Condition Monitoring Information Research Articles

Performance Reliability Prediction of Complex System Based on the Condition Monitoring Information

Complex system performance reliability prediction is one of the means to understand complex systems reliability level, make maintenance decision, and guarantee the safety of operation. By the use of complex system condition monitoring information and condition monitoring information based on support vector machine, the paper aims to provide an evaluation of the degradation of complex system performance. With degradation assessment results as input variables, the prediction model of reliability is established in Winer random process. Taking the aircraft engine as an example, the effectiveness of the proposed method is verified in the paper.

Operating Reliability Assessment for Aero-engine Based on Condition Monitoring Information

The aero-engine is a pivotal component of an airplane.The operating reliability assessment of the aero-engine is greatly meaningful in guaranteeing the flight safety.In practice,operating conditions of the aero-engines vary.It leads to that degradation degrees and failure times for different aero-engines are with great degrees of discreteness.Aiming at solving the problem that reliability assessment methods based on probability statistical analysis are inappropriate to assess the reliability of the individual aero-engine,a novel method using the condition monitoring information is proposed.The condition subspace of the aero-engine is constructed by utilizing the Kernel principal component analysis(KPCA) to describe the performance change of the aero-engine.The principal angles between the subspaces from the normal state and the damage state are calculated.The principal angles are transformed into operating reliability index by a proper mapping function.The proposed method is validated by using both the aero-engine run-to-failure data shared by National Aeronautics and Space Administration and the practical test data from a repair factory of aero-plane.The results illustrate the proposed method can assess the operating reliability of the aero-plane reasonably.It also offers valid approach for the operating reliability assessment of the aero-plane whose failure model subjects to small sample characteristics.

Failure probability prediction based on condition monitoring data of wind energy systems for spare parts supply

The feasibility of maintenance processes relies on the availability of spare parts. Spare part inventory planning is capital intensive. It is based on demand forecasting, which possesses a high potential in reducing inventories. Even if condition monitoring systems are installed in technical systems, condition monitoring information is barely used to predict the failure probability of units. Therefore, an enhanced forecast model, which integrates SCADA information, has been developed. This leads to more accurate spare part demand forecasts. The approach presented in the paper is based on data mining, the proportional hazards model (PHM) and a binomial distribution. It has been validated with maintenance data of wind energy systems.

Operation Reliability Assessment for Cutting Tools by Applying a Proportional Covariate Model to Condition Monitoring Information

The reliability of cutting tools is critical to machining precision and production efficiency. The conventional statistic-based reliability assessment method aims at providing a general and overall estimation of reliability for a large population of identical units under given and fixed conditions. However, it has limited effectiveness in depicting the operational characteristics of a cutting tool. To overcome this limitation, this paper proposes an approach to assess the operation reliability of cutting tools. A proportional covariate model is introduced to construct the relationship between operation reliability and condition monitoring information. The wavelet packet transform and an improved distance evaluation technique are used to extract sensitive features from vibration signals, and a covariate function is constructed based on the proportional covariate model. Ultimately, the failure rate function of the cutting tool being assessed is calculated using the baseline covariate function obtained from a small sample of historical data. Experimental results and a comparative study show that the proposed method is effective for assessing the operation reliability of cutting tools.

Estimating Mean Residual Life for a Case Study of Rail Wagon Bearings

This paper develops a prognostics model to estimate the Mean Residual Life of Rail Wagon Bearings within certain confidence intervals. The prognostics model is constructed using a Proportional Hazards approach, informed by imperfect data from a bearing acoustic monitoring system, and a failure database. The model supports prediction within a defined maintenance planning window from the time of receipt of the latest acoustic condition monitoring information. We use the model to decide whether to replace a bearing, or leave it until collection of the next condition monitoring indicators. The model is tested on a limited number of cases, and demonstrates good predictive capability. Opportunities to improve the performance of the model are identified, and the processes necessary and time required to build the model are described. Lessons learned from dealing with real field data will assist those interested in using prognostics to support maintenance planning activities.

Joint decision making for maintenance and production scheduling of production systems

Deteriorated equipment has a significant impact on the product quality and maintenance policies. In this paper, we present a decision-making architecture to determine maintenance and product dispatching policies based on condition-monitoring information and the relationship between machine degradation and associated product quality. We use a Markov decision process for the long-term decision making and integer programming for the short-term decision making with a multi-product, multi-station system. We demonstrate the advantage of the proposed approach by comparing the proposed policy with traditional decision-making approaches. Furthermore, we illustrate the improvement of the proposed policy over the current usage-based maintenance policy with a semiconductor manufacturing process application.

An investigation of the acoustic characteristics of a compression ignition engine operating with biodiesel blends

In this paper, an experimental investigation has been carried out on the acoustic characteristics of a compression ignition (CI) engine running with biodiesel blends under steady state operating conditions. The experiment was conducted on a four-cylinder, four-stroke, direct injection and turbocharged diesel engine which runs with biodiesel (B50 and B100) and pure diesel. The signals of acoustic, vibration and in-cylinder pressure were measured during the experiment. To correlate the combustion process and the acoustic characteristics, both phenomena have been investigated. The acoustic analysis resulted in the sound level being increased with increasing of engine loads and speeds as well as the sound characteristics being closely correlated to the combustion process. However, acoustic signals are highly sensitive to the ambient conditions and intrusive background noise. Therefore, the spectral subtraction was employed to minimize the effects of background noise in order to enhance the signal to noise ratio. In addition, the acoustic characteristics of CI engine running with different fuels (biodiesel blends and diesel) was analysed for comparison. The results show that the sound energy level of acoustic signals is slightly higher when the engine fuelled by biodiesel and its blends than that of fuelled by normal diesel. Hence, the acoustic characteristics of the CI engine will have useful information for engine condition monitoring and fuel content estimation.

A parameter estimation method for a condition-monitored device under multi-state deterioration

The overall performance of a mechanical device under random shocks, fatigue, and gradual degradation may continuously deteriorate over time, leading to multi-state health conditions. This deterioration can be represented by a continuous-time degradation process – with multiple discrete states – that reflects the relative degree of deterioration. This paper focuses on a condition-monitored device with multi-state deterioration, where its degradation state is not directly observable and only incomplete information is available through condition monitoring. After modeling this multi-state device, an unsupervised parameter estimation method is developed, which employs historical condition monitoring information to estimate the unknown characteristic parameters of the degradation process and the observation process. The results are evaluated through numerical experiments.

A New Method of Reliability Evaluation Based on Wavelet Information Entropy for Equipment Condition Identification

Aiming at reliability evaluation of condition identification of mechanical equipment, it is necessary to analyze condition monitoring information. A new method of reliability evaluation based on wavelet information entropy extracted from vibration signals of mechanical equipment is proposed. The method is quite different from traditional reliability evaluation models that are dependent on probability statistics analysis of large number sample data. The vibration signals of mechanical equipment were analyzed by means of second generation wavelet package (SGWP). We take relative energy in each frequency band of decomposed signal that equals a percentage of the whole signal energy as probability. Normalized information entropy (IE) is obtained based on the relative energy to describe uncertainty of a system instead of probability. The reliability degree is transformed by the normalized wavelet information entropy. A successful application has been achieved to evaluate the assembled quality reliability for a kind of dismountable disk-drum aero-engine. The reliability degree indicates the assembled quality satisfactorily.

Wind turbine SCADA alarm analysis for improving reliability

ABSTRACTPrevious research for detecting incipient wind turbine failures, using condition monitoring algorithms, concentrated on wind turbine Supervisory Control and Data Acquisition (SCADA) signals, such as power output, wind speed and bearing temperatures, using power‐curve and temperature relationships. However, very little research effort has been made on wind turbine SCADA alarms. When wind turbines are operating in significantly sized wind farms, these alarm triggers are overwhelming for operators or maintainers alike because of large number occurring in a 10 min SCADA period. This paper considers these alarms originating in two large populations of modern onshore wind turbines over a period of 1–2 years. First, an analysis is made on where the alarms originate. Second, a methodology for prioritizing the alarms is adopted from an oil and gas industry standard to show the seriousness of the alarm data volume. Third, two methods of alarm analysis, time‐sequence and probability‐based, are proposed and demonstrated on the data from one of the wind turbine populations, considering pitch and converter systems with known faults. The results of this work show that alarm data require relatively little storage yet provide rich condition monitoring information. Both the time‐sequence and probability‐based analysis methods have the potential to rationalize and reduce alarm data, providing valuable fault detection, diagnosis and prognosis from the conditions under which the alarms are generated. These methods should be developed and integrated into an intelligent alarm handling system for wind farms, aimed at improving wind turbine reliability to reduce downtime, increase availability and leading to a well‐organized maintenance schedule. Copyright © 2011 John Wiley & Sons, Ltd.

A Bayesian Inventory Model Using Real‐Time Condition Monitoring Information

Lack of coordination between machinery fault diagnosis and inventory management for spare parts can lead to increased inventory costs and disruptions in production activity. We develop a framework for incorporating real‐time condition monitoring information into inventory decisions for spare parts. We consider a manufacturer who periodically replenishes inventory for a machine part that is subject to deterioration. The deterioration is captured via condition monitoring and modeled using a Wiener process. The resulting degradation model is used to derive the life distribution of a functioning part and to estimate the demand distribution for spare parts. This estimation is periodically updated, in a Bayesian manner, as additional information on part deterioration is obtained. We develop an inventory model that incorporates this updated demand distribution and demonstrate that a dynamic base‐stock policy, in which the optimal base‐stock level is a function of some subset of the observed condition monitoring information, is optimal. We propose a myopic critical fractile policy that captures the essence of the optimal policy, but is easier to compute. Computational experiments indicate that this heuristic performs quite well relative to the optimal policy. Adaptive inventory policies such as these can help manufacturers to increase machine availability and reduce inventory costs.

Time–frequency signal analysis for gearbox fault diagnosis using a generalized synchrosqueezing transform

The vibration data, especially those collected during the system run-up and run-down periods, contain rich information for gearbox condition monitoring. Time–frequency (TF) signal analysis is an effective tool to detect gearbox faults under varying shaft speed. However, the feature of the amplitude modulated–frequency modulated (AM–FM) gearbox fault signal usually cannot be directly extracted from the blurred time–frequency representation (TFR) caused by the time-varying frequency and noisy multicomponent measurement. As such, we propose to use a generalized synchrosqueezing transform (GST)-based TF method to detect and diagnose gearbox faults. With this method, the original vibration signal is first mapped into another analytical signal to facilitate synchrosqueezing of the TF picture. A time-scale domain restoration process is then applied to recover the instantaneous frequency profile with concentrated TFR. The gearbox fault, if any, can then be detected by observing the presence of the meshing frequency and sideband components in the TFR. The faulty gear can be identified via frequency relation analysis of AM–FM components. The proposed method is evaluated using both simulated and experimental gearbox vibration signals. The results show that the proposed approach is effective for gearbox condition monitoring.

Cutting tool wear monitoring for reliability analysis using proportional hazards model

Aiming at operational reliability analysis and assessment based on condition monitoring information, a methodology of reliability modeling and assessment based on feature extraction from cutting tool vibration signals using proportional hazards model is proposed in this paper. Root mean square and peak of time domain index from vibration signals, which are closely related to cutting tool wear degradation states, are selected as covariates introduced to proportional hazards model for the cutting tool wear reliability analysis. The proposed approach shows considerable advantages of establishing significant association relationship between the cutting tool condition monitoring information and the life distribution of cutting tool wear. It is appropriate to provide individual cutting tool operational reliability assessment effectively. The experimental study on a CNC lathe turning process is given to validate the effectiveness of the proposed method. The results show that the approach is desirable and gives a good estimation of the reliability for cutting tool wear degradation states.

Overview of a semi-stochastic filtering approach for residual life estimation with applications in condition based maintenance

Maintenance policies include break-down-based maintenance, time-based maintenance, and condition-based maintenance. The advances in condition monitoring techniques have made condition-based maintenance a popular and increasingly important choice. With the increased use of condition monitoring information, there is obviously a need for appropriate decision support in plant maintenance planning utilizing available condition monitoring information. However, compared with the extensive literature on diagnosis, relatively little research has been done on the prognosis side of condition-based maintenance. In plant prognosis, a key, but often uncertain, quantity to be modelled is the residual life prediction based on available condition information to date. This paper overviews a semi-stochastic filtering-based residual life prediction approach for the monitored items in condition-based maintenance and introduces the associated applications. First the role of residual life prediction in condition-based maintenance decision making is demonstrated, which highlights the need for such a prediction. Then a detailed discussion is presented of the semi-stochastic filtering models developed for residual life prediction, the extensions made, and the case applications applied to. Finally the results of a comparative study between the semi-stochastic filtering based model and another popular model using empirical data are briefly given. The results show that the filtering-based approach is better in terms of prediction accuracy and cost effectiveness.

In This Issue

In This Issue

Wireless Sensor Failure Identification Technology for Thermal Monitoring System of NC Machine Tools Based on Bayesian Networks

Wireless sensors are increasingly adopted in mechanical systems to acquire and wirelessly transmit sensed information for machine condition monitoring. For wireless sensors on spindle, the reliability of the sensors system at high rotary speed is the key factor to guarantee the validity of monitoring. How to identify sensor failure accurately and timely is essential to enhance reliability of monitoring system. To address this issue, a novel method based on the BNs was presented to distinguish sensor failure from other transmission errors. The method described causal relationships of factors inducing sensor failure by graph theory and deduced sensor failure by Bayesian statistical techniques. Experiments carried on NC machining center prove the validity of this approach.

An approximate algorithm for prognostic modelling using condition monitoring information

Established condition based maintenance modelling techniques can be computationally expensive. In this paper we propose an approximate methodology using extended Kalman-filtering and condition monitoring information to recursively establish a conditional probability density function for the residual life of a component. The conditional density is then used in the construction of a maintenance/replacement decision model. The advantages of the methodology, when compared with alternative approaches, are the direct use of the often multi-dimensional condition monitoring data and the on-line automation opportunity provided by the computational efficiency of the model that potentially enables the simultaneous condition monitoring and associated inference for a large number of components and monitored variables. The methodology is applied to a vibration monitoring scenario and compared with alternative models using the case data.

Condition based maintenance optimization for multi-component systems using proportional hazards model

The objective of condition based maintenance (CBM) is typically to determine an optimal maintenance policy to minimize the overall maintenance cost based on condition monitoring information. The existing work reported in the literature only focuses on determining the optimal CBM policy for a single unit. In this paper, we investigate CBM of multi-component systems, where economic dependency exists among different components subject to condition monitoring. The fixed preventive replacement cost, such as sending a maintenance team to the site, is incurred once a preventive replacement is performed on one component. As a result, it would be more economical to preventively replace multiple components at the same time. In this work, we propose a multi-component system CBM policy based on proportional hazards model (PHM). The cost evaluation of such a CBM policy becomes much more complex when we extend the PHM based CBM policy from a single unit to a multi-component system. A numerical algorithm is developed in this paper for the exact cost evaluation of the PHM based multi-component CBM policy. Examples using real-world condition monitoring data are provided to demonstrate the proposed methods.

A periodic inspection and replacement policy for systems subject to competing failure modes due to degradation and traumatic events

This paper deals with the condition-based maintenance of single-unit systems which are subject to the competing and dependent failures due deterioration and traumatic shock events. The main aim is to provide a model to assess the value of condition monitoring information for the maintenance decision-making. A condition-based periodic inspection/replacement policy is developed and compared with a benchmark time-based block replacement policy. Numerical results show that it is indeed useful to follow closely the actual evolution of the system to adapt the maintenance decisions to the true system state to improve the performance of maintenance policies. The analysis of the maintenance costs savings can be used to justify or not the choice to implement a policy based on condition monitoring information and to invest in condition monitoring devices.

Condition based maintenance optimization for wind power generation systems under continuous monitoring

By utilizing condition monitoring information collected from wind turbine components, condition based maintenance (CBM) strategy can be used to reduce the operation and maintenance costs of wind power generation systems. The existing CBM methods for wind power generation systems deal with wind turbine components separately, that is, maintenance decisions are made on individual components, rather than the whole system. However, a wind farm generally consists of multiple wind turbines, and each wind turbine has multiple components including main bearing, gearbox, generator, etc. There are economic dependencies among wind turbines and their components. That is, once a maintenance team is sent to the wind farm, it may be more economical to take the opportunity to maintain multiple turbines, and when a turbine is stopped for maintenance, it may be more cost-effective to simultaneously replace multiple components which show relatively high risks. In this paper, we develop an optimal CBM solution to the above-mentioned issues. The proposed maintenance policy is defined by two failure probability threshold values at the wind turbine level. Based on the condition monitoring and prognostics information, the failure probability values at the component and the turbine levels can be calculated, and the optimal CBM decisions can be made accordingly. A simulation method is developed to evaluate the cost of the CBM policy. A numerical example is provided to illustrate the proposed CBM approach. A comparative study based on commonly used constant-interval maintenance policy demonstrates the advantage of the proposed CBM approach in reducing the maintenance cost.