A data-driven framework for integrating visual inspection into injection moulding pipeline
Recent advances in machine vision has led to new opportunities for automating that entire manufacturing pipeline. Consider, for example, the situation where an unattended computer vision system inspects the widget and decides whether or not to discard it. Even this little amount of automation can save many hundreds of person-hours on a typical factory floor. While for simple designs, we now have automated inspection methods relying upon lasers, 3D scanning or other imaging modalities that can decide if a widget has any defect. For complex designs, this ability remains elusive. More importantly, however, automated inspection schemes can only decide if a widget deviates from its intended design, say available in the form of a CAD drawing, it cannot decide what changes should be made down the manufacturing pipeline to prevent similar defects in the future. This project aims to explore machine learning techniques that integrate automated inspection with manufacturing process. Specifically, we will focus on injection moulding process in this project. We will develop new theory and methods for characterizing the injection moulding process in terms of quantities measured via an automated inspection system. This effort will lead to a deeper understanding of the role of myriad of parameters that control injection moulding processes.
Design and Development of Autonomous Disinfecting Embedded Systems for COVID-19
One of the major challenges during the COVID-19 pandemic is frequent disinfecting. This is very critical for places like hospitals and long-term care. In most places, human operators perform the cleaning but it may cause them to be infected with the virus because of the shortages of personal protective equipment (PPE) and many of the unknowns of COVID-19. The aim of thisCOVID-19 project is to improve Cyberworks Robotics’ navigation technology on existing (a) floor disinfection machines (e.g. wet floor scrubbers) of various types used in hospitals, (b) high-intensity UV disinfection machines, and (c) chemical mist disinfection machines. This would allow hospitals to disinfect the hospital surfaces on a more frequent basis than is possible with human cleaners (due to both the cost and availability of human operators) and also simultaneously to increase the quality of cleaning by ensuring that some surfaces are not missed due to human error and neglect
Machine Learning for Materials Discovery and Design
The objective of this project is to combine machine learning methodologies and electronic structure theory for the purpose of designing new materials through computational modelling. Achieving this goal will be important for the fields of Advanced Manufacturing and Energy (Materials). We will perform electronic structure calculations on a large database of existing materials (transition metal surfaces) and use results of these simulations as input to a machine learning model. The developed model will then be tested against new materials outside of the test set to confirm the model’s validity and transferability. This machine learning model will be used to identify new catalytic materials for use in water splitting and CO2 reforming devices. The project will combine high performance computing and machine learning to enable accelerated material discovery.
Reducing material waste and improving print quality in 3D printing through AI-based early failure detection
3D printing technologies are rapidly evolving. Fused Deposition Modeling (FDM) is one of the most popular types of 3D printers. However, there are still many challenges related to product quality, robustness, and reliability, which hinders the business expansion of 3D printing in the manufacturing industry. Research on the failure detection for the typical FDM machines and the corresponding automatic monitoring methods are required to address these challenges. This research program proposes an AI-based early failure detection system for 3D printing. This research program aims to achieve the following 4 objectives: (1) investigate the failure mechanisms in the 3D printing process to reproduce failures for data collection. (2) design experiment, collect the failure data, carry out correlation analysis, and extract the best features for failure detection. (3)based on the selected features, design the AI-based algorithms to detect failures. (4) implement the early failure detection system in the cloud-based 3D printing management system at Mech Solutions. This proposed project will combine the AI-based early fault detection system developed in Dr. Lin’s lab and the commercialization capability of the industrial partner. The NSERC Alliance Grant program and the computing resources from SOSCIP provide an opportunity for us to develop advanced failure detection methods in the university lab. The industrial partner, Mech Solutions, can benefit from the developed algorithms from Dr. Lin’s lab to improve the 3D printing service. The results will significantly benefit the relevant products and services in a wide range of important applications in Canada through direct transfer of knowledge and technology to the industry. The outcomes from this project will reduce the waste in 3D printing and bring a positive impact on the environment.