This work explores the use of a commodity ultra-wideband (UWB) radar based device to detect breathing rate for health monitoring applications. Health monitoring devices observe physiological signals to detect medical conditions. We focus on capturing the small mechanical movements caused by breathing. This is traditionally done via a strain gauge worn around the chest or stomach, but these systems limit user movement. Contactless systems provide a unique design that allows free user movement by eliminating all direct contact with the user. Additionally, these systems have the potential to support full health monitoring in a Smart Built Environment (SBE). In this work, a comparative evaluation is performed on a commodity UWB radar based device, the Walabot, to determine the accuracy and possible health monitoring applications. Based on results from a systematic review, six research challenges were identified: (1) high cost, functional limitations based on the user's (2) location, (3) orientation, and (4) movement, (5) dependency on system hardware placement, and (6) vulnerabilities in signal processing methods. A comparative evaluation was designed to test the Walabot against a medical grade wearable system in the context of these research challenges. The data was processed using two breathing rate derivation techniques: Fast Fourier Transformation (FFT) and Peak Detection. Results suggest great potential for the Walabot coupled with the FFT technique. However, the system requires further testing to address all of the research challenges. Overall, this work provides important steps toward using the Walabot in health monitoring applications. / Master of Science / The goal of research in the field of health monitoring is to gather medical information about a user by constantly collecting physiological signals emitted by their body. Four physiological signals are deemed the "vital signs" because they provide information about the overall health of the patient. These vital signs are heart rate, breathing rate, temperature and blood pressure. Breathing rate is an important vital sign that, when monitored closely, can indicate the oncoming of dangerous health conditions and events. The act of breathing causes the chest to expand and contract. This movement can be captured by placing a strain gauge around a user's chest and analyzing fluctuation in strain readings. However, this is not practical for health monitoring applications because this system is uncomfortable to wear and the accuracy of the system is heavily dependent on the user's ability to wear the chest band constantly and correctly. Capturing this signal without any direct user contact would eliminate the user's discomfort and provide better reliability. This can be done by several methods, but the focus of this work is on systems that capture chest movements using ultra-wideband (UWB) radar. In this work, a specific UWB radar based device, called the Walabot, is tested against a standard strain gauge system to determine if it has health monitoring applications. Other radar based devices that aim to detect breathing rate are limited by their high cost and inaccuracies in signal processing techniques. The functionality of the devices are also dependent on the user's location and body orientation relative to the system, any user movement and the placement of the system itself. The study in this work was designed to determine the Walabot accuracy when the data is processed by two common breathing rate derivation methods. Results showed that the Walabot is cost effective and flexible in terms of user location and system placement. Overall, this work demonstrates the potential of the Walabot as a breathing rate monitor.

Reliable and efficient utilization and operation of any engineering asset require carefully designed maintenance planning and maintenance related data in the form of failure times, repair times, Mean Time between Failure (MTBF) and conditioning data etc. play a pivotal role in maintenance decision support. With the advancement in data analytics sciences and industrial artificial intelligence, maintenance related data is being used for maintenance prognostics modeling to predict future maintenance requirements that form the basis of maintenance design and planning in any maintenance-conscious industry like railways. The lack of such available data creates a no. of different types of problems in data driven prognostics modelling. There have been a few methods, the researchers have employed to counter the problems due to lack of available data. The proposed methodology involves data augmentation technique using Markov Chain Monte Carlo (MCMC) Simulation to enhance maintenance data to be used in maintenance prognostics modeling that can serve as basis for better maintenance decision support and planning.

As a consequence of the recent deregulation in the electrical power production industry, there has been a shift in the traditional ownership of power plants and the way they are operated. To hedge their business risks, the many new private entrepreneurs enter into long-term service agreement (LTSA) with third parties for their operation and maintenance activities. As the major LTSA providers, original equipment manufacturers have invested huge amounts of money to develop preventive maintenance strategies to minimize the occurrence of costly unplanned outages resulting from failures of the equipments covered under LTSA contracts. As a matter of fact, a recent study by the Electric Power Research Institute estimates the cost benefit of preventing a failure of a General Electric 7FA or 9FA technology compressor at $10 to $20 million. Therefore, in this dissertation, a two-phase data analytics approach is proposed to use the existing monitoring gas path and vibration sensors data to first develop a proactive strategy that systematically detects and validates catastrophic failure precursors so as to avoid the failure; and secondly to estimate the residual time to failure of the unhealthy items. For the first part of this work, the time-frequency technique of the wavelet packet transforms is used to de-noise the noisy sensor data. Next, the time-series signal of each sensor is decomposed to perform a multi-resolution analysis to extract its features. After that, the probabilistic principal component analysis is applied as a data fusion technique to reduce the number of the potentially correlated multi-sensors measurement into a few uncorrelated principal components. The last step of the failure precursor detection methodology, the anomaly detection decision, is in itself a multi-stage process. The obtained principal components from the data fusion step are first combined into a one-dimensional reconstructed signal representing the overall health assessment of the monitored systems. Then, two damage indicators of the reconstructed signal are defined and monitored for defect using a statistical process control approach. Finally, the Bayesian evaluation method for hypothesis testing is applied to a computed threshold to test for deviations from the healthy band. To model the residual time to failure, the anomaly severity index and the anomaly duration index are defined as defects characteristics. Two modeling techniques are investigated for the prognostication of the survival time after an anomaly is detected: the deterministic regression approach, and parametric approximation of the non-parametric Kaplan-Meier plot estimator. It is established that the deterministic regression provides poor prediction estimation. The non parametric survival data analysis technique of the Kaplan-Meier estimator provides the empirical survivor function of the data set comprised of both non-censored and right censored data. Though powerful because no a-priori predefined lifetime distribution is made, the Kaplan-Meier result lacks the flexibility to be transplanted to other units of a given fleet. The parametric analysis of survival data is performed with two popular failure analysis distributions: the exponential distribution and the Weibull distribution. The conclusion from the parametric analysis of the Kaplan-Meier plot is that the larger the data set, the more accurate is the prognostication ability of the residual time to failure model.

ITC/USA 2009 Conference Proceedings / The Forty-Fifth Annual International Telemetering Conference and Technical Exhibition / October 26-29, 2009 / Riviera Hotel & Convention Center, Las Vegas, Nevada / Current equipment and vehicle failure analysis practices use diagnostic technology developed over the past 100 years of designing and manufacturing electrical and mechanical equipment to identify root cause of equipment failure requiring expertise with the equipment under analysis. If the equipment that failed had telemetry embedded, prognostic algorithms can be used to identify the deterministic behavior in completely normal appearing data from fully functional equipment used for identifying which equipment will fail within 1 year of use, can also identify when the presence of deterministic behavior was initiated for any equipment failure.

ITC/USA 2011 Conference Proceedings / The Forty-Seventh Annual International Telemetering Conference and Technical Exhibition / October 24-27, 2011 / Bally's Las Vegas, Las Vegas, Nevada / Current failure analysis practices use diagnostic technology developed over the past 100 years of designing and manufacturing electrical and mechanical equipment to identify root cause of equipment failure requiring expertise with the equipment under analysis. If the equipment that failed had telemetry embedded, prognostic algorithms can be used to identify the deterministic behavior in completely normal appearing data from fully functional equipment used for identifying which equipment will fail within 1 year of use, can also identify when the presence of deterministic behavior was initiated for any equipment failure.

abstract: This dissertation presents the development of structural health monitoring and prognostic health management methodologies for complex structures and systems in the field of mechanical engineering. To overcome various challenges historically associated with complex structures and systems such as complicated sensing mechanisms, noisy information, and large-size datasets, a hybrid monitoring framework comprising of solid mechanics concepts and data mining technologies is developed. In such a framework, the solid mechanics simulations provide additional intuitions to data mining techniques reducing the dependence of accuracy on the training set, while the data mining approaches fuse and interpret information from the targeted system enabling the capability for real-time monitoring with efficient computation. In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency. This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications. / Dissertation/Thesis / Doctoral Dissertation Mechanical Engineering 2019

<p>As space exploration vehicles travel deeper into space, their distance to earth increases.The increased communication delays and ground personnel costs motivatea migration of the vehicle health management into space. A way to achieve thisis to use a diagnosis system. A diagnosis system uses sensor readings to automaticallydetect faults and possibly locate the cause of it. The diagnosis system usedin this thesis is a model-based reasoning tool called RODON developed by UptimeSolutions AB. RODON uses information of both nominal and faulty behavior ofthe target system mathematically formulated in a model.The advanced diagnostics and prognostics testbed (ADAPT) developed at theNASA Ames Research Center provides a stepping stone between pure researchand deployment of diagnosis and prognosis systems in aerospace systems. Thehardware of the testbed is an electrical power system (EPS) that represents theEPS of a space exploration vehicle. ADAPT consists of a controlled and monitoredenvironment where faults can be injected into a system in a controlled manner andthe performance of the diagnosis system carefully monitored. The main goal of thethesis project was to build a model of the ADAPT EPS that was used to diagnosethe testbed and to generate decision trees (or trouble-shooting trees).The results from the diagnostic analysis were good and all injected faults thataffected the actual function of the EPS were detected. All sensor faults weredetected except faults in temperature sensors. A less detailed model would haveisolated the correct faulty component(s) in the experiments. However, the goal wasto create a detailed model that can detect more than the faults currently injectedinto ADAPT. The created model is stationary but a dynamic model would havebeen able to detect faults in temperature sensors.Based on the presented results, RODON is very well suited for stationary analysisof large systems with a mixture of continuous and discrete signals. It is possibleto get very good results using RODON but in turn it requires an equally goodmodel. A full analysis of the dynamic capabilities of RODON was never conductedin the thesis which is why no conclusions can be drawn for that case.</p><p> </p>

Le Pronostic et l'étude de l'état de santé (en anglais Prognostics and Health Management (PHM)) vise à étendre le cycle de vie d'un actif physique, tout en réduisant les coûts d'exploitation et de maintenance. Pour cette raison, le pronostic est considéré comme un processus clé avec des capacités de prédictions. En effet, des estimations précises de la durée de vie avant défaillance d'un équipement, Remaining Useful Life (RUL), permettent de mieux définir un plan d'actions visant à accroître la sécurité, réduire les temps d'arrêt, assurer l'achèvement de la mission et l'efficacité de la production. Des études récentes montrent que les approches guidées par les données sont de plus en plus appliquées pour le pronostic de défaillance. Elles peuvent être considérées comme des modèles de type " boite noire " pour l'étude du comportement du système directement à partir des données de surveillance d'état, pour définir l'état actuel du system et prédire la progression future de défauts. Cependant, l'approximation du comportement des machines critiques est une tâche difficile qui peut entraîner des mauvais pronostics. Pour la compréhension de la modélisation de pronostic guidé par les données, on considère les points suivants. 1) Comment traiter les données brutes de surveillance pour obtenir des caractéristiques appropriées reflétant l'évolution de la dégradation ? 2) Comment distinguer les états de dégradation et définir des critères de défaillance (qui peuvent varier d'un cas à un autre)? 3) Comment être sûr que les modèles définis seront assez robustes pour montrer une performance stable avec des entrées incertaines s'écartant des expériences acquises, et seront suffisamment fiables pour intégrer des données inconnues (c'est à dire les conditions de fonctionnement, les variations de l'ingénierie, etc.)? 4) Comment réaliser facilement une intégration sous des contraintes et des exigences industrielles? Ces questions sont des problèmes abordés dans cette thèse. Elles ont conduit à développer une nouvelle approche allant au-delà des limites des méthodes classiques de pronostic guidé par les données. Les principales contributions sont les suivantes. <br>- L'étape de traitement des données est améliorée par l'introduction d'une nouvelle approche d'extraction des caractéristiques à l'aide de fonctions trigonométriques et cumulatives qui sont basées sur trois caractéristiques : la monotonie, la "trendability" et la prévisibilité. L'idée principale de ce développement est de transformer les données brutes en indicateur qui améliorent la précision des prévisions à long terme. <br>- Pour tenir compte de la robustesse, la fiabilité et l'applicabilité, un nouvel algorithme de prédiction est proposé: Summation Wavelet-Extreme Learning Machine (SWELM). Le SW-ELM assure de bonnes performances de prédiction, tout en réduisant le temps d'apprentissage. Un ensemble de SW-ELM est également proposé pour quantifier l'incertitude et améliorer la précision des estimations. <br>- Les performances du pronostic sont également renforcées grâce à la proposition d'un nouvel algorithme d'évaluation de la santé: Subtractive-Maximum Entropy Fuzzy Clustering (S-MEFC). S-MEFC est une approche de classification non supervisée qui utilise l'inférence de l'entropie maximale pour représenter l'incertitude de données multidimensionnelles. Elle peut automatiquement déterminer le nombre d'états, sans intervention humaine. <br>- Le modèle de pronostic final est obtenu en intégrant le SW-ELM et le S-MEFC pour montrer l'évolution de la dégradation de la machine avec des prédictions simultanées et l'estimation d'états discrets. Ce programme permet également de définir dynamiquement les seuils de défaillance et d'estimer le RUL des machines surveillées. Les développements sont validés sur des données réelles à partir de trois plates-formes expérimentales: PRONOSTIA FEMTO-ST (banc d'essai des roulements), CNC SIMTech (Les fraises d'usinage), C-MAPSS NASA (turboréacteurs) et d'autres données de référence. En raison de la nature réaliste de la stratégie d'estimation du RUL proposée, des résultats très prometteurs sont atteints. Toutefois, la perspective principale de ce travail est d'améliorer la fiabilité du modèle de pronostic.

Cette thèse propose une approche originale d’ordonnancement de la production de plates-formes de machines hétérogènes et distribuées, utilisées en parallèle pour fournir un service global commun. L’originalité de la contribution réside dans la proposition de modifier les conditions opératoires des machines au cours de leur utilisation. Il est supposé qu'utiliser une machine avec des performances dégradées par rapport à un fonctionnement nominal permet d'allonger sa durée de vie avant maintenance. L’étude s’inscrit dans la partie décisionnelle du PHM (Prognostics and Health Management), au sein duquel une étape de pronostic permet de déterminer les durées de vie résiduelles des machines. Le problème d’optimisation consiste à déterminer à chaque instant l’ensemble des machines à utiliser et un profil de fonctionnement pour chacune d’entre elles de manière à maximiser l’horizon de production de la plate-forme avant maintenance. Deux modèles sont proposés pour la définition des profils de fonctionnement. Le premier traduit le comportement à l'usure de machines pouvant fournir un nombre discret de performances. Pour ce cas, la complexité de plusieurs variantes du problème d'optimisation est étudiée et plusieurs méthodes de résolution optimales et sous-optimales sont proposées pour traiter le problème d'ordonnancement. Plusieurs méthodes de résolution sous-optimales sont ensuite proposées pour le second modèle, qui s'applique à des machines dont le débit peut varier de manière continue entre deux bornes. Ces travaux permettent de déterminer la durée maximale d’utilisation avant défaillance d’un système à partir des durées de vie résiduelles des équipements qui le composent. / This thesis addresses the problem of maximizing the production horizon of a heterogeneous distributed platform composed of parallel machines and which has to provide a global production service. Each machine is supposed to be able to provide several throughputs corresponding to different operating conditions. It is assumed that using a machine with degraded performances compared to nominal ones allows to extend its useful life before maintenance. The study falls within the decisional step of PHM (Prognostics and Health Management), in which a prognostics phase allows to determine remaining useful lives of machines. The optimization problem consists in determining the set of machines to use at each time and a running profile for each of them so as to maximize the production horizon before maintenance. Machines running profiles are defined on the basis of two models. First one depicts the behavior of machines used with a discrete number of performances. For this case, the problem complexity is first studied considering many variants of the optimization problem. Several optimal and sub-optimal resolution methods are proposed to deal with the scheduling problem. Several sub-optimal resolution methods are then proposed for the second model, which applies to machines whose throughput rate can vary continuously between two bounds. These research works allow to determine the time before failure of a system on the basis of its components remaining useful lives.

Recent refinements in Industry 4.0 and Machine Learning demonstrate the positive effects of using deep learning models for intelligent maintenance. The primary benefit of Deep Learning (DL) is its capability to extract attributes and make fast, accurate, and automated predictions without supervision. However, DL requires high computational power, significant data preprocessing, and vast amounts of data to make accurate predictions for intelligent maintenance. Given the considerable obstacles, meta-learning has been developed as a novel way to overcome these challenges. As a learning technique, meta-learning aims to quickly acquire knowledge of new tasks using theminimal available data by learning through meta-knowledge. There has been less research in the area of using meta-learning for Predictive Maintenance (PdM) and we considered it necessary to conduct this review to understand the applicability of meta-learning’s capabilities and functions to PdM since the outcomes of this technique seem to be rather promising. The review started with the development of a methodology and four research questions: (1) What is the taxonomy of meta-learning for PdM?, (2) What are the current state-of-the-art methodologies? (3) Which datasets are available for meta-learning in PdM?, and (4) What are the open issues, challenges, and opportunities of meta-learning in PdM?. To answer the first and second questions, a new taxonomy was proposed and meta-learnings role in predictive maintenance was identified from selected 55 papers. To answer the third question, we determined which types of datasets and their characteristics exist for this domain. Finally, the challenges, open issues, and opportunities of meta-learning in predictive maintenance were examined to answer the final question. The results of the research questions provided suggestions for future research topics.