Search results for "autoencoder"
showing 10 items of 34 documents
Data-driven Fault Diagnosis of Induction Motors Using a Stacked Autoencoder Network
2019
Current signatures from an induction motor are normally used to detect anomalies in the condition of the motor based on signal processing techniques. However, false alarms might occur if using signal processing analysis alone since missing frequencies associated with faults in spectral analyses does not guarantee that a motor is fully healthy. To enhance fault diagnosis performance, this paper proposes a machinelearning based method using in-built motor currents to detect common faults in induction motors, namely inter-turn stator winding-, bearing- and broken rotor bar faults. This approach utilizes single-phase current data, being pre-processed using Welch’s method for spectral density es…
Multi-Component Fault Detection in Wind Turbine Pitch Systems Using Extended Park's Vector and Deep Autoencoder Feature Learning
2018
Pitch systems are among the wind turbine components with most frequent failures. This article presents a multicomponent fault detection for induction motors and planetary gearboxes of the electric pitch drives using only the three-phase motor line currents. A deep autoencoder is used to extract features from the extended Park's vector modulus of the motor three-phase currents and a support vector machine to classify faults. The methodology is validated in a laboratory setup of a scaled pitch drive, with four commonly occurring faults, namely, the motor stator turns fault, broken rotor bars fault, planetary gearbox bearing fault and planet gear faults, under varying load and speed conditions.
Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders
2020
This paper proposes a method for calculating a health indicator (HI) for low-speed axial rolling element bearing (REB) health assessment by utilizing the latent representation obtained by variational inference using Variational Autoencoders (VAEs), trained on each speed reference in the dataset. Further, versatility is added by conditioning on the speed, extending the VAE to a conditional VAE (CVAE), thereby incorporating all speeds in a single model. Within the framework, the coefficients of autoregressive (AR) models are used as features. The dimensionality reduction inherent in the proposed method lowers the need of expert knowledge to design good condition indicators. Moreover, the sugg…
Combining Auto-Encoder with LSTM for WiFi-Based Fingerprint Positioning
2021
Although indoor positioning has long been investigated by various means, its accuracy remains concern. Several recent studies have applied machine learning algorithms to explore wireless fidelity (WiFi)-based positioning. In this paper, we propose a novel deep learning model which concatenates an auto-encoder with a long short term memory (LSTM) network for the purpose of WiFi fingerprint positioning. We first employ an auto-encoder to extract representative latent codes of fingerprints. Such an extraction is proven to be more reliable than simply using a deep neural network to extract representative features since a latent code can be reverted back to its original input. Then, a sequence o…
An Encrypted Traffic Classification Framework Based on Convolutional Neural Networks and Stacked Autoencoders
2020
In recent years, deep learning-based encrypted traffic classification has proven to be effective; especially, using neural networks to extract features from raw traffic to classify encrypted traffic. However, most of the neural networks need a fixed-sized input, so that the raw traffic need to be trimmed. This will cause the loss of some information; for example, we do not know the number of packets in a session. To solve these problems, a framework, which implements both a convolutional neural network (CNN) and a stacked autoencoder (SAE), is proposed in this paper. This framework uses a CNN to extract high-level features from raw network traffic and uses an SAE to encode the 26 statistica…
Open Set Audio Classification Using Autoencoders Trained on Few Data.
2020
Open-set recognition (OSR) is a challenging machine learning problem that appears when classifiers are faced with test instances from classes not seen during training. It can be summarized as the problem of correctly identifying instances from a known class (seen during training) while rejecting any unknown or unwanted samples (those belonging to unseen classes). Another problem arising in practical scenarios is few-shot learning (FSL), which appears when there is no availability of a large number of positive samples for training a recognition system. Taking these two limitations into account, a new dataset for OSR and FSL for audio data was recently released to promote research on solution…
A 3D Network Based Shape Prior for Automatic Myocardial Disease Segmentation in Delayed-Enhancement MRI
2021
Abstract Objectives: In this work, a new deep learning model for relevant myocardial infarction segmentation from Late Gadolinium Enhancement (LGE)-MRI is proposed. Moreover, our novel segmentation method aims to detect microvascular-obstructed regions accurately. Material and methods: We first segment the anatomical structures, i.e., the left ventricular cavity and the myocardium, to achieve a preliminary segmentation. Then, a shape prior based framework that fuses the 3D U-Net architecture with 3D Autoencoder segmentation framework to constrain the segmentation process of pathological tissues is applied. Results: The proposed network reached outstanding myocardial segmentation compared wi…
Assessment of Deep Learning Methodology for Self-Organizing 5G Networks
2019
In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of …
Vector representation of non-standard spellings using dynamic time warping and a denoising autoencoder
2017
The presence of non-standard spellings in Twitter causes challenges for many natural language processing tasks. Traditional approaches mainly regard the problem as a translation, spell checking, or speech recognition problem. This paper proposes a method that represents the stochastic relationship between words and their non-standard versions in real vectors. The method uses dynamic time warping to preprocess the non-standard spellings and autoencoder to derive the vector representation. The derived vectors encode word patterns and the Euclidean distance between the vectors represents a distance in the word space that challenges the prevailing edit distance. After training the autoencoder o…
Autoencoders and Recurrent Neural Networks Based Algorithm for Prognosis of Bearing Life
2018
Bearings are one of the most critical components in electric motors, gearboxes and wind turbines. Therefore, bearing fault detection and prognosis of remaining useful life are important to prevent productivity losses. In this study, a novel method is proposed for prognosis of bearing life using an autoencoder and recurrent neural networks-based prediction algorithm. Promising results have been obtained from the experimental data. A monotonic upward trend of the produced health indicator is obtained for all test cases, being one of critical indicators of a proper prognosis. The remaining useful life estimation is moderately accurate under a limited data.