In a typical heavy engineering operation, there is a myriad of expensive assets distributed globally, equipped with onboard diagnostic systems communicating the current state of the asset. The prevalence of IOT has forced OT and IT groups to collaborate for improved operational efficiencies, and also making data more easily accessible for business users.
The core challenge that companies are facing to enable IOT for their business is how to store data and leverage it. “For example, the automotive industry has sufficient information coming out of a car via onboard diagnostic systems, but efficient data management and extracting actionable intelligence from this data is where everybody struggles,” states Modukuru. This is where Cyient Insights sees the future value of IOT and advanced analytics. “With core competence in connected architecture, data management and data sciences, we distill down and find actionable insights from the huge amount of siloed data being generated from IOT devices,” he adds.
There is a framework in the IoT and advanced analytics lifecycle that Modukuru classifies into four categories; descriptive, diagnostic, predictive, and prescriptive analytics.
We’re investing in building cognitive models enabled by IoT that will greatly optimize operations to drive both top and bottom-line growth for the industries
These could be machines/equipment, facilities, fleet and network of operations. “I’m a big proponent of edge, fog and cloud analytics; data-analytics performed at the edge—near the source—for actionable intelligence drives tremendous value,” illustrates Modukuru. Data consolidation at the fog layer (consolidation at the site) and subsequently the data from all the locations to the centralized repository, will enable deep learning. Most importantly, this approach allows OT access to the real-time data and IT access to data in the corporate big data cloud.
Cyient Insights helped many early IoT adopters. “We begin with an open-minded consulting approach and deliver according to the customer’s core requirements, like reducing equipment downtime, or wanting to get more out of their current investments,” delineates Modukuru. Recently, a global heavy engineering company was facing frequent unplanned downtimes. By amassing data from over 150 data streams like logs, op-metrics and onboard diagnostics, Cyient Insights enabled the fleet manager to identify issues proactively and move to a predictive/prescriptive maintenance model from a preventive/reactive maintenance model, thus avoiding unscheduled downtime, while optimizing the scheduled downtime.
Cyient Insights has been consistently turning chaotic asset-intensive facilities into smart connected environments in the U.S., Europe, and APAC regions across the industry segments. “To further boost our capabilities to become best-in-class, we’re investing in building cognitive models enabled by IoT that will greatly optimize operations to drive both top- and bottom-line growth for the industries,” assures Modukuru.