The development of condition monitoring and fault diagnosis systems for wind turbines has received considerable attention in recent years. With wind playing an increasing part in Canada’s electricity demand from renewable resources, installations of new wind turbines are experiencing significant growth in the region. Hence, there is a need for efficient condition monitoring and fault diagnosis systems for wind turbines. Gearbox, as one of the highest risk elements in wind turbines, is responsible for smooth operation of wind turbines. Moreover, the availability of the whole system depends on the serviceability of the gearbox. This work presents signal processing and soft computing techniques to increase the detection and diagnosis capabilities of wind turbine gearbox monitoring systems based on vibration signal analysis. Although various vibration based fault detection and diagnosis techniques for gearboxes exist in the literature, it is still a difficult task especially because of huge background noise and a large solution search space in real world applications. The objective of this work is to develop a novel, intelligent system for reliable and real time monitoring of wind turbine gearboxes. The developed system incorporates three major processes that include detecting the faults, extracting the features, and making the decisions. The fault detection process uses intelligent filtering techniques to extract faulty information buried in huge background noise. The feature extraction process extracts fault-sensitive and vibration based transient features that best describe the health of the gearboxes. The decision making module implements probabilistic decision theory based on Bayesian inference. This module also devises an intelligent decision theory based on fuzzy logic and fault semantic network. Experimental data from a gearbox test rig and real world data from wind turbines are used to verify the viability, reliability, and robustness of the methods developed in this thesis. The experimental test rig operates at various speeds and allows the implementation of different faults in gearboxes such as gear tooth crack, tooth breakage, bearing faults, iv and shaft misalignment. The application of hybrid conventional and evolutionary optimization techniques to enhance the performance of the existing filtering and fault detection methods in this domain is demonstrated. Efforts have been made to decrease the processing time in the fault detection process and to make it suitable for the real world applications. As compared to classic evolutionary optimization framework, considerable improvement in speed has been achieved with no degradation in the quality of results. The novel features extraction methods developed in this thesis recognize the different faulty signatures in the vibration signals and estimate their severity under different operating conditions. Finally, this work also demonstrates the application of intelligent decision support methods for fault diagnosis in gearboxes. / UOIT

There are increasing safety concerns in chemical and petrochemical process industry. The huge explosion of Nowruz oil Field platform that happened in Persian gulf-IRAN at 1983, along with other disastrous events have effected chemical industrial renaissance and led to high demand to enhance safety. Oil and chemical Industries involve complex processes and handle hazardous materials that may potentially cause catastrophic consequences in terms of human losses, injuries, asset lost and environmental stresses. One main reason of such catastrophic events is the lack of effective control and monitoring approaches that are required to achieve successful fault diagnosis and accurate hazard identification. Currently, there are aggressive worldwide efforts to propose an effective, robust, and high accuracy fault propagation analysis and monitoring techniques to prevent undesired events at early stages prior to their occurrence. Among these requirements is the development of an intelligent and automated control and monitoring system to first diagnose faulty equipment and process variable deviations, and then identify hazards associated with faults and deviations. Research into safety and control issues become high priority in all aspects. To support these needs, predictive control and intelligent monitoring system is under study and development at the Energy Safety and Control Laboratory (ESCL) – University of Ontario Institute of Technology (UOIT). The purpose of this research is to present a real time fault propagation analysis method for chemical / petrochemical process industry through fault semantic network (FSN) using accurate process variable interactions (PV-PV interactions). The effectiveness, feasibility, and robustness of the proposed method are demonstrated on simulated data emanating from a well-known Tennessee Eastman (TE) chemical process. Unlike most existing probabilistic approaches, fault propagation analysis module classifies faults and identifies faulty equipment and deviations according to obtained data from the underlying processes. It is an expert system that identifies corresponding causes and consequences and links them together. FSN is an integrated framework that is used to link fault propagation scenarios qualitatively and quantitatively. Probability and fuzzy rules are used for reasoning causes and consequences and tuning FSN. / UOIT