Condition monitoring

About: Condition monitoring is a research topic. Over the lifetime, 13911 publications have been published within this topic receiving 201649 citations.

Condition‐based Maintenance Optimization Using Neural Network‐based Health Condition Prediction

Abstract: Artificial neural network (ANN)-based methods have been extensively investigated for equipment health condition prediction. However, effective condition-based maintenance (CBM) optimization methods utilizing ANN prediction information are currently not available due to two key challenges: (i) ANN prediction models typically only give a single remaining life prediction value, and it is hard to quantify the uncertainty associated with the predicted value; (ii) simulation methods are generally used for evaluating the cost of the CBM policies, while more accurate and efficient numerical methods are not available, which is critical for performing CBM optimization. In this paper, we propose a CBM optimization approach based on ANN remaining life prediction information, in which the above-mentioned key challenges are addressed. The CBM policy is defined by a failure probability threshold value. The remaining life prediction uncertainty is estimated based on ANN lifetime prediction errors on the test set during the ANN training and testing processes. A numerical method is developed to evaluate the cost of the proposed CBM policy more accurately and efficiently. Optimization can be performed to find the optimal failure probability threshold value corresponding to the lowest maintenance cost. The effectiveness of the proposed CBM approach is demonstrated using two simulated degradation data sets and a real-world condition monitoring data set collected from pump bearings. The proposed approach is also compared with benchmark maintenance policies and is found to outperform the benchmark policies. The proposed CBM approach can also be adapted to utilize information obtained using other prognostics methods. Copyright © 2012 John Wiley & Sons, Ltd.

An agent-based anomaly detection architecture for condition monitoring

Abstract: Online diagnostics and online condition monitoring are important functions within the operation and maintenance of a power plant. When there is knowledge of the relationships between the raw data and the underlying phenomena within the plant item, typical intelligent system-based interpretation algorithms can be implemented. Increasingly, health data is captured without any underlying knowledge concerning the link between the data and their relationship to physical and electrical phenomena within the plant item. This leads to the requirement for dynamic and learning condition monitoring systems that are able to determine the expected and normal plant behavior over time. This paper describes how multi-agent system technology can be used as the underpinning platform for such condition monitoring systems. This is demonstrated through a prototype multi-agent anomaly detection system applied to a 2.5-MW diesel engine driven alternator system.

A framework for condition monitoring and condition based maintenance

Abstract: This paper discusses a framework for determining appropriate condition based maintenance policy for an industrial system. The framework can be considered as providing practitioners with guidelines for condition based maintenance (CBM) management or as the first step in the development of an expert system for CBM management. The framework proposes that components of the system of interest be classified using multi-dimensional Pareto analysis, with this classification then indicating appropriate maintenance actions. For a particular component, condition based maintenance may then be an appropriate action. In this case, it is proposed that a binary decision tree is used to suggest an appropriate condition based maintenance decision model for the component. Such decision models are briefly reviewed. The ideas in the paper are illustrated throughout using examples from condition based maintenance and maintenance modelling in general.

Online Detection of High-Resistance Connections in the Incoming Electrical Circuit for Induction Motors

Abstract: A high-resistance (R) connection in an induction-motor electrical circuit results in localized overheating and supply-voltage unbalance, which leads to a decreased efficiency and reliability and an increased fire hazard in the electrical distribution system and motor. Therefore, it is important to monitor and correct high-R connections for a reliable, efficient, and safe operation of the industrial facility. This paper focuses on the development of an online technique for detecting poor connections based on monitoring the asymmetry in the voltage and current measurement. The development of the technique begins with the derivation of the dynamic model of an induction motor with high-R connections. Based on the analysis of the model, two approaches for detecting poor contacts using the negative-sequence current and zero-sequence voltage are proposed. In addition to detecting the existence of faults, the location and severity of the fault can also be determined using the proposed method. An experimental study on a 10-hp induction machine under simulated and realistic high-R conditions shows that the proposed techniques provide a simple low-cost solution for reliably detecting poor contact problems at an early stage. It is also shown that the severity and location of the high-R contact fault can be assessed with high accuracy.

Mechanical system monitoring using hidden Markov models

Abstract: A hidden Markov model (HMM)-based approach to mechanical system monitoring is presented. The resulting system is shown to be useful for machining applications with the associated problems of tool wear detection and prediction. The approach is based on continuous density, left-right HMMs that closely match the one-way, fresh-to-worn transition process of machining tools. The Baum-Welch iterative training procedure is modified to incorporate prior knowledge of the transitions between tool wear states. Results presented demonstrate that a multisensor HMM-based system is an effective approach for tool wear detection and prediction. >