Showing papers on "Condition monitoring published in 2021"
TL;DR: A new method is proposed for fault detection of wind turbine, in which the convolutional neural network cascades to the long and short term memory network (LSTM) based on attention mechanism, which verifies the effectiveness of the proposed method.
130 citations
TL;DR: The analysis results demonstrated that the proposed hybrid deep learning model can achieve higher detection accuracy than CNN and gcForest, which may be favorable to practical applications.
119 citations
TL;DR: In this article, a data-driven approach for condition monitoring of generator bearing using temporal temperature data is presented, where four algorithms, the support vector regression machine, neural network, extreme learning machine, and the deep belief network are applied to model the bearing behavior.
Abstract: Wind turbines are widely installed as the new source of cleaner energy production. Dynamic and random stress imposed on the generator bearing of a wind turbine may lead to overheating and failure. In this paper, a data-driven approach for condition monitoring of generator bearings using temporal temperature data is presented. Four algorithms, the support vector regression machine, neural network, extreme learning machine, and the deep belief network are applied to model the bearing behavior. Comparative analysis of the models has demonstrated that the deep belief network is most accurate. It has been observed that the bearing failure is preceded by a change in the prediction error of bearing temperature. An exponentially-weighted moving average (EWMA) control chart is deployed to trend the error. Then a binary vector containing the abnormal errors and the normal residuals are generated for classifying failures. LS-SVM based classification models are developed to classify the fault bearings and the normal ones. The proposed approach has been validated with the data collected from 11 wind turbines.
106 citations
TL;DR: A comprehensive review and comparison of CM schemes for different types of dc-link applications with emphasis on the application objectives, implementation methods, and monitoring accuracy when being used is provided.
Abstract: Capacitors are widely used in dc links of power electronic converters to balance power, suppress voltage ripple, and store short-term energy. Condition monitoring (CM) of dc-link capacitors has great significance in enhancing the reliability of power converter systems. Over the past few years, many efforts have been made to realize CM of dc-link capacitors. This article gives an overview and a comprehensive comparative evaluation of them with emphasis on the application objectives, implementation methods, and monitoring accuracy when being used. First, the design procedure for the CM of capacitors is introduced. Second, the main capacitor parameters estimation principles are summarized. According to these principles, various possible CM methods are derived in a step-by-step manner. On this basis, a comprehensive review and comparison of CM schemes for different types of dc-link applications are provided. Finally, application recommendations and future research trends are presented.
98 citations
TL;DR: In this paper, the authors proposed a new feature engineering model which combines Fast Fourier Transform (FFT), Continuous Wavelet Transform (CWT) and statistical features of raw signals.
95 citations
TL;DR: A health indicator estimation method based on the digital-twin concept aiming for condition monitoring of power electronic converters is proposed, which is noninvasive, without additional hardware circuits, and calibration requirements.
Abstract: This article proposes a health indicator estimation method based on the digital-twin concept aiming for condition monitoring of power electronic converters. The method is noninvasive, without additional hardware circuits, and calibration requirements. An application for a buck dc–dc converter is demonstrated with theoretical analyses, practical considerations, and experimental verifications. The digital replica of an experimental prototype is established, which includes the power stage, sampling circuit, and close-loop controller. Particle swarm optimization algorithm is applied to estimate the unknown circuit parameters of interest based on the incoming data from both the digital twin and the physical prototype. Cluster-data of the estimated health indicators under different testing conditions of the buck converter is analyzed and used for observing the degradation trends of key components, such as capacitor and MOSFET. The outcomes of this article serve as a key step for achieving noninvasive, cost-effective, and robust condition monitoring for power electronic converters.
95 citations
TL;DR: An algorithm is proposed to extract the impulse features for signal reconstructions, which are useful for an accurate diagnosis of the fault type and have a better performance in dealing with impulsive-like signals than other TFA methods.
Abstract: The impulse features in a condition monitoring (CM) signal usually imply the occurrence of a defect in a rotating machine. To accurately capture the impulse components in a CM signal, a concentrated time-frequency analysis (TFA) method based on time-reassigned synchrosqueezing transform (TSST) is proposed. First, the limitation of the TSST method in dealing with strong frequency-varying signals is explored. Second, an iteration procedure is introduced to address the blurry time frequency representation problem of TSST. The convergence of the iteration algorithm is also analyzed. Finally, an algorithm is proposed to extract the impulse features for signal reconstructions, which are also useful for an accurate diagnosis of the fault type. A simulated noise-contaminated signal and three sets of experimental data are employed in this article to evaluate the performance of the proposed method. Results obtained from this article confirm that the proposed method has a better performance in dealing with impulsive-like signals than other TFA methods.
94 citations
TL;DR: In this article, an improved dynamic model of ACBB is proposed to consider the influences of elastic hysteresis, differential sliding friction torques, and elastohydrodynamic lubrication (EHL) rolling on the ball motion state.
85 citations
TL;DR: In this article, condition-based maintenance and fault diagnosis of rotating machinery (RM) has a vital role in the modern industrial world, however, the remaining useful life (RUL) of machiner...
Abstract: Nowadays, condition-based maintenance (CBM) and fault diagnosis (FD) of rotating machinery (RM) has a vital role in the modern industrial world. However, the remaining useful life (RUL) of machiner...
81 citations
TL;DR: A review of the machine learning algorithm applications in fault detection in induction motors and the future prospects and challenges for an efficient machine learning based fault detection systems are presented.
Abstract: Fault detection prior to their occurrence or complete shut-down in induction motor is essential for the industries. The fault detection based on condition monitoring techniques and application of machine learning have tremendous potential. The power of machine learning can be harnessed and optimally used for fault detection. The faults especially in induction motor needs to be addressed at a proper time for avoiding losses. Machine learning algorithm applications in the domain of fault detection provides a reliable and effective solution for preventive maintenance. This paper presents a review of the machine learning algorithm applications in fault detection in induction motors. This paper also presents the future prospects and challenges for an efficient machine learning based fault detection systems.
81 citations
Abstract: Online parameter estimation of permanent magnet synchronous machines is critical for improving their control performance and operational reliability. This paper provides an overview of the recent achievements of online parameter estimation of PMSMs with examples. The critical issues in parameter estimation are firstly analysed, especially the rank-deficient issue and inverter nonlinearities. Then, the state-of-the-art online parameter estimation modelling techniques are reviewed and assessed. Finally, some typical applications and examples are outlined, e.g. estimation of mechanical parameters, improvement of sensored and sensorless control performance, thermal condition monitoring, and fault diagnosis, together with future research trends.
TL;DR: A generalized RUL prediction method is proposed for complex systems with multiple Condition Monitoring signals, and a nonlinear data fusion method based on Genetic Programming is proposed to construct a superior composite HI.
TL;DR: A fault diagnosis method based on parameter-based transfer learning and convolutional autoencoder (CAE) for wind turbines with small-scale data is proposed and can transfer knowledge from similar wind turbines to the target wind turbine.
TL;DR: It was observed that with the increase in the number of features in the data set, the accuracy, sensitivity, TPR, TNR, F1 score and Kappa metrics increased above 99% at 95% confidence interval, and FPR and FNR metrics fell below 1%.
TL;DR: This paper is dedicated to analyze the different AE principles in RE systems, and to comprehensively summarize and clearly highlight the advanced methods and challenges.
TL;DR: A method based on long short-term memory (LSTM) and auto-encoder (AE) neural network is introduced to assess sequential condition monitoring data of the wind turbine to improve the reliability and reduce maintenance costs during operation of wind turbine.
TL;DR: A RUL prediction method based on a multi-sensor data fusion model where the inherent degradation process of the system state is expressed using a state transition function following a Wiener process.
TL;DR: In this article, a physics-informed deep learning approach was proposed for bearing condition monitoring and fault detection, which consists of a simple threshold model and a deep convolutional neural network (CNN) model.
TL;DR: The results demonstrate that the proposed system is a visually effective monitoring system for environmental monitoring management, and is expected to provide a robust and practical tool for reliable data collection, analysis, and visualization to facilitate intelligent monitoring of the thermal condition in buildings.
TL;DR: It is observed that the vibration-based techniques are reported to be effective for the identification of mechanical faults while motor current signature analysis is effective for electrical fault in an induction motor.
Abstract: An induction motor is at the heart of every rotating machine and hence it is a very vital component. Almost in every industry, around 90% of the machines apply an induction motor as a prime mover. It is a very important driving unit of the machine. Hence, it is necessary to monitor its condition to avoid any catastrophic failure and stoppage of production. The breakdown of the induction motor would not be affordable due to remarkable financial loss, unpredicted shutdown, and the associated repair cost. Vibration is a manifestation of induction motor due to the issues in alignment, balancing, and clearances. Bearing, the most vulnerable to failure due to continuous working under fatigue loading leads to defects. These defects cause changes in the vibration signature over time. The vibration monitoring techniques helps to effectively diagnose mechanical faults such as bearing defect and stator rotor rub. The purpose of this review paper is to summarize the major faults in induction motor, recent diagnostics methods augmented with advanced signal processing techniques, and real-life applications in electric vehicles. It also discusses possible research gaps and opportunities to contribute based on the review findings in the field of condition monitoring. This article presents a detailed review of recent trends in the research of condition monitoring and fault diagnosis of the induction motor. The emphasis is given on the major faults in the induction motor covering time-domain, frequency-domain, and time–frequency domain methods along with an application of artificial intelligence techniques for fault detection. This article presents a comprehensive review of literature which highlights the development and new propositions by researchers in the field of diagnostic techniques for the different faults of induction motor in the last decade. Researchers documented applications of the different conventional methods, advanced signal processing techniques, and soft computing techniques for fault identification of induction motor. This review is carried out for fault identification of induction motor used in machines in general and in particular for identifying the faults in an induction motor of an electric vehicle. A dedicated discussion on the review findings, research gaps, future trends in the field of condition monitoring of induction motor is presented. Condition monitoring of the induction motor in an electric vehicle is also discussed in this paper. It is observed that the vibration-based techniques are reported to be effective for the identification of mechanical faults while motor current signature analysis is effective for electrical fault in an induction motor. The review presented to analyze the suitability of various condition monitoring techniques for the induction motor fault identification in general and particularly its application in an electric vehicle. It is observed that the diagnosis of faults at the incipient level without using the signal processing technique is challenging. Fault diagnosis of induction motor has witnessed the changes from traditional diagnosis techniques to advanced techniques with a hybrid application of signal processing and artificial intelligence techniques. Still, there is a potential of improvement in reliability, efficiency, robustness, computational time, and real-time diagnostics of faults in IM.
TL;DR: In this article, a hybrid approach based on both condition monitoring and physic model is presented to improve the accuracy and precision of RUL estimation for lithium-ion battery, where an artificial intelligence estimation method based on recurrent neural network (RNN) is integrated with a state-space estimation technique.
Abstract: Prognostic and condition-based maintenance of lithium-ion batteries is a fundamental topic, which is rapidly expanding since a long battery lifetime is required to ensure economic viability and minimize the life cycle cost. Remaining useful life (RUL) estimation is an essential tool for prognostic and health management of batteries. In this article, a hybrid approach based on both condition monitoring and physic model is presented to improve the accuracy and precision of RUL estimation for lithium-ion battery. An artificial intelligence estimation method based on recurrent neural network (RNN) is integrated with a state-space estimation technique, which is typical of filtering-based approach. The state-space estimation is used to generate a big dataset for the training of the RNN. Some additional deep layers are used to improve the prediction of nonlinear trends (typical of batteries), while the performance optimization of the RNN is ensured using a genetic algorithm. The performances of the proposed method have been tested using a battery degradation dataset from the data repository of Prognostics Center of Excellence at NASA. Two different degradation models are compared, the widely known empirical double exponential model and an innovative single exponential model that allows to ensure optimal performance with fewer parameters required to be estimated.
TL;DR: With the combination of vibration signal- and image processing techniques the evaluation time and computational resource requirements are decreased enhancing more efficient and accurate analysis, nevertheless opens the possibility of a real-time condition monitoring based on a basic vibration measurement.
TL;DR: In this paper, a comprehensive review of the application of UAVs in bridge condition monitoring, used in conjunction with remote sensing technologies, is presented, in terms of ease of use, accuracy, cost-efficiency, employed data collection tools, and simulation platforms.
Abstract: Deterioration of bridge infrastructure is a serious concern to transport and government agencies as it declines serviceability and reliability of bridges and jeopardizes public safety. Maintenance and rehabilitation needs of bridge infrastructure are periodically monitored and assessed, typically every two years. Existing inspection techniques, such as visual inspection, are time-consuming, subjective, and often incomplete. Non-destructive testing (NDT) using Unmanned Aerial Vehicles (UAVs) have been gaining momentum for bridge monitoring in the recent years, particularly due to enhanced accessibility and cost efficiency, deterrence of traffic closure, and improved safety during inspection. The primary objective of this study is to conduct a comprehensive review of the application of UAVs in bridge condition monitoring, used in conjunction with remote sensing technologies. Remote sensing technologies such as visual imagery, infrared thermography, LiDAR, and other sensors, integrated with UAVs for data acquisition are analyzed in depth. This study compiled sixty-five journal and conference papers published in the last two decades scrutinizing NDT-based UAV systems. In addition to comparison of stand-alone and integrated NDT-UAV methods, the facilitation of bridge inspection using UAVs is thoroughly discussed in the present article in terms of ease of use, accuracy, cost-efficiency, employed data collection tools, and simulation platforms. Additionally, challenges and future perspectives of the reviewed UAV-NDT technologies are highlighted.
TL;DR: A review of the fault diagnostic techniques based on machine is presented in this paper and some promising machine learning-based diagnostic techniques are presented in the perspective of their attributes.
Abstract: A review of the fault diagnostic techniques based on machine is presented in this paper. As the world is moving towards industry 4.0 standards, the problems of limited computational power and available memory are decreasing day by day. A significant amount of data with a variety of faulty conditions of electrical machines working under different environments can be handled remotely using cloud computation. Moreover, the mathematical models of electrical machines can be utilized for the training of AI algorithms. This is true because the collection of big data is a challenging task for the industry and laboratory because of related limited resources. In this paper, some promising machine learning-based diagnostic techniques are presented in the perspective of their attributes.
TL;DR: In the proposed SNN-based approach to bearing fault diagnosis, features extracted from raw vibration signals through the local mean decomposition (LMD) are encoded into spikes to train an SNN with the improved tempotron learning rule.
TL;DR: A hybrid fault classification approach is presented by combining finite element method (FEM) with generative adversarial networks (GANs) for rotor-bearing systems to solve insufficient fault samples problem in more complex mechanical system with agreeable fault classification accuracy.
Abstract: Condition monitoring of rotor-bearing systems using artificial intelligence has great significance to guarantee the reliability and security of mechanical systems. However, in engineering applications, AI model will fail to classify faults with insufficient fault samples owing to complex working condition. A hybrid fault classification approach is presented by combining finite element method (FEM) with generative adversarial networks (GANs) for rotor-bearing systems. Firstly, FEM simulations are employed to calculate simulation fault samples as additional sources of missing fault samples. Secondly, GANs is used to acquire abundant synthetic samples generated from the simulation and measurement samples, which aims to expand fault samples. Finally, the complete fault samples, including simulation, measurement and their corresponding synthetic samples, are utilized as training samples to train typical classifiers, and further to identify unknown faults. High classification accuracies for a rotor-bearing system using different kinds of artificial intelligent (AI) models are obtained, which demonstrates the effective of proposed method. It is noticed that the present idea can be guided to solve insufficient fault samples problem in more complex mechanical system with agreeable fault classification accuracy.
TL;DR: Experimental results demonstrate that some special cases of the generalized framework can simultaneously detect incipient rotating faults, exhibit a monotonic degradation tendency and be robust to impulsive noises, and they are better than existing sparsity measures for machine health monitoring.
TL;DR: A mixture of Gaussians-evidential hidden Markov model (MoG-EHMM) and evidential expectation–maximization algorithm is developed to fuse expert knowledge and condition monitoring information for remaining useful life prediction under the belief function theory framework.
Abstract: In this article, we develop a mixture of Gaussians-evidential hidden Markov model (MoG-EHMM) to fuse expert knowledge and condition monitoring information for remaining useful life (RUL) prediction under the belief function theory framework. The evidential expectation–maximization algorithm is implemented in the offline phase to train the MoG-EHMM based on historical data. In the online phase, the trained model is used to recursively update the health state and reliability of a particular individual system. The predicted RUL is, then, represented in the form of its probability mass function. A numerical metric is defined based on the Bhattacharyya distance to measure the RUL prediction accuracy of the developed methods. We applied the developed methods on a simulation experiment and a real-world dataset from a bearing degradation test. The results demonstrate that despite imprecisions in expert knowledge, the performance of RUL prediction can be substantially improved by fusing expert knowledge with condition monitoring information.
TL;DR: A batteryless railway monitoring system based on radio-frequency (RF) energy harvesting to detect early defects on rail tracks is proposed, achieving low installation and maintenance costs and providing a more reliable inspection than the existing methods.
Abstract: Current railway track condition monitoring relies on inefficient human inspectors and expensive inspection vehicles, where high-frequency inspection is unreachable since these methods occupy the tracks. This article proposes a batteryless railway monitoring system based on radio-frequency (RF) energy harvesting to detect early defects on rail tracks. The key part of the system is a batteryless wireless sensor tag (BLWST) installed on railway tracks. The BLWST can harvest RF energy from a reader installed on the train, and precisely measure and wirelessly transmit the vibration condition of tracks back to the reader. The proposed system eliminates the demands for cables and battery replacement, thus achieving low installation and maintenance costs. The high-frequency monitoring also provides a more reliable inspection than the existing methods. The BLWST is based on the 3-stage Dickson voltage multiplier (DVM) and can be activated by a dedicated RF power source at a maximum distance of 2.3 m. Experiments show that a maximum energy conversion efficiency of 25% and 500 working cycles per second are achieved. For demonstration, we construct a miniaturized railway system with the batteryless prototype and exhibit a reliable wireless power transfer and data communication.
TL;DR: The proposed method based on edge computing reduces the power consumption, and hence it is suitable to use on a battery-supplied IIoT node for remote PMSM condition monitoring and fault diagnosis.
Abstract: An efficient data reduction algorithm is designed and implemented on an industrial Internet of Things (IIoT) node for permanent magnet synchronous motor (PMSM) bearing fault diagnosis in variable speed conditions. Leakage flux and vibration signals are, respectively, acquired by a magnetic sensor and an accelerometer on the IIoT node in a noninvasive manner. These two signals are processed and mixed on the IIoT and transmitted to a server. The received signal is separated, the cumulative rotation angle is calculated, and the vibration signal is resampled for bearing fault identification. The proposed method can reduce about 95% of the transmission data while maintaining sufficient precision in bearing fault diagnosis in comparison to a traditional method. The proposed method based on edge computing reduces the power consumption, and hence it is suitable to use on a battery-supplied IIoT node for remote PMSM condition monitoring and fault diagnosis.