No description available.

<p>Unexpected failures in rotating machinery can result in production downtime, costly repairs and safety concerns. Electric motors are commonly used in rotating machinery and are critical to their operation. Therefore, fault detection and diagnosis of electric motors can play a very important role in increasing their reliability and operational safety. This is especially true for safety critical applications.</p> <p>This research aims to develop a Fault Detection and Diagnosis (FDD) strategy for detecting motor faults at their inception. Two FDD strategies were considered involving wavelets and state estimation. Bearing faults and stator winding faults, which are responsible for the majority of motor failures, are considered. These faults were physically simulated on a Permanent Magnet Brushless DC Motor (PMBLDC). Experimental results demonstrated that the proposed fault detection and diagnosis schemes were very effective in detecting bearing and winding faults in electric motors.</p> / Master of Applied Science (MASc)

Timely Fault Detection and Diagnosis in complex manufacturing systems is critical to ensure safe and effective operation of plant equipment. Process fault is defined as a deviation from normal process behavior, defined within the limits of safe production. The quantifiable objectives of Fault Detection include achieving low detection delay time, low false positive rate, and high detection rate. Once a fault has been detected pinpointing the type of fault is needed for purposes of fault mitigation and returning to normal process operation. This is known as Fault Diagnosis. Data-driven Fault Detection and Diagnosis methods emerged as an attractive alternative to traditional mathematical model-based methods, especially for complex systems due to difficulty in describing the underlying process. A distinct feature of data-driven methods is that no a priori information about the process is necessary. Instead, it is assumed that historical data, containing process features measured in regular time intervals (e.g., power plant sensor measurements), are available for development of fault detection/diagnosis model through generalization of data. The goal of my research was to address the shortcomings of the existing data-driven methods and contribute to solving open problems, such as: 1) decentralized fault detection and diagnosis; 2) fault detection in the cold start setting; 3) optimizing the detection delay and dealing with noisy data annotations. 4) developing models that can adapt to concept changes in power plant dynamics. For small-scale sensor networks, it is reasonable to assume that all measurements are available at a central location (sink) where fault predictions are made. This is known as a centralized fault detection approach. For large-scale networks, decentralized approach is often used, where network is decomposed into potentially overlapping blocks and each block provides local decisions that are fused at the sink. The appealing properties of the decentralized approach include fault tolerance, scalability, and reusability. When one or more blocks go offline due to maintenance of their sensors, the predictions can still be made using the remaining blocks. In addition, when the physical facility is reconfigured, either by changing its components or sensors, it can be easier to modify part of the decentralized system impacted by the changes than to overhaul the whole centralized system. The scalability comes from reduced costs of system setup, update, communication, and decision making. Main challenges in decentralized monitoring include process decomposition and decision fusion. We proposed a decentralized model where the sensors are partitioned into small, potentially overlapping, blocks based on the Sparse Principal Component Analysis (PCA) algorithm, which preserves strong correlations among sensors, followed by training local models at each block, and fusion of decisions based on the proposed Maximum Entropy algorithm. Moreover, we introduced a novel framework for adding constraints to the Sparse PCA problem. The constraints limit the set of possible solutions by imposing additional goals to be reached trough optimization along with the existing Sparse PCA goals. The experimental results on benchmark fault detection data show that Sparse PCA can utilize prior knowledge, which is not directly available in data, in order to produce desirable network partitions, with a pre-defined limit on communication cost and/or robustness. / Computer and Information Science

Recent research discussed the development of image processing tools as a part of the quality control framework in manufacturing environments. This research could be divided into two image-based fault detection approaches: 1) MVS; and 2) MVS and control charts. Despite the intensive research in both groups, there is a disconnect between research and the actual needs on the shop-floor. This disconnect is mainly attributed to the following: • The literature for the first category has mainly focused on improving fault detection accuracy through the use of special setups without considering its impact on the manufacturing process. Therefore, many of these methods have not been utilized by industry, and these tools lack the capability of using images already present on the shop floor. • The studies presented on the second category have been mainly developed in isolation. In addition, most of these studies have focused more on introducing the concept of utilizing control charts on image data rather than tackling specific industry problems. • In this thesis, these limitations are investigated and are disseminated to the research community through two different journal papers. In the first paper, it was shown that a face-recognition tool could be successfully used to detect faults in real-time in stamped processes, where the changes in image lighting conditions and part location were allowed to emulate actual manufacturing environments. On the other hand, the second paper reviewed the literature on image-based control charts and suggested recommendations for future research. / Master of Science

This thesis presents an artificial neural network (ANN) approach to diagnose and detect faults in oil-filled power transformers based on dissolved gas-in-oil analysis. The goal of the research is to investigate the available transformer incipient fault diagnosis methods and then develop an ANN approach for this purpose. This ANN classifier should not only be able to detect the fault type, but also should be able to judge the cellulosic material breakdown. This classifier should also be able to accommodate more than one type of fault. This thesis describes a two-step ANN method that is used to detect faults with or without cellulose involved. Utilizing a feedforward artificial neural network, the classifier was trained with back-propagation, using training samples collected from different failed transformers. It is shown in the thesis that such a neural-net based approach can yield a high diagnosis accuracy. Several possible design alternatives and comparisons are also addressed in the thesis. The final system has been successfully tested, exhibiting a classification accuracy of 95% for major fault type and 90% for cellulose breakdown. / Master of Science

A real-time algorithm is developed for the detection of series dc arc faults in a grid-tie solar photovoltaic (PV) installation. The sensed dc bus current, which is sampled using an analog-to-digital converter with Galvanic isolation, is filtered using a wavelet-based, two-level filter bank. The filter bank, referred to as the post-processing filter, improves the robustness of the algorithm to any false tripping by rejecting power converter harmonics that are added to the dc bus current. To determine if a fault has occurred, the algorithm calculates the variance of the filter bank output and sees if the calculated variance exceeds an upper threshold value. If the upper threshold is exceeded, and the dc bus voltage falls below a predefined lower limit for a set number of instances, the algorithm trips. The algorithm can detect a series arc fault in under two seconds and does not rely on machine learning techniques to process the sensed signal. The detection algorithm is implemented on a commercial microcontroller using C code, and the filter bank convolutions are implemented using 32-bit floating point variables. / Master of Science / A device is developed for the detection of series dc arc faults in solar photovoltaic installations. Dc arc faults that result from loose connections or worn cable insulation can go unnoticed by most conventional fault detectors. Once it has ignited, the series arc can generate considerable amounts of heat and poses a significant fire risk. By contributing to the development of a dc arc fault detection system, the intention is that dc renewable energy distribution systems, most notably solar photovoltaic installations, can gain even more widespread adoption. This would make a significant impact towards decarbonizing the energy sector and tackling the threat to society posed by climate change.

Refrigeration is a fast-growing industry and has become an integral part of various industries such as food storage, pharmaceutical, residential, chemical, and data centers. Rising global temperatures have increased the need for more energy-efficient and environmentally conscious refrigeration systems. A consistent functioning refrigeration system requires good fault detection and diagnosis (FDD) system to detect faults before failures occur. A good FDD system can help reduce maintenance costs and increase energy savings. The refrigerant present in the chillers consists of greenhouse gases. Certain faults, such as refrigerant leakage, result in the release of refrigerant into the atmosphere, which has an environmental impact. Hence, an effective FDD system for chillers is important for accurately detecting and diagnosing faults. This thesis aims to build a data-driven FDD system for vapor-compression chillers. The purpose of this thesis is to address the variable operating conditions and fault conditions that occur during the operation of a chiller system. The operating conditions vary depending on the control logic, climate, and other factors that can occur in a system with multiple components. Faults can occur to varying degrees within a system. Early fault detection and diagnosis lead to prompt maintenance dispatching. It is imperative that an FDD system accommodates these conditions and accurately detect faults. This thesis uses two types of data to build an FDD model. The experimental data provided by ASHRAE RP-1043, which contained both normal and fault conditions, were used. The ASHRAE dataset contains normal conditions and seven fault conditions at the four severity levels. Other types of data used were simulated data generated using the ASHRAE RP-1043 model and a small chiller model developed by the author. Simulated data supplemented the experimental dataset with different normal operating conditions and fault severity levels. A hybrid architecture consisting of a dimensionality reduction method and classifier was proposed. This architecture facilitates the comparison of machine learning and deep learning techniques, and may be employed to develop a hybrid model that incorporates both approaches. Time series data was used to train and test this architecture. A deviation matrix method, which is a preprocessing method applied to the training and testing datasets, was proposed. This method was used with steady-state data to develop a 2D Convolutional Neural Network (CNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). The deviation matrix method proved effective for machine learning and deep learning models to detect and diagnose faults for different normal and fault severity levels. A study using steady-state time-series data and complete test cycle data was conducted to build and test the hybrid architecture. It was concluded that using steady-state time-series data yielded a higher classification accuracy for faults. The deviation matrix method was applied to the simulation and experimental data, and 2D CNN, ANN, and SVM were used to study these datasets. It was concluded that some parts of the training data could be substituted with the simulation data to obtain acceptable classification accuracy. The 2D CNN, ANN, and SVM were able to diagnose faults in the test data containing different severity levels from the training set and small-chiller data. The SVM was also effective in detecting near-normal operations. / Dissertation / Doctor of Philosophy (PhD)

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-28T16:50:59Z No. of bitstreams: 1 WAGNER DE SOUZA PORTO - DISSERTAÇÃO PPGCC 2009..pdf: 3676431 bytes, checksum: 91bede14a64447aa4598ba5c6b3365a4 (MD5) / Made available in DSpace on 2018-08-28T16:50:59Z (GMT). No. of bitstreams: 1 WAGNER DE SOUZA PORTO - DISSERTAÇÃO PPGCC 2009..pdf: 3676431 bytes, checksum: 91bede14a64447aa4598ba5c6b3365a4 (MD5) Previous issue date: 2009-09-16 / Este trabalho apresenta o Auto-FDI (Automatic Fault Detection and Isolation), uma ferramenta de detecção e isolamento de falhas em sistemas. A ferramenta usa o conceito de redundância analítica, onde sinais obtidos do sistema (possivelmente com falha) são comparados com sinais esperados, obtidos de um modelo. O isolamento de falhas emprega uma técnica desenvolvida neste trabalho, chamada isolamento automático. A técnica usa uma abordagem baseada em grafos que considera a propagação de falhas e a falta de informação sobre determinados componentes do sistema. Falhas são localizadas de forma mais precisa possível, dado o nível de detalhe do modelo. No escopo deste trabalho foi abordado todo o processo de especificação, projeto, implementação e validação da ferramenta, utilizada como prova de conceito para a técnica desenvolvida. A validação da ferramenta foi feita através da realização de um estudo de caso por potenciais usuários, o que permitiu demonstrar a aplicabilidade da ferramenta e a da técnica desenvolvida. / This work presents Auto-FDI (Automatic Fault Detection and Isolation), a software tool for detection and diagnosis of faults in systems. The tool uses the analytical redundancy concept, where signals from the (possibly faulty) system are compared with expected signals from a model. The fault isolation employs a technique developed on this work, called automatic isolation. This technique uses a graph-based approach which considers the fault propagation and the lack of information about certain components of the system. Faults are pinpointed as accurately as possible given the level of detail in the model. In the scope of this work was addressed the whole process of specification, design, implementation and validation of the tool - used as proof of concept for the developed technique. The validation of the tool was made by conducting a case study for potential users, that has demonstrated the applicability of the tool and the technique developed.

Artificial Intelligence in Automotive Industry / Cost reduction is one of the main concerns in industry. Companies invest considerably for better performance in end-of-line fault diagnosis systems. A common strategy is to use data obtained from existing instrumentation. This research investigates the challenge of learning from historical data that have already been collected by companies. Machine learning is basically one of the most common and powerful techniques of artificial intelligence that can learn from data and identify fault features with no need for human interaction. In this research, labeled sound and vibration measurements are processed into fault signatures for vehicle starter motors and alternators. A fault detection and identification system has been developed to identify fault types for end-of-line testing of motors. However, labels are relatively difficult to obtain, expensive, time consuming and require experienced humans, while unlabeled samples needs less effort to collect. Thus, learning from unlabeled data together with the guidance of few labels would be a better solution. Furthermore, in this research, learning from unlabeled data with absolutely no human intervention is also implemented and discussed as well. / Thesis / Master of Applied Science (MASc)

<p>The report begins with a general inventory of possible technical faults in a hydropower plant and of possible fault indicating measurements. Then an investigation is made concerning a few different faults. Based on this investigation a choice on seal box condition and water leakage is made as problem for a more thorough examination, in which it is concluded that the turbine water leakage is larger when the turbine is put into operation. The examination ultimately results in a computer alarm for faults related to the seal box. Finally a few things are mentioned about flow measurement and pressure measurement in relation to the project as a whole.</p> / <p>Rapporten inleds med en övergripande sammanställning av möjliga tekniska fel i en vattenkraftstation och av möjliga felindikerande mätningar. Därefter görs en probleminventering av ett antal olika fel. Baserat på denna inventering väljes sedan tätningsboxkondition och läckvatten som problem för en mer ingående undersökning, vid vilken det konstateras att turbinvattenläckaget är större när turbinen är i drift. Undersökningen utmynnar sedan i ett datalarm för fel relaterade till tätningsboxar. Slutligen nämns något om flödesmätning och tryckmätning i relation till projektet i sin helhet.</p>