• Home
  • Search
  • Anomaly detection of multivariate image time series based on Gramian angular field using convolutional autoencoder
  • Cite Icon2
  • https://doi.org/10.1117/12.2663003Copy DOI Icon

Anomaly detection of multivariate image time series based on Gramian angular field using convolutional autoencoder

  • Dec 9, 2022
  • Fatih Sultan Bayram +3 more
Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

This paper covers the implementation of predictive maintenance (PdM) predicting the wear of technical components of an industrial thermal system. Object of investigation of the technical components here is the motor of a fan. Basic requirement for the PdM system is the availability of extensive data from operating parameters of the motor, which must be recorded in advance through sensor technology. The sensor used here is a MPU 92.65 motion tracking multi sensor with three-axis acceleration, three-axis yaw rate, three-axis magnetic field and temperature measurement. Goal of this work is to develop an unsupervised Deep Learning (DL) model for anomaly detection of multivariate time series. By using the MPU 92.65 the operating parameters of the fan motor are recorded at specific time intervals ensuring sufficient data quality for the development of the DL model. In selecting a suitable DL algorithm for the anomaly detector a specific Convolutional Neural Network (CNN) called Convolutional Autoencoder (ConvAE) with 2-D convolutions has been selected. CNNs with 2-D convolutions are the typical type of neural networks normally used for images (object detection, segmentation, medical imaging etc.). However, the recorded sensor time series here are in 1-D and must therefore be transformed appropriately. The investigated approach of image transformation is the Gramian Angular Field (GAF), which encodes temporal correlation structures spatially as images. A total of four datasets is used with one representing the baseline for the deployment of the detector. The remaining datasets have been set for testing purposes with their results presented and discussed here.

Similar Papers
  • Research Article

Classification of Dense-Gas/Liquid Flow Patterns in Horizontal Pipe Through Pressure Gradient Time Series Encoded Into Images and Deep Learning

  • Feb 01, 2026
  • SPE Journal
  • July A Gómez-Camperos +4
  • Research Article
  • Citations7

Bearing fault diagnosis method based on the Gramian angular field and an SE-ResNeXt50 transfer learning model

  • Dec 01, 2023
  • Insight - Non-Destructive Testing and Condition Monitoring
  • Chaozhi Cai +3
  • Research Article
  • Citations23

UWB NLOS Recognition Based on Improved Convolutional Neural Network Assisted by Wavelet Analysis and Gramian Angular Field

  • Jul 15, 2023
  • IEEE Sensors Journal
  • Xiaogang Deng +2
  • Research Article
  • Citations50

EEG-Based Schizophrenia Diagnosis through Time Series Image Conversion and Deep Learning

  • Jul 20, 2022
  • Electronics
  • Dong-Woo Ko +1
  • PDF
  • Research Article
  • Citations7

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

  • Apr 12, 2022
  • ZANCO JOURNAL OF PURE AND APPLIED SCIENCES
  • Chiman Haydar Salh +1
  • Conference Article
  • Citations26

Epileptic Seizure Classification Based on Gramian Angular Field Transformation and Deep Learning

  • Oct 07, 2020
  • Anand Shankar +3
  • Research Article
  • Citations13

Near-infrared spectroscopy analysis of compound fertilizer based on GAF and quaternion convolution neural network

  • Jun 15, 2023
  • Chemometrics and Intelligent Laboratory Systems
  • Ailing Tan +5
  • Conference Article

Adaptive Dila-DenseNet for Image based Time Series Classification in IoT

  • Jul 18, 2021
  • Qiao Jiang +5
  • Conference Article
  • Citations7

An Image Based Approach of Energy Signal Disaggregation Using Artificial Intelligence

  • Sep 12, 2021
  • Manuri Senarathna +4
  • Conference Article
  • Citations1

NOVEL APPROACH FOR IMAGING TIME SERIES FOR THE IMPROVEMENT OF CLASSIFICATION RESULTS “GRAYSCALE FINGERPRINT FEATURES FIELD IMAGING (G3FI)”

  • Sep 12, 2023
  • Hammoud Al Joumaa
  • Book Chapter
  • Citations5

1 - Congruence of deep learning in biomedical engineering: future prospects and challenges

  • Nov 20, 2020
  • Handbook of Deep Learning in Biomedical Engineering
  • Aradhana Behura
  • PDF
  • Research Article
  • Citations11

Fault Location Method in Nonsolid-Earthed Network Based on Spatial Domain Image Fusion and Convolution Neural Network

  • Feb 07, 2022
  • Journal of Sensors
  • Sizu Hou +1
  • Research Article
  • Citations1

Coronary artery disease detection based on photoplethysmography via Gramian angular field transformation and deep learning

  • Dec 15, 2025
  • Journal of Intelligent Medicine
  • Zhaoying Li +4
  • PDF
  • Research Article
  • Citations78

Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery

  • Nov 20, 2021
  • Remote Sensing
  • Hejar Shahabi +7
  • PDF
  • Research Article
  • Citations137

An Effective Predictive Maintenance Framework for Conveyor Motors Using Dual Time-Series Imaging and Convolutional Neural Network in an Industry 4.0 Environment

  • Jan 01, 2020
  • IEEE Access
  • Kahiomba Sonia Kiangala +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.