Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case
Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application in this context is when anomaly detection is employed to test manufactured goods in assembly lines. In this work, we compare supervised, s...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/767bfa1dee5a46788481ad3eea69f2e1 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:767bfa1dee5a46788481ad3eea69f2e1 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:767bfa1dee5a46788481ad3eea69f2e12021-11-25T16:39:27ZSpatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case10.3390/app1122108612076-3417https://doaj.org/article/767bfa1dee5a46788481ad3eea69f2e12021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10861https://doaj.org/toc/2076-3417Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application in this context is when anomaly detection is employed to test manufactured goods in assembly lines. In this work, we compare supervised, semi/weakly-supervised, and unsupervised strategies to detect anomalous sequences in video samples which may be indicative of defective televisions assembled in a factory. We compare 3D autoencoders, convolutional neural networks, and generative adversarial networks (GANs) with data collected in a laboratory. Our methodology to simulate anomalies commonly found in TV devices is discussed in this paper. We also propose an approach to generate anomalous sequences similar to those produced by a defective device as part of our GAN approach. Our results show that autoencoders perform poorly when trained with only non-anomalous data—which is important because class imbalance in industrial applications is typically skewed towards the non-anomalous class. However, we show that fine-tuning the GAN is a feasible approach to overcome this problem, achieving results comparable to those of supervised methods.Lucas A. da SilvaEulanda M. dos SantosLeo AraújoNatalia S. FreireMax VasconcelosRafael GiustiDavid FerreiraAnderson S. JesusAgemilson PimentelCaio F. S. CruzRuan J. S. BelemAndré S. CostaOsmar A. da SilvaMDPI AGarticlemachine learningvideo anomaly detectionclassificationpattern recognitionweakly supervised learningTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10861, p 10861 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
machine learning video anomaly detection classification pattern recognition weakly supervised learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 |
| spellingShingle |
machine learning video anomaly detection classification pattern recognition weakly supervised learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Lucas A. da Silva Eulanda M. dos Santos Leo Araújo Natalia S. Freire Max Vasconcelos Rafael Giusti David Ferreira Anderson S. Jesus Agemilson Pimentel Caio F. S. Cruz Ruan J. S. Belem André S. Costa Osmar A. da Silva Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| description |
Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application in this context is when anomaly detection is employed to test manufactured goods in assembly lines. In this work, we compare supervised, semi/weakly-supervised, and unsupervised strategies to detect anomalous sequences in video samples which may be indicative of defective televisions assembled in a factory. We compare 3D autoencoders, convolutional neural networks, and generative adversarial networks (GANs) with data collected in a laboratory. Our methodology to simulate anomalies commonly found in TV devices is discussed in this paper. We also propose an approach to generate anomalous sequences similar to those produced by a defective device as part of our GAN approach. Our results show that autoencoders perform poorly when trained with only non-anomalous data—which is important because class imbalance in industrial applications is typically skewed towards the non-anomalous class. However, we show that fine-tuning the GAN is a feasible approach to overcome this problem, achieving results comparable to those of supervised methods. |
| format |
article |
| author |
Lucas A. da Silva Eulanda M. dos Santos Leo Araújo Natalia S. Freire Max Vasconcelos Rafael Giusti David Ferreira Anderson S. Jesus Agemilson Pimentel Caio F. S. Cruz Ruan J. S. Belem André S. Costa Osmar A. da Silva |
| author_facet |
Lucas A. da Silva Eulanda M. dos Santos Leo Araújo Natalia S. Freire Max Vasconcelos Rafael Giusti David Ferreira Anderson S. Jesus Agemilson Pimentel Caio F. S. Cruz Ruan J. S. Belem André S. Costa Osmar A. da Silva |
| author_sort |
Lucas A. da Silva |
| title |
Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| title_short |
Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| title_full |
Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| title_fullStr |
Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| title_full_unstemmed |
Spatio-Temporal Deep Learning-Based Methods for Defect Detection: An Industrial Application Study Case |
| title_sort |
spatio-temporal deep learning-based methods for defect detection: an industrial application study case |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/767bfa1dee5a46788481ad3eea69f2e1 |
| work_keys_str_mv |
AT lucasadasilva spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT eulandamdossantos spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT leoaraujo spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT nataliasfreire spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT maxvasconcelos spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT rafaelgiusti spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT davidferreira spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT andersonsjesus spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT agemilsonpimentel spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT caiofscruz spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT ruanjsbelem spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT andrescosta spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase AT osmaradasilva spatiotemporaldeeplearningbasedmethodsfordefectdetectionanindustrialapplicationstudycase |
| _version_ |
1718413084515631104 |