On 15^th June, Prof. Darek Ceglarek chaired the 2nd Global Industry 4.0 Manufacturing Virtual Summit 2021 in association with the European Manufacturing Strategies and the American Manufacturing Strategies summits. It brought together over 250 industry heads and professionals from across the globe responsible for their domestic and global operations and production within the manufacturing industry, and the wider business.

 The summit explored how Industry 4.0 helped keep manufacturing operations running through the pandemic, and in cases even emerged in a better position. Prof. Ceglarek also delivered a presentation at the summit, Closed-Loop In-Process Quality Improvement: Scaling for ‘Right-First-Time Production’ which explored configuration, optimisation and control of assembly process from design-to-production for quality and productivity improvements.

Dr Mikhail Sokolov, Research Fellow with the DLM research group, presented a paper, “Remote Laser Welding of Die Casting Aluminium Parts for Automotive Applications with Beam Oscillation and Adjustable Ring Mode Laser” (Mikhail Sokolov, Pasquale Franciosa, Darek Ceglarek) at the Lasers in Manufacturing Conference (LiM’2021) a part of the International Congress on Photonics in Europe (June 21-24, 2021), Munich, Germany. The LiM Conference is focused on the latest developments and future trends in laser materials processing. This research is partially supported by APC UK Chamaeleon, Innovate UK and WMG HVM Catapult.

Giovanni Chianese, MSc student, conducting research in the DLM research group, presented a paper, “Photodiode-Based In-Process Monitoring of Part-to-Part Gap and Weld Penetration Depth in Remote Laser Welding of Automotive Battery Tab Connectors” at the co-located 49^th SME North American Manufacturing Research Conference (NAMRC’21) and the ASME Manufacturing Science and Engineering Conference (MSEC’21) hosted by the University of Cincinnati, USA (June 21-25, 2021).

 The paper is co-authored by Pasquale Franciosa and Darek Ceglarek (DLM group), Jonas Nolte (Precitec GmbH & Co, Germany) and Stanislao Patalano (University of Naples, Italy). Experts from around the world joined the event to share the latest research and innovations in manufacturing systems and processes, additive manufacturing, cyber-physical systems, and materials processing. This research was partially supported by APC UK ALIVE and Innovate UK LIBERATE.

Sumit Sinha, Dr Pasquale Franciosa and Prof. Darek Ceglarek launched a python library implementing artificial intelligence algorithms for root cause analysis of assembly systems. The work includes a Python (Bayesian Deep Learning for Manufacturing) and Matlab (Variation Response Method (VRM)) integrated library. Key highlights of the library include:

1. Multi-task attention based Bayesian 3D U-Nets enabled by Bayes-by-Backprop and Flipout, for Root Cause Analysis of manufacturing systems with uncertainty quantification

2. Deep Reinforcement Learning models for control and correction using customizable CAE based (multi-physics) manufacturing systems

3. Low latency integration of Matlab environments and TensorFlow models

4. Closed-loop training, continual and transfer learning integrations for rapid training and scalability

5. Integration of 3D Grad-CAMs for architecture interpretability

6. Keras Tuner for rapid architecture prototyping and selection

7. Multi-station manufacturing case studies for training and benchmarking

Sumti Sinha, Dr Pasquale Franciosa and Prof. Darek Ceglarek published a paper proving a transformative framework for achieving Zero Defect Manufacturing. The paper proposed a novel Object Shape Error Response (OSER) approach to estimate the dimensional and geometric variation of assembled products and then, relate, these to process parameters, which can be interpreted as root causes (RC) of the object shape defects. The OSER approach leverages Bayesian 3D-Convolutional Neural Networks integrated with Computer-Aided Engineering (CAE) simulations for RC isolation. Compared with the existing methods, the proposed approach (i) addresses a novel problem of applying deep learning for object shape error identification instead of object detection; (ii) overcomes fundamental performance limitations of current linear approaches for Root Cause Analysis (RCA) of assembly systems that cannot be used on point cloud data; and, (iii) provides capabilities for unsolved challenges such as ill-conditioning, fault-multiplicity, RC prediction with uncertainty quantification and learning at design phase when no measurement data is available. Comprehensive benchmarking with existing machine learning models demonstrates superior performance with R₂ =0.98 and MAE = 0.05mm, thus improving RCA capabilities by 29%

Sumit Sinha presented his work co-authored by Dr Pasquale Franciosa and Prof. Darek Ceglarek. The presentation proposed the Object Shape Error Response methodology extending traditional Object Detection in Deep Learning. It is the first uncertainty enabled model overcoming shortcomings of state-of-the-art models for Root Cause Analysis of Assembly System.

The workshop demonstrated the use of Digital Twins, Multi-Fidelity CAE Simulations and Deep Learning in manufacturing that enabled right-first-time capability to reduce engineering changes during installation, commissioning and production. The developed software was demonstrated and made available with open-source code. Key external speakers included managers from Jaguar Land Rover (JLR) and technical experts from Mathworks (MatLab). Key Internal Speakers included researchers within the Digital Lifecycle Management (DLM) group. The event included 50 attendees from both academia and industry including major industries such as BMW, Rolls-Royce, JLR and Constellium. The attendees were from diverse backgrounds such as automotive manufacturing, CAE simulations, data science and software development. Key presentations included:

1. Deep learning enhanced digital twin for Closed-loop In-Process Quality Improvement by Prof. Darek Ceglarek

2. Variation response method CAE simulation suite by Dr Pasquale Franciosa

3. Deep learning in manufacturing: predicting and preventing manufacturing defects by Sumit Sinha