Machine prognostics based on health state probability estimation

The ability to accurately predict the remaining useful life of machine components is critical for machine continuous operation and can also improve productivity and enhance system’s safety. In condition-based maintenance (CBM), maintenance is performed based on information collected through condition monitoring and assessment of the machine health. Effective diagnostics and prognostics are important aspects of CBM for maintenance engineers to schedule a repair and to acquire replacement components before the components actually fail. Although a variety of prognostic methodologies have been reported recently, their application in industry is still relatively new and mostly focused on the prediction of specific component degradations. Furthermore, they required significant and sufficient number of fault indicators to accurately prognose the component faults. Hence, sufficient usage of health indicators in prognostics for the effective interpretation of machine degradation process is still required. Major challenges for accurate longterm prediction of remaining useful life (RUL) still remain to be addressed. Therefore, continuous development and improvement of a machine health management system and accurate long-term prediction of machine remnant life is required in real industry application. This thesis presents an integrated diagnostics and prognostics framework based on health state probability estimation for accurate and long-term prediction of machine remnant life. In the proposed model, prior empirical (historical) knowledge is embedded in the integrated diagnostics and prognostics system for classification of impending faults in machine system and accurate probability estimation of discrete degradation stages (health states). The methodology assumes that machine degradation consists of a series of degraded states (health states) which effectively represent the dynamic and stochastic process of machine failure. The estimation of discrete health state probability for the prediction of machine remnant life is performed using the ability of classification algorithms. To employ the appropriate classifier for health state probability estimation in the proposed model, comparative intelligent diagnostic tests were conducted using five different classifiers applied to the progressive fault data of three different faults in a high pressure liquefied natural gas (HP-LNG) pump. As a result of this comparison study, SVMs were employed in heath state probability estimation for the prediction of machine failure in this research. The proposed prognostic methodology has been successfully tested and validated using a number of case studies from simulation tests to real industry applications. The results from two actual failure case studies using simulations and experiments indicate that accurate estimation of health states is achievable and the proposed method provides accurate long-term prediction of machine remnant life. In addition, the results of experimental tests show that the proposed model has the capability of providing early warning of abnormal machine operating conditions by identifying the transitional states of machine fault conditions. Finally, the proposed prognostic model is validated through two industrial case studies. The optimal number of health states which can minimise the model training error without significant decrease of prediction accuracy was also examined through several health states of bearing failure. The results were very encouraging and show that the proposed prognostic model based on health state probability estimation has the potential to be used as a generic and scalable asset health estimation tool in industrial machinery.

Finding additional semantic entity information for search engines

Entity-oriented search has become an essential component of modern search engines. It focuses on retrieving a list of entities or information about the specific entities instead of documents. In this paper, we study the problem of finding entity related information, referred to as attribute-value pairs, that play a significant role in searching target entities. We propose a novel decomposition framework combining reduced relations and the discriminative model, Conditional Random Field (CRF), for automatically finding entity-related attribute-value pairs from free text documents. This decomposition framework allows us to locate potential text fragments and identify the hidden semantics, in the form of attribute-value pairs for user queries. Empirical analysis shows that the decomposition framework outperforms pattern-based approaches due to its capability of effective integration of syntactic and semantic features.

Projecting future expansion of invasive species: Comparing and improving methodologies for species distribution modeling

Modeling the distributions of species, especially of invasive species in non-native ranges, involves multiple challenges. Here, we developed some novel approaches to species distribution modeling aimed at reducing the influences of such challenges and improving the realism of projections. We estimated species-environment relationships with four modeling methods run with multiple scenarios of (1) sources of occurrences and geographically isolated background ranges for absences, (2) approaches to drawing background (absence) points, and (3) alternate sets of predictor variables. We further tested various quantitative metrics of model evaluation against biological insight. Model projections were very sensitive to the choice of training dataset. Model accuracy was much improved by using a global dataset for model training, rather than restricting data input to the species’ native range. AUC score was a poor metric for model evaluation and, if used alone, was not a useful criterion for assessing model performance. Projections away from the sampled space (i.e. into areas of potential future invasion) were very different depending on the modeling methods used, raising questions about the reliability of ensemble projections. Generalized linear models gave very unrealistic projections far away from the training region. Models that efficiently fit the dominant pattern, but exclude highly local patterns in the dataset and capture interactions as they appear in data (e.g. boosted regression trees), improved generalization of the models. Biological knowledge of the species and its distribution was important in refining choices about the best set of projections. A post-hoc test conducted on a new Partenium dataset from Nepal validated excellent predictive performance of our “best” model. We showed that vast stretches of currently uninvaded geographic areas on multiple continents harbor highly suitable habitats for Parthenium hysterophorus L. (Asteraceae; parthenium). However, discrepancies between model predictions and parthenium invasion in Australia indicate successful management for this globally significant weed. This article is protected by copyright. All rights reserved.

Projecting future expansion of invasive species: Comparing and improving methodologies for species distribution modeling

Modeling the distributions of species, especially of invasive species in non-native ranges, involves multiple challenges. Here, we developed some novel approaches to species distribution modeling aimed at reducing the influences of such challenges and improving the realism of projections. We estimated species-environment relationships with four modeling methods run with multiple scenarios of (1) sources of occurrences and geographically isolated background ranges for absences, (2) approaches to drawing background (absence) points, and (3) alternate sets of predictor variables. We further tested various quantitative metrics of model evaluation against biological insight. Model projections were very sensitive to the choice of training dataset. Model accuracy was much improved by using a global dataset for model training, rather than restricting data input to the species’ native range. AUC score was a poor metric for model evaluation and, if used alone, was not a useful criterion for assessing model performance. Projections away from the sampled space (i.e. into areas of potential future invasion) were very different depending on the modeling methods used, raising questions about the reliability of ensemble projections. Generalized linear models gave very unrealistic projections far away from the training region. Models that efficiently fit the dominant pattern, but exclude highly local patterns in the dataset and capture interactions as they appear in data (e.g. boosted regression trees), improved generalization of the models. Biological knowledge of the species and its distribution was important in refining choices about the best set of projections. A post-hoc test conducted on a new Partenium dataset from Nepal validated excellent predictive performance of our “best” model. We showed that vast stretches of currently uninvaded geographic areas on multiple continents harbor highly suitable habitats for Parthenium hysterophorus L. (Asteraceae; parthenium). However, discrepancies between model predictions and parthenium invasion in Australia indicate successful management for this globally significant weed. This article is protected by copyright. All rights reserved.

The CU-HTK Mandarin broadcast news transcription system

This paper discusses the development of the CU-HTK Mandarin Broadcast News (BN) transcription system. The Mandarin BN task includes a significant amount of English data. Hence techniques have been investigated to allow the same system to handle both Mandarin and English by augmenting the Mandarin training sets with English acoustic and language model training data. A range of acoustic models were built including models based on Gaussianised features, speaker adaptive training and feature-space MPE. A multi-branch system architecture is described in which multiple acoustic model types, alternate phone sets and segmentations can be used in a system combination framework to generate the final output. The final system shows state-of-the-art performance over a range of test sets. ©2006 British Crown Copyright.

Automatic transcription of conversational telephone speech

This paper discusses the Cambridge University HTK (CU-HTK) system for the automatic transcription of conversational telephone speech. A detailed discussion of the most important techniques in front-end processing, acoustic modeling and model training, language and pronunciation modeling are presented. These include the use of conversation side based cepstral normalization, vocal tract length normalization, heteroscedastic linear discriminant analysis for feature projection, minimum phone error training and speaker adaptive training, lattice-based model adaptation, confusion network based decoding and confidence score estimation, pronunciation selection, language model interpolation, and class based language models. The transcription system developed for participation in the 2002 NIST Rich Transcription evaluations of English conversational telephone speech data is presented in detail. In this evaluation the CU-HTK system gave an overall word error rate of 23.9%, which was the best performance by a statistically significant margin. Further details on the derivation of faster systems with moderate performance degradation are discussed in the context of the 2002 CU-HTK 10 × RT conversational speech transcription system. © 2005 IEEE.

Robust Speaker Recognition in Noisy Conditions

This paper investigates the problem of speaker identi-fication and verification in noisy conditions, assuming that speechsignals are corrupted by environmental noise, but knowledgeabout the noise characteristics is not available. This research ismotivated in part by the potential application of speaker recog-nition technologies on handheld devices or the Internet. Whilethe technologies promise an additional biometric layer of securityto protect the user, the practical implementation of such systemsfaces many challenges. One of these is environmental noise. Due tothe mobile nature of such systems, the noise sources can be highlytime-varying and potentially unknown. This raises the require-ment for noise robustness in the absence of information about thenoise. This paper describes a method that combines multicondi-tion model training and missing-feature theory to model noisewith unknown temporal-spectral characteristics. Multiconditiontraining is conducted using simulated noisy data with limitednoise variation, providing a “coarse” compensation for the noise,and missing-feature theory is applied to refine the compensationby ignoring noise variation outside the given training conditions,thereby reducing the training and testing mismatch. This paperis focused on several issues relating to the implementation of thenew model for real-world applications. These include the gener-ation of multicondition training data to model noisy speech, thecombination of different training data to optimize the recognitionperformance, and the reduction of the model’s complexity. Thenew algorithm was tested using two databases with simulated andrealistic noisy speech data. The first database is a redevelopmentof the TIMIT database by rerecording the data in the presence ofvarious noise types, used to test the model for speaker identifica-tion with a focus on the varieties of noise. The second database isa handheld-device database collected in realistic noisy conditions,used to further validate the model for real-world speaker verifica-tion. The new model is compared to baseline systems and is foundto achieve lower error rates.

Scalable black-box prediction models for multi-dimensional adaptation on NUMA multi-cores

This paper presents a scalable, statistical ‘black-box’ model for predicting the performance of parallel programs on multi-core non-uniform memory access (NUMA) systems. We derive a model with low overhead, by reducing data collection and model training time. The model can accurately predict the behaviour of parallel applications in response to changes in their concurrency, thread layout on NUMA nodes, and core voltage and frequency. We present a framework that applies the model to achieve significant energy and energy-delay-square (ED2) savings (9% and 25%, respectively) along with performance improvement (10% mean) on an actual 16-core NUMA system running realistic application workloads. Our prediction model proves substantially more accurate than previous efforts.

An Efficient LS-SVM-Based Method for Fuzzy System Construction

This paper proposes an efficient learning mechanism to build fuzzy rule-based systems through the construction of sparse least-squares support vector machines (LS-SVMs). In addition to the significantly reduced computational complexity in model training, the resultant LS-SVM-based fuzzy system is sparser while offers satisfactory generalization capability over unseen data. It is well known that the LS-SVMs have their computational advantage over conventional SVMs in the model training process; however, the model sparseness is lost, which is the main drawback of LS-SVMs. This is an open problem for the LS-SVMs. To tackle the nonsparseness issue, a new regression alternative to the Lagrangian solution for the LS-SVM is first presented. A novel efficient learning mechanism is then proposed in this paper to extract a sparse set of support vectors for generating fuzzy IF-THEN rules. This novel mechanism works in a stepwise subset selection manner, including a forward expansion phase and a backward exclusion phase in each selection step. The implementation of the algorithm is computationally very efficient due to the introduction of a few key techniques to avoid the matrix inverse operations to accelerate the training process. The computational efficiency is also confirmed by detailed computational complexity analysis. As a result, the proposed approach is not only able to achieve the sparseness of the resultant LS-SVM-based fuzzy systems but significantly reduces the amount of computational effort in model training as well. Three experimental examples are presented to demonstrate the effectiveness and efficiency of the proposed learning mechanism and the sparseness of the obtained LS-SVM-based fuzzy systems, in comparison with other SVM-based learning techniques.

Relating Dependent Terms in Information Retrieval

Les moteurs de recherche font partie de notre vie quotidienne. Actuellement, plus d’un tiers de la population mondiale utilise l’Internet. Les moteurs de recherche leur permettent de trouver rapidement les informations ou les produits qu'ils veulent. La recherche d'information (IR) est le fondement de moteurs de recherche modernes. Les approches traditionnelles de recherche d'information supposent que les termes d'indexation sont indépendants. Pourtant, les termes qui apparaissent dans le même contexte sont souvent dépendants. L’absence de la prise en compte de ces dépendances est une des causes de l’introduction de bruit dans le résultat (résultat non pertinents). Certaines études ont proposé d’intégrer certains types de dépendance, tels que la proximité, la cooccurrence, la contiguïté et de la dépendance grammaticale. Dans la plupart des cas, les modèles de dépendance sont construits séparément et ensuite combinés avec le modèle traditionnel de mots avec une importance constante. Par conséquent, ils ne peuvent pas capturer correctement la dépendance variable et la force de dépendance. Par exemple, la dépendance entre les mots adjacents "Black Friday" est plus importante que celle entre les mots "road constructions". Dans cette thèse, nous étudions différentes approches pour capturer les relations des termes et de leurs forces de dépendance. Nous avons proposé des méthodes suivantes: ─ Nous réexaminons l'approche de combinaison en utilisant différentes unités d'indexation pour la RI monolingue en chinois et la RI translinguistique entre anglais et chinois. En plus d’utiliser des mots, nous étudions la possibilité d'utiliser bi-gramme et uni-gramme comme unité de traduction pour le chinois. Plusieurs modèles de traduction sont construits pour traduire des mots anglais en uni-grammes, bi-grammes et mots chinois avec un corpus parallèle. Une requête en anglais est ensuite traduite de plusieurs façons, et un score classement est produit avec chaque traduction. Le score final de classement combine tous ces types de traduction. Nous considérons la dépendance entre les termes en utilisant la théorie d’évidence de Dempster-Shafer. Une occurrence d'un fragment de texte (de plusieurs mots) dans un document est considérée comme représentant l'ensemble de tous les termes constituants. La probabilité est assignée à un tel ensemble de termes plutôt qu’a chaque terme individuel. Au moment d’évaluation de requête, cette probabilité est redistribuée aux termes de la requête si ces derniers sont différents. Cette approche nous permet d'intégrer les relations de dépendance entre les termes. Nous proposons un modèle discriminant pour intégrer les différentes types de dépendance selon leur force et leur utilité pour la RI. Notamment, nous considérons la dépendance de contiguïté et de cooccurrence à de différentes distances, c’est-à-dire les bi-grammes et les paires de termes dans une fenêtre de 2, 4, 8 et 16 mots. Le poids d’un bi-gramme ou d’une paire de termes dépendants est déterminé selon un ensemble des caractères, en utilisant la régression SVM. Toutes les méthodes proposées sont évaluées sur plusieurs collections en anglais et/ou chinois, et les résultats expérimentaux montrent que ces méthodes produisent des améliorations substantielles sur l'état de l'art.

Development Of Water Pollution Early Warning System For Oyster Harvesting Areas

The objective of this study is to develop a Pollution Early Warning System (PEWS) for efficient management of water quality in oyster harvesting areas. To that end, this paper presents a web-enabled, user-friendly PEWS for managing water quality in oyster harvesting areas along Louisiana Gulf Coast, USA. The PEWS consists of (1) an Integrated Space-Ground Sensing System (ISGSS) gathering data for environmental factors influencing water quality, (2) an Artificial Neural Network (ANN) model for predicting the level of fecal coliform bacteria, and (3) a web-enabled, user-friendly Geographic Information System (GIS) platform for issuing water pollution advisories and managing oyster harvesting waters. The ISGSS (data acquisition system) collects near real-time environmental data from various sources, including NASA MODIS Terra and Aqua satellites and in-situ sensing stations managed by the USGS and the NOAA. The ANN model is developed using the ANN program in MATLAB Toolbox. The ANN model involves a total of 6 independent environmental variables, including rainfall, tide, wind, salinity, temperature, and weather type along with 8 different combinations of the independent variables. The ANN model is constructed and tested using environmental and bacteriological data collected monthly from 2001 – 2011 by Louisiana Molluscan Shellfish Program at seven oyster harvesting areas in Louisiana Coast, USA. The ANN model is capable of explaining about 76% of variation in fecal coliform levels for model training data and 44% for independent data. The web-based GIS platform is developed using ArcView GIS and ArcIMS. The web-based GIS system can be employed for mapping fecal coliform levels, predicted by the ANN model, and potential risks of norovirus outbreaks in oyster harvesting waters. The PEWS is able to inform decision-makers of potential risks of fecal pollution and virus outbreak on a daily basis, greatly reducing the risk of contaminated oysters to human health.

Predicting body and carcass characteristics of 2 broiler chicken strains using support vector regression and neural network models

As a new modeling method, support vector regression (SVR) has been regarded as the state-of-the-art technique for regression and approximation. In this study, the SVR models had been introduced and developed to predict body and carcass-related characteristics of 2 strains of broiler chicken. To evaluate the prediction ability of SVR models, we compared their performance with that of neural network (NN) models. Evaluation of the prediction accuracy of models was based on the R-2, MS error, and bias. The variables of interest as model output were BW, empty BW, carcass, breast, drumstick, thigh, and wing weight in 2 strains of Ross and Cobb chickens based on intake dietary nutrients, including ME (kcal/bird per week), CP, TSAA, and Lys, all as grams per bird per week. A data set composed of 64 measurements taken from each strain were used for this analysis, where 44 data lines were used for model training, whereas the remaining 20 lines were used to test the created models. The results of this study revealed that it is possible to satisfactorily estimate the BW and carcass parts of the broiler chickens via their dietary nutrient intake. Through statistical criteria used to evaluate the performance of the SVR and NN models, the overall results demonstrate that the discussed models can be effective for accurate prediction of the body and carcass-related characteristics investigated here. However, the SVR method achieved better accuracy and generalization than the NN method. This indicates that the new data mining technique (SVR model) can be used as an alternative modeling tool for NN models. However, further reevaluation of this algorithm in the future is suggested.

Occurrence (presence-only) of living Lophelia pertusa reefs in the Irish continental margin

The present data set was used as a training set for a Habitat Suitability Model. It contains occurrence (presence-only) of living Lophelia pertusa reefs in the Irish continental margin, which were assembled from databases, cruise reports and publications. A total of 4423 records were inspected and quality assessed to ensure that they (1) represented confirmed living L. pertusa reefs (so excluding 2900 records of dead and isolated coral colony records); (2) were derived from sampling equipment that allows for accurate (<200 m) geo-referencing (so excluding 620 records derived mainly from trawling and dredging activities); and (3) were not duplicated. A total of 245 occurrences were retained for the analysis. Coral observations are highly clustered in regions targeted by research expeditions, which might lead to falsely inflated model evaluation measures (Veloz, 2009). Therefore, we coarsened the distribution data by deleting all but one record within grid cells of 0.02° resolution (Davies & Guinotte 2011). The remaining 53 points were subject to a spatial cross-validation process: a random presence point was chosen, grouped with its 12 closest neighbour presence points based on Euclidean distance and withheld from model training. This process was repeated for all records, resulting in 53 replicates of spatially non-overlapping sets of test (n=13) and training (n=40) data. The final 53 occurrence records were used for model training.

Wind power forecasts using Gaussian processes and numerical weather prediction

Since wind at the earth's surface has an intrinsically complex and stochastic nature, accurate wind power forecasts are necessary for the safe and economic use of wind energy. In this paper, we investigated a combination of numeric and probabilistic models: a Gaussian process (GP) combined with a numerical weather prediction (NWP) model was applied to wind-power forecasting up to one day ahead. First, the wind-speed data from NWP was corrected by a GP, then, as there is always a defined limit on power generated in a wind turbine due to the turbine controlling strategy, wind power forecasts were realized by modeling the relationship between the corrected wind speed and power output using a censored GP. To validate the proposed approach, three real-world datasets were used for model training and testing. The empirical results were compared with several classical wind forecast models, and based on the mean absolute error (MAE), the proposed model provides around 9% to 14% improvement in forecasting accuracy compared to an artificial neural network (ANN) model, and nearly 17% improvement on a third dataset which is from a newly-built wind farm for which there is a limited amount of training data. © 2013 IEEE.

Conceção, planeamento,análise e orientação de uma equipa de futebol de iniciados ao longo da época desportiva 2014/2015

relatório de estágio apresentado para a obtenção do grau de Mestre em Desporto com especialização em Treino Desportivo