Fabrikam, Inc. creates innovated IoT solutions for the oil and gas manufacturing industry. It is beginning work on a new, predictive maintenance solution that targets rod pumps (the iconic pivoting pumps that dot oil fields around the world). With their solution in place, companies will be able to monitor and configure pump settings and operations remotely, and only send personnel onsite when necessary for repair or maintenance when the solution indicates that something has gone wrong. However, Fabrikam wants to go beyond reactive alerting- they want to want to enable the solution with the ability to predict problems so they can be averted before a fault occurs and damage is done.
Using Machine Learning gives Fabrikam's solution the ability to analyze readings from various elements of the rod pump mechanism and sense patterns that indicate a possible impending mechanical failure or a deviation from the pump’s optimal operating conditions. In that case, the controller can modify the operating parameters of the pump to avoid or mitigate the impact of the unexpected changes. Or, if necessary, it can shut down the pump before any damage occurs and notify the company that repairs are necessary—protecting the machinery, and preventing potential environmental damage.
Their goal in the use of such predictive models is to increase operator efficiency and safety. Addressing a typical maintenance issue takes several people and at least three days of system downtime at a cost of up to \$20,000 USD a day, not including parts and labor. "By proactively identifying pump problems through predictive analytics, companies reduce unplanned downtime, which decreases costs, increases production, and increases the agility of maintenance services." says Fabrikam's Chief Engineer. He adds that the majority of industry accidents don’t happen at the well site, they happen when personnel are driving between sites. By eliminating the need for many site visits, they can reduce those accidents.
They would like to understand their options for expediting the implementation of the PoC. Specifically they are looking to learn what offerings Azure provides that could enable a quick end-to-end start on the infrastructure for monitoring and managing devices and the system metadata. On top this, they are curious about what other platform services Azure provides that they should consider in this scenario.
They would like to start by building a proof of concept that performs the predictive analytics in the cloud. While their machine learning will initially happen in the cloud, they would like to design their solution with an eye towards the future so it could be enhanced to run the models at the edge.
In this workshop, you will look at the process for designing and implementing a predictive maintenance solution for oil and gas manufacturing.
In this workshop, you will look at designing a predictive maintenance solution for oil and gas manufacturing.
In this hands-on lab, you will look at implementing a predictive maintenance solution for oil and gas manufacturing.