Case study

Nippon Gases prevents unplanned downtime and extends its APM strategy with SymphonyAI’s Predictive Asset Intelligence

SymphonyAI team
 

Background

Nippon Gases is a leading company in Europe’s industrial and medical gas business and is part of Nippon Sanso Holdings Corporation. Present in over 13 countries, with a solid combination of bulk and bottled gases, onsite production, and pipelines that deliver across key industries, Nippon Gases supplies a broad portfolio of industrial gases for many use cases, which are production-critical and safety-critical for their customers.

Strategic Objectives and Business Challenges

Plant reliability is a critical factor for Nippon Gases’ success as a supplier of essential products for their customers’ production and safety processes. Recognizing this importance, Nippon Gases has an established reliability program to monitor equipment using classical condition monitoring techniques, such as vibration and oil analysis. While powerful, these approaches do not address all failure modes, prompting the need for a more advanced solution that could predict additional causes of unplanned equipment downtime.

Solution

Nippon Gases conducted an extensive review of potential solutions and chose SymphonyAI Predictive Asset Intelligence due to its extensive experience in AI-based condition monitoring with critical equipment such as compressors, turbines, and purifiers. Predictive Asset Intelligence provides real-time asset health monitoring with predictive AI models tailored to industrial needs.

Built on top of IRIS Foundry industrial DataOps platform, Predictive Asset Intelligence uses unified industrial data to calculate asset health, maximize uptime with predictive warnings, and optimize operations using deep learning AI-models. Additionally, Predictive Asset Intelligence contains ready-to-use templates and pre-trained AI-models, reducing the resources required for implementation.

Impact

Upon initial implementation of key critical assets, Predictive Asset Intelligence successfully  detected significant anomalies that would have eluded traditional condition-based monitoring techniques. It provided measurable added value and complemented their existing condition monitoring programs, preventing unplanned downtime due to proactive anomaly detection. Design as a no-code, intuitive solution, Predictive Asset Intelligence is helping Nippon Gases democratize AI usage within their sites, allowing more team members from various technical backgrounds to take corrective actions and contribute to asset management and operational excellence.

Testimonial

Reliability Manager Ben Engels affirmed, “Using predictive AI models from SymphonyAI integrated with critical data sources, we have already been able to proactively detect anomalies and prevent unplanned stoppages.”

Next Steps

Looking forward, Nippon Gases envisions extending the application of SymphonyAI’s Predictive Asset Intelligence to include a wider array of equipment, focusing on the consequential impact of equipment failure. Additionally, Nippon Gases is exploring opportunities to leverage the MLOps Studio in IRIS Foundry for process prediction, aiming to further optimize operational processes through advanced analytics.

Nippon Gases’ integration of SymphonyAI’s Predictive Asset Intelligence marks a significant achievement in its pursuit of operational excellence and plant reliability. The strategic application of AI-driven predictive maintenance and anomaly detection reinforces the company’s commitment to safety and productivity and sets a clear path for future enhancements and technological advancements within its operations.

Latest Insights

Factory Shopfloor predictive asset intelligence
 
Case study

Unlocking Proactive Maintenance with Predictive AI Solutions

Industrial Square Icon Svg
IRIS Workspace Demo
 
Case study

IRIS Workspace Demo

Industrial Square Icon Svg
IRIS Workspace - Unlock Operational Efficiency and Collaboration
 
Case study

IRIS Workspace – Unlock Operational Efficiency and Collaboration

Industrial Square Icon Svg