Browsing by Author "Niculita, Octavian"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    The application of Bayesian Change Point Detection in UAV fuel systems
    (Elsevier, 2014-10-31) Niculita, Octavian; Skaf, Zakwan; Jennions, Ian K.
    A significant amount of research has been undertaken in statistics to develop and implement various change point detection techniques for different industrial applications. One of the successful change point detection techniques is Bayesian approach because of its strength to cope with uncertainties in the recorded data. The Bayesian Change Point (BCP) detection technique has the ability to overcome the uncertainty in estimating the number and location of change point due to its probabilistic theory. In this paper we implement the BCP detection technique to a laboratory based fuel rig system to detect the change in the pre-valve pressure signal due to a failure in the valve. The laboratory test-bed represents a Unmanned Aerial Vehicle (UAV) fuel system and its associated electrical power supply, control system and sensing capabilities. It is specifically designed in order to replicate a number of component degradation faults with high accuracy and repeatability so that it can produce benchmark datasets to demonstrate and assess the efficiency of the BCP algorithm. Simulation shows satisfactory results of implementing the proposed BCP approach. However, the computational complexity, and the high sensitivity due to the prior distribution on the number and location of the change points are the main disadvantages of the BCP approach.
  • Thumbnail Image
    ItemOpen Access
    Comparison of different classification algorithms for fault detection and fault isolation in complex systems
    (Elsevier, 2018-02-08) Jung, Marcel; Niculita, Octavian; Skaf, Zakwan
    Due to the lack of sufficient results seen in literature, feature extraction and classification methods of hydraulic systems appears to be somewhat challenging. This paper compares the performance of three classifiers (namely linear support vector machine (SVM), distance-weighted k-nearest neighbor (WKNN), and decision tree (DT) using data from optimized and non-optimized sensor set solutions. The algorithms are trained with known data and then tested with unknown data for different scenarios characterizing faults with different degrees of severity. This investigation is based solely on a data-driven approach and relies on data sets that are taken from experiments on the fuel system. The system that is used throughout this study is a typical fuel delivery system consisting of standard components such as a filter, pump, valve, nozzle, pipes, and two tanks. Running representative tests on a fuel system are problematic because of the time, cost, and reproduction constraints involved in capturing any significant degradation. Simulating significant degradation requires running over a considerable period; this cannot be reproduced quickly and is costly.
  • Thumbnail Image
    ItemOpen Access
    Integrating IVHM and Asset Design
    (Prognostics and Health Management Society, 2016-10-31) Jennions, Ian K.; Niculita, Octavian; Esperon Miguez, Manuel
    Integrated Vehicle Health Management (IVHM) describes a set of capabilities that enable effective and efficient maintenance and operation of the target vehicle. It accounts for the collection of data, conducting analysis, and supporting the decision-making process for sustainment and operation. The design of IVHM systems endeavours to account for all causes of failure in a disciplined, systems engineering, manner. With industry striving to reduce through-life cost, IVHM is a powerful tool to give forewarning of impending failure and hence control over the outcome. Benefits have been realised from this approach across a number of different sectors but, hindering our ability to realise further benefit from this maturing technology, is the fact that IVHM is still treated as added on to the design of the asset, rather than being a sub-system in its own right, fully integrated with the asset design. The elevation and integration of IVHM in this way will enable architectures to be chosen that accommodate health ready sub-systems from the supply chain and design trade-offs to be made, to name but two major benefits. Barriers to IVHM being integrated with the asset design are examined in this paper. The paper presents progress in overcoming them, and suggests potential solutions for those that remain. It addresses the IVHM system design from a systems engineering perspective and the integration with the asset design will be described within an industrial design process.
  • Thumbnail Image
    ItemOpen Access
    Towards an Integrated COTS Toolset for IVHM Design
    (PHM Society, 2014-05-30) Niculita, Octavian; Jennions, Ian K.; Valdez, Miguel Medina
    This paper describes an end-to-end Integrated Vehicle Health Management (IVHM) development process with a strong emphasis on the automation in creating functional models from 3D Computer Aided Design (CAD) system’s representation, throughout the implementation of this process. It has been demonstrated that functional analysis enhances the design and development of IVHM but this approach is not widely adopted by industry and the research community as it carries a significant amount of subjectivism. This paper is meant to be a guideline that supports the correctness through construction of a functional representation for a complex mechatronic system. The knowledge encapsulated in the 3D CATIA™ System Design environment was linked with the Maintenance Aware Design environment (MADe™) with the scope of automatically creating functional models of the geometry of a system. The entire process is documented step by step and it is demonstrated on a laboratory fuel system test rig. The paper is part of a larger effort towards an integrated COTS toolset for IVHM design. Another objective of the study is to identify the relations between the different types of knowledge supporting the health management development process when used together with the spatial and functional dimensions of an asset. The conclusion of this work is that a 3D CAD model containing the topological representation of a complex system can automate the development of the functional model of such a system.
  • Thumbnail Image
    ItemOpen Access
    Towards design of prognostics and health management solutions for maritime assets
    (Elsevier, 2017-03-02) Niculita, Octavian; Nwora, Obinna; Skaf, Zakwan
    With increase in competition between OEMs of maritime assets and operators alike, the need to maximize the productivity of an equipment and increase operational efficiency and reliability is increasingly stringent and challenging. Also, with the adoption of availability contracts, maritime OEMs are becoming directly interested in understanding the health of their assets in order to maximize profits and to minimize the risk of a system's failure. The key to address these challenges and needs is performance optimization. For this to be possible it is important to understand that system failure can induce downtime which will increase the total cost of ownership, therefore it is important by all means to minimize unscheduled maintenance. If the state of health or condition of a system, subsystem or component is known, condition-based maintenance can be carried out and system design optimization can be achieved thereby reducing total cost of ownership. With the increasing competition with regards to the maritime industry, it is important that the state of health of a component/sub-system/system/asset is known before a vessel embarks on a mission. Any breakdown or malfunction in any part of any system or subsystem on board vessel during the operation offshore will lead to large economic losses and sometimes cause accidents. For example, damages to the fuel oil system of vessel's main engine can result in huge downtime as a result of the vessel not being in operation. This paper presents a prognostic and health management (PHM) development process applied on a fuel oil system powering diesel engines typically used in various cruise and fishing vessels, dredgers, pipe laying vessels and large oil tankers. This process will hopefully enable future PHM solutions for maritime assets to be designed in a more formal and systematic way.
  • Thumbnail Image
    ItemOpen Access
    Use of COTS functional analysis software as an IVHM design tool for detection and isolation of UAV fuel system faults
    (2012-08-20) Niculita, Octavian; Irving, Phil; Jennions, Ian K.
    This paper presents a new approach to the development of health management solutions which can be applied to both new and legacy platforms during the conceptual design phase. The approach involves the qualitative functional modelling of a system in order to perform an Integrated Vehicle Health Management (IVHM) design – the placement of sensors and the diagnostic rules to be used in interrogating their output. The qualitative functional analysis was chosen as a route for early assessment of failures in complex systems. Functional models of system components are required for capturing the available system knowledge used during various stages of system and IVHM design. MADe™ (Maintenance Aware Design environment), a COTS software tool developed by PHM Technology, was used for the health management design. A model has been built incorporating the failure diagrams of five failure modes for five different components of a UAV fuel system. Thus an inherent health management solution for the system and the optimised sensor set solution have been defined. The automatically generated sensor set solution also contains a diagnostic rule set, which was validated on the fuel rig for different operation modes taking into account the predicted fault detection/isolation and ambiguity group coefficients. It was concluded that when using functional modelling, the IVHM design and the actual system design cannot be done in isolation. The functional approach requires permanent input from the system designer and reliability engineers in order to construct a functional model that will qualitatively represent the real system. In other words, the physical insight should not be isolated from the failure phenomena and the diagnostic analysis tools should be able to adequately capture the experience bases. This approach has been verified on a laboratory bench top test rig which can simulate a range of possible fuel system faults. The rig is fully instrumented in order to allow benchmarking of various sensing solution for fault detection/isolation that were identified using functional analysis.