An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing

Yang, Tan; Jin, Baihong; Nettekoven, Alexander; Chen, Yuxin; Yue, Yisong; Topcu, Ufuk; Sangiovanni‐Vincentelli, Alberto

doi:10.1109/icmla.2019.00171

Cited by 28 publications

(24 citation statements)

References 15 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of the autoencoder in Fig. 2 was derived by a grid search based hyperparameter optimization (parameters: layers, code-size, window size, regularization by batch normalization and/or drop-out) using as starting point an architecture proposed by Tan et al [36]. The objectives of the optimization were to decrease the reconstruction error for normal data and increase it for abnormal data.…”

Section: Temporal Contextmentioning

confidence: 99%

Context awareness in process monitoring of additive manufacturing using a digital twin

Reisch

Hauser

Lutz

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Wire Arc Additive Manufacturing allows the cost-effective manufacturing of customized, large-scale metal parts. As the post-process quality assurance of large parts is costly and time-consuming, process monitoring is inevitable. In the present study, a context-aware monitoring solution was investigated by integrating machine, temporal, and spatial context in the data analysis. By analyzing the voltage patterns of each cycle in the oscillating cold metal transfer process with a deep neural network, temporal context was included. Spatial context awareness was enabled by building a digital twin of the manufactured part using an Octree as spatial indexing data structure. By means of the spatial context awareness, two quality metrics—the defect expansion and the local anomaly density—were introduced. The defect expansion was tracked in-process by assigning detected defects to the same defect cluster in case of spatial correlation. The local anomaly density was derived by defining a spherical region of interest which enabled the detection of aggregations of anomalies. By means of the context aware monitoring system, defects were detected in-process with a higher sensitivity as common defect detectors for welding applications, showing less false-positives and false-negatives. A quantitative evaluation of defect expansion and densities of various defect types such as pore nests was enabled.

show abstract

Section: Temporal Contextmentioning

confidence: 99%

Context awareness in process monitoring of additive manufacturing using a digital twin

Reisch

Hauser

Lutz

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…1. An AE consists of two main stages, an encoder and a decoder [23]. An encoder maps the given input into a compressed representation, and a decoder transforms the compressed data back into the original input.…”

Section: Architecture Recurrent Outlier Detectionmentioning

confidence: 99%

Anomaly Detection on Medical Images using Autoencoder and Convolutional Neural Network

Siddalingappa¹,

Sekar²

2021

IJACSA

View full text Add to dashboard Cite

Detection of anomalies from the medical image dataset improves prognosis by discovering new facts hidden in the data. The present study aims to discuss anomaly detection using autoencoders and convolutional neural networks. The autoencoder identifies the imbalance between normal and abnormal samples. They create learning models flexible and accurate on training data. The problem is addressed in four stages: 1) training: an autoencoder is initialized with the hyperparameters and trained on the lung cancer CT scan images, 2) test: the autoencoder reconstructs the input from the latent space representation with a slight variation from the original data, indicated by a reconstruction error as Mean Squared Error (MSE), 3) evaluate: the MSE value of the training and test dataset are compared. The MSE values of anomalous data are higher than a base threshold, detecting those as anomalies, 4) validate: the efficiency metrics such as accuracy and MSE scores are used at both training and validation phases. The dataset was further classified as benign and malignant. The accuracy reported for outlier detection and the classification task is 98% and 97.2%. Thus, the proposed autoencoder-based anomaly detection could positively isolate anomalies from the CT scan images of lung cancer.

show abstract

“…Meanwhile, image features have also been classified using convolutional neural networks (CNNs) with labelled data (Zhang et al 2018). Furthermore, autoencoders have been used to detect anomalies (Tan et al 2019). Though these studies use signals from a highly dynamic process, an i.i.d.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep semi-supervised learning of dynamics for anomaly detection in laser powder bed fusion

Larsen

Hooper

2021

J Intell Manuf

View full text Add to dashboard Cite

Highly complex data streams from in-situ additive manufacturing (AM) monitoring systems are becoming increasingly prevalent, yet finding physically actionable patterns remains a key challenge. Recent AM literature utilising machine learning methods tend to make predictions about flaws or porosity without considering the dynamical nature of the process. This leads to increases in false detections as useful information about the signal is lost. This study takes a different approach and investigates learning a physical model of the laser powder bed fusion process dynamics. In addition, deep representation learning enables this to be achieved directly from high speed videos. This representation is combined with a predictive state space model which is learned in a semi-supervised manner, requiring only the optimal laser parameter to be characterised. The model, referred to as FlawNet, was exploited to measure offsets between predicted and observed states resulting in a highly robust metric, known as the dynamic signature. This feature also correlated strongly with a global material quality metric, namely porosity. The model achieved state-of-the-art results with a receiver operating characteristic (ROC) area under curve (AUC) of 0.999 when differentiating between optimal and unstable laser parameters. Furthermore, there was a demonstrated potential to detect changes in ultra-dense, 0.1% porosity, materials with an ROC AUC of 0.944, suggesting an ability to detect anomalous events prior to the onset of significant material degradation. The method has merit for the purposes of detecting out of process distributions, while maintaining data efficiency. Subsequently, the generality of the methodology would suggest the solution is applicable to different laser processing systems and can potentially be adapted to a number of different sensing modalities.

show abstract

An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing

Cited by 28 publications

References 15 publications

Context awareness in process monitoring of additive manufacturing using a digital twin

Context awareness in process monitoring of additive manufacturing using a digital twin

Anomaly Detection on Medical Images using Autoencoder and Convolutional Neural Network

Deep semi-supervised learning of dynamics for anomaly detection in laser powder bed fusion

Contact Info

Product

Resources

About