Nippon Gases expands use of AI maintenance solutions across Europe

Industrial gas major Nippon Gases is expanding the deployment of an AI-based predictive maintenance solution to support plant operations and output across its fleet of European plants.

Announced yesterday (14th March), Nippon Gases signed a long-term agreement with SymphonyAI Industrial, a SymphonyAI division, to extend the use of its APM 360 technology.

APM 360 enables real-time prescriptive monitoring and predictive maintenance for critical plant equipment by using a mixture of Industrial Internet of Things (IIoT), AI, failure mode and effects analysis (FMEA) and physics.

This allows plant operators to ensure the optimal performance of machinery such as compressors, high-voltage motors, turbines, heat exchangers and pre-purifiers.

Commenting on the signing, Ben Engels, Reliability Manager Europe at Nippon Gases, said, “SymphonyAI Industrial’s APM 360 and its team of talented engineers have proven themselves to tae our reliability programme to the next levels.”

“The solution enabled us to take advantage of the huge amount of data we capture to make data-driven decisions that help keep our plants running with optimal performance.”

Set to transform the industry, predictive analytics in the oil and gas industry helps companies monitor machine assets, predict the probability of future machine failures, make proactive maintenance decisions, resulting in reduced operational costs arising from catastrophic machine failures.

“We are delighted to expand our relationship with Nippon Gases,” said Dominic Gallello, CEO of SymphonyAI Industrial.

“The combination of our third-generation machine reasoning-based AI capabilities and our deep engineering talent density to deliver a successful implementation is our formula for user and customer success.”

A cloud-based asset performance management solution, APM 360 has an FMEA template library that implements failure detection algorithms before using ‘layered analytics’ to analyse the collected data.

This data is then used to detect behaviour anomalies in a multi-dimensional model (also known as a digital twin).

APM 360 maps the model’s behaviour back for specific failure modes to determine advisories, recommendations and alerts, resulting in a calculation known as the Asset Health Score.

The score can be used to track the asset’s health over time and provide early warnings before failure occurs.

About the author
Related Posts
No comments yet
Get involved
You are posting as , please view our terms and conditions before submitting your comment.
Loading feed...
Please wait...