Online Condition Research Articles

Alternative Methods of Machine Online Condition Monitoring: Recommendations for Rotating Machines in the Petroleum and Chemical Industry

Alternative Methods of Machine Online Condition Monitoring: Recommendations for Rotating Machines in the Petroleum and Chemical Industry

Detection of overhead line glass insulator condition using dual function device and deep learning approach

This paper presents a design of a multifunction smart wireless device for online condition monitoring of transmission line insulators. The proposed device can measure the insulator leakage current and take images of the high-voltage insulation. Yolov5-based models and deep convolutional neural networks (DCCN) are developed to analyze and classify the measured data and estimate the insulator's health condition. We have developed and tested a prototype of the proposed device. The device can issue a real-time warning message when a sudden change takes place in the leakage current value. The control center or smartphones receive the collected data wirelessly. We analyze the transmitted data using the developed methods to detect any anomalies and take appropriate remedial action. The performance and feasibility of the developed device are assessed through extensive experimental analysis. Results attest to the robustness of the proposed device, which is easy to install for existing and future overhead transmission line insulators.

Failure evaluation of outdoor polymeric insulators based on statistical condition-assessment methods

Field aging of outdoor polymeric insulators results in unscheduled outages in power systems particularly in harsh climate conditions. In this paper, a strategic maintenance framework is proposed in order to prevent overhead line outages. The presented scheme is based on condition assessment of the real aged polymeric insulators. Data of tensile test, hardness test, thermogravimetric analysis (TGA), and Fourier transform infrared spectroscopy (FTIR) are used to extract critical features of the aged samples based on classification of fuzzy c-means clustering. Then, a lifetime prediction analysis is done based on Cox hazards analysis to develop further maintenance strategy. The proposed model is validated through numerical analyses on polymeric insulators for various validation evaluations including pollution severity analysis and hydrophobicity class (HC) measurement. Obtained results verify accuracy of the intelligent model to predict lifetime of the aged polymeric insulators. The presented strategic framework can be effectively applied to online monitoring, condition assessment and preventive maintenance programs of the power system utilities.

Profiles of teachers' emotional labour during COVID-19 and the consequences on mental health: A comparison between online and offline teaching.

Despite increasing attention on emotional labor in teacher well-being research, person-centered studies are relatively scarce, particularly concerning the emotional labor of online teaching during COVID-19 and its effects on teachers' non-work-related mental health. This study aims to address these gaps by examining emotional labor profiles and their consequences on job satisfaction, depression, and anxiety among Chinese teachers involved in either online or offline teaching during October-December 2022. Two samples of teachers were analyzed altogether: one engaged in online teaching (N=605) and the other in offline teaching (N=394). Latent profile analysis was used to identify emotional labor profiles based on three strategies: surface acting, deep acting, and expression of naturally felt emotions. A total of four subgroups of emotional workers were identified: natural expressors, actors, flexible regulators, and authentic regulators. Significant differences were found between online and offline teaching, with a higher proportion of actors and fewer flexible regulators in the online condition, suggesting that the screen acts as a barrier to authentic emotional display. Among the four classes, actors scored lowest on job satisfaction and highest on depression and anxiety, whereas authentic regulators were the most adaptive, especially in online settings. The findings highlight the impact of online teaching on teachers' emotional labor profiles and mental health, with practical implications for optimizing online teaching environments and supporting teacher well-being.

Combining Artificial Neural Networks and Mathematical Models for Unbalance Estimation in a Rotating System under the Nonlinear Journal Bearing Approach

Rotating systems are essential components and play a critical role in many industrial sectors. Unbalance is a very common and serious fault that can cause machine downtime, unplanned maintenance, and potential damage to vital rotating machines. Accurately estimating unbalance in rotor–bearing systems is crucial for ensuring the reliable and efficient operation of machinery. This research paper presents a novel approach utilizing artificial neural networks (ANNs) to estimate the unbalance masses in a multidisk system based on simulation data from a nonlinear rotor–bearing system. Additionally, this study explores the effect of various operating parameters on oil film stability and vibration response through a combination of bifurcation diagrams, spectrum cascades, Poincare maps, and orbit and FFT plots. This study demonstrates the effectiveness of ANNs for unbalance estimation in a fast and accurate way and discusses the potential of ANNs in smart online condition monitoring systems.

Degradation Mechanism and Online Electrical Monitoring Techniques of Stator Winding Insulation in Inverter-Fed Machines: A Review

Inverter-fed machines are widely used in electric vehicle drive systems and have shown a trend toward high voltage and frequency in recent years. They are subjected to multiple types of stress during operation, causing potential short-circuit fault damage to the stator winding insulation. Online condition monitoring of the insulation before or in the early stage of the short circuit fault can effectively reduce maintenance costs and ensure its health. This paper reviews and summarizes the deterioration mechanism and the recent online electrical monitoring techniques. First, four types of failure stress and each type’s failure factors and mechanisms are analyzed. The coupling effect and overall process of multi-physical fields on stator insulation failure are considered. Secondly, the latest online electrical monitoring technologies are summarized. Each technique’s principles, methods, advantages, and disadvantages are analyzed. Finally, existing problems and possible directions for improvement in current research are discussed, focusing on their feasibility and accuracy in practical applications.

Remote assessment of music perception in pediatric cochlear implant recipients

Objective The primary objective of this study was to explore the feasibility of remotely assessing music perception in paediatric cochlear implant (CI) recipients. Pitch direction discrimination (PDD) and timbre recognition (TR) tests were administered remotely. We aimed to provide insights into the potential benefits and challenges of remote assessments. Design The study was exploratory in nature. All participants underwent remote assessments for the PDD and TR tests. Eight participants completed both online and face-to-face tests. Supervising parents in remote tests completed the System Usability Scale (SUS). Study Sample A cohort of 27 children with CI, averaging 11.19 years of age, participated in this study. Results In the online condition, the average PDD score was 3.29 semitones (st), the TR score was 37.86%, and the average duration for PDD and TR testing was 9.98 and 6.18 minutes, respectively. Face-to-face sessions had an average PDD score of 3.00 st, a TR score of 32.81% and durations of 10.20 and 5.42 minutes for PDD and TR tests, respectively. The SUS score averaged 64.04. Conclusion These findings contribute to the growing body of knowledge supporting the integration of remote assessments in audiological practices.

Crack fault diagnosis in rotor bearing system by transient and study state time domain analysis

Online condition monitoring methodologies for rotor dynamic systems are an emerging trend and an essential for safe system operation. During operation fatigue cracks in rotor shaft can lead to catastrophic failures if not identified at early stage. Therefore, these systems require a reliable crack fault detection methodology. The vibrations may induce in the system due to different type of faults, like shaft transverse cracks, oil whirl and whip. To make the detection methodologies robust and reliable, redundancy in crack detection methodologies is vital. The present research is a foolproof procedure to detect the travers fatigue crack in the rotor shaft. Rotor response, orbital pattern, and response FFT during transient (runup/cost down) and study state operations at 2X & 3X sub critical speeds are analyzed to identify the presence of crack in rotor bearing system. The rotor system is analyzed by numerical Finite Element Modeling (FEM) simulations and experimental means. Open Wedge Crack (OWC) and Breathing Wedge Crack (BWC) are modeled and their behavior is studied. The effectiveness of Newton Rapson method, Houbolt numerical method, and Harmonic Balance Method (HBM) in crack diagnosis are studied. Numerical FEM results are validated with experimental and published literature results. FEM simulated and experimental response FFT shows similar response behavior with presence of crack with 98 % correlation and less than 2 % error. FEM simulated and literature response orbital pattern at 2X sub critical backward speed are similar with less than 3 % error (97.76 % close) and at 2X sub critical forward speed are similar with less than 1 % error (99.33 %).

Artificial-Intelligence-Based Condition Monitoring of Industrial Collaborative Robots: Detecting Anomalies and Adapting to Trajectory Changes

The increasing use of collaborative robots in smart manufacturing, owing to their flexibility and safety benefits, underscores a critical need for robust predictive maintenance strategies to prevent unexpected faults/failures of the machine. This paper focuses on fault detection and employs multivariate operational data from a universal robot to detect anomalies or early-stage faults using test data from designed anomalous conditions and artificial-intelligence-based anomaly detection techniques called autoencoders. The performance of three autoencoders, namely, a multi-layer-perceptron-based autoencoder, convolutional-neural-network-based autoencoder, and sparse autoencoder, was compared in detecting anomalies. The results indicate that the autoencoders effectively detected anomalies in the examined complex and noisy datasets with more than 93% overall accuracy and an F1 score exceeding 96% for the considered anomalous cases. Moreover, the integration of trajectory change detection and anomaly detection algorithms (i.e., the dynamic time warping algorithm and sparse autoencoder, respectively) was proposed for the local implementation of online condition monitoring. This integrated approach to anomaly detection and trajectory change provides a practical, adaptive, and economical solution for enhancing the reliability and safety of collaborative robots in smart manufacturing environments.

The Effect of Bearing Impedance on Online Condition Monitoring for Rotor Winding Insulation of Doubly-Fed Induction Generator

The Effect of Bearing Impedance on Online Condition Monitoring for Rotor Winding Insulation of Doubly-Fed Induction Generator

Online condition monitoring for DC-link capacitors of three-level NPC converters using noninvasive signal injection

This paper introduces an online method for monitoring the health condition of the DC-link in three-level NPC converters. This method does not require hardware changes or modifications to the control algorithm. It involves injecting a zero-sequence signal, added to the system reference voltages to generate a neutral-point current injection. A square waveform with an interharmonic cycle frequency is used for the signal injection to minimize estimation errors caused by existing signals. This combined signal allows for the simultaneous estimation of the capacitor equivalent series resistance (ESR) and capacitance (C) at different frequency components using wavelet decomposition. Additionally, a balance between the magnitudes of the system reference voltage and the signal injection is established to prevent power quality issues. Besides, the capacitor parameters are estimated in the time-frequency domain, enabling tracking of capacitor degradation and wear-out failure. A comparison with a Fourier-based approach shows that this method provides highly accurate capacitor parameter estimation with less than 2% errors, instilling confidence in its results. Experimental results from a three-level NPC converter’s laboratory setup demonstrate the proposed method’s effectiveness.

Marketing Strategy for Online Condition Monitoring (Case Study: Nanoprecise Machine Doctor)

Today’s industry is facing ever-increasing competition. To stay competitive, a company needs to maintain the high reliability and productivity of its assets. Companies must invest in maintenance programs to prevent unplanned downtime and reach their optimal reliability. Predictive maintenance or condition-based maintenance is an important aspect of a maintenance program to maintain asset reliability. One emerging predictive maintenance tool, fueled by digital disruption, is online condition monitoring. Online condition monitoring provides diagnostics with shorter intervals than walking survey analysis with portable analyzers, allowing it to diagnose faults not detectable by other condition monitoring methods. Adikari Wisesa Indonesia, a firm specializing in maintenance services, has partnered with Nanoprecise Sci Corp and is the sole distributor of Machine Doctor sensors in Indonesia to enhance its maintenance service. However, the sales of Machine Doctor were suboptimal. This study aims to identify the business issue, provide analysis, and propose a solution to the business issue. The market is analyzed using the STP framework. Then, the general environment (PESTEL), industry environment (Five Forces), and competitor analysis are performed to better understand the external environment Adikari Wisesa is currently in. After analyzing the external environment, the internal environment of Adikari Wisesa is studied by using a Resource-Based View, VRIO, and Value Chain Analysis. Then, a SWOT analysis is performed summarizing the business situation of the company. A business solution is then proposed based on a TOWS matrix.

A comparative study of principal component analysis and kernel principal component analysis for photogrammetric shape-based turbine blade damage analysis

Photogrammetry is popular as a non-contact full-field data acquisition technique for machine condition monitoring purposes. Two popular implementations thereof are Digital Image Correlation (DIC) and 3D Point Tracking (3DPT). Since these two approaches require surface preparation in the form of applying speckle patterns or discrete markers, their use is negated in several industrial applications, such as the online condition monitoring and/or assessment of horizontal axis wind turbines. A shape-based photogrammetric approach that focuses on analysing changes in the form of a rotating blade’s boundary contour is a viable alternative that does not require any surface preparation. 3D shapes of a blade at a particular instance can be extracted from a pair of stereoscopic images of the blade. Shape Principal Component Descriptors (SPCDs) determined from applying Principal Component Analysis (PCA) to Fourier coefficients of chain-code shape signatures of the blade contour can be determined. These can be regarded as indicators of the form of the shape, and as the blade rotates, variations in the SPCDs can be investigated to better understand the dynamics of the blades. This paper focuses on the application and performance evaluation of data reduction and classification techniques for a novel shape-based photogrammetry condition monitoring technique. Investigations are conducted to show that applying data reduction methods to raw time domain SPCDs can result in successful classification of differently damaged blades. Post-processing strategies are developed to ensure a more robust shape based condition monitoring tool for analysing turbine blades. Kernel Principal Component Analysis (KPCA) is implemented and it is shown that it out-performs the conventional PCA in terms of classifying different blade damage modes. The feasibility of using multi-domain statistical features as feature vectors to which PCA or KPCA is applied for classification purposes is also investigated. Results indicating how well differently damaged blades can be distinguished are provided, and it is clearly illustrated that multi-domain statistical features are more robust to noise contamination in the signals compared to using the raw SPCDs data.

Research on transformer based online condition monitoring method for IPM

Abstract The Intelligent Power Module (IPM) has the integrated packaging, leading to the advantages of convenient use, safety and reliability. However, once it fails, it will cause the whole power supply system to be inoperative, and it is necessary to perform online Condition Monitoring (CM) of the IPM. In this paper, we extract the aging characteristics such as dynamic equivalent resistance, peak-to-peak value, switching frequency, and turn-off time only from the voltage and current of IPM drain–source port, and then propose a non-intrusive online CM method for the IPM based on the transformer neural network (TNN). We analyse the internal aging mechanism of the IPM, the changing law of aging features, and construct multi-dimensional aging fusion features, and then the TNN model is used to monitor early parameters drift of multi-dimensional fusion feature vectors and realize the accurate online prediction of IPM health condition. The experimental analysis results show that the fault prediction accuracy reaches 96%, and can realize the health CM under the condition of noise interference, weak aging features and few external observable points.

Condition monitoring and warning of a belt drive system based on a logical analysis of data regression-based residual control chart

The belt drive system is commonly used to transmit power in different industrial systems to maintain high performance and safety. Online condition monitoring techniques (CMTs) are used to monitor the operational conditions of such systems. Vibration-based monitoring techniques (VMT) are among the CMTs that are used in the analysis and diagnosis of the state of a belt drive system. Machine learning techniques are integrated with the VMT based on Industry 4.0 aspects for vibration analysis and fault diagnosis. Most of these techniques are based on the collection of vibration data from the belt drive system under known normal and different known faulty operations. This enables a fault to be diagnosed when it is detected during the operation of a system. In this paper, a new condition monitoring and warning mechanism is proposed to monitor the operational conditions of a belt drive system. The mechanism is based on an integration of a logical analysis of data regression (LADR) with a residual control chart (RCC). It uses vibration data from the belt drive system under normal operation only. This mechanism exhibits better performance in fault detection and also in interpreting the root cause of the faults in a belt drive system. Experimental investigations on a belt drive test rig have been carried out to collect vibration data based on a design of experiment for operational factors during normal operation. The LADR-RCC is implemented to monitor the operation of the belt drive system and detect faulty states. The accuracy of LADR is compared with multiple linear regression-based RCC, support vector regression-based RCC and random forest-based RCC. The LADR-RCC demonstrates significant enhancements in fault detection. The advantage of LADR-RCC over other model-based RCC is that it finds the root cause of a fault that is experienced in the system.

A Multidimensional Health Indicator Based on Autoregressive Power Spectral Density for Machine Condition Monitoring.

Condition monitoring (CM) is the basis of prognostics and health management (PHM), which is gaining more and more importance in the industrial world. CM, which refers to the tracking of industrial equipment's state of health during operations, plays, in fact, a significant role in the reliability, safety, and efficiency of industrial operations. This paper proposes a data-driven CM approach based on the autoregressive (AR) modeling of the acquired sensor data and their analysis within frequency subbands. The number and size of the bands are determined with negligible human intervention, analyzing only the time-frequency representation of the signal of interest under normal system operating conditions. In particular, the approach exploits the synchrosqueezing transform to improve the signal energy distribution in the time-frequency plane, defining a multidimensional health indicator built on the basis of the AR power spectral density and the symmetric Itakura-Saito spectral distance. The described health indicator proved capable of detecting changes in the signal spectrum due to the occurrence of faults. After the initial definition of the bands and the calculation of the characteristics of the nominal AR spectrum, the procedure requires no further intervention and can be used for online condition monitoring and fault diagnosis. Since it is based on the comparison of spectra under different operating conditions, its applicability depends neither on the nature of the acquired signal nor on a specific system to be monitored. As an example, the effectiveness of the proposed method was favorably tested using real data available in the Case Western Reserve University (CWRU) Bearing Data Center, a widely known and used benchmark.

Management of Implementing Indonesian Language Learning Based on The Blended Learning Model in Islamic Higher Education

Along with the disappearance of the Covid-19 pandemic, the government began to improve and make policies to restore the learning process. Learning that was originally online is now gradually becoming offline. Therefore, this study aims to look at the Indonesian language learning process that adopts the blended learning model. This research is a mixed methods research, namely quantitative and qualitative approaches. Quantitative research uses survey methods to determine the effectiveness of using blended learning models. And using descriptive qualitative to see students' perceptions of the learning process. The research informants were 60 students from the Indonesian language education study program at the Islamic Nusantara University in Bandung. Quantitative data were analyzed descriptively and data analysis was carried out in three stages, namely data reduction, presentation, and verification. The results of this study indicate that as many as 73% of students prefer face-to-face learning, according to him face-to-face learning is more effective and interactive in increasing student knowledge. However, not a few choose to stay online because it is more flexible. Other findings reveal that the selection of learning media must be adapted to the conditions of online or offline learning, when offline the selection of interactive media is highly recommended.

Calculating a conductor’s temperature-related sag as the limiting value for a Dynamic Line Rating

The ampacity — a term that refers to the maximum current in amperes — of existing overhead lines can be increased using Dynamic Line Rating (DLR) systems. Based on ambient online conditions and electrical power flow measurements, together with a forecast of future ambient conditions, the ampacity of overhead lines can be dynamically adjusted. In essence, the ampacity of an overhead line is determined by the operating temperature of the conductor that still guarantees the required safe distances to the objects under the overhead line. This paper presents a calculation algorithm for the sag of a conductor that addresses an unequal temperature of the conductor along the line as a response to an expected problem in the future, when increasing numbers of DLR sensors will be installed on or even near overhead lines. A novel approach to the sag-temperature calculation useful for a DLR is developed based on the linearization of cable equations. As a result, the computational costs are greatly reduced, which is an important factor when the DLR system includes a large number of overhead lines and processes them simultaneously. The presented methods are open and can be adapted for an arbitrary DLR system.

Online Muscle Activation Onset Detection Using Likelihood of Conditional Heteroskedasticity of Electromyography Signals.

The real-time, accurate detection of muscle activation onset (MAO) is significant for EMG-triggered control strategies in embedded applications like prostheses and exoskeletons. This paper investigates sEMG signals using the generalized autoregressive conditional heteroskedasticity (GARCH) model, focusing on variance. A novel feature, the likelihood of conditional heteroskedasticity (LCH) extracted from the maximum likelihood estimation of GARCH parameters, is proposed. This feature effectively distinguishes signal from noise based on heteroskedasticity, allowing for the detection of MAO through the LCH feature and a basic threshold classifier. For online calculation, the model parameter estimation is simplified, enabling direct calculation of the LCH value using fixed parameters. The proposed method was validated on two open-source datasets and demonstrated superior performance over existing methods. The mean absolute error of onset detection, compared with visual detection results, is approximately 65 ms under online conditions, showcasing high accuracy, universality, and noise insensitivity. The results indicate that the proposed method using the LCH feature from the GARCH model is highly effective for real-time detection of muscle activation onset in sEMG signals. This novel approach shows great potential and possibility for real-world applications, reflecting its superior performance in accuracy, universality, and insensitivity to noise.

What works better? 1-year outcomes of an effectiveness trial comparing online, telehealth, and group-based formats of a military parenting program.

The present study, conducted with a population of military families, examined the comparative effectiveness of three program formats of Adaptive Parenting Tools (ADAPT), a parenting program for families of school-aged children in which a National Guard or Reserve (NG/R) parent had returned from deployment to the post-9/11 conflicts. Despite well-documented need, parenting programs for NG/R families are scarce and often inaccessible. We predicted that both facilitator-delivered conditions (i.e., in-person group; individual telehealth) would result in stronger improvements in observed parenting than assignment to the online self-directed condition. We further proposed a noninferiority hypothesis wherein no significant difference would be detected between telehealth and group conditions. Families (N = 244; 87% Caucasian) were recruited from NG/R units in two midwestern states. Families (with a 5-12-year-old child) were randomized to one of three conditions: in-person multifamily group, individual telehealth, or an online, self-directed condition. The intervention was delivered using the same content across conditions, over 14 weeks (group, telehealth conditions) or 12 modules (online condition); either or both parents could participate. Intent-to-treat analyses supported both hypotheses: families in both in-person group and telehealth conditions showed significant improvements to observed parenting at 1-year postbaseline compared with those assigned to the self-directed online condition. This is the first study to demonstrate that in-person group and telehealth parenting programs are equally effective and that both are superior to a self-directed online program. Limitations include differences between the session lengths in each format, as well as greater attrition in the in-person format. (PsycInfo Database Record (c) 2024 APA, all rights reserved).