This audio was created using Microsoft Azure Speech Services
Industrial organizations across multiple sectors are under pressure from shareholders, regulators and customers to increase performance and reliability while keeping costs low. These conditions mean it’s more important than ever for organizations to optimize maintenance and operations. While reactive and preventive maintenance continue to be a key part of a comprehensive maintenance program, more proactive condition-based and predictive strategies are required for critical assets.
The growth of the Industrial Internet of Things (IIoT) offers a huge business opportunity to leverage existing data to drive business results by adopting a proactive predictive maintenance strategy. The average plant has over 8,000 data points, and a utility may have more than two million points across their generation fleet. However, without context that data is simply noise, and operators are unable to use it to make informed decisions.
Predictive asset analytics, enabled by the IIoT, is key to reducing unscheduled downtime and maintenance costs. Using predictive analytics, customers are able to predict and diagnose problems before they occur. This shifts maintenance from a reactive process to a proactive strategy, moving the organization higher up the maintenance maturity pyramid.
When selecting a predictive analytics solution, there are some key points to consider. Hardware and software agnostic solutions are critical, as it drastically reduces implementation cost and time to value. Another important factor is ease of use, specifically in the model building process. Look for a solution with an intuitive model building capability that doesn’t require any programming or detailed equipment knowledge.
In addition, for customers who lack the resources to comprehensively monitor their own assets, some vendors provide turnkey remote asset monitoring as a service, including installation, system training, modeling, monitoring, and reporting of anomalies done by an offsite team of experts. This supplements the existing maintenance team, reduces the burden on the organization and is a great way to get started quickly.
Enabling predictive maintenance
As part of Schneider Electric’s Enterprise APM platform, Avantis PRiSM uses advanced pattern recognition and machine learning to identify potential problems days, weeks or months before traditional alarm set points. By catching problems before they occur, PRiSM allows users to reduce unscheduled downtime, better plan maintenance activity, reduce costs and improve asset performance. For companies wishing to outsource monitoring activities, Schneider Electric’s Monitoring & Diagnostics Services Center provides comprehensive offsite monitoring and diagnostic guidance.
Companies using PRiSM see immediate results. Two prominent successes we have seen include Tata Power, one of the largest power companies in India, and EDF Group, the largest electricity generator in the world. When Tata Power installed PRiSM across their entire generation fleet, a single early warning catch saved almost $300,000. EDF Group saw even greater benefits when they implemented PRiSM to monitor their nuclear, hydro and traditional assets – the system saved the company over 1 million euros with one catch.
To learn more about predictive analytics, listen to the Automation World podcast on Predictive Asset Analytics Enabled by the Industrial Internet of Things, featuring Rob McGreevy, vice president of Information, Asset and Operations Management for Schneider Electric. You’ll hear how predictive asset analytics contributes to closed-loop operations, the value that the IIoT unlocks for industrial organizations, and the importance of well-defined objectives and industry-specific solutions.
For more information on Avantis PRiSM and Schneider Electric’s comprehensive Enterprise APM solution, visit https://software.schneider-electric.com/eapm.