Development Of Condition Monitoring Research Articles

A framework for the practical development of condition monitoring systems with application to the roller compactor

Implementing a condition-based maintenance strategy requires an effective condition monitoring (CM) system that can be complicated to develop and even harder to maintain. In this paper, we review the main complexities of developing condition monitoring systems and introduce a four-stage framework that can address some of these difficulties. The framework achieves this by first using process knowledge to create a representation of the process condition. This representation can be broken down into simpler modules, allowing existing monitoring systems to be mapped to their corresponding module. Data-driven models such as machine learning models could then be used to train the modules that do not have existing CM systems. Even though data-driven models tend to not perform well with limited data, which is commonly the case in the early stages of pharmaceutical process development, application of this framework to a pharmaceutical roller compaction unit shows that the machine learning models trained on the simpler modules can make accurate predictions with novel fault detection capabilities. This is attributed to the incorporation of process knowledge to distill the process signals to the most important ones vis-à-vis the faults under consideration. Furthermore, the framework allows the holistic integration of these modular CM systems, which further extend their individual capabilities by maintaining process visibility during sensor maintenance.

Detection and Diagnostic with Random Forest Classifier (RFC) to Improve the Maintenance Management System in Steam Boiler of Power Plant

Industrial internet of things (IIoT), digital twin, and connected devices can continue to use smart equipment and improve access to data. While the data collected by sensors has been an invaluable asset to companies, the ability to understand and use this data to drive new insights. The development of Condition Monitoring (CM) technology and Computerized Maintenance Management System (CMMS) in power generation systems provides a validated set of operation and maintenance data with abundant event data. Maintenance decision-making is primarily based on equipment reliability and performance-based features for diagnosing equipment failure. The most critical asset and often reduces the reliability and availability of a Coal Fired Steam Power Plant (CFSPP) with the most frequency of disturbances is the steam boiler. As a departure from the idea of creating a digital twin, this article will focus on analyzing equipment health conditions and finding causes of failure of the tools, utilizing data for diagnostic purposes. Real-case used in this research are steam boilers, which are important assets in power plant generation. The online and Failure Mode and Effect Analysis (FMEA) module data will be combined to realize the concept of anomaly diagnosis which is driven by hybrid data. Hoping that accurate diagnosis result with the Random Forest Classifier (RFC) Algorithm can be obtained and be used to analyze the causes of failure and decrease in equipment performance resulting by a decrease of energy efficiency performance. The analytical approaches are carried out to have the goal of generating detection models and diagnostic insights of event data based on operational data and FMEA.

Exploring the Current Status and Development of Condition Monitoring and Fault Diagnosis for Power Machinery of Engineering Ships

With the continuous progress of science and technology, modern engineering ships are also moving towards large-scale and high-speed development. Due to the fact that the power propulsion system is one of the most important parts of the entire ship, its operational status will directly affect navigation safety and operational efficiency, etc. Therefore, real-time monitoring of it is of great significance. Based on this, this article mainly explores the current status and development trends of condition monitoring and fault diagnosis of engineering ship power machinery, aiming to enable technical personnel to quickly and better grasp and apply these advanced technologies, and promote the healthy and sustainable development of China's shipbuilding industry.

Fault detection of wind turbines using SCADA data and genetic algorithm-based ensemble learning

Due to global efforts to reduce the rise in the average global temperature by replacing fossil fuels, the amount of wind power installed worldwide is continuously increasing. The costs associated with running and maintaining wind farms make up a significant portion of the Levelized cost of wind energy. The main piece of equipment in a wind farm is a wind turbine (WT), and how well it functions safely and profitably depends heavily on its reliability. Early detection of WT faults can significantly lower the cost of wind farm maintenance. Fault detection is, therefore, essential for WTs to carry out. Supervisory control and data acquisition (SCADA) based approaches have significant advantages for developing condition monitoring systems for WTs. In this article, we have used genetic algorithm-based ensemble learning for anomaly detection of wind turbines using SCADA data. The proposed ensemble method consists of XGBoost, a random forest, and an extra tree model. XGBoost is used as a meta-model. A genetic algorithm is used for the selection of optimal features. A threshold is applied, and anomalies in the records are discovered where the RMSE is higher than the threshold. We have used several evaluation metrics to evaluate the performance of the proposed model. The proposed model’s mean absolute percentage error (MAPE) is 0.83%. We have also compared our proposed model with state-of-the-art machine learning algorithms.

An Entropy-Based Condition Monitoring Strategy for the Detection and Classification of Wear Levels in Gearboxes.

Gears are reliable and robust elements that are found in any power transmission system. However, gears are prone to present incipient faults, such as wear, since they are constantly subjected to contact forces. Due to gears playing a key role in many industrial processes, it is important to develop condition monitoring strategies that ensure the proper functioning of the related power transmission system and the overall components. In this regard, the data on entropy provide relevant information that allow us to identify and quantify the effect of different wear levels in gears. Therefore, in this work, we proposed the use of seven entropy-related features to perform the identification of different wear severities in a gearbox. The novelty of this proposal lies in the use of the entropy features to carry out a high-performance characterization of the available vibration signals that are acquired from experimental tests. The novelty of this proposal lies in the fusion of three different techniques: entropy features, linear discriminant analysis, and artificial neural networks to obtain a machine learning approach for improving the detection of different wear severities in gears compared to other reported methodologies. This situation is achieved due to the high-performance characterization of the available vibration signals that are acquired from experimental tests. Additionally, the entropy features are subjected to a feature space transformation by means of linear discriminant analysis to obtain a 2D representation and, finally, the set of features extracted by linear discriminant analysis are used as inputs of a neural network-based classifier to determine the severity of wear that is present in the gears. The proposed methodology is validated and compared with a conventional statistical approach to show the improvement in the classification.

Gate Oxide Degradation Condition Monitoring Technique for High-Frequency Applications of Silicon Carbide Power MOSFETs

Gate oxide degradation, which considerably affects turn- <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">on</small> /- <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">off</small> dynamics of the switch, embraces a large percentage of chip-related failure modes both in silicon and silicon carbide power MOSFETs. The gate oxide layer is thinner in silicon carbide power MOSFETs in comparison to their silicon-based counterparts. Consequently, the problem of gate oxide degradation has become a more crucial impediment in achieving reliable performance in silicon carbide power MOSFETs. This problem is even more severe in high-frequency applications due to higher EMI signature and complicated and costly measurement. In this article, a reliable fully analog cost-effective gate oxide degradation condition monitoring technique is proposed and validated. High-order harmonics magnitudes of drain–source voltage are used to produce a dc signal as the aging precursor of the gate oxide region. Using a dedicated degradation setup, the credibility of the developed condition monitoring technique was examined at different rates of gate oxide degradation for 650-V/22-A silicon carbide discrete MOSFET. In 200-kHz, 217-V switch operation, the proposed precursor showed 68% change in comparison to its initial value. This brings a high-resolution assessment on the reliability level of the switch gate oxide region.

Automatic fault detection system for mining conveyor using distributed acoustic sensor

Condition monitoring of mining conveyor is a highly essential task to ensure minimum disruption to the mining operational system. Failure of one or more conveyor components can result in significant operational downtime, economic loss, and safety risks. The current monitoring method still involves subjective measure from maintenance engineers, where at some cases, fault can be left undetected and leads into site incident. Therefore, there is a high demand for real-time condition monitoring technology to detect early fault on conveyor. In this study, the effective application of distributed optical fibre sensor (DOFS) was explored for long distance real-time condition monitoring of mining conveyor. The fault detection framework was developed by integrating and modifying the Isolation Forest algorithm to analyse optical signals for effective detection of defective idlers. Further, the optical signal was analysed to extract the damage progression of defective idler with time and space. The results were used to classify various levels of damage and to set appropriate damage thresholds. Also, software interface, that can be used to set the sensing parameters, to collect, analyse, and visualise the signal in real-time, was developed. Finally, the developed condition monitoring system was used to monitor a 1.6 km long section of a conveyor structure in Western Australia for a period of 10 months. The results and findings from the field monitoring were presented together with automated fault detection framework for condition monitoring of mining conveyor.

Investigation of defects in roll contacts of machine elements with Acoustic Emission and Unsupervised Machine Learning

In the age of Industry 4.0 and IIoT machines are becoming increasingly connected enabling continuous monitoring. A variety of information from machines and installed sensors is used to develop condition monitoring solutions. These systems are used to prevent premature failures and the follow-up costs due to machine downtime associated with them. Recent research in this area applies supervised machine learning, extracting features from captured signals and training classifiers. Supervised learning approaches require large amounts of labeled data, whose generation is time consuming and requires domain knowledge. For this reason, an unsupervised learning approach is being used in this work to distinguish between different defect and operation states of axial ball bearings. Within the scope of this work, acoustic emission (AE) measurements in the ultrasonic range are recorded and evaluated. Artificial defects are seeded in the rolling contact of axial bearings. From the AE signals a selection of state-of-the-art features is extracted. Then, the Laplacian Score, an unsupervised filter algorithm, is used to select the most significant features. Subsequently, the DBSCAN clustering algorithm is used to draw conclusions about the existing damage.

Intelligent Starting Current-Based Fault Identification of an Induction Motor Operating under Various Power Quality Issues

Since most of our industries use induction motors, it is essential to develop condition monitoring systems. Nowadays, industries have power quality issues such as sag, swell, harmonics, and transients. Thus, a condition monitoring system should have the ability to detect various faults, even in the presence of power quality issues. Most of the fault diagnosis and condition monitoring methods proposed earlier misidentified the faults and caused the condition monitoring system to fail because of misclassification due to power quality. The proposed method uses power quality data along with starting current data to identify the broken rotor bar and bearing fault in induction motors. The discrete wavelet transform (DWT) is used to decompose the current waveform, and then different features such as mean, standard deviation, entropy, and norm are calculated. The neural network (NN) classifier is used for classifying the faults and for analyzing the classification accuracy for various cases. The classification accuracy is 96.7% while considering power quality issues, whereas in a typical case, it is 93.3%. The proposed methodology is suitable for hardware implementation, which merges mean, standard deviation, entropy, and norm with the consideration of power quality issues, and the trained NN proves stable in the detection of the rotor and bearing faults.

Fault severity detection of a worm gearbox based on several feature extraction methods through a developed condition monitoring system

This study presents the severity detection of pitting faults on worm gearbox through the assessment of fault features extracted from the gearbox vibration data. Fault severity assessment on worm gearbox is conducted by the developed condition monitoring instrument with observing not only traditional but also multidisciplinary features. It is well known that the sliding motion between the worm gear and wheel gear causes difficulties about fault detection on worm gearboxes. Therefore, continuous monitoring and observation of different types of fault features are very important, especially for worm gearboxes. Therefore, in this study, time-domain statistics, the features of evaluated vibration analysis method and Poincaré plot are examined for fault severity detection on worm gearbox. The most reliable features for fault detection on worm gearbox are determined via the parallel coordinate plot. The abnormality detection during worm gearbox operation with the developed system is performed successfully by means of a decision tree.

The specification and testing of a Horizontal Axis Tidal Turbine Rotor Monitoring approach

The sustainable deployment of Horizontal Axis Tidal Turbines will require effective management and maintenance functions. In part, these can be supported by the engineering of suitable condition monitoring systems. The development of such a system is inevitably challenging, particularly given the present limited level of operational data associated with installed turbines during fault onset. To mitigate this limitation, a computational fluid dynamics model is used to simulate the operational response of a turbine under a known set of fault conditions. Turbine rotor imbalance faults were simulated by the introduction of increasing levels of pitch angle offset for a single turbine blade. The effects of these fault cases upon cyclic variations in the torque developed by the turbine rotor were then used to aid creation of a condition monitoring approach. A parametric tidal turbine rotor model was developed based on the outputs of the computational fluid dynamics models. The model was used to facilitate testing of the condition monitoring approach under a variety of more realistic conditions. The condition monitoring approach showed good performance in fault detection and diagnosis for simulations relating to turbulence intensities of up to 2 %. Finally, the condition monitoring approach was applied to simulations of 10 % turbulence intensity. Under the 10 % turbulence intensity case the rotor monitoring approach was successfully demonstrated in its use for fault detection. The paper closes with discussion of the effectiveness of using computational fluid dynamics simulations extended by parametric models to develop condition monitoring systems for horizontal axis tidal turbine applications.

Model reduction based on sparse identification techniques for induction machines: Towards the real time and accuracy-guaranteed simulation of faulty induction machines

The development of condition monitoring (CM) systems of induction machines (IMs) is essential for the industry because the early fault detection would help engineers to optimise maintenance plans. However, the use of several IMs to test and validate the fault diagnosis methods developed requires also costly test benches that, anyway, often face limitations in the range of faults and operating conditions to be tested. To avoid it, the use of accurate models such as those based on finite element method (FEM) would reduce the major drawbacks of test benches but their inability to execute FEM models in real time largely reduces their application in the development of on-line continuous monitoring systems. To alleviate this problem a hybrid FEM-analytical model has been proposed. It uses an analytical model that can be run in real-time in a hardware in the loop (HIL) system, after its parameters have been computed through FEM simulations. In this way, the proposed model provides high accuracy but at the cost of long simulation times and high computational costs (both computing power and memory resources) to compute the IM parameters. This work aims at reducing these drawbacks. In particular, a model based on sparse identification techniques is proposed. The method balances complexity and accuracy by selecting a sparse model that reduces the number of FEM simulations to accurately compute the coupling parameters of an IM model with different fault severity degrees. Particularly, the proposed methodology has been applied to develop models with abnormal eccentricity levels as this fault is related to development of mechanical faults that produce most of IM breakdowns.

Condition Monitoring System and Faults Detection for Impedance Bonds from Railway Infrastructure

Nowadays, sensors and condition monitoring systems are expanding rapidly and becoming cheaper. This contributes to increasing developments in condition monitoring in railway transport infrastructure. A condition monitoring system that uses an online device and sensors to acquire electrical parameters from railway infrastructure has been developed and applied for fault detection and diagnosis of impedance bonds. The impedance bond condition is monitored in real-time using current and temperature sensors, providing early warning if predefined thresholds are exceeded in terms of currents, imbalance currents, and temperatures. The proposed method and the developed monitoring device have been validated in the railway laboratory to confirm its capability to detect defects. The acquired parameters from impedance bonds are used to extract thermal stresses and technical conditions of this equipment. Experimental results and appropriate data analysis are included in the article.

사물인터넷 기반 무선 상태 모니터링 시스템 개발

With the advancements in sensor technology and open source-based controllers, the development of a condition monitoring system has become relatively easier. However, there is not enough well-organized information to develop condition monitoring system. Therefore, we present a wireless condition monitoring system based on the Internet of Things (IoT) by using an open-source controller. The developed wireless condition monitoring system consists of a sensor module, data processing unit, and condition monitoring program. This system can measure 3-axis accelerations of frequency up to 1.5 kHz, with a frequency resolution of 0.05 Hz to 20 Hz, and temperature. The developed condition monitoring system provides statistical time information and frequency spectrum for advanced condition diagnosis. Furthermore, the condition diagnosis function for low-speed rotating machines was implemented effectively.

Study of Oil Starvation in Journal Bearing Using Acoustic Emission and Vibration Measurement Techniques

Abstract This present article evaluates the state of starvation in a journal bearing using acoustic emission (AE) and vibration measurement techniques. A journal bearing requires a constant supply of oil in an adequate amount to develop a hydrodynamic film, thick enough to separate the surfaces and avoid asperity contacts. On a microscopic level, the surface interaction under starved lubrication results in deformation and fracture of asperities. This causes a proportionate increase in AE and vibration. The AE activities resulting from asperities interaction have significant energy in the frequency range of 100–400 kHz with peak frequencies in the range of 224–283 kHz. Further, the peak frequency shifts from the higher to lower side as the asperity interaction transits from the elastic to plastic contact. This information derived from the spectral analysis of AE signals can be used to develop condition monitoring parameters to proactively control the lubrication and prevent bearing failure.

Predicting Temperature Profile on the Surface of a Switched Reluctance Motor Using a Fast and Accurate Magneto-Thermal Model

In this article, a simplified 3D magneto-thermal model to study the temperature distribution over the housing of a Switched Reluctance Machine (SRM) is proposed. The main objective of such model is to study the temperature distribution profile on the body of the machine under various working conditions in order to introduce a temperature based signature to develop condition monitoring procedures. The analysis of fluid flow and heat transfer inside the SRM supports the hypothesis that the effect of turbulent flow of the fluid and the complex heat transfer phenomenon of the rotating parts can be simplified to a heat flux boundary condition representation of the heat loss. The accuracy of the model is validated through simulation and experimental results on a prototype SRM. The developed simplified model can be used as for prediction of temperature profile on SRM surface, well suited for fault diagnosis in SRM. The proposed methodology can be modified applied in developing a thermal model for other types of electric machines.

Uncertainty quantification in deep convolutional neural network diagnostics of journal bearings with ovalization fault

Bearings play a crucial role in machine longevity and is, at the same time, one of the most critical sources of failure in rotor dynamics. Particularly for journal bearings, it is not completely understood how specific damages may influence the response of the rotating system. Consequently, the identification of hydrodynamic bearing faults is challenging. Most of the literature relies on large amounts of training data collections from physical experiments or from the field, which are high in cost. This paper offers a deep learning approach to identify ovalization faults aiming to develop condition monitoring model-based strategies applied to hydrodynamic journal bearings. Therefore, a numerical model was developed to simulate the ovalization fault conditions in order to build training datasets. Afterwards, a deep convolutional neural network algorithm was trained with the generated datasets and used to predict the faults conditions. Finally, the identification performance was evaluated statistically regarding the true-positive identification by both probability density function and subjective logic. The classification accuracy showed promising results for training the machine learning algorithms with simulated data.

Development of an Improved LMD Method for the Low-Frequency Elements Extraction from Turbine Noise Background

Given the prejudicial environmental effects of fossil-fuel based energy production, renewable energy sources can contribute significantly to the sustainability of human society. As a clean, cost effective and inexhaustible renewable energy source, wind energy harvesting has found a wide application to replace conventional energy productions. However, concerns have been raised over the noise generated by turbine operating, which is helpful in fault diagnose but primarily identified for its adverse effects on the local ecosystems. Therefore, noise monitoring and separation is essential in wind turbine deployment. Recent developments in condition monitoring provide a solution for turbine noise and vibration analysis. However, the major component, aerodynamic noise is often distorted in modulation, which consequently affects the condition monitoring. This study is conducted to explore a novel approach to extract low-frequency elements from the aerodynamic noise background, and to improve the efficiency of online monitoring. A framework built on the spline envelope method and improved local mean decomposition has been developed for low-frequency noise extraction, and a case study with real near-field noises generated by a mountain-located wind turbine was employed to validate the proposed approach. Results indicate successful extractions with high resolution and efficiency. Findings of this research are also expected to further support the fault diagnosis and the improvement in condition monitoring of turbine systems.

Prognostic Health Management of Production Systems. New Proposed Approach and Experimental Evidences

Prognostic Health Management (PHM) is a maintenance policy aimed at predicting the occurrence of a failure in components and consequently minimizing unexpected downtimes of complex systems. Recent developments in condition monitoring (CM) techniques and Artificial Intelligence (AI) tools enabled the collection of a huge amount of data in real-time and its transformation into meaningful information that will support the maintenance decision-making process. The emerging Cyber-Physical Systems (CPS) technologies connect distributed physical systems with their virtual representations in the cyber computational world. The PHM assumes a key role in the implementation of CPS in manufacturing contexts, since it allows to keep CPS and its machines in proper conditions. On the other hand, CPS-based PHM provide an efficient solution to maximize availability of machines and production systems. In this paper, evolving and unsupervised approaches for the implementation of PHM at a component level are described, which are able to process streaming data in real-time and with almost-zero prior knowledge about the monitored component. A case study from a real industrial context is presented. Different unsupervised and online anomaly detection methods are combined with evolving clustering models in order to detect anomalous behaviours in streaming vibration data and integrate the so-generated knowledge into supervised and adaptive models; then, the degradation model for each identified fault is built and the resulting RUL prediction model integrated into the online analysis. Supervised methods are applied to the same dataset, in batch mode, to validate the proposed procedure.

Optical Attenuation Characterization of Water Contaminated Lubricating Grease

ABSTRACT Water-contaminated grease samples are investigated with attenuation spectra in the visible and near-infrared (NIR) regions in this article. The purpose of this investigation was to identify a model with optical attenuation spectra such that the water content of grease samples could be characterized with a simple measurement setup using common methodology from the field of instrumental chemistry. The ratio between two chosen wavelengths of light appears to approximate the water content of grease samples with an acceptable coefficient of determination using a methodology to show what can potentially be done to develop condition monitoring tools. To illustrate the outlined method, a prestudy of grease aging and oxidation levels is also investigated to show that other variables do not significantly change the measurement.