This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.

Predictive analytics promises up to 30% reduction in maintenance costs

23 June 2015

GE used the recent ACHEMA event to showcase applications for its Asset Performance Management (APM) in the chemical and process industries. 

The APM solutions are said to improve asset health by providing early detection of emerging equipment failure at chemical production facilities. As a result, unplanned downtime can be avoided while plant productivity and performance are increased. Early diagnosis of emerging failures can help reduce maintenance costs at chemical plants by up to 30%, says the company.

To achieve this, GE has replaced traditional historical data analysis with algorithm-based, predictive analytics. This means actual values are continuously compared to a set of previously determined reference values. Indicators of emerging performance issues at critical assets in the production process can be detected before a potential equipment failure would lead to unplanned downtime. Even the smallest anomalies shown by discrepancies in the data are immediately transformed into actionable insights. This allows for the predictive maintenance or replacement of pumps, valves, turbines and other critical assets before an equipment failure can cause outages.

“With GE’s APM solutions, we are opening a new world of maintenance, operational excellence and efficiency for production plants in the chemical and process industries,” said Awraam Zapounidis, sales director Europe, Software & Services, Manufacturing at GE. 


Contact Details and Archive...

Most Viewed Articles...

Print this page | E-mail this page