivered to the appropriate location once cleared through security requirements. These systems are highly dynamic, with time varying traffic demands and changing flight schedules. The focus of this research is to address the problem of directing traffic flows within a complex conveyor network to ensure correct processing and delivery.
Simulation modelling of pedestrian way-finding behaviour under normal situations
This research aims to develop a comprehensive conceptual model of pedestrian way-finding behaviour under normal and non-panic conditions. It involves investigating how to merge the strength of the two most plausible pedestrian modelling paradigms, social force model and discrete choice model, with the computational efficiency of discrete event simulation. So far in this study, the early stages of modelling have been developed and trajectories of entities captured.
Control of polymerisation batch reactor
Polymer products are used in numerous industries including construction, manufacturing, electronics, transportation, food processing, and aerospace. Despite the wide range of polymer applications, polymerisation reactor control is still a very challenging task, as the polymerisation reaction is complex and nonlinear in nature. The aim of this research is to develop advanced nonlinear controllers for monitoring polymerisation batch reactors that provide a smooth, safe and waste-free production line, as well as high-quality polymer products.