Real-time Condition Monitoring Research Articles

Innovative Method of Embedding Optical Fiber inside Titanium Alloy Utilizing Friction Stir Forming

The development of FBG (Fiber Bragg Grating) sensors is essential for intelligent parts of airplanes to achieve ultra-lightweight structures and intelligent aviation control. Awaiting solution is embedding technology of optical fiber sensors into the base material of the parts; however, it has been challenging to embed fibers into high melting temperature point alloys like titanium-based materials without having any defects. Present research fulfills the mentioned demands effectively by utilizing Friction Stir Forming (FSF). Precisely, optical fiber has been placed into a guide slit inside the titanium sheet. Then, FSF was applied to the surface of the titanium. As a result, titanium plasticizes and flows into the guide slit. This mechanically interlocks the optical fiber inside the titanium alloy. This solid-state stirring process can bury sensors inside the titanium to protect the sensor from harsh environments. Embedded sensors will detect the strain and temperature of the host titanium in real-time. Moreover, this research can have further considerable effects on the areas like aerospace and artificial intelligence systems that demand real-time condition monitoring systems.

How to get Lab Equivalent Oil Analysis 24/7

The established process for oil condition monitoring is to periodically take a sample and have it analysed in an oil laboratory. These laboratory measurements are governed by various technical standards (ASTM,DIN etc.) and customers rely on this periodic data to react to oil condition trends and/or step functions, to plan servicing and maintenance and to reduce asset downtime from failure. Real-time oil condition monitoring systems based on dielectric or impedance analysis of the oil have been available for some time but they only provide summary parameters that are hard to interpretate as they do not correlate with the laboratory oil analysis. In this paper we discuss the development of Spectrolytic’s Oil Condition Monitoring systems (FluidInspectIR®) and how, by working closely with our customers, we have developed a robust and affordable range of oil condition monitoring systems that gives our clients meaningful and understandable real time data of the same parameters and in the same units as they are commonly receive it from their oil laboratory analysis. These systems provide the customer the comfort of having quantitative and accurate key oil condition data at the touch of a button, while still utilising their standard practices through oil laboratory measurement to validate the predicted key oil parameters by the inline system.

AI-Based Low-Cost Real-Time Face Mask Detection and Health Status Monitoring System for COVID-19 Prevention

The outbreak of COVID-19 had brought a great challenge for the World Health Organization (WHO) in preventing the spreading of SARS-CoV-2. The Ministry of Health (MOH) of Malaysia introduced the MySejahtera mobile application for health monitoring and contact tracing. Wearing a face mask in public areas had been made compulsory by the Government. The overhead cost incurred in hiring the extra manpower to ensure all the visitors wear a face mask, check-in through MySejahtera and the status in MySejahtera is healthy before entering a premise. A low-cost solution is urgently needed to reduce the heavy overhead cost. An AI-Based Low-Cost Real-Time Face Mask Detection and Health Status Monitoring System (AFMHS) is proposed to perform real-time detection for the face mask and MySejahtera Check-In tickets by using artificial intelligence. MobileNetV2 was used for the detection and recognition of face and face masks. YOLOv3 was used for the detection of the region of interest for the MySejahtera Check-In ticket to locate the health and vaccination status of the visitor. Optical character recognition (OCR) is a technique that is used to detect the text captured in an image and encode the recognized text. OCR is implemented to recognize the text extracted from the ticket. Tesseract is used as the OCR engine in AFMHS. Raspberry-Pi-4B (Raspberry Pi Generation 4 Model B) with 4 GB RAM is used as the processing unit of AFMHS. The total cost of the AFMHS is only USD220. Extensive experimental tests were carried out to evaluate the performance of AFMHS. The optimum operation setup conditions are proposed to achieve 100% accuracy. The optimum operating distance for the face mask detector and MySejahtera Check-In ticket detector are 1.5m and 15cm respectively.

Real-Time Condition Monitoring System for Electrode Alignment in Resistance Welding Electrodes.

Electrode misalignment, produced by mechanical fatigue or bad adjustments of the welding gun, leads to an increase in expulsions, deformations and quality problems of the welding joints. Different studies have focused on evaluations of the influence of a misalignment of the electrodes and the final quality of the weld nugget. However, few studies have focused on determining a misalignment of the electrodes to avoid problems caused by this defect, especially in industrial environments. In this paper, a method for performing the condition monitoring of electrode alignment degradation was developed following previous research, which has shown the relationship between the misalignment of short-circuited electrodes and the magnetic field generated by them. This method was carried out by means of a device capable of measuring the magnetic field. Finally, an integral system for the detection of misalignments in real production lines is presented. This system set behavior thresholds based on the experimentation, allowing the condition monitoring of the alignment after each welding cycle.

Integration of Maintenance Management System Functions with Industry 4.0 Technologies and Features—A Review

Industry 4.0 is the latest technological age, in which recent technological developments are being integrated within industrial systems. Consequently, maintenance management of current industrial manufacturing systems is affected by the emergence of the technologies and features of Industry 4.0. This study aimed to conduct a comprehensive literature review to understand how Industry 4.0 technologies and features affect the various functions of maintenance management systems. The reviewing process was initiated by examining the most recent related literature in three different databases. In total, 54 articles were classified into three research categories. Then, the integration of the main functions and components of the adopted maintenance management model and the Industry 4.0 features and technologies were aligned, focusing on the driving force of predictive maintenance. The analysis focused mainly on the technical aspects of the integration process, including integration concepts and integration-assisting tools, identifying the main applications and highlighting the challenges identified in the analysed literature. The key findings were that the main functions of maintenance management systems are significantly influenced by different Industry 4.0 technologies, mainly artificial intelligence–machine learning, CPS, IoT, big data, augmented reality, and cloud computing, in terms of successful integration. Consequently, the overall system implied tangible improvements through the involvement of different Industry 4.0 features which promote real-time condition monitoring, enable data management and curation, increase coordination between various maintenance tasks, facilitate supervision through remote maintenance applications, and, overall, improve operations and productivity, reduce unplanned shutdowns and, as a result, reduce the associated costs. To provide research directions, examples, and methodologies for integrating the various maintenance management system functions with the cutting-edge Industry 4.0 technologies and features based on real and practical cases present in the reviewed literature, the review’s findings are comprehensively categorised and summarised.

(Invited) Switching Molecular Ionic Magnetism

Magneto-ionics of molecular based magnets, the ionic control of magnetism, promise ultralow-power sensor technologies, while the extent of reversible ion intercalation in turn is also the key state-of-charge feature in rechargeable battery electrodes. Here we report the reversible ion intercalation in molecular magnetic electrode, which simultaneously monitors the state of charge in battery and enables dynamic switching of its room-temperature magnetic transition. Microwave excited spin wave reveals lithiation degree in molecular-magnetic anode, enabling magneto-ionics towards the real-time monitoring of state of charge in rechargeable battery under a low magnetic field and radiofrequency. The structural vacancy and hydrogen-bonding networks in such molecular magneto-ionic compound enables the reversible lithiation and delithiation, which in turn, leads to a dynamical and reversible magnetization tunability.

Improving accuracy of damage quantification based on two-level consistency control of PZT layers

Structural health monitoring-based quantitative damage diagnosis technique plays a key role in real-time condition monitoring. Among the current research, piezoelectric (PZT) sensor and Guided Wave (GW) based damage quantification methods are promising, which normally establish a calibration model between GW feature and damage degree by experiments on batch specimens, and then conduct the calibration model on the monitored specimen. However, the accuracy of PZT and GW based damage quantification is affected by dispersion introduced by sensor network performance, structural material, and damage propagation among the adopted batch specimens. For improving the accuracy of damage quantification, this paper adopts PZT layer as sensor network and creatively implements theoretical and experimental research on batch PZT layers consistency control. On one hand, a two-level consistency control method based on multidimensional features-Euclidean distance is proposed to ensure the performance consistency of PZT layers placed on different specimens. On the other hand, experimental research on typical aircraft lug structures is also carried out to evaluate the requirement on performance consistency of PZT layers when performing quantitative damage diagnosis, and further verify the proposed two-level consistency control method. Experimental results show that the accuracy of damage quantification raises by 38% when the dispersion of different PZT layers is controlled within 5%.

Cutting tool wear monitoring in milling processes by integrating deep residual convolution network and gated recurrent unit with an attention mechanism

The conditions of cutting tool wear in the machining process have a great influence on the dimension accuracy and surface integrity of a workpiece. Real-time tool condition monitoring can alert a worker to changes in a tool in time before tool failure occurs to reduce downtime and improve product quality. However, traditional monitoring methods are no longer able to meet the requirements of real-time monitoring in current intelligent manufacturing. Therefore, an online monitoring method based on deep learning to monitor the cutting tool conditions is proposed In this research. In this monitoring model, one-dimensional wide-kernel convolution is used to filter the high-frequency noise in the multi-dimensional raw signals, and then a deep residual convolution layer is adopted to adaptively extract the multi-dimensional spatial features of the signals, and a gated recurrent unit (GRU) layer with an attention mechanism is employed to adaptively extract the hidden temporal features of the sequence data and adaptively assign the corresponding weights, and finally, a regression layer is used to predict the wear value of the tool according to the extracted features. The PHM 2010 challenge dataset is used to illustrate and evaluate this proposed method. The experiment results show that the proposed method can accurately predict the future flank wear values in real time based on the acquired multi-dimensional signals and avoid the complexity of the manual feature extraction.

Exploration of deep learning models for real-time monitoring of state and performance of anaerobic digestion with online sensors

The immediate response to the state disturbances of anaerobic digestion is essential to prevent anaerobic digestion failure. However, frequent monitoring of the state and performance of anaerobic digestion is challenging. Thus, deep learning models were investigated to predict the state and performance variables from online sensor data. The online sensor data, including pH, electric conductivity, and oxidation–reduction potential, were used as the input features to build deep learning models. The state and performance data measured offline were used as the labels. The model performance was compared for several deep learning models of convolutional neural network (CNN), long short-term memory (LSTM), dense layer, and their combinations. The combined model of CNN and bidirectional LSTM was robust and well-generalized in predicting the state and performance variables (R2 = 0.978, root mean square error = 0.031). The combined model is an excellent soft sensor for monitoring the state and performance of anaerobic digestion from electrochemical sensors.

A Multi-Factor Driven Model for Locomotive Axle Temperature Prediction Based on Multi-Stage Feature Engineering and Deep Learning Framework

Recently, with the increasing scale of the volume of freight transport and the number of passengers, the study of railway vehicle fault diagnosis and condition management is becoming more significant than ever. The axle temperature plays a significant role in the locomotive operating condition assessment that sudden temperature changes may lead to potential accidents. To realize accurate real-time condition monitoring and fault diagnosis, a new multi-data-driven model based on reinforcement learning and deep learning is proposed in this paper. The whole modeling process contains three steps: In step 1, the feature crossing and reinforcement learning methods are applied to select the suitable features that could efficiently shorten the redundancy of the input. In step 2, the stack denoising autoencoder is employed to extract deep fluctuation information in the features after the reinforcement learning. In step 3, the bidirectional gated recurrent unit algorithm is utilized to accomplish the forecasting model and achieve the final results. These parts of the integrated modeling structure contributed to increased forecasting accuracy than single models. By analyzing the forecasting results of three different data series, it could be summarized that: (1) The proposed two-stage feature selection method and feature extraction method could greatly optimize the input for the predictor and form the optimal axle temperature forecasting model. (2) The proposed hybrid model can achieve satisfactory forecasting results which are better than the contrast algorithms proposed by other researchers.

전처리 되지 않은 진동 신호로 플랭크 웨어 예측하는 1D-CNN, 2D-CNN과 LSTM로 구성된 인공지능 네트워크

Turning processing machines have been widely employed due to their precision and versatility. As the number of cycles increases, the performance of these devices generally degrades owing to tool wear. Therefore, real-time tool condition monitoring (TCM) that utilizes statistical or machine learning methods has gained significant attention in both academia and industry. However, these methods necessitate sufficient data pre-processing, requiring a high degree of academic understanding as well as significant amount of time. Therefore, this research proposes an advanced artificial intelligence network to monitor a wide range of tools by utilizing raw signals without pre-processing. This study first developed a method consisting of 1D and 2D multi filters convolution neural networks (CNNs) and stacked long short term memories (LSTM). To activate the LSTM in a stable manner, the CNN plays a crucial role in dimensionality reduction. Accordingly, two dimensionality reduction approaches were proposed. These were layer normalized 1D&2D-CNN Multi filters. Then, following multi filters, the stacked LSTM was used to extract the sequential features. Next, the performance of the proposed network using the NASA milling dataset was observed and compared between the 1D/2D-CNN without Flank wear information, pre-processing, and previous research network inclusion. Consequently, although the 1D-CNN method did not have them, it achieved a similar level of accuracy as the present method using past Flank wear input.

Identification of delamination severity in a tapered FRP composite plate

The typical failure in fibre-reinforced polymer (FRP) laminated composites is delamination. It reduces structural stiffness and changes in dynamic responses, which can be successfully used for assessing structural health monitoring (SHM) of composite structures. SHM often requires the solution of an inverse problem. This study focuses on solving the inverse problem with minimal computational time to predict delamination size, in-plane location, and interface. For the inverse model, two computational intelligence algorithms, the surrogate-assisted real-coded genetic algorithm (SARGA) and an artificial neural network (ANN) were used. A surrogate model is a fast-executing model for predicting the shift in the natural frequency using a forward ANN. For ANN training, the database size was optimized. The layerwise theory was solved using the finite element method for a laminated tapered FRP plate with ply drop-off, and ‘constrained mode’ is used to model the delamination. The experimental modal analysis was conducted on a glass-fibre reinforced polymer tapered composite plate with one intact plate and three artificially delaminated plates. The algorithms are validated using numerically simulated and experimentally measured frequencies. The numerical validation showed a better prediction of delamination size, in-plane location, and interface when compared with the experimental validation. Nevertheless, SARGA can reasonably predict the size, in-plane (x) location and interface of the delamination with an average overlapping ratio of 72.89%. The comparison of algorithms demonstrates the application of SARGA with the frequency-based approach for delamination detection and real-time condition monitoring in real-world applications.

Unsupervised Tool Wear Monitoring in the Corner Milling of a Titanium Alloy Based on a Cutting Condition-Independent Method

Real-time tool condition monitoring (TCM) for corner milling often poses significant challenges. On one hand, corner milling requires configuring complex milling paths, leading to the failure of conventional feature extraction methods to characterize tool conditions. On the other hand, it is costly to obtain sufficient test data on corner milling for most of the current pattern recognition methods, which are based on the supervised method. In this work, we propose a time-frequency intrinsic feature extraction strategy of acoustic emission signal (AEs) to construct a cutting condition-independent method for tool wear monitoring. The proposed new feature-extraction strategy is used to obtain the tool wear conditions through the intrinsic information of the time-frequency image of AEs. In addition, an unsupervised tool condition recognition framework, including the unsupervised feature selection, the clustering based on adjacent grids searching (CAGS) and the density factor based on CAGS, is proposed to determine the relationship between tool wear values and AE features. To test the effectiveness of the monitoring system, the experiment is conducted through the corner milling of a titanium alloy workpiece. Five metrics, PUR, CSM, NMI, CluCE and ClaCE, are used to evaluate the effectiveness of the recognition results. Compared with the state-of-the-art supervised methods, our method provides commensurate monitoring effectiveness but requires much fewer test data to build the model, which greatly reduces the operating cost of the TCM system.

Accurate Detection of Bearing Faults Using Difference Visibility Graph and Bi-Directional Long Short-Term Memory Network Classifier

This article proposes a novel bearing fault detection framework for the real-time condition monitoring of induction motors based on difference visibility graph (DVG) theory. In this regard, the vibration signals of healthy as well as different rolling bearing defects were acquired from both fan-end and drive-end accelerometers. These data were recorded for three different bearing defects and under four loading conditions. The acquired vibration time series were converted to a topological network using DVG. From the transformed vibration data in the graph domain, degree distribution (DD) was selected as feature to discriminate different fault networks. Using analysis of variance test and false discovery rate correction, most discriminative DD features were selected. These features were subsequently fed as inputs to a deep learning model, i.e., a bidirectional long short-term memory network classifier for fault classification. In this study, 112 classification problems have been addressed, and for all of them, the proposed approach delivered very high fault detection accuracy. Finally, the classification performance of the proposed framework is compared with other well-known deep-learning classifiers all of which delivered satisfactory results.

The Vision-Based Data Reader in IoT System for Smart Factory

The proposed research is based on a real plastic injection factory for cutting board production. Most existing approaches for smart manufacturing tried to build the total solution of IoT by moving forward to the standard of industry 4.0. Under the cost considerations, this will not be acceptable to most factories, so we proposed the vision based technology to solve their immediate problem. Real-time machine condition monitoring is important for making great products and measuring line productivity or factory productivity. The study focused on a vision-based data reader (VDR) in edge computing for smart factories. A simple camera embedded in Field Programmable Gate Array (FPGA) was attached to monitor the screen on the control panel of the machines. Each end device was preprogrammed to capture images and process data on its own. The preprocessing step was then performed to have the normalized illumination of the captured image. A saliency map was generated to detect the required region for recognition. Finally, digit recognition was performed and the recognized digits were sent to the IoT system. The most significant contribution of the proposed VDR system used the compact deep learning model for training and testing purposes to fit the requirement of cost consideration and real-time monitoring in edge computing. To build the compact model, different convolution filters were tested to fit the performance requirement. Experimentations on a real plastic cutting board factory showed the improvement in manufacturing products by the proposed system and achieved a high digit recognition accuracy of 97.56%. In addition, the prototype system had low power and low latency advantages.

Ensuring Data Freshness for Blockchain-Enabled Monitoring Networks

The Age of Information (AoI) is a recently proposed metric for quantifying data freshness in real-time status monitoring systems, where timeliness is of importance. In this article, the problem of characterizing and controlling the AoI is studied in the context of blockchain-enabled monitoring networks (BeMNs). In BeMN, status updates from sources are transmitted and recorded in a blockchain. To investigate the statistical characteristics of the AoI in BeMN, the transmission latency and the consensus latency are first rigorously modeled. Then, the average AoI, the AoI violation probability, and the peak AoI violation probability are derived in a closed form so as to quantify the performance of BeMN. Furthermore, a simplified form is derived for the AoI violation probability, and it is shown that this quantity can capture the upper or lower bounds of the actual AoI violation probability. Simulation results show that each BeMN parameters (i.e., target successful transmission probability, block size, and timeout) can have conflicting effects on the AoI-related performance. Subsequently, design insights are provided to maintain the freshness of the status data in BeMN. Then, experimental results with a real Hyperledger Fabric platform further validate the accuracy of our modeling and analysis.

Lithiating magneto-ionics in a rechargeable battery

Magneto-ionics, real-time ionic control of magnetism in solid-state materials, promise ultralow-power memory, computing, and ultralow-field sensor technologies. The real-time ion intercalation is also the key state-of-charge feature in rechargeable batteries. Here, we report that the reversible lithiation/delithiation in molecular magneto-ionic material, the cathode in a rechargeable lithium-ion battery, accurately monitors its real-time state of charge through a dynamic tunability of magnetic ordering. The electrochemical and magnetic studies confirm that the structural vacancy and hydrogen-bonding networks enable reversible lithiation and delithiation in the magnetic cathode. Coupling with microwave-excited spin wave at a low frequency (0.35 GHz) and a magnetic field of 100 Oe, we reveal a fast and reliable built-in magneto-ionic sensor monitoring state of charge in rechargeable batteries. The findings shown herein promise an integration of molecular magneto-ionic cathode and rechargeable batteries for real-time monitoring of state of charge.

Physiological responses and stress levels of high-speed rail train drivers under various operating conditions - a simulator study in China

ABSTRACT The stress level of high-speed rail (HSR) train drivers directly impacts their job performance and thus the safety of HSR operations. This paper attempts to develop a quantitative understanding of train drivers’ stress levels and the contributing factors by the experimental study conducted in a realistic HSR simulator. An extensive statistical analysis found that the ultra-short-term heart rate variability metrics could differentiate different stress levels. Three different machine-learning classifiers were evaluated for stress detection, including support vector machine (SVM), random forests (RF), and K-nearest neighbour (KNN). The RF model was shown to perform the best in terms of robustness and classification accuracy. Moreover, the research found that the driver’s stress level should be detected rather than the type of stressor. The findings from this research could contribute to the development of real-time HSR driver condition monitoring systems and the improvement of current HSR operation safety regulations.

Joint optimization of inspection and maintenance strategy for complex multi-component systems using a quantum-inspired genetic algorithm

Advances in sensor and data technology enable real-time condition monitoring, thus extending the opportunities for condition-based maintenance (CBM) to be applied in practice. In this paper, a joint inspection and maintenance strategy for multi-component systems is proposed. The objective of this strategy is to minimize the long-run expected operational cost by jointly considering the inspection frequency of each health monitor in the system and the threshold for the maintenance initialization. To find the optimal strategy, a dynamic Bayesian network-based maintenance model is developed at first to provide reasoning of the dynamic reliability of degrading components in the multi-component system, in which complex relationship among inspections by different health monitors, different failure modes in the system, and different maintenance actions to system components are considered and quantified. Then, a quantum-inspired genetic algorithm (QGA) is proposed to optimize the strategy. With quantum encoding method, improved rotation gate, and specially designed crossover and mutation operators, the QGA is able to find the optimal strategy for multi-component systems with a general system structure. An example simplified from real practice is presented to demonstrate the effectiveness and advantages of the proposed strategy and the optimization algorithm, with comparison to similar strategies and traditional intelligent optimization algorithms.

A Comprehensive Review on Signal-Based and Model-Based Condition Monitoring of Wind Turbines: Fault Diagnosis and Lifetime Prognosis

Wind turbines play an increasingly important role in renewable power generation. To ensure the efficient production and financial viability of wind power, it is crucial to maintain wind turbines’ reliability and availability (uptime) through advanced real-time condition monitoring technologies. Given their plurality and evolution, this article provides an updated comprehensive review of the state-of-the-art condition monitoring technologies used for fault diagnosis and lifetime prognosis in wind turbines. Specifically, this article presents the major fault and failure modes observed in wind turbines along with their root causes, and thoroughly reviews the techniques and strategies available for wind turbine condition monitoring from signal-based to model-based perspectives. In total, more than 390 references, mostly selected from recent journal articles, theses, and reports in the open literature, are compiled to assess as exhaustively as possible the past, current, and future research and development trends in this substantial and active investigation area.