Technological complexities of current ground combat systems require advanced maintenance methods to keep the fleet in a state of operational readiness. Currently, maintenance personnel use paper Technical Manuals (TM) that are cumbersome and not easily transportable or updated in the field. This thesis proposes using the latest technology to support maintainers in the field or depot by integrating the TMs with the onboard diagnostics Built-In-Test (BIT) and Fault Isolation Test (FIT) of the vehicle, to provide the maintainer with an improved diagnostics tool to expedite troubleshooting analysis. This will be accomplished by connecting the vehicle, using the vehicle's 1553 multiplex bus, with the Graphical User Interface (GUI) of an Intelligent Maintenance Aid (IMA). The IMA will use Troubleshooting Procedure (TP) codes generated during BIT and FIT testing. Using the information provided by these TP codes, through the IMA GUI, information from the technical manuals will be displayed to aid the maintainers in their diagnostic work. The results of this thesis will serve as a baseline for further research and will be presented to the program management office for combat systems (PM-CS) for further consideration and development. / US Army RDECOM-TACOM author (civilian).

[Abstract]: With the increasing use of fibre reinforced polymer (FRP) composites in civil engineering structures, there is a growing realisation of the need to develop newstructural systems which can utilise the unique characteristics of these materials in a more efficient and economical manner. In many instances this will require thedevelopment of new materials tailored to address the unique performance and economic parameters of mainstream construction. Over recent years, researchers at the University of Southern Queensland have pioneeredthe use of a new type of particulate filled polymer core material which greatly improves the robustness and cost effectiveness of FRP structural systems. These compositematerials are composed of small hollow spherical fillers (microspheres) in a thermosetting polymer matrix. Initial research into these materials, including theirfeasibility in prototype structural elements, have shown these materials to have major potential for widespread application in structural composite systems.One of the most promising classes of these materials investigated to date are vinyl ester / cenosphere composites, which utilise cenospheres derived from fly ash in a vinyl ester matrix. Previously reported studies into these materials have been restricted to initialsurveys of material behaviour which sought to identify key parameters in achieving desired performance outcomes in the composite. This dissertation presents the first in-depth investigation of these materials specifically as a core material option for civil infrastructure applications. The particular focus of this work is on the relationship of the vinyl ester matrix to the characteristics of the resultingcomposite. Several key matrix parameters were identified and assessed as to their influence on cure characteristics, fabrication operations, mechanical properties and theretention of such properties under elevated service temperatures. The outcomes of this work have significantly improved the understanding of matrix influences on the behaviour of these composite systems and have been drawn together to provide a number of recommendations on the application of this new technology to new structural systems.

The first objective of this research project is to carry out multi-objective optimization (MOO) for four simple chemical engineering processes to clearly demonstrate the wealth of information on a given process that can be obtained from the MOO instead of a single aggregate objective function. The four optimization case studies are the design of a PI controller, an SO2 to SO3 reactor, a distillation column and an acrolein reactor. Results that were obtained from these optimization case studies show the benefit of generating and using the Pareto domain to gain a deeper understanding of the underlying relationships between the various process variables and the different performance objectives. In addition, an acrylic acid production plant model is developed in order to propose a methodology to solve multi-objective optimization for the two-reactor system model using artificial neural networks (ANNs) as metamodels, in an effort to reduce the computational time requirement that is usually very high when first-principles models are employed to approximate the Pareto domain. Once the metamodel was trained, the Pareto domain was circumscribed using a genetic algorithm and ranked with the Net Flow method (NFM). After the MOO was carry out with the ANN surrogate model, the optimization time was reduced by a factor of 15.5.

This work focuses on the autonomous exploration of unknown areas by a swarm of mobile robots, referred to as agents. When an emergency happens within a building, it is dangerous to send human responders to search the area for hazards and victims. This motivates the need for autonomous agents that are able to coordinate with each other to explore the area as fast as possible. We investigate this problem from an algorithmic, rather than a robotics point of view, and thus abstract away from practical problems, such as obstacle detection and navigation over rough terrain. Our focus is on distributed algorithms that can cope with the following challenges: the topology of the area is typically unknown, communication between agents is intermittent and unreliable, and agents are not aware of their location in indoor environments. In order to address these challenges, we adopt the stigmergy approach, that is, we assume that the area is instrumented with small inexpensive sensors (called tags) and agents coordinate indirectly with each other by reading and updating the state of local tags. We propose three novel distributed algorithms that allow agents to explore unknown areas by coordinating indirectly through a tag-instrumented environment. In addition, we propose two mechanisms for discovering evacuation routes from critical points in the area to emergency exits. Agents are able to combine the tasks of area exploration and evacuation route discovery in a seamless manner. We study the proposed algorithms analytically, and evaluate them empirically in a custom-built simulation environment in a variety of scenarios. We then build a real testbed of agents and tags, and investigate practical mechanisms that allow agents to detect and localise nearby tags, and navigate toward them. Using the real testbed, we derive realistic models of detection, localisation and navigation errors, and investigate how they impact the performance of the proposed exploration algorithms. Finally, we design fault-tolerant exploration algorithms that are robust to these errors and evaluate them extensively in a simulation environment.

D.Ing. (Electrical and Electronic Engineering) / The electricity shortage in South Africa has required the implementation of demand side management (DSM) projects. The DSM projects were implemented by installing energy monitoring and control systems to monitor certain mining aspects such as water pumping systems. Certain energy saving procedures and control systems followed by the mining industry are not sustainable and must be updated regularly in order to meet any changes in the water pumping system. In addition, the present water pumping, monitoring, and control system does not predict the energy consumption or the underground water dam levels. Hence, there is a need to introduce new monitoring system that could control and predict the energy consumption of the underground water pumping system and dam levels based on present and historical data. The work is undertaken to investigate the feasibility of using artificial intelligence in certain aspects of the mining industry. If successful, artificial intelligence systems could lead to improved safety and reduced electrical energy consumption, and decreased human error that could occur throughout the pump station monitoring and control process ...

Ultrasound-based fetal biometry is used to derive important clinical information for identifying IUGR (intra-uterine growth restriction) and managing risk in pregnancy. Accurate and reproducible biometric measurement relies heavily on a good standard image plane. However, qualitative visual assessment, which includes the visual identification of certain anatomical landmarks in the image is prone to inter- and intra-reviewer variability and is also time-consuming to perform. Automated anatomical structure detection is the first step towards the development of a fast and reproducible quality assessment of fetal biometry images. This thesis deals specifically with abdominal scans in the development and evaluation of methods to automatically detect the stomach and the umbilical vein within them. First, an original method for detecting the stomach and the umbilical vein in fetal abdominal scans was developed using a machine learning framework. A classifier solution was designed with AdaBoost learning algorithm with Haar features extracted from the intensity image. The performance of the new method was compared on different clinically relevant gestational age groups. Speckle and the low contrast nature of ultrasound images motivated the idea of introducing features extracted from local phase images. Local phase is contrast invariant and has proven to be useful in other ultrasound image analysis application compared with intensity. Nevertheless, it has never been implemented in a machine learning environment before. In our second experiment, local phase features were proven to have higher discriminative power than intensity features which enabled them to be selected as the first weak classifiers with large classifier weight. Third, a novel approach to improving the speed of the detection was developed using a global feature symmetry map based on local phase to select the candidate locations for the stomach and the umbilical vein. It was coupled with a local intensity-based classifier to form a “hybrid” detector. A nine-fold increase in the average computational speed was recorded along with higher accuracy in the detection of both the anatomical structures. Quantitative and qualitative evaluations of all the algorithms were presented using 2384 fetal abdominal images retrieved from the image database study of the Oxford Ultrasound Quality Control Unit of the INTERGROWTH-21st project. Finally, the “hybrid” detection method was evaluated in two potential application scenarios. The first application was clinical scoring in which both the computer algorithm and four experts were asked to record presence or absence of the stomach and the umbilical vein in 400 ultrasound images. The computer-experts agreement was found to be comparable with the inter-expert agreement. The second application concerned selecting the standard image plane from 3D abdominal ultrasound volume. The algorithm was successful in selecting 93.36% of the images plane defined by the expert in 30 ultrasound volumes.

The everything as a service concept enables dynamic resource provisions to be seen and delivered as services. Their proliferation nowadays leads to the creation of new value-added services composed of several sub-services in a pre-specified manner, known as service workflows. The use of service workflow appears in various domains, ranging from the basic interactions found in several e-commerce and several online interactions to the complex ones such as Virtual Organizations, Grids, and Cloud Computing. However, the dynamic nature in open environments makes a workflow constantly changing, to be adaptable to the change of new circumstances. How to determine suitable services has becomes a very important challenge. Requirements from both workflow owners and service providers play a significant role in the process of service acquisition, composition, and interoperations. From the workflow owner viewpoint, requirements can specify properties of services to be acquired for tasks in a workflow. On the other hand, requirements from service providers affect trust-based decision in workflow participation. The lack of formal languages to specify these requirements poses difficulties in the success of service collaborations in a workflow. It impedes: (1) workflow scalability that tends to be limited within a certain set of trusted domains; (2) dynamicity when each service acts in an autonomous and unpredictable manner where any change might affect existing requirements; and (3) inconsistency in dealing with the disparate representations of requirements, causing high overhead for compliance checking. This thesis focuses on developing a framework to overcome, or at least alleviate, these problems. It situates in inter-disciplinary areas including logics, workflow modelling, specification languages, trust management, decision support system, and compliance checking. Two core elements are proposed: (1) a formal logic-based requirement specification language, namely Trust Specification (TS), such that the requirements can be formally and uniformly expressed; and (2) compliance checking algorithms to automatically check for the compliance of requirements in service workflows. It is worth noting that this thesis contains some proofs of logic extension, workflow modelling, specification language, and compliance checking algorithms. These might raise a concern to people focusing deep on one particular area such as logics, or workflow modelling who might overlook the essence of the work, for example (1) the application of a formal specification language to the exclusive characteristics of service workflows, and (2) bridging the gap of the high level languages such as trust management down to the lower logic-based ones. The first contribution of the framework is to allow requirements to be independently and consistently expressed by each party where the workflow participation decision and acquisition are subject to the compliance of requirements. To increase scalability in large-scale interoperations, the second contribution centres on automatic compliance checking where TS language and compliance checking algorithms are two key components. The last contribution focuses on dynamicity. The framework allows each party to modify existing requirements and the compliance checking would be automatically activated to check for further compliance. As a result, it is anticipated that the solution will encourage the proliferation of service provisions and consumption over the Internet.

In this thesis, we investigate the problem of human layout estimation in unconstrained still images. This involves predicting the spatial configuration of body parts. We start our investigation with pictorial structure models and propose an efficient method of model fitting using skin regions. To detect the skin, we learn a colour model locally from the image by detecting the facial region. The resulting skin detections are also used for hand localisation. Our next contribution is a comprehensive dataset of 2D hand images. We collected this dataset from publicly available image sources, and annotated images with hand bounding boxes. The bounding boxes are not axis aligned, but are rather oriented with respect to the wrist. Our dataset is quite exhaustive as it includes images of different hand shapes and layout configurations. Using our dataset, we train a hand detector that is robust to background clutter and lighting variations. Our hand detector is implemented as a two-stage system. The first stage involves proposing hand hypotheses using complementary image features, which are then evaluated by the second stage classifier. This improves both precision and recall and results in a state-of-the-art hand detection method. In addition we develop a new method of non-maximum suppression based on super-pixels. We also contribute an efficient training algorithm for structured output ranking. In our algorithm, we reduce the time complexity of an expensive training component from quadratic to linear. This algorithm has a broad applicability and we use it for solving human layout estimation and taxonomic multiclass classification problems. For human layout, we use different body part detectors to propose part candidates. These candidates are then combined and scored using our ranking algorithm. By applying this bottom-up approach, we achieve accurate human layout estimation despite variations in viewpoint and layout configuration. In the multiclass classification problem, we define the misclassification error using a class taxonomy. The problem then reduces to a structured output ranking problem and we use our ranking method to optimise it. This allows inclusion of semantic knowledge about the classes and results in a more meaningful classification system. Lastly, we substantiate our ranking algorithm with theoretical proofs and derive the generalisation bounds for it. These bounds prove that the training error reduces to the lowest possible error asymptotically.

- / Criticality-based maintenance (CBM) is a prioritized approach to the maintenance of (industrial) process equipment. CBM requires personnel with a thorough knowledge of the process/equipment under scrutiny. In this paper a criticality assessment system that is implemented by a local company (which represents the expertise and knowledge of the company experts) is reviewed and fuzzy logic theory is applied to improve the system's capability and reliability. The quality of the fuzzy system is evaluated based on several case studies. The results show that the fuzzy logic based system does not only what the conventional system does, but also outperforms in terms of reliability and has a unique ranking capability.

While a lot of efforts have been on outdoor intelligent systems, internal living environment system that suits the occupancy’s behaviour has not received much attention. The intelligent living environment designed in this study has three components; the physical world (environment), the database and the decision maker. The study sought to design a model that senses ever changing home conditions such as lights, doors and windows. Other variables that were looked at include, but not limited to the number of people in the room and inside thermodynamics and human activity. Global information such as temperature, gas or electricity usage and time of the day will also be received by the system through various sensing facilities. The information will be sent to a rules engine for a decision on an appropriate action to be taken. The action may include just turning off the lights, in the case of a mild abnormality or a high alert to an emergency response unit in a most severe case. The study proposes a context aware and proactive neural networks control system to control a living environment with a main focus on the aged citizens living alone. The proposed living environment was not developed to an actual or “mock” building containing a representation of subset of sensors, actuators and controllers as used in the actual systems due to lack of funding. However, the study will report on the modelling and simulation of the home system variables based on the chosen Artificial Intelligent technique using MATLAB/SIMULINK. These results indicate a possibility of implementing the designed living environment to increase the resident’s security. / Electrical and Mining Engineering / M. Tech. (Engineering: Electrical)