Novel Approach For Fault Diagnosis Research Articles

Handling Domain Drift and Unknown Fault Detection in Rotating Machinery Using Few‐Shot Learning With Data Scaling

ABSTRACTThis article presents a novel approach for fault diagnosis in rotating machinery using the few‐shot learning‐based unknown recognition and classification (FSLB‐UR&C) model. The core contribution of this research lies in addressing the challenges of domain drift, unknown fault detection, and uneven sampling intervals. The model effectively incorporates data scaling using Min–Max scaling to manage vibration data drift without altering the source data distribution, significantly extending the classification range. Principal component analysis visualizations substantiate the superior performance of Min–Max scaling over standard methods in processing drifted data, thus enhancing model accuracy. We validated the model on an in‐house bearing simulator and a coal conveyor motor, demonstrating its enhanced ability to classify drifted data and identify previously unknown faults. Additionally, time interpolation was applied to handle irregular sampling intervals, further optimizing the framework's robustness. Compared to other deep learning techniques, the FSLB‐UR&C model with data scaling exhibits markedly improved performance.

Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference

Modern industrial processes are typically characterized by large-scale and intricate internal relationships. Therefore, the distributed modeling process monitoring method is effective. A novel distributed monitoring scheme utilizing the Kantorovich distance-multiblock variational autoencoder (KD-MBVAE) is introduced. Firstly, given the high consistency of relevant variables within each sub-block during the change process, the variables exhibiting analogous statistical features are grouped into identical segments according to the optimal quality transfer theory. Subsequently, the VAE model is separately established, and corresponding T2 statistics were calculated. To improve fault sensitivity further, a novel statistic, derived from Kantorovich distance, is introduced by analyzing model residual from perspective of probability distribution. The thresholds of the both statistics were determined by kernel density estimation. Finally, monitoring results for both types of statistics within all blocks are amalgamated using Bayesian inference. Additionally, a novel approach for fault diagnosis is introduced. The feasibility and efficiency of the introduced scheme is verified through two cases.

Enhancing robotic manipulator fault detection with advanced machine learning techniques

The optimization of rotating machinery processes is crucial for enhanced industrial productivity. Automatic machine health monitoring systems play a vital role in ensuring smooth operations. This study introduces a novel approach for fault diagnosis in robotic manipulators through motor sound analysis to enhance industrial efficiency and prevent machinery downtime. A unique dataset is generated using a custom robotic manipulator to examine the effectiveness of both deep learning and traditional machine learning in identifying motor anomalies. The investigation includes a two-stage analysis, initially leveraging 2D spectrogram features with neural network architectures, followed by an evaluation of 1D MFCC features using various conventional machine learning algorithms. The results reveal that the proposed custom CNN and 1D-CNN models significantly surpass traditional methods, achieving an F1-score exceeding 92%, highlighting the potential of sound analysis for automated fault detection in robotic systems. Additional experiments were carried out to investigate 1D MFCC features with various machine learning algorithms, including KNN, DT, LR, RF, SVM, MLP, and 1D-CNN. Augmented with additional data collected from the locally designed manipulator, our experimental setup significantly enhances model performance. Particularly, the 1D-CNN stands out as the top-performing model on the augmented dataset.

Fault diagnosis in semiconductor manufacturing processes using a CNN-based generative adversarial network1

In the current industry, quality inspection in semiconductor manufacturing is of immense significance. Significant achievements have been made in fault diagnosis in fabricated semiconductor wafer manufacturing due to the development of machine learning. Since real-time intermediate signals are non-linear and time-varying, the signals undergo various distortions due to changes in equipment, material, and process. This leads to a drastic change in information in intermediate signals. This paper presents a fault diagnosis model for semiconductor manufacturing processes using a generative adversarial network (GAN). The study aims to address the challenges associated with efficient and accurate fault identification in these complex processes. Our approach involves the extraction of relevant components, development of a paired generator model, and implementation of a deep convolutional neural network. Experimental evaluations were conducted using a comprehensive dataset and compared against six existing models. The results demonstrate the superiority of our proposed model, showcasing higher accuracy, specificity, and sensitivity across various shift tasks. This research contributes to the field by introducing a novel approach for fault diagnosis, paving the way for improved process control and product quality in semiconductor manufacturing. Future work will focus on further optimizing the model and extending its applicability to other manufacturing domains.

A Novel Approach for Fault Diagnosis in Mechanical Systems Using Time-Frequency Analysis and Unsupervised Learning

A Novel Approach for Fault Diagnosis in Mechanical Systems Using Time-Frequency Analysis and Unsupervised Learning

A novel method for polymer electrolyte membrane fuel cell fault diagnosis using 2D data

This paper proposes a novel approach for fault diagnosis of polymer electrolyte membrane fuel cell (PEMFC) with two-dimension (2D) image data, and investigates its effectiveness of identifying faults at different PEMFCs in terms of discrimination capacity and robustness. In the analysis, one-dimension (1D) voltage data from single cell is converted to corresponding 2D image using signal-to-image conversion technique. Various features are then extracted from the 2D image data, and optimal features are determined using Fisher discriminant analysis (FDA). Test data from PEMFC at different faulty states, including flooding and dehydration states, is collected for the analysis, and the effectiveness of optimal features in discriminating various states is investigated using K-means clustering method. Moreover, diagnostic performance with 2D image data is compared to those using 1D voltage signals, such that its effectiveness can be better highlighted. Furthermore, with test data collected from two different single cells, robustness of proposed method can be illustrated.

A novel approach for fault diagnosis of induction motor with invariant character vectors

This paper proposes a novel approach for the fault diagnosis of induction motors. The invariant character vectors of fault signals are first extracted from the training samples. A single-class support vector machine (SC-SVM) is then used to detect the occurrence of faults, and the obtained invariant character vectors are employed as the desired references to classify the faults associated with the nearest neighbor classifier. The new diagnosis algorithm is validated for an induction motor (Y132S-4), which has shown excellent performance.

A Novel Approach for Fault Diagnosis in Wireless Sensor Networks

The following article has been retracted due to special reason of the author. This paper published in Vol.5 No. 2, 2013, has been removed from this site.

Evaluation of thermography image data for machine fault diagnosis

A novel approach for fault diagnosis of rotating machine based on thermal image investigation using image histogram features is proposed in this paper. Herein, the machine learning and statistical approach are adopted along with thermal image signal to machine condition diagnosis. Using thermal images, the information of machine condition can be investigated more simply than other conventional methods of machine condition monitoring. In this work, the behaviour of thermal image is investigated with different conditions of machine. A test-rig that represents the machine in industry was set up to produce thermal image data in the experiment. Some significant features have been extracted and selected by means of principal component analysis, and independent component analysis, and other irrelevant features have been discarded. The aim of this study is to retrieve thermal images by means of selecting a proper feature to recognise the fault pattern of the machine. The result shows that the classification process of thermal image features by support vector machine and other classifiers can serve machine fault diagnosis.

Fault diagnosis of time-delay complex dynamical networks using output signals

This paper proposes a novel approach for fault diagnosis of a time-delay complex dynamical network. Unlike the other methods, assuming that the dynamics of the network can be described by a linear stochastic model, or using the state variables of nodes in the network to design an adaptive observer, it only uses the output variable of the nodes to design an observer and an adaptive law of topology matrix in the observer of a complex network, leading to simple design of the observer and easy realisation of topology monitoring for the complex networks in real engineering. The proposed scheme can monitor any changes of the topology structure of a time-delay complex network. The effectiveness of this method is successfully demonstrated by virtue of a complex networks with Lorenz model.

FAULT DIAGNOSIS OF ELECTROHYDRAULIC SYSTEMS

Reliability is essential for electro-hydraulic systems due to the high energy densities associated with their operation. A failure can have catastrophic results, for example, if a contamination failure of hydraulic fluid at high pressure occurs. A novel approach for fault diagnosis of hydraulic systems has been proposed, using genetic algorithms as the parameter optimization method, and model based simulation. Performance tracking of critical parameters within the hydraulic system assesses subtle state changes and attempts to identify failure modes associated with these state changes. The proposed approach, which requires analysis of each component of the hydraulic system under normal operation and with specific, induced failure modes, has been successfully applied to a hydraulic system incorporating a servovalve and linear actuator. The results of this study provide a basis for future studies of more complex hydraulic components and systems.

A fuzzy diagnosis approach using dynamic fault trees

By incorporating digraph models, fault trees and fuzzy inference mechanisms in a unified framework, a novel approach for fault diagnosis is developed in this work. To relieve the on-line computation load, the fault origins considered in diagnosis are limited to the basic events in the cut sets of a given fault tree. The symptom occurrence order associated with each root cause is derived from system digraph with the qualitative simulation techniques. The implied candidate patterns are enumerated according to two proposed theorems and then encoded in the inference system with IF–THEN rules. The simulation results show that the proposed approach is not only feasible but also capable of identifying the most likely cause(s) of a hazardous event at the earliest possible time.