Anomaly detection in formed sheet metals using convolutional autoencoders

Research output: Journal contributionsConference article in journalResearchpeer-review

Authors

Autoencoders are used to compress data and learn how to reliably reconstruct it. Through comparing the reconstruction error with a set threshold, they are able to detect anomalies in unseen datasets where the data does not quite match the reconstructed input samples. In this work, we attempt to investigate the use of convolutional autoencoders in the field of visual quality inspection, where images of formed sheet metals from a real production line are inspected for the occurrence of cracks and wrinkle formation. This approach tackles the problem of needing enough defective samples to attain reliable detection accuracies
Original languageEnglish
JournalProcedia CIRP
Volume93
Pages (from-to)1281-1285
Number of pages5
ISSN2212-8271
DOIs
Publication statusPublished - 01.01.2020
Event53rd CIRP Conference on Manufacturing Systems - CMS 2020 - Chicago, United States
Duration: 01.07.202003.07.2020
Conference number: 53

Bibliographical note

The authors gratefully acknowledge the financial support given by the Federal Ministry for Economic Affairs and Energy (BMWi) under the Central Innovation Programme for SMEs IM)(Zorfe thopjrectartSPm“”ress on the basis of a decision of the German Bundestag (grant number: ZF4084503GR7).

    Research areas

  • Engineering - Artifical intelligence, Deep autoencoders, Process monitoring, Surface quality inspection

Documents

DOI

Recently viewed

Activities

  1. Plenary lecture entitled: "Wavelet Packets for Applications in Signal Processing and Control Systems"
  2. From Text to Data: AI and Human Expertise in Provenance Linked Open Data
  3. Dynamic Resource Development: How Parties Exploit vs. Invest into Common Resources
  4. Adaptive Teaching interventions in mathematical problem-solving lessons
  5. “Visual Rhetoric as a three-dimensional practice. Theorizing the interconnections between the visual rhetorical objects and the process of spectatorship”
  6. Control of a two-thermoelectric-cooler system for ice-clamping application using Lyapunov based approach
  7. A geometric approach for the design and control of an electromagnetic actuator to optimize its dynamic performance
  8. Convergence analysis of an approximated response function of the impedance probe
  9. Enhancing metacognition by using flipping classroom with geogebra
  10. Context-based discrimination in school
  11. A Wavelet Packet Algorithm for Online Detection of Pantograph Vibrations
  12. Users’ Handedness and Performance when Controlling Integrated Input Devices - Implications for Automotive HMI
  13. Problem Framing Workshop with Local NGOs
  14. Transdisciplinary Evaluation of Alternative Adaptation Strategies Value-Tree Method as a Tool to Integrate Multiple Values of Science, Practice and the General Public into Decision-Making
  15. “Through the Threshold: responsive, performative, self-referential”
  16. Using a Longitudinal Mixed-Methods Approach in HESD Research: Reflections on Pitfalls and Added Value
  17. Beyond Gamification: From Problem-solving to Problem-making
  18. Orientation workshop on "historical research projects using geographical data and GIS technology" - 2013
  19. EvoLang XIII

Publications

  1. Identification of structure-biodegradability relationships for ionic liquids - clustering of a dataset based on structural similarity
  2. The Scalable Question Answering Over Linked Data (SQA) Challenge 2018
  3. Exact and approximate inference for annotating graphs with structural SVMs
  4. Development of a quality assurance framework for the open source development model
  5. Different approaches to learning from errors: Comparing the effectiveness of high reliability and error management approaches
  6. A Control Scheme for PMSMs using Model Predictive Control and a Feedforward Action in the Presence of Saturated Inputs
  7. Changing the Administration from within:
  8. Dynamically changing sequencing rules with reinforcement learning in a job shop system with stochastic influences
  9. Joint entity and relation linking using EARL
  10. Using cross-recurrence quantification analysis to compute similarity measures for time series of unequal length with applications to sleep stage analysis
  11. Accounting and Modeling as Design Metaphors for CEMIS
  12. Using complexity metrics with R-R intervals and BPM heart rate measures
  13. Recurrence quantificationanalysis as a general-purpose tool for bridging the gap between qualitative and quantitative analysis
  14. ActiveMath - a Learning Platform With Semantic Web Features
  15. An expert-based reference list of variables for characterizing and monitoring social-ecological systems
  16. Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention
  17. Using transition management concepts for the evaluation of intersecting policy domains ('grand challenges')
  18. Global temporal typing patterns in foreign language writing
  19. Complex problem solving and intelligence
  20. Finding Creativity in Predictability: Seizing Kairos in Chronos Through Temporal Work in Complex Innovation Processes
  21. XOperator - An extensible semantic agent for instant messaging networks
  22. Proxies
  23. Conceptualizing Role Development in Agile Transformations
  24. Integration of Environmental Management Information Systems and ERP systems using Integration Platforms
  25. Enhancing the Building Information Modeling Lifecycle of Complex Structures with IoT
  26. Intersection tests for the cointegrating rank in dependent panel data
  27. On robustness properties in permanent magnet machine control by using decoupling controller