incremental learning approach for an industrial
play

Incremental Learning Approach for an Industrial Inspection System - PowerPoint PPT Presentation

Mar 08, 2024 •143 likes •410 views

Incremental Learning Approach for an Industrial Inspection System MATLAB Expo 2019, Bern Dr. Jianyong Wen & Ralph Stephan, Stubli Sargans AG MATLAB Expo 2019, Bern Stubli at a Glance 2 2019-05-23 Stubli Sargans AG MATLAB Expo

  1. Incremental Learning Approach for an Industrial Inspection System MATLAB Expo 2019, Bern Dr. Jianyong Wen & Ralph Stephan, Stäubli Sargans AG

  2. MATLAB Expo 2019, Bern Stäubli at a Glance 2 2019-05-23 Stäubli Sargans AG

  3. MATLAB Expo 2019, Bern Company Presentation 3 2019-05-23 Stäubli Sargans AG

  4. MATLAB Expo 2019, Bern Three activities – four divisions 4 2019-05-23 Stäubli Sargans AG

  5. MATLAB Expo 2019, Bern Stäubli Textile Our Textile manufacturing products and services range from ▪ Shedding solutions for frame weaving and Jacquard weaving to ▪ Carpet weaving systems, ▪ Weaving systems for technical fabrics, ▪ Automation solutions for sock knitting machines, ▪ Automated weaving preparation systems . 5 2019-05-23 Stäubli Sargans AG

  6. MATLAB Expo 2019, Bern Stäubli Weaving Preparation Systems ▪ Located in Sargans, SG, since 1994 ▪ ~120 employees (~30 in R&D) ▪ Product lines ▪ Drawing-in ▪ Tying ▪ Leasing ▪ Inspection 6 2019-05-23 Stäubli Sargans AG

  7. MATLAB Expo 2019, Bern Drawing-In 7 2019-05-23 Stäubli Sargans AG

  8. MATLAB Expo 2019, Bern Tying 8 2019-05-23 Stäubli Sargans AG

  9. MATLAB Expo 2019, Bern Leasing, Reading-in and other Equipment 9 2019-05-23 Stäubli Sargans AG

  10. MATLAB Expo 2019, Bern Inspection 10 2019-05-23 Stäubli Sargans AG

  11. MATLAB Expo 2019, Bern From Idea to Product Idea Model Feedback Design Data Model Collection Verification Field SoC Application Integration Integration Test 11 2019-05-23 Stäubli Sargans AG

  12. MATLAB Expo 2019, Bern Challenges in Embedded Application ▪ Real-time industrial fabric inspection systems face challenges of a great number of pattern variations, fast and easy training process. ▪ Strongly imbalanced datasets ▪ Limitation of hardware resources in embedded systems 12 2019-05-23 Stäubli Sargans AG

  13. MATLAB Expo 2019, Bern Approach ▪ The incremental model developed at Stäubli Sargans AG consists of two process stages, combining machine learning and deep learning models. Image Pre - processing Incremental Learning Sub- model Initial Learning Sub-model 13 2019-05-23 Stäubli Sargans AG

  14. MATLAB Expo 2019, Bern Development Process Developing models HDL Code generation Optimization parameters Verification Functionality test Efficiency and Speed Test 14 2019-05-23 Stäubli Sargans AG

  15. MATLAB Expo 2019, Bern Preprocessing Debayer Segmentation Resizing Filtering Feature extraction 15 2019-05-23 Stäubli Sargans AG

  16. MATLAB Expo 2019, Bern Initial Learning Sub-Model ▪ Classification based on extracted features from pre-processing Gray Level Co- Statistical Edges Lawmasks Corners Occurrence Matrix Features Classifier 16 2019-05-23 Stäubli Sargans AG

  17. MATLAB Expo 2019, Bern Incremental Sub-Model CNN with 15 Layers Class FC Conv. Relu Output Input Soft- Batch Maxpool max Image Norm 17 2019-05-23 Stäubli Sargans AG

  18. MATLAB Expo 2019, Bern Incremental Learning Model in MATLAB 18 2019-05-23 Stäubli Sargans AG

  19. MATLAB Expo 2019, Bern Simulink Design and Simulation 19 2019-05-23 Stäubli Sargans AG

  20. MATLAB Expo 2019, Bern HDL-Code Generation and Resource Utilization Analysis 20 2019-05-23 Stäubli Sargans AG

  21. MATLAB Expo 2019, Bern Advantages ▪ Applicability ❖ The CNN sub-model improves classification accuracy during production process (incremental learning). ▪ Efficiency ❖ Based on the initial sub-model, the complexity of the CNN sub-model can be reduced (resource and speed efficiency). 21 2019-05-23 Stäubli Sargans AG

  22. MATLAB Expo 2019, Bern Achievements and Outlook Idea Model Feedback Design future past Data Model Collection Verification Field SoC present Application Integration Integration Test 22 2019-05-23 Stäubli Sargans AG

  23. MATLAB Expo 2019, Bern Benefits and Challenges Idea Model Feedback Design ▪ Challenges Data Model Collection Verification ▪ matching of tools and data sets ▪ debugging with blackbox IP Field SoC ▪ limited computing power Application Integration Integration ▪ large databases Test 23 2019-05-23 Stäubli Sargans AG

  24. MATLAB Expo 2019, Bern Benefits and Challenges Idea Model Feedback Design ▪ Benefits Data Model Collection Verification ▪ fast and simple code generation ▪ step-by-step implementation and Field SoC verification (controlled progress) Application Integration Integration ▪ consistent and comparable Test intermediate results ▪ validation of results together with customers 24 2019-05-23 Stäubli Sargans AG

  25. MATLAB Expo 2019, Bern Concluding Remarks Idea Model Feedback Design ▪ There are no limit to imagination Data Model Collection Verification ▪ Limits are given by Field SoC ▪ Our knowledge and implementation capacity Application Integration Integration ▪ The capabilities and limitations of our tools Test 25 2019-05-23 Stäubli Sargans AG

  26. Thank You! www.staubli.com

Recommend

Incremental Approach to Interpretable Classification Rule Learning Bishwamittra Ghosh and Kuldeep

Incremental Approach to Interpretable Classification Rule Learning Bishwamittra Ghosh and Kuldeep

Incremental Approach to Interpretable Classification Rule Learning Bishwamittra Ghosh and Kuldeep S. Meel School of Computing, National University of Singapore CP 2019 Bishwamittra Ghosh Incremental Approach to Interpretable Classification Rule

267 views • 23 slides
Paper Presentation Insights for incremental learning Zheng Shou 03-04-2015 1 Overview 1.

Paper Presentation Insights for incremental learning Zheng Shou 03-04-2015 1 Overview 1.

Paper Presentation Insights for incremental learning Zheng Shou 03-04-2015 1 Overview 1. Previous approach: Xiao, T., Zhang, J., Yang, K., Peng, Y., Zhang, Z. Error-Driven Incremental Learning in Deep Convolutional Neural Network for

324 views • 14 slides
A constructive approach to incremental learning Mario Rosario Guarracino October 12, 2006

A constructive approach to incremental learning Mario Rosario Guarracino October 12, 2006

High Performance Computing and Networking Institute National Research Council, Italy The Data Reference Model: A constructive approach to incremental learning Mario Rosario Guarracino October 12, 2006 10/13/2006 10:26 PM Acknowledgements

762 views • 41 slides
Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 ,

Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 ,

Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1 , Albert Bifet 2 , Bernhard Pfahringer 2 , Geoff Holmes 2 1 Department of Signal Theory and Communications Universidad Carlos III Madrid, Spain 2

568 views • 19 slides
Incremental and Non-incremental Learning of Control Knowledge for Planning Daniel Borrajo Mill

Incremental and Non-incremental Learning of Control Knowledge for Planning Daniel Borrajo Mill

1 Incremental and Non-incremental Learning of Control Knowledge for Planning Daniel Borrajo Mill an joint work with Manuela Veloso, Ricardo Aler, and Susana Fern andez Universidad Carlos III de Madrid Avda. de la Universidad, 30. 28911

630 views • 59 slides
Industrial Transfer Learning Introduction to Industrial Transfer Learning Industrial Transfer

Industrial Transfer Learning Introduction to Industrial Transfer Learning Industrial Transfer

Industrial Transfer Learning Introduction to Industrial Transfer Learning Industrial Transfer Learning Motivation Machine Learning in Manufacturing Decision Support Automation Process Control Self-Optimization Predictive Quality Predictive

742 views • 24 slides
On the validity of the incremental approach to calculate the impact of cities on air quality

On the validity of the incremental approach to calculate the impact of cities on air quality

On the validity of the incremental approach to calculate the impact of cities on air quality Philippe Thunis Athens June 2017 Motivations Determine at which level/scale air quality measures should be taken to abate air pollution in the

540 views • 17 slides
Program Synthesis in the Industrial World: Inductive, Incremental, Interactive Alex Polozov

Program Synthesis in the Industrial World: Inductive, Incremental, Interactive Alex Polozov

Program Synthesis in the Industrial World: Inductive, Incremental, Interactive Alex Polozov Sumit Gulwani polozov@cs.washington.edu sumitg@microsoft.com And the rest of the PROSE team! prose-contact@microsoft.com July 18, 2016 SYNT-16,

603 views • 44 slides
Building Structured Web Community Portals: A Top-Down, Compositional, and Incremental Approach

Building Structured Web Community Portals: A Top-Down, Compositional, and Incremental Approach

Building Structured Web Community Portals: A Top-Down, Compositional, and Incremental Approach Pedro DeRose University of Wisconsin-Madison Joint work with Warren Shen, Fei Chen, AnHai Doan, and Raghu Ramakrishnan 1 Structured Web Community

528 views • 26 slides
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence Arslan

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence Arslan

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence Arslan Chaudhry et al. Presented by Milo Prgr Pattern Recognition and

653 views • 39 slides
A Trie Merging Approach with Incremental Updates for Virtual Routers Layong Luo* , Gaogang

A Trie Merging Approach with Incremental Updates for Virtual Routers Layong Luo* , Gaogang

A Trie Merging Approach with Incremental Updates for Virtual Routers Layong Luo* , Gaogang Xie*, Kav e Salamatian , Steve Uhlig , Laurent Mathy , Yingke Xie* *Institute of Computing Technology, Chinese Academy of Sciences (CAS),

377 views • 9 slides
Efficient Computation of Extensions for Dynamic Abstract Argumentation Frameworks: An Incremental

Efficient Computation of Extensions for Dynamic Abstract Argumentation Frameworks: An Incremental

Introduction Incremental Computation Experiments Conclusions and future work Efficient Computation of Extensions for Dynamic Abstract Argumentation Frameworks: An Incremental Approach Gianvincenzo Alfano, Sergio Greco, Francesco Parisi {

541 views • 29 slides
Incremental Classification: First Step into Lifelong Learning PAN Xinyu MMLab, Department of IE

Incremental Classification: First Step into Lifelong Learning PAN Xinyu MMLab, Department of IE

Incremental Classification: First Step into Lifelong Learning PAN Xinyu MMLab, Department of IE Multi-task Incremental Classification: Setup Training Data ... Target Model Multi-task Incremental Classification: Setup Training

746 views • 33 slides
Incremental learning of motion primitives for full body motions Dana Kuli c Department of

Incremental learning of motion primitives for full body motions Dana Kuli c Department of

Incremental learning of motion primitives for full body motions Dana Kuli c Department of Electrical and Computer Engineering, University of Waterloo, Canada Incremental learning of motion primitives for full body motions p. 1/43

703 views • 43 slides
Formalization of Incremental Simplex Algorithm by Stepwise Refinement Mirko Spasi c, Filip

Formalization of Incremental Simplex Algorithm by Stepwise Refinement Mirko Spasi c, Filip

Introduction Approach and Techniques Linear Arithmetic, Incremental Simplex Evaluation Conclusions Formalization of Incremental Simplex Algorithm by Stepwise Refinement Mirko Spasi c, Filip Mari c Faculty of Mathematics, University of

537 views • 41 slides
A systematic approach to constructing families of incremental topology control algorithms using

A systematic approach to constructing families of incremental topology control algorithms using

A systematic approach to constructing families of incremental topology control algorithms using graph transformation Presentation at ICGT 2018 Toulouse, France, 2018-06-25 Sensor node Properties Topology control Aux. Algorithm Weight

331 views • 30 slides
An incremental approach RCGC Defined Each object has associated count of references to it

An incremental approach RCGC Defined Each object has associated count of references to it

An incremental approach RCGC Defined Each object has associated count of references to it Objects reference count When reference to object created Pointer copied from one place to another assignment RC of pointee is

313 views • 19 slides
IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules

IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules

IMLI: An Incremental Framework for MaxSAT-Based Learning of Interpretable Classification Rules Bishwamittra Ghosh Joint work with Kuldeep S. Meel 1 Applications of Machine Learning 2 Example Dataset 3 Representation of an interpretable

1.24k views • 55 slides
The Incremental approach Practical guidance and training to facilitate research data management

The Incremental approach Practical guidance and training to facilitate research data management

The Incremental approach Practical guidance and training to facilitate research data management in Cambridge Elin Stangeland DSpace@Cambridge Repository Manager Cambridge University Library RDMF VI Leicester 5-6 th of May 2011 Outline

467 views • 18 slides
A Systematic Approach to Incremental Redundancy over Erasure Channels Anoosheh Heidarzadeh (Texas

A Systematic Approach to Incremental Redundancy over Erasure Channels Anoosheh Heidarzadeh (Texas

A Systematic Approach to Incremental Redundancy over Erasure Channels Anoosheh Heidarzadeh (Texas A&M University) Joint work with Jean-Francois Chamberland (Texas A&M University), Parimal Parag (Indian Institute of Science, Bengaluru),

559 views • 40 slides
Algorithms for Dynamic Argumentation Frameworks: An Incremental SAT-Based Approach Andreas

Algorithms for Dynamic Argumentation Frameworks: An Incremental SAT-Based Approach Andreas

Algorithms for Dynamic Argumentation Frameworks: An Incremental SAT-Based Approach Andreas Niskanen Matti J arvisalo HIIT, Department of Computer Science, University of Helsinki, Finland ECAI 2020 Niskanen and J arvisalo (HIIT, UH)

460 views • 14 slides
Incremental Learning of Robot Dynamics using Random Features Arjan Gijsberts, Giorgio Metta

Incremental Learning of Robot Dynamics using Random Features Arjan Gijsberts, Giorgio Metta

Incremental Learning of Robot Dynamics using Random Features Arjan Gijsberts, Giorgio Metta Cognitive Humanoids Laboratory Dept. of Robotics, Brain and Cognitive Sciences Italian Institute of Technology general setting learning

388 views • 23 slides
Incremental and adaptive learning for online monitoring of embedded software Monica Loredana

Incremental and adaptive learning for online monitoring of embedded software Monica Loredana

Incremental and adaptive learning for online monitoring of embedded software Monica Loredana Angheloiu Supervisors: Marie-Odile Cordier Laurence Roz 1 20/06/2012 Outline Introduction Context of the internship Previous work

1.04k views • 70 slides
Population-Based Incremental Learning for Multiobjective Optimisation Sujin Bureerat and Krit

Population-Based Incremental Learning for Multiobjective Optimisation Sujin Bureerat and Krit

Population-Based Incremental Learning for Multiobjective Optimisation Sujin Bureerat and Krit Sriworamas Department of Mechanical Engineering, Faculty of Engineering, Khon Kaen University, Thailand, 40002 Sujbur@kku.ac.th Outlines

562 views • 38 slides

More recommend