Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating LSTM Autoencoder Detector and Diagnostic Classifiers

Mallak, Ahlam; Fathi, Madjid

doi:10.3390/s21020433

Cited by 44 publications

(16 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine faults are a major cause of unexpected downtime and production loses of industries [1]. Rotating machines constitute an integral part of most industrial equipment, especially the emerging multiport energy conversion systems, e.g., wind mills, electric vehicles and hydraulics, etc.…”

Section: Introductionmentioning

confidence: 99%

An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis

Kafeel¹,

Aziz

Awais

et al. 2021

Sensors

View full text Add to dashboard Cite

Accurate and early detection of machine faults is an important step in the preventive maintenance of industrial enterprises. It is essential to avoid unexpected downtime as well as to ensure the reliability of equipment and safety of humans. In the case of rotating machines, significant information about machine’s health and condition is present in the spectrum of its vibration signal. This work proposes a fault detection system of rotating machines using vibration signal analysis. First, a dataset of 3-dimensional vibration signals is acquired from large induction motors representing healthy and faulty states. The signal conditioning is performed using empirical mode decomposition technique. Next, multi-domain feature extraction is done to obtain various combinations of most discriminant temporal and spectral features from the denoised signals. Finally, the classification step is performed with various kernel settings of multiple classifiers including support vector machines, K-nearest neighbors, decision tree and linear discriminant analysis. The classification results demonstrate that a hybrid combination of time and spectral features, classified using support vector machines with Gaussian kernel achieves the best performance with 98.2% accuracy, 96.6% sensitivity, 100% specificity and 1.8% error rate.

show abstract

Section: Introductionmentioning

confidence: 99%

An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis

Kafeel¹,

Aziz

Awais

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The authors analyze various methods for detecting attacks and anomalies, based on machine learning algorithms (Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Artificial Neural Network (ANN), and k-Nearest Neighbor (KNN)), to protect against cybersecurity threats on the Internet of Things. In contrast to previous work on individual classifiers, they also analyze ensemble methods such as packing, boosting, and summation to improve the performance of their detection system [ 20 , 21 , 22 , 23 ]. The authors integrate feature selection, cross-validation, and multi-class classification for the cybersecurity field.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Protection System for Sensor Networks Based on Analysis of Neighboring Nodes

Gamec

Basan

et al. 2021

Sensors

View full text Add to dashboard Cite

Creation and operation of sensor systems is a complex challenge not only for industrial and military purposes but also for consumer services (“smart city”, “smart home”) and other applications such as agriculture (“smart farm”, “smart greenhouse”). The use of such systems gives a positive economic effect and provides additional benefits from various points of view. At the same time, due to a large number of threats and challenges to cyber security, it is necessary to detect attacks on sensor systems in a timely manner. Here we present an anomaly detection method in which sensor nodes observe their neighbors and detect obvious deviations in their behavior. In this way, the community of neighboring nodes works collectively to protect one another. The nodes record only those parameters and attributes that are inherent in any node. Regardless of the node’s functionality, such parameters include the amount of traffic passing through the node, its Central Processing Unit (CPU) load, as well as the presence and number of packets dropped by the node. Our method’s main goal is to implement protection against the active influence of an internal attacker on the whole sensor network. We present the anomaly detection method, a dataset collection strategy, and experimental results that show how different types of attacks can be distinguished in the data produced by the nodes.

show abstract

“…Deep learning methods that have been developed have been applied to intelligent condition diagnosis, achieving favorable results [13] using architectures such as convolutional neural networks (CNNs) [14][15][16][17][18], AEs [19][20][21][22][23], and recurrent neural networks [24][25][26][27][28]. CNNs, which employ neural nodes as a type of filter, enable deep learning structures to extract features from complex and highly nonlinear signals.…”

Section: Introductionmentioning

confidence: 99%

Stamping Tool Conditions Diagnosis: A Deep Metric Learning Approach

Dzulfikri

Huang

2021

Applied Sciences

View full text Add to dashboard Cite

Stamping processes remain crucial in manufacturing processes; therefore, diagnosing the condition of stamping tools is critical. One of the challenges in diagnosing stamping tool conditions is that traditionally, the tools need to be visually checked, and the production processes thus need to be halted. With the development of Industry 4.0, intelligent monitoring systems have been developed by using accelerometers and algorithms to diagnose the wear classification of stamping tools. Although several deep learning models such as the convolutional neural network (CNN), auto encoder (AE), and recurrent neural network (RNN) models have demonstrated promising results for classifying complex signals including accelerometer signals, the practicality of those methods are restricted due to the flexibility of adding new classes and low accuracy when faced to low numbers of samples per class. In this study, we applied deep metric learning (DML) methods to overcome these problems. DML involves extracting meaningful features using feature extraction modules to map inputs into embedding features. We compared the probability method, the contrastive method, and a triplet network to determine which method was most suitable for our case. The experimental results revealed that, compared with other models, a triplet network can be more effectively trained with limited training data. The triplet network demonstrated the best test results of the compared methods in the noised test data. Finally, when tested using unseen class, the triplet network and the probability method demonstrated similar results.

show abstract

Sensor and Component Fault Detection and Diagnosis for Hydraulic Machinery Integrating LSTM Autoencoder Detector and Diagnostic Classifiers

Cited by 44 publications

References 36 publications

An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis

An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis

An Adaptive Protection System for Sensor Networks Based on Analysis of Neighboring Nodes

Stamping Tool Conditions Diagnosis: A Deep Metric Learning Approach

Contact Info

Product

Resources

About