Fault detection and diagnosis is a critical component of operations management systems. The goal of FDD is to identify the occurrence and causes of abnormal events. While many approaches are available, data-driven approaches for FDD have proven to be robust and reliable. Exploiting these advantages, the present study applied functional principal component analysis (FPCA) to carry out feature extraction for fault detection in internal combustion engines. Furthermore, a feature subset that explained 95% of the variance of the original vibrational sensor signal was used in a multilayer perceptron to carry out prediction for fault diagnosis. Of the engine states studied in the present work, the ending diagnostic performance shows the proposed approach achieved an overall prediction accuracy of 99.72 %. These results are encouraging because they show the feasibility for applying FPCA for feature extraction which has not been discussed previously within the literature relating to fault detection and diagnosis.

Faulty manufactured alternators lead to commercial and safety concerns when installed in vehicles. Alternators have a major role in the Electrical Power Generation System (EPGS) of vehicles, and a defective alternator will lead to damaging of the battery and other important electric accessories. Therefore, fault detection and diagnosis of alternators can be implemented to quickly and accurately determine the health of an alternator during end of line testing, and not let faulty components leave the manufacturer. The focus of this research is to develop a Model Based Fault Detection and Diagnosis (FDD) strategy for detecting alternator faults during end of line testing. The proposed solution uses Extended Kalman Smooth Variable Structure Filter (EK-SVSF) to detect common alternator faults. A solution using the Dual Extended Kalman Filter (DEKF) is also discussed. The alternator faults were programmatically simulated on alternator measurements. The experimental results prove that both the EK-SVSF and DEKF strategies were very effective in alternator modeling and detecting open diode faults, shorted diode faults, and stator imbalance faults. / Thesis / Master of Applied Science (MASc)

Deep Learning Networks (DLN) is a relatively new artificial intelligence algorithm that gained popularity quickly due to its unprecedented performance. One of the key elements for this success is DL’s ability to extract a high-level of information from large amounts of raw data. This ability comes at the cost of high computational and memory requirements for the training process. Estimation algorithms such as the Extended Kalman Filter (EKF) and the Smooth Variable Structure Filter (SVSF) are used in literature to train small Neural Networks. However, they have failed to scale well with deep networks due to their excessive requirements for computation and memory size. In this thesis the concept of using EKF and SVSF for DLN training is revisited. A New family of filters that are efficient in memory and computational requirements are proposed and their performance is evaluated against the state-of-the-art algorithms. The new filters show competitive performance to existing algorithms and do not require fine tuning. These new findings change the scientific community’s perception that estimation theory methods such as EKF and SVSF are not practical for their application to large networks. A second contribution from this research is the application of DLN to Fault Detection and Diagnosis. The findings indicate that DL can analyze complex sound and vibration signals in testing of automotive starters to successfully detect and diagnose faults with 97.6% success rates. This proves that DLN can automate end-of-line testing of starters and replace operators who manually listen to sound signals to detect any deviation. Use of DLN in end-of-line testing could lead to significant economic benefits in manufacturing operations. In addition to starters, another application considered is the use of DLN in monitoring of the State-Of-Charge (SOC) of batteries in electric cars. The use of DLN for improving the SOC prediction accuracy is discussed. / Thesis / Doctor of Science (PhD) / There are two main ideas discussed in this thesis, both are related to Deep Learning (DL). The first investigates the use of estimation theory in DL network training. Training DL networks is challenging as it requires large amounts of data and it is computationally demanding. The thesis discusses the use of estimation theory for training of DL networks and its utility in information extraction. The thesis also presents the application of DL networks in an end-of-line Fault Detection and Diagnosis system for complex automotive components. Failure of appropriately testing automotive components can lead to shipping faulty components that can harm a manufacturer’s reputation as well as potentially jeopardizing safety. In this thesis, DL is used to detect and analyze complex fault patterns of automotive starters, complemented by sound and vibration measurements.

De par l’augmentation de leur utilisation, la sécurisation du vol des drones devient de plus en plus importante. La commande tolérante aux fautes peut alors contribuer à l’obtention d’un niveau de sécurité acceptable. Le but de cette thèse est de développer une méthode de commande tolérante aux fautes basée sur deux types d’approches : l’approche Automatique qui utilise une représentation de systèmes à l’aide de modèles décrivant des évolutions continues et l’approche Intelligence Artificielle qui se base sur la représentation de systèmes à l’aide de modèles discrets ou logiques. Ainsi la première contribution de cette recherche est le développement d'une méthode générique de commande tolérante aux fautes utilisant les cadres de modélisation discret et continu. L’idée consiste à combiner une modélisation continue permettant d’estimer l’état et les paramètres de fautes et une modélisation discrète permettant de prendre une décision en ligne quant au contrôleur à utiliser. L’estimation continue permet d’avoir plus d’informations sur la faute qu’avec une modélisation discrète, alors que celle-ci prend en compte des probabilités de panne et des techniques d’optimisation qui sont plus adaptées à la tâche de décision. La seconde contribution concerne le développement et la validation d’une méthode permettant de détecter et de diagnostiquer la faute. Pour ses avantages, l’idée a été de développer un filtre de Kalman sensibles aux sauts de panne pour l’estimation de l’état et des paramètres de fautes. Pour la détection et le diagnostic de la panne, l’idée a été d’utiliser les données de l’estimation de façon probabiliste. Une fois la faute détectée et identifiée, le système de commande doit réagir pour pouvoir compenser cette faute. La troisième contribution porte donc sur l’amélioration du suivi de la trajectoire par reconfiguration du système de commande. L’objectif est de combiner les méthodes de commutation et d’adaptation, afin de limiter le nombre de contrôleurs en utilisant des contrôleurs adaptatifs pour les modes dégradés, tout en ayant des contrôleurs faciles à concevoir. Des techniques d’optimisation sont alors utilisées de façon à prendre une décision en ligne quant au choix du contrôleur. Finalement, la méthode développée doit être vérifiée avant de pouvoir être implémentée sur un drone. La dernière contribution est l’évaluation de la capacité de la méthode à suivre une trajectoire d’atterrissage en cas de pannes capteurs ou actionneurs grâce à un modèle de drone. / Major security risks appear with the increase of the number of UAV in the air space. Thus, UAV security is more and more important and Fault Tolerant Control (FTC) methods could support the achievement of acceptable security level. The aims of this research is to develop a FTC method which combines two approaches : Automatic Control approach which is based on model which have a continuous representation of the system and Artificial Intelligence approach which is based on discrete or logical model to represent the system. Thus, the first contribution of this thesis is the development of a generic fault tolerant control method which uses discrete and continuous frameworks. The idea was to combine a continuous framework to estimate the state and fault parameters and a discrete framework to take on line a decision about the controller. The continuous estimation provides more knowledge on the fault whereas a discrete model allows the use of different optimization tools which are more adapted to decision task. The second contribution is the development and the validation of a method for fault detection and diagnosis. For its potential, a Kalman filter is adapted in order to be sensitive to abrupt faults and used for state and fault parameters estimation. These estimates are then used in a probabilistic way to detect and identify the fault. Once the fault is detected, the control system should react to compensate the fault. Thus, the third contribution of this thesis is the improvement of the trajectory tracking by reconfiguration of the control system. The aim is to combine switching and adaptive methods in order to limit the number of controllers by using adaptive controllers for degraded modes while having convenient controllers. Optimization tools are then used to take the decision on the controller to use. Finally, the method has to be validated before being implemented on line. The last contribution is the evaluation of the ability of the method to follow its trajectory despite the apparition of actuator or sensor faults during a landing approach.

Submitted by Maria Aparecida (cidazen@gmail.com) on 2017-08-24T15:00:02Z No. of bitstreams: 1 Ronnie.pdf: 3320281 bytes, checksum: 56be4f928c1366ece428d2ae6caf9627 (MD5) / Made available in DSpace on 2017-08-24T15:00:02Z (GMT). No. of bitstreams: 1 Ronnie.pdf: 3320281 bytes, checksum: 56be4f928c1366ece428d2ae6caf9627 (MD5) Previous issue date: 2012-08-31 / This work aims to monitor and analyze the data from the instrumentation system of a substation as a way to identify false alarms, which can result in a decision by the mistaken maintenance and operation. This project was conceived because of the need for a research and development project which is called Maintenance Management Center (MMC) whose overall objective is to assist in the maintenance of their equipment operational intervention. Data is extracted from the automation system that has digital relay protection function and measurement of the electric grid, passing through a sequence of data processing to achieve the results that will serve for the detection and diagnosis of faults. We applied methods based on quantitative model by transforming the data system of continuous variables (SVC) and qualitative data by transforming the system of discrete event (SDE) applying analytical redundancy techniques and neural networks respectively, thus aiming a simplified model for detection and diagnosis fault (DDF). The model has been designed taking into account the characteristics DDF due to its stages, thereby providing a good system failure recovery. Know filter if certain event is real or a false alarm is not an easy task, but this system will have to meet this purpose. Technological resources are used fairly consolidated in the industrial process for the integration of the solution, because the time factor and information processing are critical in the results generated by the system recovery. Another key point of this trial was to have developed a system based on experiential knowledge, because it has higher robustness in results. / Este trabalho tem como objetivo monitorar e analisar os dados provenientes do sistema de instrumentação de uma subestação como forma de identificar falsos alarmes, que pode acarretar em uma tomada de decisão equivocada por parte da manutenção e operação. Este projeto foi concebido devido à necessidade de um projeto de pesquisa e desenvolvimento que se intitula Centro de Gestão da Manutenção (CGM) cujo objetivo global é auxiliar a manutenção na intervenção operacional de seus equipamentos. Os dados são extraídos do sistema de automação provenientes dos reles digitais que tem função de proteção e medição da rede elétrica, passando por um sequencia de transformação dos dados até chegar aos resultados, que servirá para detecção e diagnostico de falhas. Foram aplicados métodos baseados no modelo quantitativo através da transformação dos dados do sistema de variáveis contínuas (SVC) e qualitativo através da transformação dos dados do sistema de eventos discretos (SED) aplicando técnicas de redundância analítica e redes neurais respectivamente, objetivando assim um modelo simplificado para detecção e diagnóstico da falha (DDF). O modelo foi concebido levando em consideração as características DDF decorrente de suas etapas, propiciando assim um bom sistema de recuperação de falha. Saber filtrar se determinado evento é real ou um falso alarme não é uma tarefa fácil, porém este sistema terá que atender este propósito. Foram utilizados recursos tecnológicos bastante consolidados no processo industrial para garantir a integração da solução, pois o fator tempo e o processamento da informação são decisivos nos resultados gerados pelo sistema de recuperação. Outro ponto fundamental neste trabalho foi ter desenvolvido um sistema baseado no conhecimento experimental, pois se tem maior robustez nos resultados.

Ce travail de thèse s’inscrit dans le cadre d’une Convention Industrielle de Formation par la REcherche (CIFRE) ayant pour objectif la mise en place de solutions innovantes pour le diagnostic de défaillances. Il s’agit de répondre au besoin de la société Zodiac Actuation Systems afin de diagnostiquer les défaillances pouvant survenir sur leurs systèmes d’actionnement de sièges d’avion. Premièrement, le cadre ainsi que les motivations de l’étude sont exposés. Ensuite un état de l’art sur les méthodes de diagnostic de défaillances est donné. Puis la problématique de l’hybridation de ces méthodes est abordée. Ceci a permis d’adopter la méthode de classification supervisée pour le diagnostic. Ensuite, les campagnes de mesures, le processus de construction des bases de données ainsi que les différents algorithmes nécessaires pour la classification sont présentés. Une expérimentation sur la partie du dossier d’un siège d’avion est exposée et les résultats sont donnés. Afin d’améliorer les résultats obtenus, une approche de classification renforcée par des observateurs d’état est proposée et appliquée sur le dossier du siège. Ce renforcement est réalisé à l’aide des données estimées par les observateurs tout en construisant des bases de données augmentées. Trois types d’observateurs, linéaire, Takagi-Sugeno (TS) et TS à entrées inconnues (TSEI) sont employés. L’observateur TSEI apparait comme le mieux adapté à notre application. Finalement, une extension de l'approche proposée sur l’ensemble du siège d’avion est proposée. Celle-ci consiste en la mise en œuvre d’observateurs décentralisés TSEI pour chaque sous-ensemble du siège en tenant compte de leurs interconnexions. Ces derniers ont permis d’améliorer les résultats de détection de défaillances sur l’ensemble du siège d’avion. / This study was supported by Zodiac Actuation Systems within the framework of a ``CIFRE'' project which aims to design a Fault Detection and Diagnosis (FDD) approach for actuation systems of passengers seats in commercial aircrafts. First of all, the industrial context as well as the motivations of our project have been explained. Then, a state of the art on FDD methods is presented. Among them, hybridization of FDD methods can be found and seems interesting to our application. In a first step, the supervised classification method for the FDD has been considered. To do this, the process measurements and the concept of databases construction are presented. Then, different types of classification algorithms are explained. From experimental measurements, the classification results for FDD purpose on the recline of the seat are given. In a second step, an enhanced classification approach is proposed. It consists in estimating non-measurable variables by the state observers. These variables are then added, as estimated attributes, to the measured database. The aim is to enrich the knowledge used by the classifier and thus to improve the rate of FDD. Three types of state observers are considered: linear, then Takagi-Sugeno (TS) and Unknown Input Takagi-Sugeno (UITS) observers. It appears that the UITS observer-based results are more accurate for our application. Finally, the proposed FDD approach is extended to the hole of the seat by considering a decentralized approach. In this context, decentralized UITS are proposed for each segment of the seat by taking into account their interconnexions. It is shown that these decentralized observers improve the FDD results of the considered aircraft seat.

Made available in DSpace on 2014-12-17T14:55:21Z (GMT). No. of bitstreams: 1 MarceloRBGV_TESE.pdf: 4018928 bytes, checksum: 7940c018115fd94c74a5dbbd7d3f7fb6 (MD5) Previous issue date: 2014-06-27 / The industries are getting more and more rigorous, when security is in question, no matter is to avoid financial damages due to accidents and low productivity, or when it s related to the environment protection. It was thinking about great world accidents around the world involving aircrafts and industrial process (nuclear, petrochemical and so on) that we decided to invest in systems that could detect fault and diagnosis (FDD) them. The FDD systems can avoid eventual fault helping man on the maintenance and exchange of defective equipments. Nowadays, the issues that involve detection, isolation, diagnose and the controlling of tolerance fault are gathering strength in the academic and industrial environment. It is based on this fact, in this work, we discuss the importance of techniques that can assist in the development of systems for Fault Detection and Diagnosis (FDD) and propose a hybrid method for FDD in dynamic systems. We present a brief history to contextualize the techniques used in working environments. The detection of fault in the proposed system is based on state observers in conjunction with other statistical techniques. The principal idea is to use the observer himself, in addition to serving as an analytical redundancy, in allowing the creation of a residue. This residue is used in FDD. A signature database assists in the identification of system faults, which based on the signatures derived from trend analysis of the residue signal and its difference, performs the classification of the faults based purely on a decision tree. This FDD system is tested and validated in two plants: a simulated plant with coupled tanks and didactic plant with industrial instrumentation. All collected results of those tests will be discussed / As ind?strias est?o cada vez mais rigorosas quando o assunto ? seguran?a, tanto para evitar preju?zos financeiros com acidentes e baixa produtividade, quanto para preservar o meio ambiente. Diante dos grandes acidentes em todo o mundo envolvendo aeronaves e processos industriais (nucleares, petroqu?micos etc) procurou-se investir em sistemas que pudessem detectar e diagnosticar falhas (FDD-Fault Detection and Diagnosis). Os sistemas FDD podem evitar eventuais falhas auxiliando o homem na manuten??o e troca de equipamentos defeituosos. Nos dias de hoje os assuntos que envolvem detec??o, isolamento, identifica??o e diagn?stico de falhas est?o ganhando for?a no meio acad?mico e industrial. Diante deste impulso, neste trabalho ser? discutido a import?ncia do estudo de t?cnicas que possam auxiliar o desenvolvimento de sistemas de detec??o e diagn?stico de falhas e proposto um m?todo h?brido para a detec??o e diagn?stico de falhas em sistemas din?micos. Um breve hist?rico ? apresentado de forma a contextualizar as t?cnicas utilizadas no trabalho. A detec??o de falhas pelo sistema proposto ? baseada em observadores de estado juntamente com outras t?cnicas estat?sticas. A ideia principal ? utilizar o pr?prio observador, para al?m de servir como redund?ncia anal?tica, permitir a cria??o de um res?duo que ser? utilizado na detec??o da falha e tamb?m no seu diagn?stico. Um banco de assinaturas auxiliar? o sistema de identifica??o de falhas, que, baseado nas assinaturas oriundas das an?lises de tend?ncia do sinal do res?duo e sua derivada, ir? realizar a classifica??o das falhas baseada em uma ?rvore de decis?o. Este sistema FDD ser? submetido a alguns testes e valida??es em duas plantas: uma planta simulada de tanques acoplados e em uma planta did?tica com instrumenta??o industrial. Os resultados colhidos desses ensaios se mostraram satisfat?rios para um grupo de falhas testadas e ser?o discutidos no decorrer do trabalho

<p><h1>Abstract</h1></p> <p>As a compact, robust, and reliable power distribution method, hydraulic systems have been used for flight surface control for decades. Electro-hydrostatic Actuator (EHA) is increasingly replacing the conventional valve-controlled system for better performance, lighter weight and higher energy efficiency. The EHA is increasingly being used for flight control. As such its reliability is thereby critical important for flight safety. This research focuses on fault detection and diagnosis (FDD) for the EHA to enable predictive unscheduled maintenance when fault detected at its inception.</p> <p>An EHA prototype previously built at McMaster University is studied in this research and modified to physically simulate two faults conditions pertaining to leakage and friction. Nine different working conditions including normal running and eight fault conditions are simulated. Physical model has been derived mathematically capable of numerically simulating the fault conditions. Furthermore, for comparison, parametric model was obtained through system identification for each fault condition. This comparison revealed that parametric models are not suitable for fault detection and diagnosis due to the computation complexity.</p> <p>The FDD approach in this research uses model-based state estimation using filters. The filter based combined with the Interacting Multiple Model fault detection and diagnosis algorithm is introduced. Based on this algorithm, three FDD strategies are developed using a combination of the Extended Kalman Filter and IMM (IMM-EKF), the Smooth Variable Structure Filter with Varying Boundary and IMM (IMM-SVSF (VBL)), and the Smooth Variable Structure Filter with Fixed Boundary and IMM (IMM-SVSF (FBL)). All the three FDD strategies were implemented on the EHA prototype. Based on the results, the IMM-SVSF (VBL) provided the best performance. It detected and diagnosed faults correctly at high mode probabilities with excellent robustness to modeling uncertainties. It also was able to detect slow growing leakage fault, and predicted the changing trend of fault conditions.</p> / Master of Applied Science (MASc)

Les travaux présentés dans ce mémoire contribuent à la définition de méthodes pour la détection et le diagnostic de défauts affectant les systèmes aéronautiques. Un système représentatif sert de support d'étude, constitué du modèle non linéaire à six degrés de liberté d'un missile intercepteur, de ses capteurs et actionneurs ainsi que d'une boucle de guidage-pilotage. La première partie est consacrée au développement de deux méthodes de diagnostic exploitant l'information de commande en boucle fermée et les caractéristiques des modèles aéronautiques. La première méthode utilise les objectifs de commande induits par les lois de guidage-pilotage pour générer des résidus indiquant la présence de défauts. Ceci permet la détection des défauts sur les actionneurs et les capteurs, ainsi que leur localisation pour ces derniers. La deuxième méthode exploite la mesure de dérivées des variables d'état (via une centrale inertielle) pour estimer la valeur de la commande réalisée par les actionneurs, sans intégration du modèle non linéaire du système. Le diagnostic est alors effectué en comparant cette estimée avec la valeur désirée, ce qui permet la détection, la localisation et l'identification de défauts multiples sur les actionneurs.La seconde partie propose une méthodologie de réglage automatique des paramètres internes (les hyperparamètres) de méthodes de diagnostic. Ceci permet une comparaison plus objective entre les méthodes en évaluant la meilleure performance de chacune. Le réglage est vu comme un problème d'optimisation globale, la fonction à optimiser étant calculée via la simulation numérique (potentiellement coûteuse) de cas test. La méthodologie proposée est fondée sur un métamodèle de krigeage et une procédure itérative d’optimisation bayésienne, qui permettent d’aborder ce problème à faible coût de calcul. Un nouvel algorithme est proposé afin d'optimiser les hyperparamètres d'une façon robuste vis à vis de la variabilité des cas test pertinents.Mots clés : détection et diagnostic de défauts, guidage-pilotage, krigeage, minimax continu, optimisation globale, redondance analytique, réglage automatique, systèmes aéronautiques. / This manuscript reports contributions to the development of methods for fault detection and diagnosis applied to aeronautical systems. A representative system is considered, composed of the six-degree-of-freedom nonlinear model of a surface-to-air missile, its sensors, actuators and the associated GNC scheme. The first part is devoted to the development of two fault diagnosis approaches that take advantage of closed-loop control information, along with the characteristics of aeronautical models. The first method uses control objectives resulting from guidance laws to generate residuals indicative of the presence of faults. This enables the detection of both actuator and sensor faults, and the isolation of sensor faults. The second method exploits the measurement of derivatives of state variables (as provided by an IMU) to estimate the control input as achieved by actuators, without the need to integrate the nonlinear model. Detection, isolation and identification of actuator faults can then be performed by comparing this estimate with the desired control input.The second part presents a new automatic-tuning methodology for the internal parameters (the hyperparameters) of fault diagnosis methods. This allows a fair comparison between methods by evaluating their best performance. Tuning is formalised as the global optimization of a black-box function that is obtained through the (costly) numerical simulation of a set of test cases. The methodology proposed here is based on Kriging and Bayesian optimization, which make it possible to tackle this problem at a very reduced computational cost. A new algorithm is developed to address the optimization of hyperparameters in a way that is robust to the variability of the test cases of interest.

Les travaux de cette thèse portent sur la détection et le diagnostic des défauts naissants dans les systèmes d’ingénierie et industriels, par des approches statistiques non-paramétriques. Un défaut naissant est censé provoquer comme tout défaut un changement anormal dans les mesures des variables du système. Ce changement est imperceptible mais aussi imprévisible dû à l’important rapport signal-sur défaut, et le faible rapport défaut-sur-bruit caractérisant le défaut naissant. La détection et l’identification d’un changement général nécessite une approche globale qui prend en compte la totalité de la signature des défauts. Dans ce cadre, la divergence de Kullback-Leibler est proposée comme indicateur général de défauts, sensible aux petites variations anormales cachées dans les variations du bruit. Une approche d’analyse spectrale globale est également proposée pour le diagnostic de défauts ayant une signature fréquentielle. L’application de l’approche statistique globale est illustrée sur deux études différentes. La première concerne la détection et la caractérisation, par courants de Foucault, des fissures dans les structures conductrices. La deuxième application concerne le diagnostic des défauts de roulements dans les machines électriques tournantes. En outre, ce travail traite le problème d’estimation de l’amplitude des défauts naissants. Une analyse théorique menée dans le cadre d’une modélisation par analyse en composantes principales, conduit à un modèle analytique de la divergence ne dépendant que des paramètres du défaut. / This phD dissertation deals with the detection and diagnosis of incipient faults in engineering and industrial systems by non-parametric statistical approaches. An incipient fault is supposed to provoke an abnormal change in the measurements of the system variables. However, this change is imperceptible and also unpredictable due to the large signal-to-fault ratio and the low fault-to-noise ratio characterizing the incipient fault. The detection and identification of a global change require a ’global’ approach that takes into account the total faults signature. In this context, the Kullback-Leibler divergence is considered to be a ’global’ fault indicator, which is recommended sensitive to abnormal small variations hidden in noise. A ’global’ spectral analysis approach is also proposed for the diagnosis of faults with a frequency signature. The ’global’ statistical approach is proved on two application studies. The first one concerns the detection and characterization of minor cracks in conductive structures. The second application concerns the diagnosis of bearing faults in electrical rotating machines. In addition, the fault estimation problem is addressed in this work. A theoretical study is conducted to obtain an analytical model of the KL divergence, from which an estimate of the amplitude of the incipient fault is derived.