Showing papers on "Condition monitoring published in 2001"

Method and system for condition monitoring of vehicles

Abstract: A method and system for an improved vehicle monitoring system in order to provide a cost-effective and scalable system design for industrial application through the use of machine learning and data mining technologies on data acquired from a plurality of vehicles to create models. Frequent acquisition of vehicle sensor and diagnostic data enables comparison with the created models to provide continuing analysis of the vehicle with respect to repair, maintenance and diagnostics.

An on-line stator winding resistance estimation technique for temperature monitoring of line-connected induction machines

Abstract: A new technique for stator resistance (R/sub s/)-based thermal monitoring of small line-connected induction machines is proposed in this paper. A simple device is developed for injecting a small DC signal into line-connected induction machines for estimation of R/sub s/. The proposed DC injection device is capable of intermittently injecting a controllable DC bias into the motor with very low power dissipation. Experimental results under motor startup, load variation, and abnormal cooling conditions verify that the proposed technique provides an accurate estimate of R/sub s/ that is capable of responding to the changes in the motor thermal characteristics, resulting in reliable thermal protection. The proposed technique is a very practical method for thermal protection of small line-connected induction machines that can be implemented with low cost in a motor condition monitoring system.

Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs)

Abstract: Monitoring of tool wear condition for drilling is a very important economical consideration in automated manufacturing. Two techniques are proposed in this paper for the on-line identification of tool wear based on the measurement of cutting forces and power signals. These techniques use hidden Markov models (HMMs), commonly used in speech recognition. In the first method, bargraph monitoring of the HMM probabilities is used to track the progress of tool wear during the drilling operation. In the second method, sensor signals that correspond to various types of wear status, e.g., sharp, workable and dull, are classified using a multiple modeling method. Experimental results demonstrate the effectiveness of the proposed methods. Although this work focuses on on-line tool wear condition monitoring for drilling operations, the HMM monitoring techniques introduced in this paper can be applied to other cutting processes.

Environment and hazard condition monitoring system

Abstract: An environment and hazard condition monitoring system is provided. One embodiment of the environment monitoring system is adapted to incorporate a plurality of preexisting sensors. The environment monitoring system comprises at least one user interface and a plurality of sensor agents, with each sensor agent communicating with the preexisting sensors, the user interface and with the other sensor agents. Another embodiment of the invention provides new sensors that include sensor agents that can communicate with each other and with a user interface. The sensor agent in either environment monitoring system can also communicate with portable devices.

A general prognostic tracking algorithm for predictive maintenance

Abstract: Prognostic health management (PHIM) is a technology that uses objective measurements of condition and failure hazard to adaptively optimize a combination of availability, reliability, and total cost of ownership of a particular asset. Prognostic utility for the signature features are determined by transitional failure experiments. Such experiments provide evidence for the failure alert threshold and of the likely advance warning one can expect by tracking the feature(s) continuously. Kalman filters are used to track changes in features like vibration levels, mode frequencies, or other waveform signature features. This information is then functionally associated with load conditions using fuzzy logic and expert human knowledge of the physics and the underlying mechanical systems. Herein is the greatest challenge to engineering. However, it is straightforward to track the progress of relevant features over time using techniques such as Kalman filtering. Using the predicted states, one can then estimate the future failure hazard, probability of survival, and remaining useful life in an automated and objective methodology.

A survey of new techniques in insulation monitoring of power transformers

Abstract: This paper presents a survey of new monitoring and diagnostic technologies and applications, including laboratory experimental work, in power transformer insulation monitoring for the purpose of condition assessment.

Efficient reactive monitoring

Abstract: Networks are monitored in order to ensure that the system operates within desirable parameters. The increasing complexity of networks and services provided by them increases this need for monitoring. Monitoring consists of measuring properties of the network, and of inferring an aggregate predicate from these measurements. Conducting such monitoring introduces traffic overhead that may reduce the overall effective throughput. This paper studies ways to minimize the monitoring communication overhead in IP networks. We develop and analyze several monitoring algorithms that achieve significant reduction in the management overhead while maintaining the functionality. The main idea is to combine global polling with local event driven reporting. The amount of traffic saving depends on the statistical characterization of the monitored data. We indicate the specific statistical factors that affect the saving and show how to choose the right algorithm for the type of monitored data. In particular our results show that for Internet traffic our algorithms can save more than 90% of the monitoring traffic.

Optimizing a mine haul truck wheel motors’ condition monitoring program Use of proportional hazards modeling

Abstract: Discusses work completed at Cardinal River Coals in Canada to improve the existing oil analysis condition monitoring program being undertaken for wheel motors. Oil analysis results from a fleet of 55 haul truck wheel motors were analyzed along with their respective failures and repairs over a nine‐year period. Detailed data cleaning procedures were applied to prepare data for modeling. In addition, definitions of failure and suspension were clarified depending on equipment condition at replacement. Using the proportional hazards model approach, the key condition variables relating to failures were found from among the 19 elements monitored, plus sediment and viscosity. Those key variables were then incorporated into a decision model that provided an unambiguous and optimal recommendation on whether to continue operating a wheel motor or to remove it for overhaul on the basis of data obtained from an oil sample. Wheel motor failure implied extensive planetary gear or sun gear damage necessitating the replacement of one or more major internal components in a general overhaul. The decision model, when triggered by incoming data, provided both a recommendation based on an optimal decision policy as well as an estimate of the unit’s remaining useful life. By optimizing the times of repair as a function both of age and condition data a 20‐30 percent potential savings in overhaul costs over existing practice was identified.

Condition monitoring of slow-speed rolling element bearings using stress waves:

Abstract: Condition monitoring of rolling element bearings through the use of vibration analysis is an established technique for detecting early stages of component degradation. However, this success...

Support vector machines for detection and characterization of rolling element bearing faults

Abstract: Artificial neural networks (ANNs) have been used to detect faults in rotating machinery for a number of years, using statistical estimates of the vibration signal as input features, and they have been shown to be highly successful in this type of application. Support vector machines (SVMs) are a more recent development, and little use has been made of them in the condition monitoring (CM) arena. The availability of a limited amount of training data creates some problems for the use of SVMs, and a strategy is offered that improves the generalization performance significantly in cases where only limited training data are available. This paper examines the performance of both types of classifier in one given scenario—a multiclass fault characterization example.

On-line condition monitoring of induction motors

Abstract: Condition monitoring of induction motors is a process that may be used to great advantage in mining and other industrial applications. The early detection of motor winding deterioration prior to a complete failure provides an opportunity for maintenance to be performed on a scheduled routine without the loss of production time. Presented in this paper is a theoretical and experimental analysis of a voltage mismatch technique that may be used in operating situations to monitor the health of induction motor windings. It extends previous work in this area by demonstrating the robust nature of the monitoring process not only under conditions of power supply unbalance but also in situations where motor construction imperfections exist and mechanical loads are unpredictable. A suggested procedure for application of this condition monitoring process in industrial situations is also included.

An Evaluation of Engine Faults Diagnostics Using Artificial Neural Networks

Abstract: Application of artificial neural network (ANN)-based method to perform engine condition monitoring and fault diagnosis is evaluated. Back-propagation, feedforward neural nets are employed for constructing engine diagnostic networks. Noise-contained training and testing data are generated using an influence coefficient matrix and the data scatters. The results indicate that under high-level noise conditions ANN fault diagnosis can only achieve a 50-60 percent success rate. For situations where sensor scatters are comparable to those of the normal engine operation, the success rates for both four-input and eight-input ANN diagnoses achieve high scores which satisfy the minimum 90 percent requirement. It is surprising to find that the success rate of the four-input diagnosis is almost as good as that of the eight-input. Although the ANN-based method possesses certain capability in resisting the influence of input noise, it is found that a preprocessor that can perform sensor data validation is of paramount importance. Autoassociative neural network (AANN) is introduced to reduce the noise level contained. It is shown that the noise can be greatly filtered to result in a higher success rate of diagnosis. This AANN data validation preprocessor can also serve as an instant trend detector which greatly improves the current smoothing methods in trend detection. It is concluded that ANN-based fault diagnostic method is of great potential for future use. However, further investigations using actual engine data have to be done to validate the present findings.

An effective neuro-fuzzy paradigm for machinery condition health monitoring

Abstract: An innovative neuro-fuzzy network appropriate for fault detection and classification in a machinery condition health monitoring environment is proposed. The network, called an incremental learning fuzzy neural (ILFN) network, uses localized neurons to represent the distributions of the input space and is trained using a one-pass, on-line, and incremental learning algorithm that is fast and can operate in real time. The ILFN network employs a hybrid supervised and unsupervised learning scheme to generate its prototypes. The network is a self-organized structure with the ability to adaptively learn new classes of failure modes and update its parameters continuously while monitoring a system. To demonstrate the feasibility and effectiveness of the proposed network, numerical simulations have been performed using some well-known benchmark data sets, such as the Fisher's Iris data and the Deterding vowel data set. Comparison studies with other well-known classifiers were performed and the ILFN network was found competitive with or even superior to many existing classifiers. The ILFN network was applied on the vibration data known as Westland data set collected from a U.S. Navy CH-46E helicopter test stand, in order to assess its efficiency in machinery condition health monitoring. Using a simple fast Fourier transform (FFT) technique for feature extraction, the ILFN network has shown promising results. With various torque levels for training the network, 100% correct classification was achieved for the same torque Levels of the test data.

Fault Identification in Rotating Machinery Using the Correlation Dimension and Bispectra

Abstract: This paper reports on the application of nonlinear dynamics andhigher-order spectra, with particular regard to the correlationdimension and bispectra in rotating machinery fault identification. Theperformance of the two methods is evaluated from the view of thepractitioners' point. The correlation dimension of nonlinear dynamicalsystem is of value to engineers because it provides an estimation of thenumber of degrees of freedom that an engineering system possesses. Itcan provide some intrinsic information of an underlying dynamic system,and can be used to classify different faults intelligently. Therefore,correlation dimension is helpful for an automatic fault detectionprocedure. Bispectral analysis offers a method for determining thenonlinear coupling and energy exchange between Fourier modes, andexplains the origins of spectra peaks at certain values in the frequencyspectrum. Such frequency domain information is necessary in order toclassify different faults in rotating machinery. Therefore, acombination of correlation dimension and bispectra offer a gooddescription of a nonlinear system. These methods can be complementary toeach other in machinery condition monitoring and fault diagnosis field.

Extended PLS approach for enhanced condition monitoring of industrial processes

Abstract: An extended partial-least squares (EPLS) algorithm is introduced to correct a deficiency of conventional partial least squares (PLS) when used as a tool to detect abnormal operating conditions in industrial processes. In the absence of feedback control, an abnormal operating condition that affects only process response variables will not be propagated back to the process predictor (or input) variables. Thus monitoring tools developed under the conventional PLS framework and based only on the predictor matrix will fail to detect the abnormal condition. The EPLS algorithm described removes this deficiency by defining new scores that are based on both predictor and response variables. The EPLS approach provides two monitoring charts to detect abnormal process behavior, as well as contribution charts to diagnose this behavior. To demonstrate the utility of the new approach, the extended algorithm and monitoring tools are applied to a realistic simulation of a fluid catalytic cracking unit and to a real industrial process that involves a complex chemical reaction.

Condition Assessment of Power Transformer on-Load Tap-Changers Using Wavelet Analysis

Abstract: The operation of a power transformer on-load tap-changer (OLTC) produces a well-defined series of vibration bursts as its signature. Due to the harmonic and nonstationary nature of the transient vibration signal, traditional frequency and time-frequency techniques are on longer effective for characterization of this type of vibration signals, as the localized time domain features, such as delays between bursts, the number of bursts, and the strengths of bursts, are essential for the condition assessment of OLTC. A wavelet transform based technique is developed in this paper to characterize the OLTC vibration signals. This technique gives a simplified format for displaying and representing the essential features of the OLTC vibration signatures. Application results from a selector type OLTC demonstrate that the features extracted in the wavelet domain can be utilized to provide reliable indications of the actual heath of an OLTC.

A decision fusion algorithm for tool wear condition monitoring in drilling

Abstract: Tool wear monitoring of cutting tools is important for the automation of modern manufacturing systems. In this paper, several innovative monitoring methods for on-line tool wear condition monitoring in drilling operations are presented. Drilling is one of the most widely used manufacturing operations and monitoring techniques using measurements of force signals (thrust and torque) and power signals (spindle and servo) are developed in this paper. Two methods using Hidden Markov models, as well as several other methods that directly use force and power data are used to establish the health of a drilling tool in order to avoid catastrophic failure of the drill. In order to increase the reliability of these methods, a decision fusion center algorithm (DFCA) is proposed which combines the outputs of the individual methods to make a global decision about the wear status of the drill. Experimental results demonstrate the effectiveness of the proposed monitoring methods and the DFCA.

Vehicle battery condition monitoring system

Abstract: A method and an apparatus for monitoring a vehicle battery installed on a motor vehicle and indicating the condition of the battery is provided which does not require removal of the battery from the vehicle. Upon initial movement of the ignition key from off to on, open circuit voltage is measured and compared to an allowable range. If open circuit voltage is acceptable, the possibility that polarization is skewing the result is determined, and if the possibility is indicated, a load test is imposed on the engine. Results of testing are maintained as data records to provide updates of the comparison values used for subsequent tests.

Thermography based diagnostics of power equipment

Abstract: Infrared analysis tools and an algorithm to assess the condition of power equipment are demonstrated. Thermographic analysis capabilities and limitations are highlighted, and then the dedicated software toolbox is presented with its features overview. Finally an approach to infrared measurements trending for use in condition monitoring applications is demonstrated. Feasibility of the proposed solution is verified with a case study of an HV disconnector inspection.

Condition Monitoring of Power Transformer On-Load Tap-Changers. Part 1: Automatic Condition Diagnostics

Abstract: Automatic diagnostics for an on-load tap-changer (OLTC) requires a reliable technique that can classify vibration signals measured using an accelerometer mounted on the tank. In the paper, the authors investigate the automatic classification of OLTC vibration signatures using a self-organising map (SOM) and develop a feature extraction procedure that can extract essential features from the original vibration signature. The proposed SOM signature classifier is evaluated with a database established for one type of distribution class OLTC. The application results reveal the practical advantages of SOM for a number of tasks in OLTC condition diagnostics.

Condition monitoring of power transformer on-load tap-changers. Part 2: Detection of ageing from vibration signatures

Abstract: The paper describes a technique for on-line automatic condition assessment of an on-load tap-changer (OLTC) using a self-organising map (SOM). With a condition indicator giving the correct indication of the current condition status, an estimate can be made of the remaining life of the equipment. The condition assessment technique is demonstrated using the signatures collected by on-line monitoring systems installed on selector type OLTCs in distribution substations. Using the real-time fault detection procedure, reliable identification of incipient faults in the equipment can be achieved for the pre-specified false alarming rate.

A multi agent system for monitoring industrial gas turbine start-up sequences

Abstract: This paper introduces a novel technique for the condition monitoring of gas turbine start up sequences. The vast amount of data and the complex processes behind online fault detection indicate the need for an automated solution. A multi agent system that views the problem as the interaction of simple independent software entities, for effective use of the available data, is presented. The overall solution is derived from the combination of partial solutions provided by the components of the multi-agent system. As a consequence, data interpretation is achieved by converting the data into appropriate information and combining individual agents' information, resulting in an automatic fault diagnosis for the engineers. This multi-agent system can employ various intelligent system techniques and has been implemented using the ZEUS Agent building Toolkit.

Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions

Abstract: Dimensional or nondimensional symptom parameters are usually used for condition monitoring of plant machinery. However, it is difficult to extract the most important symptom parameters and the functions of those parameters by which machinery faults can be sensitively detected and the fault types can be precisely distinguished. In order to overcome this difficulty and to ensure highly accurate fault diagnosis, a new method, called "automated function generation of symptom parameters" using genetic algorithms (GA) is presented in this paper. By applying the method to real machinery diagnosis problems, it has been shown that the key symptom parameter function can be quickly generated. We give a diagnosis example of rolling bearings whose operating conditions are variable in terms of rotation speed and load.

A New Cepstral Analysis Procedure of Recovering Excitations for Transient Components of Vibration Signals and Applications to Rotating Machinery Condition Monitoring

Abstract: A new cepstral analysis procedure with the complex cepstrum for recovering excitations causing multiple transient signal components from vibration signals, especially from rotor vibration signals, has been developed. Along with the problem of singularity, a major problem of the cepstrum is that it cannot provide a correct distribution of the excitations. To solve these problems, a signal preprocessing method, whose function is to provide a definition for the distribution of the excitations along the quefrency axis and remove singular points from the transform, has been added to the cepstrum analysis. With this procedure, a correct distribution of the excitations can be obtained. An example of application to the condition monitoring of rotor machinery is also presented.

A Reliability Centered Optimal Visual Inspection Model for Distribution Feeders

Abstract: For an electric power distribution system, highly reliable operation is important for maintaining customer satisfaction. To maintain high levels of system reliability, inspection is used to identify potential problems, allowing necessary maintenance actions to be taken before failure occurs. The question is then how much inspection is required to maintain high reliability levels. This paper describes a Markov model of the inspection process. The model finds the optimal inspection frequency by considering the tradeoff between the cost of inspection and the cost of poor reliability. An objective function is formulated that minimizes the total cost of inspection, repair, and reliability. This model has been specifically created for determining the optimal visual inspection frequency for distribution feeder rights-of-way. The results from applying this model to a practical distribution system are presented, and extensions of this model to other systems are discussed.