scispace - formally typeset
Search or ask a question

Showing papers on "Condition monitoring published in 2000"


Journal ArticleDOI
TL;DR: In this paper, a gear pair affected by a fatigue crack is compared with those obtained by means of the well-accepted cepstrum analysis and time-synchronous average analysis.

330 citations


Journal ArticleDOI
TL;DR: A novel method of detecting and unambiguously diagnosing the type and magnitude of three induction machine fault conditions from the single sensor measurement of the radial electromagnetic machine vibration is described.
Abstract: This paper describes a novel method of detecting and unambiguously diagnosing the type and magnitude of three induction machine fault conditions from the single sensor measurement of the radial electromagnetic machine vibration. The detection mechanism is based on the hypothesis that the induction machine can be considered as a simple system, and that the action of the fault conditions are to alter the output of the system in a characteristic and predictable fashion. Further, the change in output and fault condition can be correlated allowing explicit fault identification. Using this technique, there is no requirement for a priori data describing machine fault conditions, the method is equally applicable to both sinusoidally and inverter-fed induction machines and is generally invariant of both the induction machine load and speed. The detection mechanisms are rigorously examined theoretically and experimentally, and it is shown that a robust and reliable induction machine condition-monitoring system has been produced. Further, this technique is developed into a software-based automated commercially applicable system.

176 citations


Journal ArticleDOI
TL;DR: A model is presented to advise at a monitoring check what maintenance action to take based upon the condition monitoring and preventive maintenance information obtained to date, relevant to a large class of condition monitoring techniques currently employed in industry including vibration and oil analysis.
Abstract: This paper considers a stochastic dynamic system subject to random deterioration, with regular condition monitoring and preventive maintenance. A model is presented to advise at a monitoring check what maintenance action to take based upon the condition monitoring and preventive maintenance information obtained to date. A general assumption adopted in the paper is that the performance of the system concerned can not be described directly by the monitored information, but is correlated with it stochastically. The model is relevant to a large class of condition monitoring techniques currently employed in industry including vibration and oil analysis. The model is constructed under fairly general conditions and includes two novel developments. Firstly, the concept of the conditional residual time is used to measure the condition of the monitored system at the time of a monitoring check, and secondly, contrary to previous practice, the monitored observation is now assumed to be a function of the system condition. Relationships between the observed history of condition monitoring, preventive maintenance actions, and the condition of the system are established. Methods for estimating model parameters are discussed. Since the model presented is generally beyond the scope for an analytical solution, a numerical approximation method is also proposed. Finally, a case example is presented to illustrate the modelling concepts in the case of non-maintained plant.

149 citations


Patent
05 Jan 2000
TL;DR: In this paper, a method for invoking condition monitoring among a plurality of machines, comprising establishing a network of automated local experts at generally fixed locations and interconnected by at least one network connection, is provided.
Abstract: A method is provided for invoking condition monitoring among a plurality of machines, comprising establishing a network of automated local experts at generally fixed locations and interconnected by at least one network connection, configuring each of the local experts to receive vibration data from at least one of the plurality of machines which is located in relative physical proximity thereto and configuring each of the local experts to analyze the received vibration data and to diagnose a condition of the machine providing the received vibration data based on the received vibration, and configuring each of the local experts to transmit diagnostic information relating to the condition of the respective machines via the at least one network connection.

146 citations


Journal ArticleDOI
01 Jun 2000
TL;DR: In this article, the use of a GA was used to select the most significant input features from a large set of possible features in machine condition monitoring, achieving an accuracy of 99.8%.
Abstract: Artificial neural networks (ANNs) can be used successfully to detect faults in rotating machinery. Using statistical estimates of the vibration signal as input features. In any given scenario, there are many different possible features that may be used as inputs for the ANN. One of the main problems facing the use of ANNs is the selection of the best inputs to the ANN, allowing the creation of compact, highly accurate networks that require comparatively little preprocessing. The paper examines the use of a genetic algorithm (GA) to select the most significant input features from a large set of possible features in machine condition monitoring. Using a GA, a subset of six input features is selected from a set of 66 giving a classification accuracy of 99.8%, compared with an accuracy of 87.2% using an ANN without feature selection and all 66 inputs. From a larger set of 156 different features, the GA is able to select a set of six features to give 100% recognition accuracy.

119 citations


Journal ArticleDOI
TL;DR: This paper presents an efficient composite technique for track profile extraction with real-time image processing that high throughput is obtained by algorithmic prefiltering to restrict the image area containing the track profile, while high accuracy is achieved by neural reconstruction of the profile itself.
Abstract: Checking railway status is critical to guarantee high operating safety, proper maintenance schedule, and low maintenance and operating costs. This operation consists of the analysis of the rail profile and level as well as overall geometry and undulation. Traditional detection systems are based on mechanical devices in contact with the track. Innovative approaches are based on laser scanning and image analysis. This paper presents an efficient composite technique for track profile extraction with real-time image processing. High throughput is obtained by algorithmic prefiltering to restrict the image area containing the track profile, while high accuracy is achieved by neural reconstruction of the profile itself.

118 citations


Journal ArticleDOI
TL;DR: In this article, the authors reviewed the investigation into overhead line deterioration, briefly outlined the inspection methods available at present, and finally introduced a current project being undertaken in the Power and Energy Systems Research Group at the University of Bath in collaboration with two major utilities in the UK, into on-line condition monitoring of overhead lines.

116 citations


Journal ArticleDOI
01 Aug 2000
TL;DR: Experimental results show that the proposed system can reliably detect tool conditions in drilling operations in real time and is viable for industrial applications.
Abstract: Wavelet transforms and fuzzy techniques are used to monitor tool breakage and wear conditions in real time according to the measured spindle and feed motor currents, respectively. First, continuous and discrete wavelet transforms are used to decompose the spindle and feed ac servo motor current signals to extract signal features so as to detect the breakage of drills successfully. Next, the models of the relationships between the current signals and the cutting parameters are established under different tool wear states. Subsequently, fuzzy classification methods are used to detect tool wear states based on the above models. Finally, the two methods above are integrated to establish an intelligent tool condition monitoring system for drilling operations. The monitoring system can detect tool breakage and tool wear conditions using very simple current sensors. Experimental results show that the proposed system can reliably detect tool conditions in drilling operations in real time and is viable for industrial applications.

115 citations


Journal ArticleDOI
TL;DR: The feed cutting force estimated with the aid of an inexpensive current sensor installed on the AC servomotor of a computerized numerical control tuning center is used to monitor tool wear condition.
Abstract: Tool wear condition monitoring has the potential to play a critical role in ensuring the dimensional accuracy of the workpiece and prevention of damage to cutting equipment. It could also help in automating cutting processes. In this paper, the feed cutting force estimated with the aid of an inexpensive current sensor installed on the AC servomotor of a computerized numerical control tuning center is used to monitor tool wear condition. To achieve this, the feed drive system is modeled, using neuro-fuzzy techniques, to provide the framework for estimating the feed cutting force based on the feed motor current measured. Functional dependence of the feed cutting force on tool wear and cutting parameters are then expressed in the form of a difference equation relating variation in the feed cutting force to tool wear rate. The computerized system automatically compares successive feed cutting force estimates and determines the onset of accelerated tool wear in order to issue a request for tool replacement. Experimental results show that the tool wear condition monitoring is effective and industrially applicable.

102 citations


01 Jan 2000
TL;DR: In this article, the main concern is the development of methods for automatic condition monitoring of control loops withapplication to the process industry, by condition monitoring both detection and detection detection methods.
Abstract: The main concern of this work is the development of methodsfor automatic condition monitoring of control loops withapplication to the process industry. By condition monitoringboth detection and dia ...

100 citations


Journal ArticleDOI
TL;DR: A model-based approach to the detection and diagnosis of mechanical faults in rotating machinery is studied and algorithms suitable for real-time implementation are developed and evaluated using computer simulation.
Abstract: A model-based approach to the detection and diagnosis of mechanical faults in rotating machinery is studied in this paper. For certain types of faults, for example, raceway faults in rolling element bearings, an increase in mass unbalance, and changes in stiffness and damping, algorithms suitable for real-time implementation are developed and evaluated using computer simulation.

Journal ArticleDOI
TL;DR: The modelling of condition monitoring information for three critical water pumps at a large soft-drinks manufacturing plant is described to predict the distribution of the residual lifetimes of the individual pumps.
Abstract: In this paper the modelling of condition monitoring information for three critical water pumps at a large soft-drinks manufacturing plant is described. The purpose of the model is to predict the distribution of the residual lifetimes of the individual pumps. This information is used to aid maintenance management decision-making, principally relating to overhaul. We describe a simple decision rule to determine whether maintenance action is necessary given monitoring information to date.

Journal ArticleDOI
TL;DR: In this paper, an approach, termed ASPS (automated sensory and signal processing selection system), aimed at aiding the systematic design of condition monitoring systems for machine tools and machining operations is presented.

Journal ArticleDOI
01 May 2000
TL;DR: In this paper, a recently developed condition-based maintenance model is described which utilizes reliability data combined with condition-monitoring and measurements to predict the remaining useful life of critical components in a hot strip steel mill.
Abstract: A recently developed condition-based maintenance model is described which utilizes reliability data combined with condition-monitoring and measurements to predict the remaining useful life of critical components in a hot strip steel mill. The results obtained from case studies are presented which indicate how the model can be used as part of a condition-based maintenance strategy.

Journal ArticleDOI
TL;DR: In this paper, the authors summarized common faults, fault mechanisms and their effect on diesel engine performance, and reviewed standard condition monitoring and fault diagnosis (CMFD) methods for parameters and CMFD systems for diesel engines.
Abstract: Technical advances and environmental legislation in recent years have stimulated the development of a number of techniques for condition monitoring and fault diagnosis (CMFD) in diesel engines. This paper firstly summarises common faults, fault mechanisms and their effect on diesel engine performance. Corresponding measurands are presented. Standard CMFD methods for parameters and CMFD systems for diesel engines are reviewed. Finally, some advanced CMFD techniques, including neural networks and fuzzy logic, which may be more powerful, are discussed.


Proceedings ArticleDOI
08 Oct 2000
TL;DR: In this article, an on-line neural network based diagnostic scheme for induction machine stator winding turn fault detection is presented, consisting of a feed-forward neural network combined with a self-organizing feature map (SOFM) to visually display the operating condition of the machine on a two-dimensional grid.
Abstract: A novel on-line neural network based diagnostic scheme, for induction machine stator winding turn fault detection, is presented. The scheme consists of a feed-forward neural network combined with a self-organizing feature map (SOFM) to visually display the operating condition of the machine on a two-dimensional grid. The operating point moves to a specific region on the map as a fault starts developing and can be used to alert the motor protection system to an incipient fault. This is a useful tool for commercial condition monitoring systems. Experimental results are provided, with data obtained from a specially wound test motor, to illustrate the robustness of the proposed turn fault detection scheme. The new method is not sensitive to unbalanced supply voltages or asymmetries in the machine and instrumentation.

Journal ArticleDOI
TL;DR: In this article, a wavelet filter with very narrow frequency-band and autocorrelation enhancement is proposed as a means of monitoring the natural frequencies in real-time, which can provide realtime monitoring based on the changes of significant and natural frequencies, corresponding to the change in conditions.

Journal ArticleDOI
TL;DR: In this paper, a Fourier-based algorithm for estimating the parameters of the oscillating modes which arise after a system disruption is presented, based on the sliding window method discussed by K. Poon et al. (see ibid., p.1573-9, 1988) but has a number of innovations.
Abstract: The monitoring of power systems after faults or disturbances is an important problem. These disturbances generally give rise to oscillating modal components, which in a worst case scenario, can be exponentially growing sinusoids. The latter, if not detected and damped out, can pose a serious threat to system reliability. It is thus necessary to monitor whether any of these modes do exhibit exponential growth (rather than the more acceptable scenario of exponential decay). There are currently a number of approaches to predicting/monitoring disturbances in power system networks. One approach is eigenanalysis, based on a linearized modeling of the power system. A more direct approach is spectral analysis of the signals recorded immediately after a fault or disruption. For this latter approach both Prony's method and conventional Fourier techniques have been used. This paper presents a Fourier based algorithm for estimating the parameters of the oscillating modes which arise after a system disruption. The algorithm is based on the sliding window method discussed by K. Poon et al. (see ibid., p.1573-9, 1988) but has a number of innovations.

Patent
02 Aug 2000
TL;DR: In this paper, a method for assembling condition monitoring histories of same-type machines that have lived in same type environments and have failed as a result of the same failure mode, estimating the remaining life with confidence bounds is presented.
Abstract: A method for assembling condition monitoring histories of same-type machines that have lived in same-type environments and have failed as a result of the same failure mode, estimating the remaining life with confidence bounds in an operating machine that presents a set of condition symptoms over time and that is diagnosed with a pending failure mode, and deciding when to replace/repair an operating machine (diagnosed with a specific failure mode condition) based on the cost of its estimated performance over its predicted remaining life.

Journal ArticleDOI
TL;DR: A multi-net fault diagnosis system designed to provide an early warning of combustion-related faults in a diesel engine is presented and is shown to be effective when compared with the performance of the component nets from which it was assembled.
Abstract: A multi-net fault diagnosis system designed to provide an early warning of combustion-related faults in a diesel engine is presented. Two faults (a leaking exhaust valve and a leaking fuel injector nozzle) were physically induced (at separate times) in the engine. A pressure transducer was used to sense the in-cylinder pressure changes during engine cycles under both of these conditions, and during normal operation. Data corresponding to these measurements were used to train artificial neural nets to recognise the faults, and to discriminate between them and normal operation. Individually trained nets, some of which were trained on subtasks, were combined to form a multi-net system. The multi-net system is shown to be effective when compared with the performance of the component nets from which it was assembled. The system is also shown to outperform a decision-tree algorithm (C5.0), and a human expert; comparisons which show the complexity of the required discrimination. The results illustrate the improvements in performance that can come about from the effective use of both problem decomposition and redundancy in the construction of multi-net systems.

Journal ArticleDOI
TL;DR: In this paper, the authors defined the concept of symptom reliability for systems in use or in operation, which means that the reliability is based on symptoms of the systems under consideration, and proposed the symptom-dependent hazard functions for their use.

Journal ArticleDOI
TL;DR: In this paper, the authors presented an analysis of the vibrational behavior of a deep groove ball bearing with a structurally integrated force sensor, which accommodated within a slot on the bearing's outer ring.
Abstract: This paper presents an analysis of the vibrational behavior of a deep groove ball bearingwith a structurally integrated force sensor. The miniaturized force sensor, accommodatedwithin a slot on the bearing’s outer ring, provides on-line condition monitoring capabilityto the bearing. Analytical and finite element models were developed to predict the sensoroutput due to bearing dynamic load and rotational speed variations. Experimental studieswere conducted on a ball bearing to validate the analytical and numerical solutions.Good agreement was found between the model-predicted sensor outputs and the experi-mental results. The findings validated the approach of integrated-sensing for on-linebearing condition monitoring. @S0739-3717~00!00203-8#

Journal ArticleDOI
TL;DR: The VI system presents an effective and user-friendly human-machine interface for on-line bearing condition monitoring, which is of critical importance to real-time fault diagnosis and intelligent manufacturing.
Abstract: This paper presents the design, optimization, and implementation of a virtual instrument (VI), which is an essential part of an integrated bearing condition monitoring system. The VI is designed using the graphical programming language LabVIEW and is capable of performing on-line measurement functions, including data acquisition, display, and analyses in the time and frequency domains, as well as data archiving. The issues of data length selection and VI real-time capability have been investigated to optimize the VI operation and improve data-processing efficiency. The VI system presents an effective and user-friendly human-machine interface for on-line bearing condition monitoring, which is of critical importance to real-time fault diagnosis and intelligent manufacturing.


Proceedings ArticleDOI
03 Apr 2000
TL;DR: This paper describes the system architecture, data fusion, and classification algorithms employed in a distributed, wireless bearing and gear health monitoring system and the role and integration of prognostic algorithms--required to predict future system health--are discussed.
Abstract: A new paradigm for machinery maintenance is emerging as preventive maintenance strategies are being replaced by condition-based maintenance. In condition-based maintenance, machinery is repaired or serviced only when an intell igent monitoring system indicates that the system cannot fulfill mission requirements. The implementation of such systems requires a combination of sensor data fusion, feature extraction, classification, and prediction algorithms. In addition, new system architectures are being developed to facilitate the reduction of wide bandwidth sensor data to concise predictions of ability of the system to complete its current mission or future missions. This paper describes the system architecture, data fusion, and classification algorithms employed in a distributed, wireless bearing and gear health monitoring system. The role and integration of prognostic algorithms – required to predict future system health - are also discussed. Examples are provided which illustrate the application of the system architecture and algorithms to data collected on a machinery diagnostics test bed at the Applied Research Laboratory at The Pennsylvania State University.

Journal ArticleDOI
TL;DR: In this paper, the authors present the results of a 2-year study focusing on the development of a condition monitoring system for a fed-batch fermentation system operated by Biochemie Ltd in Austria.

Proceedings ArticleDOI
06 Mar 2000
TL;DR: In this paper, the sound generation of a diesel engine is modelled based upon the combustion process, and time-frequency analysis is used to reveal the underlying characteristics of the sound waves.
Abstract: In this, Part 1 of the paper, the sound generation of a diesel engine is modelled based upon the combustion process, and time-frequency analysis is used to reveal the underlying characteristics of the sound waves. Simulation shows that the frequency bandwidth of the generated acoustic signals is significantly widened around the engine''s top dead center (TDC) positions, with the energy concentrated predominantly at the firing frequency and its harmonics. As anticipated, the model predicts an increase in sound level with increasing engine load and speed, and the model-predicted noise generation is correlated with waveforms extracted from intrusively-monitored cylinder pressure. Real monitored data, taken in an ordinary engine test-bay environment and without special acoustic monitoring precautions, is shown to be highly contaminated due to adverse environmental acoustics and intrusive background noise. The representation of acoustic signals using the smoothed pseudo-Wigner- Ville distribution (SPWVD) and continuous wavelet transform (CWT), however, is found to permit recognition of the adverse influences of the measurement environment. This subsequently allows the monitored sound characteristics to be closely correlated to the combustion process. Part 1 concludes with an investigation of the influences of the measurement environment upon the acoustic data, and of the signal conditioning and representation techniques required to reveal the condition-indicating content of the monitored acoustic data. The sister paper to this (""Part 2 - Fault Detection and Diagnosis""), puts the developed methodology to the test by investigating its capability to detect and distinguish between a range of realistic yet incipient engine faults on a standard production engine in an uncontrolled industrial environment.

Journal ArticleDOI
TL;DR: The overall hardware and software designs of this implemented system monitors power, vibration, temperature and pressure of the drives and spindles with a total of 72 diagnostic features and uses a cost-weighted function to identify diagnostic solutions with the lowest cost.

Journal ArticleDOI
TL;DR: A new approach for an expert system concept is proposed, characterised by using a total quality maintenance (TQMain) concept; having a common database, and a continuously improved knowledge base with an intelligent inference engine to enhance data reliability, decision making certainty, and remove the redundancy in monitoring systems.
Abstract: In manufacturing systems intelligent techniques are being used to integrate and interpret data from multiple sensors to predict tool wear and tool life. Less attention is devoted to developments of integrated condition monitoring systems, which enable the user to evaluate a multi‐variant system based on the data collected from, e.g. maintenance, quality, production, etc. In this paper we discussed different approaches of how to keep availability, quality and productivity at high levels. Also, we proposed a new approach for an expert system concept, which is characterised by using a total quality maintenance (TQMain) concept; having a common database, and a continuously improved knowledge base with an intelligent inference engine. It can enhance data reliability, decision making certainty, remove the redundancy in monitoring systems, and allow the user to detect and eliminate reasons behind variations through effective diagnosis and prognosis. This will enhance the performance‐efficiency, availability and quality rate, i.e. overall equipment effectiveness of the manufacturing systems.