Overview
Machining technology is a multidisciplinary field, integrating expertise from mechanics, materials, thermodynamics, vibrations, control systems, sensors, actuators, and software engineering. Machining research spans cutting process and material behaviour modeling, to machine tool (MT) dynamics and controls, to the design of cutters and coatings, and the prediction of MT and part accuracy. With increasing availability of computational power and ML algorithms comes the opportunity to integrate fundamental knowledge, experimental data, and machine leaning (ML) algorithms, to create advanced and robust virtual representations of the equipment, processes, and products of machining systems, known as Digital Twins (DTs). DTs can be used to enhance productivity, product quality, resource efficiency, and machine longevity. The research and training of CANRIMT3 will not only strengthen Canada's technological competitiveness, productivity, and economy, but will also contribute to environmental protection and climate change mitigation, by helping reduce energy consumption, material waste, and extending the lifecycle of capital equipment in high-end industrial manufacturing applications.
The CANRIMT3 research program was designed in collaboration with the industry partners, who identified the core challenges and promising technologies that are the motivation for individual projects. The program is composed of 5 research themes encompassing the broad landscape of machining technology research, with a focus on DT development and deployment. The research themes, their objectives, and individual projects are outlined below.
Themes and Projects
- Theme I - Digital machining and its integration with additive processes
Objectives:
- Develop new macro-level virtual models for critical, challenging, and emerging machining processes (e.g., machining of gears, thin-walled parts, and additively manufactured parts).
Better understand the physics of cutting operations and its on impact part surface integrity.
- Develop new fundamental knowledge, implementation guidelines, and process configurations for electrophysical and additive manufacturing processes.
- Theme II - Production machines and their digitalization – dynamics, mechatronics, and controls
Objectives:
Develop rapid and non-intrusive methods to establish Digital Twins (DTs) (i.e., physics-based and/or data-driven models) that accurately mirror and predict the dynamic response of machine tools.
- Predict the dynamic interaction between the machine tool, workpiece, and the cutting process to ensure stable and productive machining, which extends machine and tool life and improves part quality.
Develop DTs of trajectory planning algorithms used in industry and new types of trajectory optimization capable of achieving greater productivity beyond the current state-of-the-art.
Develop new generation mechatronic devices and control algorithms that further the stability, productivity, accuracy, and quality outcomes of machining operations.
Theme III – High performance tooling and processes
Objectives:
Develop new tooling materials and designs, considering macro- and micro-level phenomena, and compile the results in tooling databases to help industry identify the right tool for a given application.
Develop a process parameter selection framework that considers workpiece material properties, tool/machine capabilities, tool life, energy/resource consumption, and final machining productivity and part quality in recommendations for cost-effective machining, while mitigating environmental impacts.
Theme IV - Smart sensors, and machine and part metrology
Objectives:
Develop new smart sensor systems that can be practically integrated into machining systems for enhanced digital model building, operational monitoring, and control of machining processes.
Improve models and develop in situ-sensors to estimate machine errors to facilitate their factory calibration and allow in-situ monitoring.
Characterize the capability of robotic vision systems and develop DT-based uncertainty estimation on geometric dimensioning and tolerancing (GD&T) callouts.
Objectives:
Theme V - Digital twin-based optimization, monitoring, control, and diagnosis
- Develop a new class of algorithms and software solutions that integrate DT predictions and ML for enhanced process monitoring, machine fault diagnosis, and machining control capabilities, which will surpass the performance of deploying physics-based DTs or data-driven ML algorithms alone.
Integrate DT/ML with novel IoT sensors to improve machining productivity and part accuracy.
