Assessment of Prototype Scour Data
Scour is the removal of riverbed sediment which can be induced due to the presence of channel contraction, hydraulic structures, natural fluctuations in discharge, or changes in sediment supply in a fluvial environment. Scour and erosion have been identified as the primary cause of the majority of bridge failures in North America. Several investigators have concluded that about 50% of all bridge collapses occur due to scourͲrelated complications. The prevalence of scourͲinduced bridge collapses is indicative of the criticality of scour estimation in the interest of public safety as well as mitigation of infrastructure costs, as this type of collapse often requires significant investment for design and construction of replacement bridges, fault analysis and potential rehabilitation. The available bridge design codes are mostly extracted from estimates of scour at the laboratory scale (experiments in reducedͲscale physical models), acquired under highly controlled conditions. Some sources of model inaccuracy include scale effects in physical hydraulic modelling; a lack of understanding of the flow physics of the phenomenon; and the limitations of current computational methods used to model sediment transport. A way to improve the prediction ability of current scour methodologies could be using observed scour values in real rivers to verify/correct such methods, as this proposed research intends to do. The aim of the present project is to study prototype scour data at various field site as well as to use computational tools to assess the efficacy of scour estimation methods for investigating the possible improvements to existing approaches.
Computer vision powered digital twin for tracking manual manufacturing processes
Over 70% of tasks in manufacturing are still manual; therefore, over 75% of the variation in manufacturing comes from human beings. Human errors were the primary driver behind $22.1 billion in vehicle recalls in 2016. Currently, when plant operators want to gain an understanding of their manual processes, they send out their highly paid industrial engineers to run time studies. These studies produce highly biased and inaccurate data that provides minimal value to manufacturing teams. This project aims to develop a computer vision powered digital twin prototype that is ready to test on the client’s site, which helps manufacturing plant operators gain unprecedented visibility into their manual production operations, allowing them to optimize their worker efficiency while maximizing productivity. This will be done by automated data generation using computer vision, conversion of raw data into useable information, visualization of information using standard Business Intelligence methodologies and lastly, prediction of future plant performance based on historical information, as well as information about other market drivers.
Modelling, assessment, and reduction of unsteady pressure fluctuations in gas turbine testing facilities
In a gas turbine engine testing facility, the engine draws air in from the surrounding environment through a large inlet. This process entrains additional flow beyond that which goes through the engine. Downstream of the engine, the engine exhaust and this entrained flow both enter a long cylindrical flow channel during which the two streams partially mix. Further downstream the flow diffuses and impinges on a conical flow redirection device (cone) before exiting into an exhaust stack via a perforated cylinder. This project aims to develop solutions and new insight related to reducing undesired large amplitude, low frequency pressure fluctuations in the exhaust stream of a gas turbine engine testing facility. The analysis will be carried out using high fidelity numerical simulations of unstead fluid flow such as a large eddy simulation. Solutions will be investigated by identifying how best to model the unsteady pressure fluctuations numberically and then determining how changes to the geometry of existing facility components can best reduce the pressure fluctations. Simultaneously, the phsyical mechanisms driving the pressure fluctuations will be firmly established and solutions based on reducing the ultimate source of the unsteadiness will be proposed. Thse may be more substantial than simply changing existing facility component geometry and thus will serve as backup solutions if the fluctuations cannot be adequately reduced via simple component geometry changes.
Remote production monitoring in a post COVID manufacturing environment
Given COVID-19 spread around the world, the importance of maintaining health is further understood through maintaining social distancing as when one coughs, sneezes or speaks, they spray small liquid droplets from their nose or mouth, which may contain the virus. If someone is too close to a person, he or she can breathe in the droplets, including the COVID-19 virus. This project proposes an approach to provide a real-time computer vision and deep learning method for inspection of social distancing as well as optimizing production operations while non-essential personnel, i.e. operations managers and manufacturing/production engineers, work remotely for manufacturing organizations. It will be the ideal solution for Canadian manufacturers that are re-starting production post-COVID-19 ensuring that worker safety is maintained without sacrificing production output and quality.
The bandwidth bottleneck has become worse post-COVID-19 as more people are working from home and thereby taking up much bandwidth. Small manufacturers, who cannot afford high-speed internet, are more critically impacted by this limitation. Hence, the goal of this project is to move video processing from the cloud to manufacturing sites via a reliable gateway device design and deployment that does not sacrifice quality and reliability for speed. This means videos do not have to be streamed to the cloud, and only the vital information extracted from the video feeds will be uploaded. Therefore, data transfer to the cloud can be accomplished with low internet bandwidth to ensure live-stream video feeds can be processed in near real-time without loss of quality or reliability for the required monitoring systems at hand.
Short-term prediction of border crossing times for trucks
International borders, where trucks are subject to immigration, customs and security inspection, can impose extreme unpredictability on delivery times. This is a particular problem for trucks serving just-in-time supply chains where goods must arrive within narrow time windows. For example, at automotive assembly plants numerous components must arrive shortly before they are needed on the assembly line – even one component arriving late could stop the line. Providing short-term crossing time predictions can help alleviate this problem. If a truck can be warned of a major delay a few minutes or hours before it gets to the border, it will be possible for supply chain managers to initiate actions such as redirecting the truck to an alternative crossing, dispatching a substitute shipment from a different location, or warning the receiving facility of the delay so that contingency plans can be implemented. Traffic conditions at the border can change rapidly, so trucks need predictions, rather than current reports, of crossing times to help them plan ahead. No such predictions, however, are currently available. In our proposed project, researchers at the University of Windsor will team with mobile application developer Innovex Inc. to develop a smartphone application that will provide accurate predictions of crossing times for trucks over a range of time intervals from 10 minutes to two hours, and deliver notification of likely schedule delay to shippers, dispatchers, drivers, receivers and other supply chain participants.