Machine Condition Monitoring Research Articles

Generation of Unmeasured Loading Levels Data for Condition Monitoring of Induction Machine Using Machine Learning

Generation of Unmeasured Loading Levels Data for Condition Monitoring of Induction Machine Using Machine Learning

Condition monitoring of Industrial machine’s transmission elements – MSDF feature extraction approach

ABSTRACT Predictive maintenance is a modern Industry 4.0 strategy in which machines are continuously monitored to detect flaws and prevent breakdowns before they occur. A single sensor focuses on a single variable while neglecting larger information components, resulting in poor data quality and an increased risk of issues in critical rotating equipment. Multi-sensory configuration technology has been developed to collect huge amounts of data from a machine in order to enhance monitoring capabilities in terms of precision, resolution, efficiency, resilience, and trustworthiness of the overall system. The goal of this work is to provide an integrated perspective on machine monitoring using the Multi Sensor Data Fusion (MSDF) technique. On four fault bearings, a case study contrasts the results of single and multiple sensors. A feature-level data fusion method is used, in which computations using time-domain vibration signature data are utilised to build a fusional vector, which is then classified using SVM and analysed with Gaussian kernels. The experimental results suggest that the proposed Gaussian kernel with SVM technique outperforms single sensor data interpretation in terms of classification accuracy and generalisation capability. It is an efficient way for finding defects in rotating machinery in excessively noisy environments.

Multi-Node Feature Learning Network Based on Maximum Spectral Harmonics-to-Noise Ratio Deconvolution for Machine Condition Monitoring

Since the cyclostationarity in vibration signals is the key to judge the rotating machine health state, spectral harmonics-to-interference ratio (SHIR) has been used to construct single node feature learning network (SHIR-based blind deconvolution, BD-SHIR) to realize condition monitoring of machine. However, BD-SHIR still has several obvious limitations, including the need for prior fault information and the tendency to fall into local optimal solutions which will affect its feature learning and state monitoring performance. Therefore, this paper proposes a multi-node feature learning network based on BDSHIR, which does not rely on prior information, multi-node adaptive BDSHIR (MABD-SHIR). It uses each filter in the 1/3 binary tree filter bank to design each initial node (filter) in the learning network correspondingly, and introduces an adaptive fault characteristic frequency (FCF) detection process. Since this initialization can give some filters close to the fault resonant band, iterations starting from these nodes are more likely to detect the precise FCF and converge to the optimal solution. Finally, MABD-SHIR can obtain multiple local optimal solutions, among which the one with the largest SHIR is generally closer to the global optimal solution than the one obtained by BD-SHIR. Simulation and experimental data of defective rotating machinery verify the effectiveness of MABD-SHIR in machinery condition monitoring and fault feature learning. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the problems that the rotating machine condition monitoring based on BDSHIR is easy to prematurely fall into local optimal solution and requires prior fault information. These problems can be effectively solved by extending BDSHIR from single node structure to multi-node structure and introducing adaptive period detection technique (A-DPT). The core idea is to start iterations from multiple initial filters and to detect the FCF adaptively during each iteration. Multiple features conforming to filtered signals’ SHIR maximization can be finally learned. Therefore, in this paper, MABD-SHIR is proposed, which is equivalent to a multi-node feature learning network. Since the objective function of BD is usually non-convex, MABD-SHIR can obtain multiple local optimal solutions without requiring prior FCFs. This is more likely to achieve a global optimal solution than BDSHIR, which starts iteration from only one initial filter and ends up with one local optimal solution. In addition, the objective function of MABD-SHIR has lower mathematical complexity, which reduces the difficulty of optimization.

Hybrid machine condition monitoring based on interpretable dual tree methods using Wasserstein metrics

Hybrid machine condition monitoring based on interpretable dual tree methods using Wasserstein metrics

Intelligent Machinery Fault Diagnosis With Event-Based Camera

Event-based cameras are the emerging bio-inspired technology in vision sensing. Different from the traditional standard cameras, the event-based cameras asynchronously record the brightness change per pixel, and have the great merits of high temporal resolution, low energy consumption, high dynamic range, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> . While the event-based cameras have been initially exploited in several common vision-based tasks in the recent years, the investigation on machine condition monitoring problem is quite limited. This paper offers the first attempt in the current literature on exploring the contactless event vision data for machine fault diagnosis. A vibration event representation is proposed to transform the event records into typical data samples, and a deep convolutional neural network model is used for processing the event information. To enhance the model robustness against environmental noisy vision events, an event data augmentation method is proposed to introduce variations of the event patterns. A deep representation clustering method is further proposed to improve the pattern recognition performance with respect to different machine health conditions. Experiments on the event vision-based rotating machine fault diagnosis problem are carried out. It is extensively validated that high fault diagnosis accuracies can be obtained using the vision data from the event-based cameras, which are competitive with the popular accelerometer data. Considering the properties of flexibility, portability and data recognizability, the event-based cameras thus provide a promising new tool for contactless machine health condition monitoring and fault diagnosis.

A bibliometric analysis on condition monitoring of machinery using IR Thermography

In order to extend the life of machinery, condition monitoring of equipment has become crucial in every industry or power plant. IR Thermography is a strong tool for condition monitoring since it can detect flaws earlier than other techniques. The most important technique for condition monitoring is infrared thermography. Machine condition monitoring has evolved along with machine maintenance, from manual maintenance through approaches involving the use of sensors to the now under discussion methods and techniques centered on shared automation, data processing, and exchange. The purpose of this paper is to give a brief summary of the academic work that has been done on using IR thermography to monitor the status of machinery. In order to present an up-to-date, content-based analysis that includes bibliometric performance analysis and systematic literature evaluation, this paper evaluates the body of current literature. The writers may concentrate on identifying the most important researchers, journals, and publications, as well as the most significant and influential researchers, thanks to the mix of literature review methodologies used. These conclusions have prompted the authors to outline research trends pertinent to the studied domain and, in addition, to identify potential future research goals from engineering viewpoints.

Machine Health in a Click: A Website for Real-Time Machine Condition Monitoring

Machine Health in a Click: A Website for Real-Time Machine Condition Monitoring

An Adaptive Parallel Feature Learning and Hybrid Feature Fusion-Based Deep Learning Approach for Machining Condition Monitoring.

The rapid development of information and communication technologies has facilitated machining condition monitoring toward a data-driven paradigm, of which the Industrial Internet of Things (IIoT) serves as the fundamental basis to acquire data from physical equipment with sensing technologies as well as to learn the relationship between the system condition and the collected condition monitoring data. However, most data-driven methods suffer from using a single-domain space, ignoring the importance of the learned features, and failing to incorporate the handcrafted features assisted by domain knowledge. To solve these limitations, a novel deep learning approach is proposed for machining condition monitoring in the IIoT environment, which consists of three phases, including: 1) the unsupervised parallel feature extraction; 2) adaptive feature importance weighting; and 3) hybrid feature fusion. First, separate sparse autoencoders are utilized to conduct the unsupervised parallel feature extraction, which enables to learn abstract feature representation from multiple domain spaces simultaneously. Then, an attention module is designed for the adaptive feature importance weighting, which can assign higher weights to those critical features accordingly. Moreover, a hybrid feature fusion is deployed to complement the automatic feature learning and further yield better model performance by fusing the handcrafted features assisted by domain knowledge. Finally, a real-life case study and extensive experiments have been conducted to show the effectiveness and superiority of the proposed approach.

A high sensitivity cross-capacitive sensor for water droplets and bubble detection in hydraulic oil.

The presence of moisture and air in hydraulic oil will seriously affect the reliability of machines. This paper proposes a new cross-capacitive oil pollution detection sensor, which is based on the Thompson and Lampard theorem. The sensing unit consists of four identical copper electrodes with infinitesimally small gaps. The sensor can effectively distinguish water droplets and air bubble pollutants mixed in the oil through the pulse direction of the signal. Compared with traditional capacitive sensors, the sensor has a significant improvement in detection accuracy and detection throughput. In this paper, the relationship between the cross-capacitance value with the dielectric constant and the frequency in an alternating electric field was deduced, and the best excitation frequency was chosen as 1.9MHz. Experiments show that the sensor can effectively detect water droplets of 140-160 µm and bubbles of 170-190 µm and has good linearity for detecting water droplets and air bubbles of different sizes. The sensor provides a new method for machine condition monitoring of hydraulic systems.

Interpretable fusion methodology of health indices with an application to industrial turbine cavitation condition monitoring.

Using health indices (HIs) to characterize machine conditions is greatly helpful to prevent machine failures and their subsequent catastrophe. Fusion and interpretation of the main contributions of HIs to machine condition monitoring are still challenging. In this paper, an interpretable fusion methodology of HIs is proposed for machine condition monitoring. The proposed methodology begins with elements of statistical learning for classification, following by an essence of how HIs are fused with their associated linear weights to realize machine condition monitoring. One main contribution of this paper gives a theoretical justification for positive and negative weights of the proposed fusion methodology for understanding their importance for machine condition monitoring and making the proposed methodology physically interpretable. In order to be suitable for two practical situations, in which whether faulty data are available or not, two solutions including an offline solution with healthy and faulty datasets and an online solution with only available healthy datasets are suggested to estimate interpretable weights of the proposed methodology. Finally, industrial turbine cavitation status data collected from our group are used to verify the proposed methodology and show its superiority to two existing popular machine fault diagnosis methods. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

Condition monitoring of permanent magnet AC machines for all‐electric transportation systems: State of the art

AbstractThe current state of the art on emerging and efficient techniques for condition monitoring of permanent magnet (PM) alternating‐current (AC) machines deployed in electric vehicle (EV) applications is presented. The discussion includes the most common and specific types of faults in PM motors, such as rotor demagnetisation and stator inter‐turn faults, respectively. Fault indicators, such as voltage (vs) and current (is) signals and machine signatures based on motor back electromotive force (EMF) (EB) and magnetic flux (ϕ), are taken into account as a measuring quantity in diagnosing motor faults. Other signatures, including thermal analysis, acoustic noise, and vibrations, are also illustrated as some of the emerging techniques in estimating the performance of EV motors while under operations. In addition, various fault modelling methods, condition monitoring techniques, and comprehensive approaches applied in diagnosing the effect of machine faults during its incipient stages are illustrated. Since most of the fault diagnostic techniques discussed here include only machine‐based quantities as fault indices/indicators, the provided solutions are therefore found to be more reliable and accurate for diagnosing the motor faults. This comprehensive review study is inclusive of the existing fault diagnostic techniques, which are currently employed in industrial and commercial practices, in addition to the new methodologies proposed by the authors. All the given condition monitoring schemes therefore seem significantly vital in estimating the state of health of PM AC machines while under operation in all‐electric transportation systems.

A Few-Shot Learning Based Fault Diagnosis Model Using Sensors Data from Industrial Machineries

Efficient maintenance in the face of complex and interconnected industrial equipment is crucial for corporate competitiveness. Traditional reactive approaches often prove inadequate, necessitating a shift towards proactive strategies. This study addresses the challenges of data scarcity and timely defect identification by providing practical guidance for selecting optimal solutions for various equipment malfunction scenarios. Utilizing three datasets—Machine Sound to Machine Condition Monitoring and Intelligent Information (MIMII), Case Western Reserve University (CWRU), and Machinery Failure Prevention Technology (MFPT)—the study employs the Short-Time Fourier Transform (STFT) as a preprocessing method to enhance feature extraction. To determine the best preprocessing technique, Gammatone Transformation, and raw data are also considered. The research optimizes performance and training efficiency by adjusting hyperparameters, minimizing overfitting, and using the KERAS Early Halting API within resource constraints. To address data scarcity, which is one of the major obstacles to detecting faults in the industrial environment, Few-shot learning (FSL) is employed. Various architectures, including ConvNeXt Base, Large MobileNetV3, ResNet-18, and ResNet-50, are incorporated within a prototypical network-based few-shot learning model. MobileNet’s lower parameter count, high accuracy, efficiency, and portability make it the ideal choice for this application. By combining few-shot learning, MobileNet architecture, and STFT preprocessing, this study proposes a practical and data-efficient fault diagnosis method. The model demonstrates adaptability across datasets, offering valuable insights for enhancing industrial fault detection and preventive maintenance procedures.

A Self‐Decoupled and High‐Resolution 2D Displacement Sensor Based on Triboelectric Nanogenerator for Manipulator Precision Positioning

Abstract2D displacement sensor (2DDS) is significant in precision manufacturing positioning, machine condition monitoring, robotic manipulation, and human–computer interaction system. However, the reported 2DDSs have severe limitations, such as low accuracy, poor decoupling, and lack of smart signal analysis. Herein, a self‐decoupled and high‐resolution 2DDS based on two freestanding triboelectric nanogenerators (F‐TENGs) is presented. This sensor achieves self‐decoupling by two orthogonal and independent 1D displacement sensors with low‐cost grating‐structured PCB. The test results of the sensor exhibit a high accuracy ≥99.06% (1D) and 98.94% (2D). Also, the experimental and simulation results demonstrate that this sensor has a high resolution of 200 µm and the function of initial position identification. A 2D displacement sensing system is developed that is capable of collecting F‐TENGs’ open‐circuit voltages in real‐time and performing 2D trajectory synthesis and display. This work expands the potential application of the TENG‐based 2DDS in robotic precision machining.

Special Issue on Machine Condition Monitoring and Fault Diagnosis: From Theory to Application

Modern machines are becoming more complex in structure and are operating under harsher loading and operational conditions [...]

A Fourier-based explanation of 1D-CNNs for machine condition monitoring applications

Neural networks (NN) have generated extensive interest in the field of machine condition monitoring (MCM). Many applications are however adapting structures and approaches from fields where NNs are highly established (e.g., image classification). This is done despite many neural network layers presenting strong similarities to signal processing steps that are well established in MCM. This paper aims at providing a mathematical analysis of typical NN architectures and layers, with specific attention to similarities to common signal processing steps such as filtering, downsampling, and enveloping. The set of strong analogies between NN and traditional MCM tools enables this work to provide MCM-specific guidelines for the design and tuning of NN architectures for MCM-specific applications. Most MCM applications are often characterised by periodic and cyclostationary signals, a situation not frequently encountered in many other NN applications. Hence, the Fourier-based explanation of the typical NN layers will be specific to the solution of typical MCM problems (e.g., diagnostics of gears and bearings). The study is aligned with the current trends of explainable AI and physics informed neural networks (PINN), in the sense that it aims at producing mathematical rules for a rational design of the network, drawing on the expertise accumulated in decades of signal processing for MCM. This is however done without upsetting traditional NN architectures, but rather trying to provide clear reasons for the setting of network parameters. The analytical work will be verified with numerical tests, which will also enable practical considerations, and by application of the suggested guidelines to the popular Case Western Reserve University (CWRU) experimental dataset.

Analysis of contact behaviours and vibrations in a defective deep groove ball bearing

Rolling element bearings are vital parts for rotating machinery. When a defect occurs on the surface of the bearing raceway or rolling element, giving rise to the abnormal vibration of the bearing and even the rotating machine. Thus, it is of great significance to understand the vibration characteristics of the bearing for fault diagnosis and machine condition monitoring. In recent decades, researches on defect-induced bearing vibration in machine condition monitoring have attracted increasing attention. Model-based investigation is a highly useful method for enhancing our understanding of defect-induced vibration and fault excitation mechanism of the bearing. It also serves as a basis for establishing the theory of bearing failure. With this in mind, a novel dynamic model of deep groove ball bearing (DGBB) with a localized outer race defect is proposed in this paper. In this model, the additional displacement excitation which is modelled as a piecewise function based on kinematics is considered, and the angle-based contact force is developed and modelled as a piecewise function taking into account the angular position, collision velocity, and impact force. In addition, an analytical formulation of the angle-varying effective stiffness matrix of the DGBB with a localized raceway defect of varying size is established. The proposed dynamic model is used to study the influences of different defect scenarios (i.e. angular positions and widths) on the time-varying contact stiffness, contact force, spectral characteristics, and bearing vibrations. The comparisons between the simulations and the experiments show that the proposed model is effective.

Anomalous sound detection for machine condition monitoring using 3D tensor representation of sound and 3D deep convolutional neural network

Anomalous sound detection for machine condition monitoring using 3D tensor representation of sound and 3D deep convolutional neural network

Machine condition monitoring in FDM based on electret microphone, SVM, and neural networks

Machine condition monitoring in FDM based on electret microphone, SVM, and neural networks

Maximizing model generalization for machine condition monitoring with Self-Supervised Learning and Federated Learning

Deep Learning (DL) can diagnose faults and assess machine health from raw condition monitoring data without manually designed statistical features. However, practical manufacturing applications require robust and repeatable solutions that can be trusted in dynamic environments.Machine data is often unlabeled and from very few health conditions (e.g., only normal operating data). Furthermore, models often encounter shifts in domain as process parameters change and new categories of faults emerge. Traditional supervised learning may struggle to learn compact, discriminative representations that generalize to these unseen target domains since it depends on having plentiful classes to partition the feature space with decision boundaries. Transfer Learning (TL) with domain adaptation attempts to adapt these models to unlabeled target domains but assumes similar underlying structure that may not be present if new faults emerge. This study proposes focusing on maximizing the feature generality on the source domain and applying TL via weight transfer to copy the model to the target domain. Specifically, Self-Supervised Learning (SSL) with Barlow Twins may produce more discriminative features for monitoring health condition than supervised learning by focusing on semantic properties of the data. Furthermore, Federated Learning (FL) for distributed training may also improve generalization by efficiently expanding the effective size and diversity of training data by sharing information across multiple client machines. Results show that Barlow Twins outperforms supervised learning in an unlabeled target domain with emerging motor faults when the source training data contains very few distinct categories. Incorporating FL may also provide a slight advantage by diffusing knowledge of health conditions between machines. Future work should continue investigating SSL and FL performance in these realistic manufacturing scenarios.

Identification and evaluation of the characteristics of a selected commercial mems based vibration sensor for the machine condition monitoring

Identification and evaluation of the characteristics of a selected commercial mems based vibration sensor for the machine condition monitoring