Functional and advanced functional and causal relationship diagrams for remote condition monitoring

Analysing the condition of an asset is a big challenge as there can be many aspects which can contribute to the overall functional reliability of the asset that have to be considered. In this paper we propose a two-step functional and causal relationship diagram (FCRD) to address this problem. In the first step, the FCRD is designed to facilitate the analysis of the condition of an asset by evaluating the interdependence (functional and causal) relationships between different components of the asset with the help of a relationship diagram. This is followed by the advanced FCRD (AFCRD) which refines the information from the FCRD into a comprehensive and manageable format. This new two-step methodology for asset condition monitoring is tested and validated for the case of a water treatment plant. © IMechE 2012.

RCA method for fault diagnosis in digital substations of power systems

The authors present a Cause-Effect fault diagnosis model, which utilises the Root Cause Analysis approach and takes into account the technical features of a digital substation. The Dempster/Shafer evidence theory is used to integrate different types of fault information in the diagnosis model so as to implement a hierarchical, systematic and comprehensive diagnosis based on the logic relationship between the parent and child nodes such as transformer/circuit-breaker/transmission-line, and between the root and child causes. A real fault scenario is investigated in the case study to demonstrate the developed approach in diagnosing malfunction of protective relays and/or circuit breakers, miss or false alarms, and other commonly encountered faults at a modern digital substation.

Utilising Reliability and Condition Monitoring Data for Asset Health Prognosis

The ability to forecast machinery health is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models which attempt to forecast machinery health based on condition data such as vibration measurements. This paper demonstrates how the population characteristics and condition monitoring data (both complete and suspended) of historical items can be integrated for training an intelligent agent to predict asset health multiple steps ahead. The model consists of a feed-forward neural network whose training targets are asset survival probabilities estimated using a variation of the Kaplan–Meier estimator and a degradation-based failure probability density function estimator. The trained network is capable of estimating the future survival probabilities when a series of asset condition readings are inputted. The output survival probabilities collectively form an estimated survival curve. Pump data from a pulp and paper mill were used for model validation and comparison. The results indicate that the proposed model can predict more accurately as well as further ahead than similar models which neglect population characteristics and suspended data. This work presents a compelling concept for longer-range fault prognosis utilising available information more fully and accurately.

Characterisation of combustion related acoustic emission sources for diesel engine condition monitoring

This thesis represents a major step forward in understanding the link between the development of combustion related faults in diesel engines and the generation of acoustic emissions. The findings presented throughout the thesis provide a foundation so that future diesel engine monitoring systems are able to more effectively detect and monitor developing faults. In undertaking this research knowledge concerning engine function and relevant failure mechanisms was combined with different modelling methods to generate a framework that was used to effectively identify fault related activity within acoustic emissions recorded from different engines.

Fault diagnosis of low speed bearing based on acoustic emission signal and multi-class relevance vector machine

This study presents an acoustic emission (AE) based fault diagnosis for low speed bearing using multi-class relevance vector machine (RVM). A low speed test rig was developed to simulate the various defects with shaft speeds as low as 10 rpm under several loading conditions. The data was acquired using anAEsensor with the test bearing operating at a constant loading (5 kN) andwith a speed range from20 to 80 rpm. This study is aimed at finding a reliable method/tool for low speed machines fault diagnosis based on AE signal. In the present study, component analysis was performed to extract the bearing feature and to reduce the dimensionality of original data feature. The result shows that multi-class RVM offers a promising approach for fault diagnosis of low speed machines.

A data mining approach for fault diagnosis: An application of anomaly detection algorithm

Rolling-element bearing failures are the most frequent problems in rotating machinery, which can be catastrophic and cause major downtime. Hence, providing advance failure warning and precise fault detection in such components are pivotal and cost-effective. The vast majority of past research has focused on signal processing and spectral analysis for fault diagnostics in rotating components. In this study, a data mining approach using a machine learning technique called anomaly detection (AD) is presented. This method employs classification techniques to discriminate between defect examples. Two features, kurtosis and Non-Gaussianity Score (NGS), are extracted to develop anomaly detection algorithms. The performance of the developed algorithms was examined through real data from a test to failure bearing. Finally, the application of anomaly detection is compared with one of the popular methods called Support Vector Machine (SVM) to investigate the sensitivity and accuracy of this approach and its ability to detect the anomalies in early stages.

Data mining approaches to software fault diagnosis

Automatic identification of software faults has enormous practical significance. This requires characterizing program execution behavior and the use of appropriate data mining techniques on the chosen representation. In this paper, we use the sequence of system calls to characterize program execution. The data mining tasks addressed are learning to map system call streams to fault labels and automatic identification of fault causes. Spectrum kernels and SVM are used for the former while latent semantic analysis is used for the latter The techniques are demonstrated for the intrusion dataset containing system call traces. The results show that kernel techniques are as accurate as the best available results but are faster by orders of magnitude. We also show that latent semantic indexing is capable of revealing fault-specific features.

Incipient turn-to-turn winding fault diagnosis of power transformers by the on-load exciting current Extended Park`s Vector Approach

This paper presents the application of the on-load exciting current Extended Park's Vector Approach for diagnosing incipient turn-to-turn winding faults in operating power transformers. Experimental and simulated test results demonstrate the effectiveness of the proposed technique, which is based on the spectral analysis of the AC component of the on-load exciting current Park's Vector modulus.

Low-cost vibration sensors: tendencies and applications in condition monitoring of machines and structures

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

Constraint satisfaction techniques under uncertain conditions for fault diagnosis in nonlinear dynamic systems

The speed of fault isolation is crucial for the design and reconfiguration of fault tolerant control (FTC). In this paper the fault isolation problem is stated as a constraint satisfaction problem (CSP) and solved using constraint propagation techniques. The proposed method is based on constraint satisfaction techniques and uncertainty space refining of interval parameters. In comparison with other approaches based on adaptive observers, the major advantage of the presented method is that the isolation speed is fast even taking into account uncertainty in parameters, measurements and model errors and without the monotonicity assumption. In order to illustrate the proposed approach, a case study of a nonlinear dynamic system is presented

Fault diagnosis by refining the parameter uncertainty space of nonlinear dynamic systems

This paper deals with fault detection and isolation problems for nonlinear dynamic systems. Both problems are stated as constraint satisfaction problems (CSP) and solved using consistency techniques. The main contribution is the isolation method based on consistency techniques and uncertainty space refining of interval parameters. The major advantage of this method is that the isolation speed is fast even taking into account uncertainty in parameters, measurements, and model errors. Interval calculations bring independence from the assumption of monotony considered by several approaches for fault isolation which are based on observers. An application to a well known alcoholic fermentation process model is presented

Acoustic condition monitoring for cold metal forming

One of the most important objectives of cold metal forming research is to develop techniques that enable better manufacturing efficiencies. Within this monitoring of tooling condition is vital to providing high quality manufacturing. The objective of this research is to determine the signature derived from Acoustic Emission (AE) sensors, in order to establish the current condition of a machine tool, as applied to bolt-making. From here we aim to develop and implement an on-line condition monitoring tool for the cold forming process. A review of the literature has shown that much research into AE has been successfully applied in metal cutting operations; such as milling, drilling and turning, but little research has been done related to metal forming. This appears to be due to the complexity of obtaining consistent signals using Acoustic Emission systems, because the presence of noise in many forms. This paper will detail many of the AE signals acquired and analysed through our research. The extensive results indicate this form of condition monitoring is not suitable for metal forming in its current configuration. Further tests are proposed to enable such research to move forward, so a condition monitoring system can be established.

Emission-based condition monitoring technique for ZnO surge arrester

In this paper, electromagnetic emission at the frequency range of 30MHz to 300MHz is used to detect physical defects on the 22kV outdoor zinc-oxide (ZnO) surge arresters. Different weather conditions combining with artificially created pollution were produced in a laboratory environment and measurements were recorded over a fixed period of time. Pollution due to fine dust particles has been created according to IEC standard under both wet and dry conditions. The aim is to detect the defects (bushing damage) when the surge arrester is subjected to various weather and surface condition. The collected electromagnetic signals were sampled and analyzed using analysis tools such as the autocorrelation coefficient and Wigner-Ville distribution. The results from the present paper indicate that electromagnetic radiation from the defects on surge arrester combining with the adequate analysis tools can be used as a valuable diagnostic tool for power system operator.