Showing papers on "Condition monitoring published in 2007"

A Survey of Methods for Detection of Stator-Related Faults in Induction Machines

Abstract: As evidenced by industrial surveys, stator-related failures account for a large percentage of faults in induction machines. The objective of this paper is to provide a survey of existing techniques for detection of stator-related faults, which include stator winding turn faults, stator core faults, temperature monitoring and thermal protection, and stator winding insulation testing. The root causes of fault inception, available techniques for detection, and recommendations for further research are presented. Although the primary focus is online and sensorless methods that use machine voltages and currents to extract fault signatures, offline techniques such as partial discharge detection are also examined. Condition monitoring, fault diagnostics, insulation testing, interlaminar core faults, partial discharge (PD), temperature monitoring, turn faults.

Induction Machine Condition Monitoring Using Neural Network Modeling

Abstract: Condition monitoring is desirable for increasing machinery availability, reducing consequential damage, and improving operational efficiency. Model-based methods are efficient monitoring systems for providing warning and predicting certain faults at early stages. However, the conventional methods must work with explicit motor models, and cannot be applied effectively for vibration signal diagnosis due to their nonadaptation and the random nature of vibration signal. In this paper, an analytical redundancy method using neural network modeling of the induction motor in vibration spectra is proposed for machine fault detection and diagnosis. The short-time Fourier transform is used to process the quasi-steady vibration signals to continuous spectra for the neural network model training. The faults are detected from changes in the expectation of vibration spectra modeling error. The effectiveness of the proposed method is demonstrated through experimental results, and it is shown that a robust and automatic induction machine condition monitoring system has been produced

Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems

Abstract: We present the results of our investigation into the use of genetic algorithms (GAs) for identifying near optimal design parameters of diagnostic systems that are based on artificial neural networks (ANNs) for condition monitoring of mechanical systems. ANNs have been widely used for health diagnosis of mechanical bearing using features extracted from vibration and acoustic emission signals. However, different sensors and the corresponding features exhibit varied response to different faults. Moreover, a number of different features can be used as inputs to a classifier ANN. Identification of the most useful features is important for an efficient classification as opposed to using all features from all channels, leading to very high computational cost and is, consequently, not desirable. Furthermore, determining the ANN structure is a fundamental design issue and can be critical for the classification performance. We show that a GA can be used to select a smaller subset of features that together form a genetically fit family for successful fault identification and classification tasks. At the same time, an appropriate structure of the ANN, in terms of the number of nodes in the hidden layer, can be determined, resulting in improved performance.

A Neural Network Integrated Decision Support System for Condition-Based Optimal Predictive Maintenance Policy

Abstract: This paper develops an integrated neural-network-based decision support system for predictive maintenance of rotational equipment. The integrated system is platform-independent and is aimed at minimizing expected cost per unit operational time. The proposed system consists of three components. The first component develops a vibration-based degradation database through condition monitoring of rolling element bearings. In the second component, an artificial neural network model is developed to estimate the life percentile and failure times of roller bearings. This is then used to construct a marginal distribution. The third component consists of the construction of a cost matrix and probabilistic replacement model that optimizes the expected cost per unit time. Furthermore, the integrated system consists of a heuristic managerial decision rule for different scenarios of predictive and corrective cost compositions. Finally, the proposed system can be applied in various industries and different kinds of equipment that possess well-defined degradation characteristics

Bearing Condition Monitoring Methods for Electric Machines: A General Review

Abstract: Bearing faults account for approximately half of all electric machine failures. Bearing condition monitoring is of practical importance. In this paper, up to seven different bearing condition monitoring methods in terms of the measuring medium are reviewed, with an emphasis on their implementation considerations. The major advantages and disadvantages of those methods are also summarized. This paper attempts to provide a general guide for choosing proper bearing condition monitoring strategies in practice for electric machines.

Condition Monitoring and ault Diagnosis in Wind Energy Conversion Systems: A Review

Abstract: There is a constant need for the reduction of operational and maintenance costs of wind energy conversion systems (WECS). The most efficient way of reducing these costs would be to continuously monitor the condition of these systems. This allows for early detection of the degeneration of the generator health, facilitating a proactive response, minimizing downtime, and maximizing productivity. Wind generators are also inaccessible since they are situated on extremely high towers, which are normally 20 m or greater in height. There are also plans to increase the number of offshore sites increasing the need for a remote means of WECS monitoring that eliminates some of the difficulties faced due to accessibility problems. Therefore and due to the importance of condition monitoring and fault diagnosis in WECS (blades, drive trains, and generators); and keeping in mind the need for future research, this paper is intended as a tutorial overview based on a review of the state of the art, describing different type of faults, their generated signatures, and their diagnostic schemes.

Quantification of condition monitoring benefit for offshore wind turbines

Abstract: Condition monitoring (CM) systems are increasingly installed in wind turbines with the goal of providing component-specific information to wind farm operators, theoretically increasing equipment availability via maintenance and operating actions based on this information. In the offshore case, economic benefits of CM systems are often assumed to be substantial, as compared with experience of onshore systems. Quantifying this economic benefit is non-trivial, especially considering the general lack of utility experience with large offshore wind farms. A quantitative measure of these benefits is therefore of value to utilities and operations and maintenance (O & M) groups involved in planning and operating future offshore wind farms. The probabilistic models presented in this paper employ a variety of methods including discrete-time Markov Chains, Monte Carlo methods and time series modelling. The flexibility and insight provided by this framework captures the necessary operational nuances of this complex pr...

Optimal condition based maintenance with imperfect information and the proportional hazards model

Abstract: Condition based maintenance (CBM) is based on collecting observations over time, in order to assess equipment's state, to prevent its failure and to determine the optimal maintenance strategies. In this paper, we derive an optimal CBM replacement policy when the state of equipment is unknown but can be estimated based on observed condition. We use a proportional hazards model (PHM) to represent the system's degradation. Since equipment's state is unknown, the optimization of the optimal maintenance policy is formulated as a partially observed Markov decision process (POMDP), and the problem is solved using dynamic programming. Practical advantages of combining the PHM with the POMDP are shown.

Detection and Classification of Stator Turn Faults and High Resistance Electrical Connections for Induction Machines

Abstract: The goal of stator winding turn fault detection is to detect the fault at an early stage, and shut down the machine immediately to prevent catastrophic motor failure due to the large fault current. A number of turn fault detection techniques have been proposed; however, there is currently no method available for distinguishing turn faults from high-resistance(R) connections, which also result in 3 phase system asymmetry. It is important to distinguish the two faults since a high-R connection does not necessarily require immediate motor shutdown. In this paper, new sensorless on-line monitoring techniques for detecting and classifying stator turn faults and high-R electrical connections in induction machines based on the zero sequence voltage or negative sequence current measurements are proposed. An experimental study on a 10 hp induction motor performed under simulated turn faults and high-resistance circuit conditions verifies that the two faults can be reliably detected and classified. The proposed technique helps improve the reliability, efficiency, and safety of the motor system and industrial plant, and also allows maintenance to be performed in a more efficient manner since the course of action can be determined based on the type and severity of the fault.

Robust Satellite Techniques (RST) for Natural and Environmental Hazards Monitoring and Mitigation: Theory and Applications

Abstract: Several algorithms and data analysis techniques have been proposed using satellite observations (within atmospheric spectral windows) for cloud and surface parameters studies and for human environment monitoring applications. Quite all these algorithms are difficult to extend to different geographical, seasonal conditions, generally offering poor performances and uncertain reliability especially when applied in environmental risk prevision, monitoring and/or mitigation. In this paper the generalized satellite data analysis approach RST (Robust Satellite Technique) is described which extend the use of RAT (Robust AVHRR Techniques) approach -previously proposed by the same author in 1998 -to whatever satellite sensors. Successful RST applications are also described with reference to results so far achieved by using optical and microwaves passive sensors for volcanic eruption monitoring and prediction, forest fire detection, floods mapping, monitoring and early warning, possible earthquake precursors monitoring, oil spill detection and pipeline networks monitoring.

Detection of Rotor Eccentricity Faults in a Closed-Loop Drive-Connected Induction Motor Using an Artificial Neural Network

Abstract: A new method for the detection of rotor eccentricity faults in a closed-loop drive-connected induction motor is reported in this paper. Unlike a line-fed electric motor, the eccentricity-related fault signals exist in the current as well as the voltage of a drive-connected motor. Meanwhile, since the speed and therefore the mechanical load can change widely in variable speed applications, the amplitudes of the fault signals will vary accordingly. An artificial neural network is used in the detection to learn the complex relationship between the eccentricity-related harmonic amplitudes and the operating conditions. The neural network can estimate a threshold corresponding to an operating condition, which can then be used to predict the motor condition. The neural network is trained and tested with data collected on drive-connected 4-pole, 7.5 Hp, three-phase induction motors. The experimental results validate that the detection method is feasible over the whole range of operating conditions of the experimental motors.

A wavelet-based methodology for grinding wheel condition monitoring

Abstract: Grinding wheel surface condition changes as more material is removed. This paper presents a wavelet-based methodology for grinding wheel condition monitoring based on acoustic emission (AE) signals. Grinding experiments in creep feed mode were conducted to grind alumina specimens with a resinoid-bonded diamond wheel using two different conditions. During the experiments, AE signals were collected when the wheel was 'sharp' and when the wheel was 'dull'. Discriminant features were then extracted from each raw AE signal segment using the discrete wavelet decomposition procedure. An adaptive genetic clustering algorithm was finally applied to the extracted features in order to distinguish different states of grinding wheel condition. The test results indicate that the proposed methodology can achieve 97% clustering accuracy for the high material removal rate condition, 86.7% for the low material removal rate condition, and 76.7% for the combined grinding conditions if the base wavelet, the decomposition level, and the GA parameters are properly selected.

Condition Monitoring of Generators & Other Subassemblies in Wind Turbine Drive Trains

Abstract: Offshore wind turbines, incorporating electrical generators and converters, operate in locations where accessibility can lead to long mean times to repair. Condition-based maintenance is therefore essential if cost-effective availability targets are to be reached. As yet the condition monitoring techniques appropriate for offshore wind turbines have not been resolved. Reliability studies have shown that the majority of failure modes in wind turbines are concentrated in drive train subassemblies, including the electrical generator and converter, and are heavily affected by wind conditions. A 30 kW test rig has been constructed, with features similar to a wind turbine drive train, to enable the development of the signal processing techniques necessary for this variable speed, high torque variation application. The test rig includes a low speed shaft, high speed shaft, gearbox and an electrical generator and can be driven by simulated wind conditions. The test rig can also be used to inform the selection of appropriate monitoring instrumentation for offshore wind turbines. A series of condition monitoring approaches have been investigated on this test rig, using measured torque, speed, shaft displacement and gearbox vibration to detect faults. By the use of appropriate signal processing techniques, changes to load conditions, properties of the gearbox and coil faults can be detected.

A particle filtering-based framework for real-time fault diagnosis and failure prognosis in a turbine engine

Abstract: This paper presents the implementation of an online particle-filtering-based framework for fault diagnosis and failure prognosis in a turbine engine. The methodology considers two autonomous modules, and assumes the existence of fault indicators (for monitoring purposes) and the availability of real-time measurements. A fault detection and identification (FDI) module uses a hybrid state-space model of the plant, and a particle filtering algorithm to calculate the probability of a crack in one of the blades of the turbine; simultaneously computing the state probability density function (pdf) estimates that will be used as initial conditions in the prognosis module. The failure prognosis module, on the other hand, computes the remaining useful life (RUL) pdf of the faulty subsystem in real-time, using a particle-filtering-based algorithm that consecutively updates the current state estimate for a nonlinear state-space model (with unknown time-varying parameters), and predicts the evolution in time of the probability distribution for the crack length. The outcome of the prognosis module provides information about precision and accuracy of long-term predictions, RUL expectations and 95% confidence intervals for the failure condition under study. Data from a seeded fault test is used to validate the proposed approaches.

Providing Decision Support for the Condition-Based Maintenance of Circuit Breakers Through Data Mining of Trip Coil Current Signatures

Abstract: The focus of this paper centers on the condition assessment of 11-kV-33-kV distribution circuit breakers (CBs) from the analysis of their trip coil current signatures captured using an innovative condition monitoring technology developed by others. Using available expert knowledge in conjunction with a structured process of data mining, thresholds associated with features representing each stage of a CB's operation may be defined and used to characterize varying states of the CB condition. The knowledge and understanding of the satisfactory and unsatisfactory breaker condition can be gained and made explicit from the analysis of captured trip signature data and subsequently used to form the basis of condition assessment and diagnostic rules implemented in a decision support system, used to inform condition-based decisions affecting CB maintenance. This paper proposes a data mining method for the analysis of condition monitoring data, and demonstrates this method in its discovery of useful knowledge from trip coil data captured from a population of Scottish Power - Energy Networks' in-service CBs. This knowledge then forms the basis of a decision support system for the condition assessment of these CBs during routine trip testing

Parameter Identification for a High-Performance Hydrostatic Actuation System Using the Variable Structure Filter Concept

Abstract: Parameter estimation is an important concept that can be used for health and condition monitoring. Estimation or measurement of physically meaningful parameters and their evaluation against predetermined thresholds allows detection of gradual or abrupt deteriorations in the plant. This early detection of faults enables preventative unscheduled maintenance that is of benefit to industries concerned with reliability and safety. In this paper, a recently proposed state estimation strategy referred to as the smooth variable structure filter (SVSF) is reviewed and extended to parameter estimation. The SVSF is applied to a novel hydrostatic actuation system referred to as the electrohydraulic actuator (EHA). Condition monitoring of the EHA for preventative unscheduled maintenance would increase its safety in applications pertaining to aerospace and would reduce its operational and maintenance costs.

Real-Time Condition Monitoring of the Electrolytic Capacitors for Power Electronics Applications

Abstract: The objective of this paper is to propose a new low cost method to detect the changes in equivalent series resistor (ESR) and the capacitance value of an electrolytic capacitor in order to realize the real-time condition monitoring of an electrolytic capacitor. Experimental and simulation results are discussed to illustrate the proposed condition monitoring technique. In addition, it is shown that the proposed method can be used for a non-stationary system where waveforms are continuously varying in amplitude, frequency, and phase. The proposed on-line failure prediction method has the merits of low cost and circuit simplicity.

Modelling, monitoring and diagnostic techniques for fluid power systems

Abstract: Modelling and Computer Simulation as an Aid to Understanding Circuit Behaviour.- Condition Monitoring Methods.- Common Faults and Breakdowns that can occur in a Hydraulic Circuit.