Condition Monitoring Applications Research Articles

Using artificial neural network-self-organising map for data clustering of marine engine condition monitoring applications

ABSTRACTCondition monitoring is the process of monitoring parameters expressing machinery condition, interpreting them for the identification of change which could indicate developing faults. Data processing is important in a ship condition monitoring software tool, as misinterpretation of data can significantly affect the accuracy and performance of the predictions made. Data for key performance parameters for a PANAMAX container ship main engine cylinder are clustered using a two-stage approach. Initially, the data is clustered using the artificial neural network (ANN)-self-organising map (SOM) and then the clusters are interclustered using the Euclidean distance metric into groups. The case study results demonstrate the capability of the SOM to monitor the main engine condition by identifying clusters containing data which are diverse compared to data representing normal engine operating conditions. The results obtained can be further expanded for application in diagnostic purposes, identifying faults, their causes and effects to the ship main engine.

Finite Element Modeling and Simulation of Condition Monitoring on Composite Materials Using Piezoelectric Transducers - ANSYS®

In this paper an integrated smart structure approach for condition monitoring application is modelled and simulated using ANSYS®. An array of piezoelectric transducer is embedded within the structure for both actuation and sensing. The Finite Element governing equation is derived by using Hamilton’s principle for the conversion of the mechanical energy of the structure into the electrical energy of the Piezoelectric material. A computational program is applied for investigating the static and dynamic behavior of composite plates with Piezoelectric layers symmetrically bonded to the top and bottom surfaces. Debonding of piezoelectric sensors/actuators can result in significant changes to the static and dynamic responses. A set of numerical simulation is carried out and the results are compared with those from analytical formation in the literature and with ANSYS®17.0. Numerical results demonstrate the performance of the element and the global and local effects of debonding sensor/ actuators on the dynamic response of the adaptive laminate.

Wind turbine dynamics modelling by a bond graph approach

Wind energy is immensely promising source for power generation. Although the prospect of this field is truly reliable, but people are still facing challenges on precisely controlling the turbine due to uncertainty of wind flow, cracks in shaft, structural vibration, wear and tear in bearings and so on. An integrated and impeccable model of the wind turbine system is a momentous way in predicting numerous phenomena and there by enhance the efficacy of the control system in various conditions. Considering those indisputable facts, this research presents a novel horizontal-axis multi-body wind turbine system model based on a bond graph approach. The uniqueness of this wind turbine is to consider roller bearing in multi-body system. Furthermore, bond graph approach reveals two types of models based on the essence of causality where integral and derivative causal system models are obtained. Rigorous mathematical derivations are shown subsequently to support those two possible scenarios with Newtonian and Lagrangian methods that provide new insights in the philosophy of system modelling. Model is validated later by conducting virtual experiment in SOLIDWORKS and comparing results with a literature as well. At the end, model application in machine condition monitoring is emphasized by illustrating a backlash between gear teeth of the wind turbine system.

Energy Autonomous Wireless Valve Leakage Monitoring System With Acoustic Emission Sensor

Industrial internet will improve process control and increase efficiency to maximize industrial output. Key enabling technologies include low-power wireless communication, energy harvesting power autonomous devices along with the latest in sensing devices. This paper presents a wireless sensing system developed for the key industrial application of condition monitoring, specifically; valve leakage detection. The system integrates advances in all of the three aforementioned topics. A novel MEMS-based acoustic emission sensor is described to detect valve leakage manifested as vibrations in certain frequency bands. An in-house developed ultra-low power wake up radio technology, which enables the deployment of this sensor, will be presented. Two energy-harvesting systems: thermal harvesting in the sensor node and an industrial current loop harvester for the base station are developed. Integration and piloting of this system is described and evaluation results presented. The system presented offers a repeatable and adaptable sensor system deployed for valve leakage detection in an ATEX industrial environment.

Self-Sensing Induction Motors for Condition Monitoring

Motors have been exploited as their own sensors for diagnostic and operating conditions at least, since the dawn of modern computing. Contracting systems theory offers a new level of precision in detecting small parameter and state changes in an electric machine for load fault detection and diagnostics from the motor terminals. The presented offline method successfully solves the motor inverse problem to reconstruct the characteristic instantaneous angular speed and load torque signals of the motor during periodic operation. The solution includes a motor parameter estimation step that reflects the specific temperatures and magnetic saturation of the motor during data acquisition. This identification or inversion method is suitable for induction motors driving periodic loads with and without rotor angle-dependent loading. A practical condition monitoring application is demonstrated: valve and cylinder fault detection in reciprocating compressors.

2-Channel Electroencephalography Sensor Frontend for Portable Health Condition Monitoring Applications

2-Channel Electroencephalography Sensor Frontend for Portable Health Condition Monitoring Applications

Methods for wavelet-based autonomous discrimination of multiple partial discharge sources

Recent years have seen increased interest in the application of on-line condition monitoring of medium voltage networks as the need to maintain and operate ageing cable networks increases. Detection and analysis of partial discharge (PD) activity is generally used as an indicator of pre-breakdown processes that may be indicative of insulation degradation over time. A significant challenge for on-line monitoring is discrimination between multiple partial discharge sources that will often naturally exist in the data. To discriminate between PD sources each PD signal is represented as a feature vector and a clustering algorithm is used to identify clusters in the resulting feature vector space, often after dimensional reduction. Each cluster identified in the data corresponds to a distinct PD source. In this work a comparison of clustering algorithms and dimensional reduction techniques is performed to identify clusters for a variety of PD data sets, in all cases the feature vector is created using wavelet decomposition energies. The three clustering algorithms used were Density Based Spatial Clustering of Applications with Noise (DBSCAN), Ordering Points to Identify Clustering Structure (OPTICS) and Simple Statistics-based Near Neighbour clustering technique (SSNN). The two dimensional reduction techniques considered were Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbour Embedding (t-SNE). At present the most commonly used combination of dimensional reduction technique and clustering algorithm for PD data are PCA and DBSCAN respectively. From the comparison performed in this work it was found that t-SNE combined with OPTICS or SsNN were the most successful at clustering PD data. For use in practical situations SSNN is preferred over OPTICS as it requires only a single input parameter, which generally be hardcoded, leading to a completely autonomous technique. It is therefore suggested that a combination of t-SNE and SSNN is particularly appropriate for discriminating PD sources.

Optimized state estimation by application of machine learning

The requirements concerning the technical availability as part of the overall equipment effectiveness increase constantly in production nowadays. Unplanned downtimes have to be prevented via efficient methods. Predictive, condition-based maintenance represents a valuable approach for fulfilling these demands, but precise models for state estimation are missing. From the manufacturers’ point of view the challenge consists in wear models with the capability of specifying the correct component’s state as well as providing reliable failure forecasts. Unfortunately, nowadays creation of wear models is based on specific stress tests or design of experiments from the manufacturer. The integration of the production phase or even data feedback and user knowledge does not take place. New potential is promised by cross-cutting technologies from ICT like cloud technologies—in general virtual platform concepts—or approaches of machine learning as enabling technologies. The objective of this paper is to adopt existing algorithms to the new application of condition monitoring in order to evaluate the applicability for automated training of robust wear models. In that context the most commonly used algorithms are described and the reader gets an impression what challenges have to be met when dealing with machine learning. A selection of about ten algorithms with 45 variants is evaluated for four different features within a packaging machine. In the outlook the embedding of the trained model in a cloud architecture is presented.

Dynamic modeling for rigid rotor bearing systems with a localized defect considering additional deformations at the sharp edges

Rotor bearing systems (RBSs) play a very valuable role for wind turbine gearboxes, aero−engines, high speed spindles, and other rotational machinery. An in−depth understanding of vibrations of the RBSs is very useful for condition monitoring and diagnosis applications of these machines. A new twelve−degree−of−freedom dynamic model for rigid RBSs with a localized defect (LOD) is proposed. This model can formulate the housing support stiffness, interfacial frictional moments including load dependent and load independent components, time−varying displacement excitation caused by a LOD, additional deformations at the sharp edges of the LOD, and lubricating oil film. The time−varying displacement model is determined by a half−sine function. A new method for calculating the additional deformations at the sharp edges of the LOD is analytical derived based on an elastic quarter−space method presented in the literature. The proposed dynamic model is utilized to analyze the influences of the housing support stiffness and LOD sizes on the vibration characteristics of the rigid RBS, which cannot be predicted by the previous dynamic models in the literature. The results show that the presented method can give a new dynamic modeling method for vibration formulation for a rigid RBS with and without the LOD on the races.

An artificial neural network‐based condition monitoring method for wind turbines, with application to the monitoring of the gearbox

AbstractMajor failures in wind turbines are expensive to repair and cause loss of revenue due to long downtime. Condition‐based maintenance, which provides a possibility to reduce maintenance cost, has been made possible because of the successful application of various condition monitoring systems in wind turbines. New methods to improve the condition monitoring system are continuously being developed. Monitoring based on data stored in the supervisory control and data acquisition (SCADA) system in wind turbines has received attention recently. Artificial neural networks (ANNs) have proved to be a powerful tool for SCADA‐based condition monitoring applications. This paper first gives an overview of the most important publications that discuss the application of ANN for condition monitoring in wind turbines. The knowledge from these publications is utilized and developed further with a focus on two areas: the data preprocessing and the data post‐processing. Methods for filtering of data are presented, which ensure that the ANN models are trained on the data representing the true normal operating conditions of the wind turbine. A method to overcome the errors from the ANN models due to discontinuity in SCADA data is presented. Furthermore, a method utilizing the Mahalanobis distance is presented, which improves the anomaly detection by considering the correlation between ANN model errors and the operating condition. Finally, the proposed method is applied to case studies with failures in wind turbine gearboxes. The results of the application illustrate the advantages and limitations of the proposed method. Copyright © 2017 John Wiley & Sons, Ltd.

Scalable prognostic models for large-scale condition monitoring applications

ABSTRACTHigh-value engineering assets are often embedded with numerous sensing technologies that monitor and track their performance. Capturing physical and performance degradation entails the use of various types of sensors that generate massive amounts of multivariate data. Building a prognostic model for such large-scale datasets, however, often presents two key challenges: how to effectively fuse the degradation signals from a large number of sensors and how to make the model scalable to the large data size. To address the two challenges, this article presents a scalable semi-parametric statistical framework specifically designed for synthesizing and combining multistream sensor signals using two signal fusion algorithms developed from functional principal component analysis. Using the algorithms, we identify fused signal features and predict (in near real-time) the remaining lifetime of partially degraded systems using an adaptive functional (log)-location-scale regression modeling framework. We validate the proposed multi-sensor prognostic methodology using numerical and data-driven case studies.

Operational Modal Analysis for Crack Detection in Rotating Blades

Abstract Vibration analysis has found widespread application for condition monitoring in a variety of applications and industries. With the continual development of cheaper and more powerful processing hardware, such systems have developed from utilizing simple checks on amplitude to those based around sophisti- cated spectral analysis. The paper presents application of the model based diagnostic method for early detection of faults in rotating machinery. The proposed diagnostics system based on modal analysis methods (OMA and OMAX methods). In the paper the diagnostic system based on such modelling is presented. The proposed system was verified during research on a specialized test rig, which can generate vibration signals.

Experimental Aspects in the Vibration-Based Condition Monitoring of Large Hydrogenerators

Based on experimental observations on a set of twenty 700 MW hydrogenerators, compiled from several technical reports issued over the last three decades and collected from the reprocessing of the vibration signals recorded during the last commissioning tests, this paper shows that the accurate determination of the journal bearings operating conditions may be a difficult task. It shows that the outsize bearing brackets of large hydrogenerators are subject to substantial dimensional changes caused by external agents, like the generator electromagnetic field and the bearing cooling water temperature. It also shows that the shaft eccentricity of a journal bearing of a healthy large hydrogenerator, operating in steady-state condition, may experience unpredictable, sudden, and significant changes without apparent reasons. Some of these phenomena are reproduced in ordinary commissioning tests or may be noticed even during normal operation, while others are rarely observed or are only detected through special tests. These phenomena modify journal bearings stiffness and damping, changing the hydrogenerator dynamics, creating discrepancies between theoretical predictions and experimental measurements, and making damage detection and diagnostics difficult. Therefore, these phenomena must be analyzed and considered in the application of vibration-based condition monitoring to these rotating machines.

Information Fusion of Conflicting Input Data.

Sensors, and also actuators or external sources such as databases, serve as data sources in order to realise condition monitoring of industrial applications or the acquisition of characteristic parameters like production speed or reject rate. Modern facilities create such a large amount of complex data that a machine operator is unable to comprehend and process the information contained in the data. Thus, information fusion mechanisms gain increasing importance. Besides the management of large amounts of data, further challenges towards the fusion algorithms arise from epistemic uncertainties (incomplete knowledge) in the input signals as well as conflicts between them. These aspects must be considered during information processing to obtain reliable results, which are in accordance with the real world. The analysis of the scientific state of the art shows that current solutions fulfil said requirements at most only partly. This article proposes the multilayered information fusion system MACRO (multilayer attribute-based conflict-reducing observation) employing the μBalTLCS (fuzzified balanced two-layer conflict solving) fusion algorithm to reduce the impact of conflicts on the fusion result. The performance of the contribution is shown by its evaluation in the scope of a machine condition monitoring application under laboratory conditions. Here, the MACRO system yields the best results compared to state-of-the-art fusion mechanisms. The utilised data is published and freely accessible.

Fibre Bragg Grating-Based Cascaded Acoustic Sensors for Potential Marine Structural Condition Monitoring

This paper explores the potential of using multiple fibre Bragg grating-based sensors for acoustic emission (AE) detection, thus offering an effective alternative to conventional piezoelectric (PZT) sensors, especially where they have shown limitations in use, such as in the marine sector. A cascaded fibre optic acoustic sensor system, using optical filter signal demodulation has been developed and its performance extensively evaluated. To undertake this under standardized conditions, the optical sensor system was evaluated using a glass plate to detect the acoustic signal, followed by an evaluation using a metal plate to identify the location of acoustic sources, when subjected to sonotrode excitation, mimicking acoustic detection in cavitation detection. Under these circumstances, very good agreement has been reached between the outputs of the optical acoustic sensors and of the colocated PZT acoustic sensors. This work confirms the utility of these sensors—they can detect not only weak AE signals, but also enable multipoint simultaneous measurement, showing their potential for condition monitoring applications, especially in the marine sector.

Fault identification and severity assessment of rolling element bearings based on EMD and fast kurtogram

Faults in rolling element bearings often cause the breakdown of rotating machinery. Not only the fault type identification but also the fault severity assessment is important. So this paper emphasizes the fault severity assessment. The method proposed in this paper contains two steps: first, identify the fault type based on the combination of empirical mode decomposition (EMD) and fast kurtogram; Second, assess the fault severity. In the first step, the original signal is firstly decomposed into some intrinsic mode functions (IMFs) and the representative IMFs are selected based on correlation analysis, and then the reconstruction signal (RS) is generated; Secondly, the fast kurtogram method is applied to the RS, and the optimum band width and center frequency is obtained. The fault type can be identified based on the fault characteristic frequency marked in the envelope demodulation spectrum. In the second step, the energy percentage of the most fault-related IMF is chosen as an indicator of the fault severity assessment. Experimental data of rolling element bearings inner raceway fault (IRF) with three severities at four running speeds were analyzed. The results show that the IRF identification and fault severity assessment is realized. The breakthrough attempt provides the great potential in the application of condition monitoring of bearings.

Enhanced model of gear transmission dynamics for condition monitoring applications: Effects of torque, friction and bearing clearance

Gear transmissions remain as one of the most complex mechanical systems from the point of view of noise and vibration behavior. Research on gear modeling leading to the obtaining of models capable of accurately reproduce the dynamic behavior of real gear transmissions has spread out the last decades. Most of these models, although useful for design stages, often include simplifications that impede their application for condition monitoring purposes. Trying to filling this gap, the model presented in this paper allows us to simulate gear transmission dynamics including most of these features usually neglected by the state of the art models.This work presents a model capable of considering simultaneously the internal excitations due to the variable meshing stiffness (including the coupling among successive tooth pairs in contact, the non-linearity linked with the contacts between surfaces and the dissipative effects), and those excitations consequence of the bearing variable compliance (including clearances or pre-loads). The model can also simulate gear dynamics in a realistic torque dependent scenario.The proposed model combines a hybrid formulation for calculation of meshing forces with a non-linear variable compliance approach for bearings. Meshing forces are obtained by means of a double approach which combines numerical and analytical aspects. The methodology used provides a detailed description of the meshing forces, allowing their calculation even when gear center distance is modified due to shaft and bearing flexibilities, which are unavoidable in real transmissions. On the other hand, forces at bearing level were obtained considering a variable number of supporting rolling elements, depending on the applied load and clearances. Both formulations have been developed and applied to the simulation of the vibration of a sample transmission, focusing the attention on the transmitted load, friction meshing forces and bearing preloads.

Application of micro-magnetic testing systems for non-destructive analysis of wear progress in case-hardened 16MnCr5 gear wheels

Abstract Micro-magnetic testing methods are qualified for non-destructive quantification of hardness, hardness depth and residual stresses. Among others they are applied for detection of grinding burn in gear wheels, but an application for wear condition monitoring has not yet been published. In this paper, results of initial research of determination of wear condition in gear wheels by application of micro-magnetic testing systems are presented. For comparison of different wear conditions, gears were loaded for increasing numbers of cycles in a test rig based on FVA information sheet 54/7 and DIN ISO 14635 part 1. Operating conditions were altered by usage of different lubricants. Afterwards, wear conditions were determined by conventional techniques, i. e., measuring change in profile and loss of material. Four measurement principles were evaluated for change in micro-magnetic properties determination, magnetic Barkhausen noise analysis, permeability and eddy-current measurements, as well as harmonic analysis of tangential field strength. A general suitability of micro-magnetic testing approach for characterization of wear condition of gear wheels could be demonstrated by comparison of micro-magnetic properties with common wear indicators. Micro-magnetic properties were not solely influenced by wear condition, as the selected oil, and hence the tribochemical conditions in contact also showed a significant effect on measured values. Therefore, further survey is required for direct correlation of micro-magnetic properties with (micro-)structural material changes.

Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model

In a high speed milling operation the cutting tool acts as a backbone of machining process, which requires timely replacement to avoid loss of costly workpiece or machine downtime. To this aim, prognostics is applied for predicting tool wear and estimating its life span to replace the cutting tool before failure. However, the life span of cutting tools varies between minutes or hours, therefore time is critical for tool condition monitoring. Moreover, complex nature of manufacturing process requires models that can accurately predict tool degradation and provide confidence for decisions. In this context, a data-driven connectionist approach is proposed for tool condition monitoring application. In brief, an ensemble of Summation Wavelet-Extreme Learning Machine models is proposed with incremental learning scheme. The proposed approach is validated on cutting force measurements data from Computer Numerical Control machine. Results clearly show the significance of our proposition.

Data Mining In A Vibration Analysis Domain By Extracting Symbolic Rules From Rbf Neural Networks

Neural networks are becoming an increasingly popular technique for modelling data with complex and/or non-linear relationships. Diagnostic systems for condition monitoring applications fall particularly into this category, especially those using spectral vibration data. However, neural networks do have some major disadvantages compared with rule based diagnostic systems. The most important criticism is the lack of any explanation system, which would open up the neural networks internal operation for scrutiny. This paper illustrates how the internal parameters of an RBF network can be converted into symbolic rule format. The rule extraction algorithm and is described in detail