This paper presents a novel approach for anomaly detection in industrial processes. The system solely relies on unlabeled data and employs a 1D-convolutional neural network-based deepautoencoder architecture. As a co...
详细信息
This paper presents a novel approach for anomaly detection in industrial processes. The system solely relies on unlabeled data and employs a 1D-convolutional neural network-based deepautoencoder architecture. As a core novelty, we split the autoencoder latent space in discriminative and reconstructive latent features and introduce an auxiliary loss based on k-means clustering for the discriminatory latent variables. We employ a Top-K clustering objective for separating the latent space, selecting the most discriminative features from the latent space. We use the approach to the benchmark Tennessee Eastman data set to prove its applicability. We provide different ablation studies and analyze the method concerning various downstream tasks, including anomaly detection, binary and multi-class classification. The obtained results show the potential of the approach to improve downstream tasks compared to standard autoencoder architectures.
Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of CO2 sequestration). Here, we extend and present a non-intrusive reduced or...
详细信息
Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of CO2 sequestration). Here, we extend and present a non-intrusive reduced order model of natural convection in porous media employing deep convolutional autoencoders for the compression and reconstruction and either radial basis function (RBF) interpolation or artificial neural networks (ANNs) for mapping parameters of partial differential equations (PDEs) on the corresponding nonlinear manifolds. To benchmark our approach, we also describe linear compression and reconstruction processes relying on proper orthogonal decomposition (POD) and ANNs. We present comprehensive comparisons among different models through three benchmark problems. The reduced order models, linear and nonlinear approaches, are much faster than the finite element model, obtaining a maximum speed-up of 7 x 10(6) because our framework is not bound by the Courant-Friedrichs-Lewy condition;hence, it could deliver quantities of interest at any given time contrary to the finite element model. Our model's accuracy still lies within a relative error of 7% in the worst-case scenario. We illustrate that, in specific settings, the nonlinear approach outperforms its linear counterpart and vice versa. We hypothesize that a visual comparison between principal component analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) could indicate which method will perform better prior to employing any specific compression strategy.
Machine fault diagnosis (MFD) has gained an important enthusiasm since the unfolding of the pattern recognition techniques in the last three decades. It refers to all of the studies that aim to automatically detect th...
详细信息
Machine fault diagnosis (MFD) has gained an important enthusiasm since the unfolding of the pattern recognition techniques in the last three decades. It refers to all of the studies that aim to automatically detect the faults on the machines using various kinds of signals that they can generate. The present work proposes a MFD system for the drilling machines that is based on the sounds they produce. The first key contribution of this paper is to present a system specifically designed for the drills, by attempting not only to detect the faulty drills but also to detect whether the sounds were generated during the active or the idling stage of the whole machinery system, in order to provide a complete remote control. The second key contribution of the work is to represent the power spectrum of the sounds as images and apply some transformations on them in order to reveal, expose, and emphasize the health patterns that are hidden inside them. The created images, the so-called power spectrum density (PSD)-images, are then given to a deep convolutional autoencoder (DCAE) for a high-level feature extraction process. The final step of the scheme consists of adopting the proposed PSD-images + DCAE features as the final representation of the original sounds and utilize them as the inputs of a nonlinear classifier whose outputs will represent the final diagnosis decision. The results of the experiments demonstrate the high discrimination potential afforded by the proposed PSD-images + DCAE features. They were also tested on a noisy dataset and the results show their robustness against noises.
Remaining useful life prediction of rolling bearings in the various operating conditions is of significance for improving the reliability and durability of rotating machinery. However, the precision of RUL prediction ...
详细信息
Remaining useful life prediction of rolling bearings in the various operating conditions is of significance for improving the reliability and durability of rotating machinery. However, the precision of RUL prediction is heavily affected by the significant differences in data feature distributions due to the different failure degradation behaviors of bearings and the various operating conditions. To address this issue, a novelty RUL prediction method based on degradation behavior judgment is proposed. Firstly, a method is proposed to judge the failure behavior, the deep convolutional autoencoder is used to construct the prior gradient health indicator and current health indicators of rolling bearings, and dynamic time warping is used to measure the difference between the two to judge failure degradation behavior. Then, an improved squeeze aggregated excitation network is proposed for RUL prediction. The squeeze aggregated excitation module, which embeds the residual shrinkage denoise module, is used to learn the mapping relationship between features and RUL to obtain comprehensive information. The maximum mean discrepancy is introduced into the final layer of the improved squeeze aggregated excitation network to reduce feature distribution differences. Results of the experiment show that this model has higher prediction precision and better robustness than other methods under three working conditions in the PHM 2012 dataset.
暂无评论