54 research outputs found
Condition Monitoring of Electric Machines: Modern Frameworks and Data-Driven Methodologies
No full textElectrical machines are at the centre of most engineering processes, with rotating electrical machines, in particular, becoming increasingly important in recent history due to their growing applications in electric vehicles and renewable energy. Although the landscape of condition monitoring in electrical machines has evolved over the past 50 years, the intensification of engineering efforts towards sustainability, reliability, and efficiency, coupled with breakthroughs in computing, has prompted a data-driven paradigm shift. This paper explores the evolution of condition monitoring of rotating electrical machines in the context of maintenance strategy, focusing on the emergence of this data-driven paradigm. Due to the broad and varying nature of condition monitoring practices, a framework is also offered here, along with other essential terms of reference, to provide a concise overview of recent developments and to highlight the modern challenges and opportunities within this area. The paper is purposefully written as a tutorial-style overview for the benefit of practising engineers and researchers who are new to the field or not familiar with the wider intricacies of modern condition monitoring systems
Methods for condition monitoring and fault diagnosis on a synchronous 2 pole generator
No full textIn order to increase the integrity of existing generation systems, it is essential to discover
problems well in advance. An investigation into methods for diagnosing multiple incipient
faults on a 2-pole synchronous generator is presented. Simulation of the generator on a
finite element analysis (FEA) software package is used to predict the effects of these
faults. Experimental analysis of the generator under fault conditions is then conducted
and confirms the predicted behaviour. The investigation utilises search coils and shaft
brushes as condition monitoring tools. Results of the investigation indicate definitive
relationships between the faults and specific harmonics of the output signals from the
condition monitoring tools. The presented techniques are viable and future work can
utilise these results in the design of a fault diagnosis system
Processing and inferential methods to improve shaft-voltage-based condition monitoring of synchronous generators
No full textThis thesis focuses on improving shaft-voltage-based condition monitoring of synchronous
generators. The work presents theory for describing and modelling shaft
voltages using fundamental electromagnetic principles. A modern framework is
adopted in developing an online, automated and intelligent fault-diagnosis system.
Novel processing and inferential methods are used by the system to provide accurate
and reliable incipient-fault detection and diagnosis. The literature shows
that shaft-voltage analysis is recognised as a technique with potential for use in
condition monitoring. However, deficiencies in the fundamental theory and the inadequacy
of methods for extracting useful information has limited its widespread
application. This work extends the knowledge of shaft voltages, validates the
merits of its use for fault diagnosis, and provides methods for practical application.
Validation of the model is completed using an experimental synchronous
generator, and results indicate that simulated shaft voltages compare well with
the measurements - i.e. total average error of the model combined with experimental
uncertainty is below 16%. The fault detection and diagnosis components
are tested separately and together as a complete shaft-voltage-based conditionmonitoring
system in an experimental setting. Results indicate that the system
can accurately diagnose faults and it represents a unique and valuable contribution
to shaft-voltage-based condition monitoring. Additionally, techniques such as optimal
measurement selection, multivariate model monitoring, and fault inference
developed for the investigations and system presented in this thesis, will assist
engineers and researchers working in the field of condition monitoring of electrical
rotating machines
An investigation of lightning risk assessment and protection requirements for small-scale rooftop photovoltaic systems
No full textM.Tech. (Electrical Engineering)Abstract: Please refer to full text to view abstract
Development of an intelligent electronic load controller for stand-alone micro-hydropower systems
No full textAbstract: People living in rural and remote areas of Sub- Saharan Africa generally lack access to electricity due to their geographical location and the costs associated with connecting these areas to the national electrical grid. A viable technology to supply electricity to some of these areas are stand-alone microhydropower systems which harnesses energy from flowing water. Self-excited induction generators (SEIGs) are commonly used for the generation of electricity in stand-alone micro-hydropower systems. The electricity supplied by a SEIG to the demand side i.e. the load needs to be maintained stable under various consumer load conditions. This is accomplished through the use of an electronic load controller (ELC). This paper presents the design and development of an intelligent ELC that is able to maintain stable voltage on the demand side of a 3-phase SEIG supplying varying single-phase consumer loads. The proposed intelligent ELC consists of an uncontrolled bridge rectifier, filtering capacitor, chopper switch, voltage sensor, optocoupler, Arduino microcontroller and a ballast load or storage, depending on site-specific requirements and economic viability. The fuzzy logic control method is implemented to maintain stable and reliable voltage. The ELC is designed and simulated under various consumer load conditions in Matlab/Simulink. Simulation results of the ELC model are verified experimentally in a laboratory setting. The proposed intelligent ELC will contribute towards providing reliable and cost-effective means of enhancing the proliferation of micro-hydropower particularly in rural and remote applications in Sub-Saharan Africa
Predictive Maintenance Framework for Cathodic Protection Systems Using Data Analytics
No full textIn the quest to achieve sustainable pipeline operations and improve pipeline safety, effective corrosion control and improved maintenance paradigms are required. For underground pipelines, external corrosion prevention mechanisms include either a pipeline coating or impressed current cathodic protection (ICCP). For extensive pipeline networks, time-based preventative maintenance of ICCP units can degrade the CP system’s integrity between maintenance intervals since it can result in an undetected loss of CP (forced corrosion) or excessive supply of CP (pipeline wrapping disbondment). A conformance evaluation determines the CP system effectiveness to the CP pipe potentials criteria in the NACE SP0169-2013 CP standard for steel pipelines (as per intervals specified in the 49 CFR Part 192 statute). This paper presents a predictive maintenance framework based on the core function of the ICCP system (i.e., regulating the CP pipe potential according to the NACE SP0169-2013 operating window). The framework includes modeling and predicting the ICCP unit and the downstream test post (TP) state using historical CP data and machine learning techniques (regression and classification). The results are discussed for ICCP units operating either at steady state or with stray currents. This paper also presents a method to estimate the downstream TP’s CP pipe potential based on the multiple linear regression coefficients for the supplying ICCP unit. A maintenance matrix is presented to remedy the defined ICCP unit states, and the maintenance time suggestion is evaluated using survival analysis, cycle times, and time-series trend analysis
Life Modelling of Metal-Oxide Surge Arresters: A Comparison of Computational Techniques for Analysing Failure Data
No full textA neural network based response model for high voltage circuit-breaker testing
No full textInnovative test methods for circuit breakers are constantly sought after to reduce maintenance time and costs, yet still provide accurate assessment of this critical substation equipment. This paper proposes a novel method for response modelling of high voltage SF6 circuit breakers, based on artificial neural networks, to provide a means of assessing its condition. The proposed method enables a timing response model of the circuit breaker to be developed using trip command parameters. In this paper, an experimental setup is used to perform trip response testing of a three-phase 75 kV circuit breaker. The obtained data is then used to train, validate and test a Bayesian regularised artificial neural network that can predict response times of the breaker for a given set of trip command parameters
An unsupervised learning approach to condition assessment on a wound-rotor induction generator
No full textAbstract: Accurate online diagnosis of incipient faults and condition assessment on generators is especially challenging to automate through supervised learning techniques, because of data imbalance. Fault-condition training and test data are either not available or are experimentally emulated, and therefore do not precisely account for all the eventualities and nuances of practical operating conditions. Thus, it would be more convenient to harness the ability of unsupervised learning in these applications. An investigation into the use of unsupervised learning as a means of recognizing incipient fault patterns and assessing the condition of a wound-rotor induction generator is presented. High-dimension clustering is performed using stator and rotor current and voltage signatures measured under healthy and varying fault conditions on an experimental wound-rotor induction generator. An analysis and validation of the clustering results are carried out to determine the performance and suitability of the technique. Results indicate that the presented technique can accurately distinguish the different incipient faults investigated in an unsupervised manner. This research will contribute to the ongoing development of unsupervised learning frameworks in data-driven diagnostic systems for WRIGs and similar electrical machines
Exploring the effects of compression via principal components analysis on X-ray image classification
No full textAbstract: Image compression in medical applications implores careful consideration of the effects on data veracity. The inexorable challenge of assessing the volume-veracity trade-off is becoming more prevalent in this critical application area, and particularly when machine learning is used for the purpose of assisted diagnostics. This paper investigates the impact of compressing X-ray images on the accuracy of fracture diagnostics. The accuracy of the classification system is assessed for X-ray images of both healthy and fracture bones when subjected to different levels of compression. Compression is achieved using principal components analysis. Results indicate that accuracy is only marginally affected under a level one compression but begins to deteriorate under level two compression. These results are potentially useful as the level one compression yields gains up to 94% with less than a 2% drop in classification accuracy
- …
