Vibration analysis for Bearing outer race condition diagnostics

This paper investigates defect detection methodologies for rolling element bearings through vibration analysis. Specifically, the utility of a new signal processing scheme combining the High Frequency Resonance Technique (HFRT) and Adaptive Line Enhancer (ALE) is investigated. The accelerometer is used to acquire data for this analysis, and experimental results have been obtained for outer race defects. Results show the potential effectiveness of the signal processing technique to determine both the severity and location of a defect. The HFRT utilizes the fact that much of the energy resulting from a defect impact manifests itself in the higher resonant frequencies of a system. Demodulation of these frequency bands through use of the envelope technique is then employed to gain further insight into the nature of the defect while further increasing the signal to noise ratio. If periodic, the defect frequency is then present in the spectra of the enveloped signal. The ALE is used to enhance the envelope spectrum by reducing the broadband noise. It provides an enhanced envelope spectrum with clear peaks at the harmonics of a characteristic defect frequency. It is implemented by using a delayed version of the signal and the signal itself to decorrelate the wideband noise. This noise is then rejected by the adaptive filter that is based upon the periodic information in the signal. Results have been obtained for outer race defects. They show the effectiveness of the methodology to determine both the severity and location of a defect. In two instances, a linear relationship between signal characteristics and defect size is indicated.

Reliability monitoring, feedback and improvement systems:their application in the machine tool industry

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT

Machine Learning Unsupervised Methods in the Design of an On-board Health Monitoring System for Satellite Applications

The dissertation starts by providing a description of the phenomena related to the increasing importance recently acquired by satellite applications. The spread of such technology comes with implications, such as an increase in maintenance cost, from which derives the interest in developing advanced techniques that favor an augmented autonomy of spacecrafts in health monitoring. Machine learning techniques are widely employed to lay a foundation for effective systems specialized in fault detection by examining telemetry data. Telemetry consists of a considerable amount of information; therefore, the adopted algorithms must be able to handle multivariate data while facing the limitations imposed by on-board hardware features. In the framework of outlier detection, the dissertation addresses the topic of unsupervised machine learning methods. In the unsupervised scenario, lack of prior knowledge of the data behavior is assumed. In the specific, two models are brought to attention, namely Local Outlier Factor and One-Class Support Vector Machines. Their performances are compared in terms of both the achieved prediction accuracy and the equivalent computational cost. Both models are trained and tested upon the same sets of time series data in a variety of settings, finalized at gaining insights on the effect of the increase in dimensionality. The obtained results allow to claim that both models, combined with a proper tuning of their characteristic parameters, successfully comply with the role of outlier detectors in multivariate time series data. Nevertheless, under this specific context, Local Outlier Factor results to be outperforming One-Class SVM, in that it proves to be more stable over a wider range of input parameter values. This property is especially valuable in unsupervised learning since it suggests that the model is keen to adapting to unforeseen patterns.

Methods for monitoring Machine Learning models

The following thesis aims to investigate the issues concerning the maintenance of a Machine Learning model over time, both about the versioning of the model itself and the data on which it is trained and about data monitoring tools and their distribution. The themes of Data Drift and Concept Drift were then explored and the performance of some of the most popular techniques in the field of Anomaly detection, such as VAE, PCA, and Monte Carlo Dropout, were evaluated.

Architecture for machining process and production monitoring based in open computer numerical control

This paper proposes an architecture for machining process and production monitoring to be applied in machine tools with open Computer numerical control (CNC). A brief description of the advantages of using open CNC for machining process and production monitoring is presented with an emphasis on the CNC architecture using a personal computer (PC)-based human-machine interface. The proposed architecture uses the CNC data and sensors to gather information about the machining process and production. It allows the development of different levels of monitoring systems with mininium investment, minimum need for sensor installation, and low intrusiveness to the process. Successful examples of the utilization of this architecture in a laboratory environment are briefly described. As a Conclusion, it is shown that a wide range of monitoring solutions can be implemented in production processes using the proposed architecture.

Application of Gage R&R methodology for improving the training and evaluation of automatic optical inspection machine operators

The current level of demand by customers in the electronics industry requires the production of parts with an extremely high level of reliability and quality to ensure complete confidence on the end customer. Automatic Optical Inspection (AOI) machines have an important role in the monitoring and detection of errors during the manufacturing process for printed circuit boards. These machines present images of products with probable assembly mistakes to an operator and him decide whether the product has a real defect or if in turn this was an automated false detection. Operator training is an important aspect for obtaining a lower rate of evaluation failure by the operator and consequently a lower rate of actual defects that slip through to the following processes. The Gage R&R methodology for attributes is part of a Six Sigma strategy to examine the repeatability and reproducibility of an evaluation system, thus giving important feedback on the suitability of each operator in classifying defects. This methodology was already applied in several industry sectors and services at different processes, with excellent results in the evaluation of subjective parameters. An application for training operators of AOI machines was developed, in order to be able to check their fitness and improve future evaluation performance. This application will provide a better understanding of the specific training needs for each operator, and also to accompany the evolution of the training program for new components which in turn present additional new difficulties for the operator evaluation. The use of this application will contribute to reduce the number of defects misclassified by the operators that are passed on to the following steps in the productive process. This defect reduction will also contribute to the continuous improvement of the operator evaluation performance, which is seen as a quality management goal.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Monitoring network optimisation for spatial data classification using support vector machines

The paper presents a novel method for monitoring network optimisation, based on a recent machine learning technique known as support vector machine. It is problem-oriented in the sense that it directly answers the question of whether the advised spatial location is important for the classification model. The method can be used to increase the accuracy of classification models by taking a small number of additional measurements. Traditionally, network optimisation is performed by means of the analysis of the kriging variances. The comparison of the method with the traditional approach is presented on a real case study with climate data.

Field Evaluation of Compaction Monitoring Technology: Phase II Volumes 1 and 2, TR-495, 2006

This report documents an extensive field program carried out to identify the relationships between soil engineering properties, as measured by various in situ devices, and the results of machine compaction monitoring using prototype compaction monitoring technology developed by Caterpillar Inc. Primary research tasks for this study include the following: (1) experimental testing and statistical analyses to evaluate machine power in terms of the engineering properties of the compacted soil (e.g., density, strength, stiffness) and (2) recommendations for using the compaction monitoring technology in practice. The compaction monitoring technology includes sensors that monitor the power consumption used to move the compaction machine, an on-board computer and display screen, and a GPS system to map the spatial location of the machine. In situ soil density, strength, and stiffness data characterized the soil at various stages of compaction. For each test strip or test area, in situ soil properties were compared directly to machine power values to establish statistical relationships. Statistical models were developed to predict soil density, strength, and stiffness from the machine power values. Field data for multiple test strips were evaluated. The R2 correlation coefficient was generally used to assess the quality of the regressions. Strong correlations were observed between averaged machine power and field measurement data. The relationships are based on the compaction model derived from laboratory data. Correlation coefficients (R2) were consistently higher for thicker lifts than for thin lifts, indicating that the depth influencing machine power response exceeds the representative lift thickness encountered under field conditions. Caterpillar Inc. compaction monitoring technology also identified localized areas of an earthwork project with weak or poorly compacted soil. The soil properties at these locations were verified using in situ test devices. This report also documents the steps required to implement the compaction monitoring technology evaluated.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Field Evaluation of Compaction Monitoring Technology: Phase I, 2004

This Phase I report describes a preliminary evaluation of a new compaction monitoring system developed by Caterpillar, Inc. (CAT), for use as a quality control and quality assurance (QC/QA) tool during earthwork construction operations. The CAT compaction monitoring system consists of an instrumented roller with sensors to monitor machine power output in response to changes in soil machine interaction and is fitted with a global positioning system (GPS) to monitor roller location in real time. Three pilot tests were conducted using CAT’s compaction monitoring technology. Two of the sites were located in Peoria, Illinois, at the Caterpillar facilities. The third project was an actual earthwork grading project in West Des Moines, Iowa. Typical construction operations for all tests included the following steps: (1) aerate/till existing soil; (2) moisture condition soil with water truck (if too dry); (3) remix; (4) blade to level surface; and (5) compact soil using the CAT CP-533E roller instrumented with the compaction monitoring sensors and display screen. Test strips varied in loose lift thickness, water content, and length. The results of the study show that it is possible to evaluate soil compaction with relatively good accuracy using machine energy as an indicator, with the advantage of 100% coverage with results in real time. Additional field trials are necessary, however, to expand the range of correlations to other soil types, different roller configurations, roller speeds, lift thicknesses, and water contents. Further, with increased use of this technology, new QC/QA guidelines will need to be developed with a framework in statistical analysis. Results from Phase I revealed that the CAT compaction monitoring method has a high level of promise for use as a QC/QA tool but that additional testing is necessary in order to prove its validity under a wide range of field conditions. The Phase II work plan involves establishing a Technical Advisor Committee, developing a better understanding of the algorithms used, performing further testing in a controlled environment, testing on project sites in the Midwest, and developing QC/QA procedures.

Design of a Condition Monitoring System for a Glass Wool Production Line

Työn tarkoituksena oli suunnitella kunnonvalvontajärjestelmä kahdelle lasivillan tuotantolinjalle. Suunnitteluprosessin lisäksi työssä on esitelty erilaisia kunnonvalvontamenetelmiä. Työn alussa on kerrottu erilaisista kunnonvalvontamenetelmistä, joilla voidaan seurata erilaisten laitteiden ja koneiden toimintakuntoa.Erityisesti työssä on tarkasteltu teollisuudessa yleistyviä kunnonvalvonnan värähtelymittauksia. Työssä suunniteltu kunnonvalvontajärjestelmä perustuu viiteen eri menetelmään, jotka ovat värähtelymittaus, lämpötilanmittaus lämpökameralla, lämpötilanmittaus kannettavalla mittarilla, kuuntelu elektronisella stetoskoopilla ja pyörivien osien kunnontarkkailu stroboskoopilla. Kunnonvalvontajärjestelmän suunnittelu on tehty useassa eri vaiheessa. Ensin työssä on kartoitettu tuotannon kannalta tärkeimmät laitteet ja niiden mahdolliset vikaantumistavat. Seuraavaksi on valittu sopivat kunnonvalvontamenetelmät ja tehty mittaussuunnitelma, jossa on esitetty eri laitteille suoritettavat mittaukset ja mittausten aikavälit.Lopuksi työssä on esitelty muutama esimerkkitapaus kunnonvalvontamenetelmien käytöstä sekä kerrottu mahdollisista tulevaisuuden kehitysmahdollisuuksista.

A layered JavaScript virtual machine supporting dynamic instrumentation

L’observation de l’exécution d’applications JavaScript est habituellement réalisée en instrumentant une machine virtuelle (MV) industrielle ou en effectuant une traduction source-à-source ad hoc et complexe. Ce mémoire présente une alternative basée sur la superposition de machines virtuelles. Notre approche consiste à faire une traduction source-à-source d’un programme pendant son exécution pour exposer ses opérations de bas niveau au travers d’un modèle objet flexible. Ces opérations de bas niveau peuvent ensuite être redéfinies pendant l’exécution pour pouvoir en faire l’observation. Pour limiter la pénalité en performance introduite, notre approche exploite les opérations rapides originales de la MV sous-jacente, lorsque cela est possible, et applique les techniques de compilation à-la-volée dans la MV superposée. Notre implémentation, Photon, est en moyenne 19% plus rapide qu’un interprète moderne, et entre 19× et 56× plus lente en moyenne que les compilateurs à-la-volée utilisés dans les navigateurs web populaires. Ce mémoire montre donc que la superposition de machines virtuelles est une technique alternative compétitive à la modification d’un interprète moderne pour JavaScript lorsqu’appliqué à l’observation à l’exécution des opérations sur les objets et des appels de fonction.