Field Of Condition Monitoring Research Articles

Incorporating the Time-synchronous Averaging Method into Vibration Analysis Methodologies for the Detection and Localization of Bearing Defects

Objective: The objectives of this paper are to highlight the significance of vibration analysis, especially in predictive maintenance for rotating machinery, and to emphasize the importance of detecting bearing defects that may result in machinery failure. Methods: The proposed methodology combines the use of time-synchronous averaging (TSA) with existing vibration analysis techniques. TSA involves aligning vibration data with specific events or phases in the machinery's operation, such as shaft rotation. By synchronizing the data in this way, the methodology aims to reduce noise and enhance the signal related to bearing defects, making them more distinguishable. Additionally, the methodology incorporates well-established vibration analysis techniques. These techniques may include frequency analysis, amplitude modulation analysis, waveform analysis, and others commonly used in the field of condition monitoring and predictive maintenance. Results: The results of the analysis begin with waveform analysis, which involves examining the shape and pattern of vibration signals captured from the pinion. This analysis provides valuable insights into the dynamic behavior of the pinion gear, including any variations or abnormalities in its motion. Moreover, the use of synchronized waveforms is crucial in this analysis. By aligning the vibration data with specific events or phases in the gear mesh cycle, such as tooth engagement, the analysis can pinpoint moments when potential faults or wear in the machinery may occur. This synchronization allows for a more precise assessment of the vibration signals, enabling the detection of irregularities that may indicate underlying issues with the pinion or other components of the machinery. Conclusion: A pivotal aspect of the methodology involves envelope spectra analysis, significantly enhancing diagnostic capabilities. This analysis identifies fault patterns that might not be readily apparent in conventional vibration analysis. The incorporation of envelope spectra proves instrumental in proactive maintenance, enabling early detection of potential issues. This, in turn, contributes to the overall reliability and optimization of machinery performance.

Object detection algorithm for indoor switchgear components in substations based on improved YOLOv5s

With the continuous progress of science and technology, electric power equipment detection systems are developing in the direction of artificial intelligence. To achieve good automatic detection results, a high-quality and speedy algorithm is designed to intelligently detect indoor switchgear components in substations. This proposed method can detect the status of components based on image processing technology, which belongs to the field of condition monitoring. In this paper, the targets to be detected include multi-colour buttons or lights and the ammeters or voltmeters of the electrical switchgear. Two hybrid improved algorithms are used to optimise the you only look once v5s (YOLOv5s) network framework for increasing the detection speed and performance. Firstly, deeper feature map extraction is achieved using HorNet recursive gated convolution to replace the original C3 module for more efficient results. Then, a bidirectional feature pyramid network (BiFPN) algorithm is used to achieve the bidirectional propagation of feature information in the feature pyramid. This method can promote better fusion of feature information at different levels and help to convey feature and location information in the image. Finally, the improved YOLOv5s-BH model is used to detect the targets in substations. The experimental results show that the proposed method provides encouraging detection results for indoor switchgear components in substations.

A single-stage anchor-free rotating target visual detection algorithm suitable for flexible body vibration displacement measurement

The phenomenon of angular inclination of flexible structures during vibration poses a significant challenge to the applicability of visual vibration measurement methods because the target locked in the captured image will produce unknown geometric deformations such as scale, displacement, and angle in the time domain space, and the horizontal rectangular frame used for matching during target detection will also increase the false detection rate of the target due to the introduction of more background information. Such subtle geometric deformations and false detections can lead to severe fit errors in the displacement curves regressed by the visual vibration measurement algorithm. To effectively improve the accuracy and robustness of vibration image target recognition, this article takes the flexible body captured by a high-speed camera as the target of vibration displacement measurement. It introduces the rotating target detection method based on deep learning into the field of visual vibration measurement, which verifies the feasibility of the deep learning method in flexible body vibration measurement, and based on the deep convolutional neural network framework, a high-precision displacement measurement algorithm based on single-stage anchor-free rotating target detection is proposed. The algorithm in this article first uses the CSPDarknet backbone network to extract multi-scale features of flexible structural image sequences. It then uses PANet to fuse the top-down and bottom-up bidirectional feature maps of the four bridge target feature maps obtained through the backbone network. The shallow and deep information is used for semantic feature fusion and combined with the Coordinate Attention mechanism to achieve target finding and fine positioning on the feature map. Finally, we use the coordinates of the bounding box obtained from the test to regress the position offset of the object’s center point. To verify the accuracy of the algorithm in this article, we conducted experimental validation on the cable-stayed bridge model and the actual bridge and compared the performance with the traditional template matching algorithm, differential optical flow method, and various deep learning algorithms with different localization principles, as well as the displacement signals collected and processed by accelerometers. The experimental results of time-frequency characteristics analysis show that the vibration displacement trajectories regressed by the algorithm in this paper have the best overlap with the displacement measurements collected by the accelerometer, which verifies that the algorithm in this article has good application potential and implementation space in the field of condition monitoring of flexible structural bodies.

Revolutionizing condition monitoring techniques with integration of artificial intelligence and machine learning

The field of condition monitoring has made great strides in the development of innovative techniques that facilitate early detection and diagnosis of faults in equipment. Present article provides a comprehensive overview of condition-monitoring technologies, namely, ultrasound technique and radiography. By providing detailed insight into the strengths and weaknesses of mentioned techniques, present work highlights their suitability for various industrial applications and how artificial intelligence and machine learning can be integrated to form multimodal systems that improve overall performance. Additionally, it evaluates developments in artificial intelligence and machine learning that enable accurate and reliable condition monitoring systems.

Rotating box multi-objective visual tracking algorithm for vibration displacement measurement of large-span flexible bridges

Visual displacement measurement methods for flexible structural bodies like large-span bridges has gained wide popularity in recent years, but practical applications still have some limitations. For instance, when acquiring images of large-span flexible bridges at a distance, the slight angular tilt of the detection target due to irregular vibrations can cause extremely serious misfit errors in the displacement curves returned by the vision measurement algorithm. To improve the reliability of vibration displacement measurement of flexible structural bodies, this paper takes the bridge subjected to external excitation in the acquired image sequence as the object of vibration displacement measurement and uses a designed high-precision displacement measurement algorithm for a single-stage rotating target tracking anchor-free box to track the vibration displacement of the target in the flexible structural body. We first extract multi-scale feature information of bridge model image sequences using the improved YOLOv5-s backbone network and combine the Transformer self-attention mechanism with PANet to perform a top-down and bottom-up bi-directional fusion of target feature maps at three different scales to achieve semantic feature fusion of shallow and deep information. Second, the improved Efficient Decoupled Head performs the detection of rotating target centroid offset and bounding box size. Finally, the detected results are passed into the multi-objective tracking algorithm ByteTrack, which strengthens the spatio-temporal correlation between frames and obtains a better-fitting vibration displacement curve. The validation and comparison of traditional visual measurement methods and deep learning measurement methods on cable-stayed bridge models, small arch bridges, and large span bridges show that the vibration displacement trajectories regressed by the algorithm in this paper have the best fit with the actual vibration displacement trajectories, which also verifies that the algorithm in this paper has good potential for engineering applications and implementation space in the field of condition monitoring of flexible structural bodies.

A spectral self-focusing fault diagnosis method for automotive transmissions under gear-shifting conditions

Transmissions are core components of automobiles in adjusting the speed. The time-varying operation conditions, particularly the frequent gear shifting, present significant challenges for condition monitoring and fault locating of transmissions. At present, most existing studies primarily focus on the issues arising from time-varying speed, but they do not consider the challenges introduced by gear shifting. Gear shifting changes the meshing gear pairs within the transmission, causing the monitoring indicator amplitude fluctuates greatly. Consequently, the indicator fails to reflect the overall degradation trend of the transmission. To address this problem, this paper proposes a fault diagnosis method for automotive transmissions with the consideration of gear shifting. Our contributions are as follows: Firstly, we propose a spectral variation sparsity indicator (SVSI) based on the order spectrum at each gear position. Secondly, we fuse SVSI from different gear positions and create a comprehensive indicator called weighted health indicator (WHI). Finally, a diagnosis method based on SVSI and WHI is proposed for automotive transmissions under gear-shifting conditions. The effectiveness of the proposed method is validated using datasets from four automotive transmissions. The results demonstrate that our method is capable of detecting faults prior to inspection and accurately identifying faulty gears. Moreover, the performance of WHI is compared with several existing indicators. The results demonstrate that WHI exhibits stronger correlation, monotonicity, and robustness. This indicates that WHI is able to effectively mitigate the influence of gear shifting, thereby better reflecting the overall degradation trend of the transmission. Consequently, our proposed method significantly contributes to the field of condition monitoring and fault locating for automotive transmissions.

Latent indicators for temporal-preserving latent variable models in vibration-based condition monitoring under non-stationary conditions

Condition-based monitoring for critical assets is reliant on the quality of the indicators used for condition inference. These indicators must be sensitive to the development of faults under constant and non-stationary operating conditions. Latent variable models in the time-preserving framework offer a powerful learning-based technique for the monitoring of critical assets as they only require healthy asset data, and provide indicators from the data space for asset condition inference. However, the latent manifold of latent variable models is often disregarded in favour of data space indicators, such as reconstruction errors, which are primarily focused on measuring the likelihood of the observed data. The latent space is often unintentionally unutilised. In this work, we highlight that the latent manifold is a powerful resource for condition inference and should be utilised for condition monitoring. We conceptually categorise and identify five classes of latent space health indicators that capture various manifold perspectives. These five classes introduce and allow for latent health indicator derivation and are useful for the condition inference task. Fifteen latent health indicators are considered in this work and are applied to the fault diagnostics task on two experimental datasets. An ensemble-based inference procedure is used, which produces a modular fault diagnosis framework. The indicators are shown to be informative for condition inference in both constant and variable operating conditions. Utilising the latent manifold in condition monitoring tasks is important to further develop the learning-based condition monitoring field.

Condition Monitoring and Fault Detection in Cables using Line Impedance Resonance Analysis

Line Impedance Resonance Analysis is a powerful technique to determine the location of water trees and physical damage in all cables, from LV to EHV. The technique, which uses the concept of frequency-domain reflectometry, was originally developed for nuclear plants and has now been commercialized for practical applications in the field of condition monitoring as well as fault location.

IMS Technical Committee TC-3: Condition Monitoring and Fault Diagnosis Instrument

This article provides an overview of the IEEE Instrumentation and Measurement Society (IMS) Technical Committee TC-3 on Condition Monitoring and Fault Diagnosis Instrument. TC-3 aims at serving as a platform for scientists and engineers involved in the field of condition monitoring and fault diagnosis, with a focus on potential applications in the industry.

Autonomous Bearing Tone Tracking Algorithm

To date, much of the research done in the field of condition monitoring of rotating machinery is conducted in the frequency domain. The frequency domain analysis specifically for bearings is based on extracting features from the spectrum of the vibration signature. These features are mostly based on the amplitude at the bearing tones along with their sidebands and high order harmonics. Therefore, it is important to determine the location of the mentioned bearing tones in the spectrum accurately and automatically. For the case of ball bearings this process can be problematic due to slippage of the rolling elements and variations in the angle of contact. These may cause the bearing tone to deviate from its nominal value.
 To this day, the common practice for bearing diagnostics is based on the vibration level at the analytical bearing tones or involvement of experts to identify the true location of the bearing tone. In this research an autonomous algorithm for bearing tone extraction, based on pattern matching, was developed. The proposed algorithm is based on the common assumption that the spectrum of a faulted bearing contains a certain known pattern of prominent peaks. The algorithm “scans” the entire spectrum and determines the frequency value which has the highest correlation to the mentioned pattern.
 The proposed algorithm was validated and its capabilities are illustrated using experimental data. This algorithm is able to assist any diagnostic approach towards automatic and reliable feature extraction process, both for physics based and data driven approaches.

Optimal Data Reduction of Training Data in Machine Learning-Based Modelling: A Multidimensional Bin Packing Approach

In these days, when complex, IT-controlled systems have found their way into many areas, models and the data on which they are based are playing an increasingly important role. Due to the constantly growing possibilities of collecting data through sensor technology, extensive data sets are created that need to be mastered. In concrete terms, this means extracting the information required for a specific problem from the data in a high quality. For example, in the field of condition monitoring, this includes relevant system states. Especially in the application field of machine learning, the quality of the data is of significant importance. Here, different methods already exist to reduce the size of data sets without reducing the information value. In this paper, the multidimensional binned reduction (MdBR) method is presented as an approach that has a much lower complexity in comparison on the one hand and deals with regression, instead of classification as most other approaches do, on the other. The approach merges discretization approaches with non-parametric numerosity reduction via histograms. MdBR has linear complexity and can be facilitated to reduce large multivariate data sets to smaller subsets, which could be used for model training. The evaluation, based on a dataset from the photovoltaic sector with approximately 92 million samples, aims to train a multilayer perceptron (MLP) model to estimate the output power of the system. The results show that using the approach, the number of samples for training could be reduced by more than 99%, while also increasing the model’s performance. It works best with large data sets of low-dimensional data. Although periodic data often include the most redundant samples and thus provide the best reduction capabilities, the presented approach can only handle time-invariant data and not sequences of samples, as often done in time series.

In Plane Radial Vibration of Uncracked and Cracked Circular Curved Beams Subjected to Moving Loads

The dynamic response of structures subjected to moving load is a subject of great importance from a practical point of view. In this work, the in-plane dynamic response of a cracked isotropic circular curved beam subjected to moving loads is investigated using the finite element method. The curved beam is modeled using curved beam elements, which is developed based on the Timoshenko beam theory. Furthermore, a cracked curved beam element is developed to incorporate the presence of cracks in the structure. The effect of moving load speed, depth, and the location of the crack on the dynamic response of the beam is investigated. The outcome of the work can be useful in the study of real-life moving load problems like bridges and railways and also in the field of condition monitoring using moving loads.

Knowledge Modeling of Airborne Missile Management System Based on Multi-dimensional Fuzzy Ontology

Health management system of airborne missiles has a large amount and variety of knowledge, but such technical documents are lack of effective management in the knowledge level. According to the technical characteristics of knowledge in the field of airborne missile health management, a HTA analysis model (Hierarchy, time, and activity analysis model) based on multi-dimensional fuzzy ontology in the health management field of airborne missiles is constructed, and ontology description language OWL is introduced to express knowledge. It provides a theoretical and methodological basis for the dynamic management of health knowledge in the field of condition monitoring, prediction and evaluation, fault diagnosis, technical service.

A deep sequence multi-distribution adversarial model for bearing abnormal condition detection

Time series anomaly detection is one of the key challenges in the field of condition monitoring. Many anomaly detection methods are inefficient and easy to lose effective information due to manual features extracting. Deep learning-based methods can solve the problem effectively, but the detection accuracy is still not satisfactory. In addition, most of the methods cannot take the time-ordered specialty into account which is significant for time-series-based anomaly detection. To address these issues, a novel method named deep sequence multi-distribution adversarial model (DSMDA) is proposed to improve the accuracy of anomaly detection in bearing condition monitoring. The proposed model utilizes the data reconstruction capability of the Variational Autoencoder (VAE) under the framework of generative adversarial network (GAN) to make full use of information. The feedforward neural network layer of VAE is replaced by the long-term and short-term memory (LSTM) layer, which uses the forgetting mechanism of LSTM to effectively avoid the false alarms caused by the excessive influence of the old sequences. Additionally, the fault-attention abnormal state index can be constructed by the real-time spatial distribution and latent spatial distribution features learned by the double discriminators. To verify the effectiveness of the proposed approach, experiments on two public datasets are carried out with only healthy data in training stage that is more suitable for practical industrial applications. The results show that the proposed method is superior to GANomaly and other advanced methods. Furthermore, the 2-D visualization results can indicate the level of fault while the last feature space of the two discriminators is combined and embedded into the visualization, and the fault-attention abnormal state indictor constructed on these features can indicate abnormalities well.

Analysis of Muara Tawar CCPP Block 1 Steam Turbine Vibration

Condition monitoring of steam turbine enables early detection of faults and avoid unexpected breakdowns. Vibration analysis has gained much attention in the field of condition monitoring because of its accuracy in detecting faults and its ability for proper diagnosis of the faults. Muara Tawar CCPP block 1 has a steam turbine generator with a capacity of 215 MW. Steam turbine roll after inspection shows high vibration occurs on bearing 1. This study aims to find the cause of this high vibration and provide recommendations to avoids such symptoms. The vibration data used in the analysis are obtained from vibration analyzer tools associated with vibration monitoring systems. It is found that the amplitude of vibration at rotational speed frequency (1X) increased and phase angle changes at a constant speed. The vibration level at the coast down is higher than the observed vibration level at run-up. There is a shift in the position of critical speed which indicates a change of rotor stiffness. It is concluded that the high vibration is likely by a thermal bow on the rotor. The thermal rotor bow is caused by a light partial rubbing between rotor and labyrinth seal on the stator.

Applications of Digital Signal Processing in Monitoring Machining Processes and Rotary Components: A Review

Condition monitoring is a significant requirement for ensuring safe and reliable working of machining processes and rotary components. Recent developments in digital signal processing techniques along with emergence of miniature sensors and high-speed data acquisition devices furnish a peculiar opportunity for the development and implementation of effective, in-situ, non-intrusive condition monitoring methods for a broad range of machining processes and rotary components. The selection of most appropriate signal processing technique, best suited for a particular application, is a major challenge in the field of condition monitoring, especially when working in a competitive industrial environment. This problem can only be solved if one has a thorough understanding of various aspects such as which parameter to be monitored, aim of monitoring, processing limitations and possible future scope of such monitoring method. Signal processing methods applicable to machining processes and rotary components have been investigated in relation to the parameters monitored, purpose of monitoring and future scope for that method. Limitations of such processing methods have also been reviewed to make the reader aware of disadvantages in using a particular signal processing method. This paper is intended as a valuable guide for researchers to assist in identification and application of the best possible condition monitoring method for machining processes and rotary components.

Condition Monitoring and Fault Diagnosis of Induction Motor

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.

Self-Assessment of Health Conditions of Electrical Assets and Grid Components: A Contribution to Smart Grids

Broadening the concept of smart grid to include bi-directional interactions between grid and asset electrical components as regards their health conditions would help optimizing maintenance and operation actions from asset/grid management side. However, as long as data processing from diagnostic tools requires long and costly expert time, there is no real chance that the knowledge and technology developed in the field of condition monitoring can become broadly available for grid smart management. This article presents algorithms able to automate the acquisition of health information from electrical asset components. Referring to partial discharges, which are associated with the most harmful insulation aging factor, an innovative technique able to reject noise and thus make automatic partial discharge recognition possible, is proposed and its validity assessed. The information from partial discharge measurement, and other diagnostic quantity monitored is translated into a simple and straightforward indication of component health. This assessment can be automatic, dynamic and continuously updating during operation, thus making feasible an effective time-based condition maintenance approach. The outcome of the proposed approach is to contribute keeping asset reliability at a specified level, minimizing disastrous outages and increasing the return of investment. This benefits also optimal electrical component operation and power flow.

Data processing and augmentation of acoustic array signals for fault detection with machine learning

This paper proposes a novel method to detect and localize disturbances in dynamical systems using non-collocated acoustic arrays by processing their data such that established artificial intelligence techniques can be used. Methods are proposed to compress time-domain based separate microphone data into frequency-domain based images. Furthermore, a data augmentation solution is given to significantly reduce the amount of required training data by using augmentation in the time domain. The use of artificial intelligence in the field of condition monitoring and diagnostics is becoming increasingly popular. However, the vast majority of work is based on sensors collocated in the machines. Therefore, the possibility of using acoustic arrays as a non-intrusive contactless sensor is emerging. The goal of this work is to develop data processing methods that allow for analysis of acoustic array images of vibration patterns. These methods have been demonstrated on a newly created experimental dataset where the a vibrating plate is measured using a 32 by 32 microphone array. On this plate, a disturbance mass placed in different positions to modify the dynamic properties of the system. The experimental results show that the proposed methods are able to determine the position of the disturbance mass even with low amounts of training data. They show to be promising for applications where space-frequency information is of essence.

Graph-based change detection for condition monitoring of industrial machinery: an enhanced framework for non-stationary condition signals

The detection of change(s) in machine running state has become an important problem in the field of condition monitoring of industrial machinery. The graph model has been introduced very recently for this problem with an assumption of periodical stationarity of condition signals. In real-world engineering scenarios, however, machines often operate under unsteady environment and external loading conditions, thus resulting in non-stationary condition signals. This paper is a significant upgrade and expansion on the potential of the graph model to machine monitoring under unsteady operating conditions, where the collected signals are considered to be non-stationary. This paper proposes a new algorithm to achieve this end, which basically includes two steps: cycle segmentation and cycle normalization. Cycle segmentation is first performed to temporally divide the original data into individual cycles. The resulting cycles are subsequently normalized with a timing average procedure. With this, the obtained periodically normalized data can be appropriate for the graph model to process. Meanwhile, in order to avoid the over-segmentation problem, a control time-line is also designed, and simultaneously operates to report a potential change when performing cycle segmentation and normalization. The proposed algorithm is validated on both simulation data and real-world engineering signals. Experimental results reveal its great potential in real applications.