One of the largest challenges with managing large datasets is ensuring they are complete. Many use cases can use machine learning (ML) and artificial intelligence (AI) algorithms to accurately identify and fill gaps of unknown historical data sets with data extrapolated from other data sources. We recently put this to the test by analyzing electric vehicle (EV) adoption levels in the U.S. and identifying which states and regions have (or will have) high and low EV adoption. See how Altair’s data analytics solutions rose to the challenge.
One of the essential problems involved in managing large datasets is ensuring they’re complete. Many use cases, including materials databases, can use machine learning (ML) and artificial intelligence (AI) algorithms to accurately identify and fill gaps with data extrapolated from other data in the set. The datasets might contain time series data which, for example, may track the movement of components through a supply chain and/or static data like a parts inventory or test results. Altair’s data science tools are well suited to this task.
Serba Dinamik is an engineering company specializing in operations and maintenance (O&M), engineering, procurement, construction and commissioning (EPCC), and IT solutions for energy exploration and production firms. Their team worked with Altair to develop a Smart Predictive Maintenance Data System (SPMDS) utilizing Knowledge Studio and Panopticon. Maintenance crews use Panopticon-powered dashboards built into SPMDS to monitor every sensor mounted on operating turbines in real time. AI models built with Knowledge Studio identify potential failures or issues that require engineering attention, and, based on that understanding, take turbines offline only when necessary.
The Electric Storage Company is a Northern Ireland-based firm that manages electric power in households from renewable sources using battery storage and Internet of Things (IoT) technologies. The company installs smart batteries in homes and communities, along with sophisticated management software that lets homeowners sell excess energy back to grid operators when prices are high and helps them maintain the lowest possible energy input costs. Managing varieties of base load and intermittent renewable power sources requires the ability to ingest, process, and analyze high frequency information emanating from the grid and thousands of devices. The company needs real-time insight into energy markets, the grid, battery systems, and generation facilities, as well as customer-level power consumption patterns. Understanding consumption and generation trends optimizes power routing and battery storage and ensures that power sold back to the grid or on the open market is fetching the best possible price.