Book a Live Demo

Value-Based Maintenance: RWE’s Digital Transformation with Seeq

Executive Summary

RWE, Europe’s second-largest operator of gas turbine fleets, with over 31 power plants globally and 15.7 GW of gas-fired generation capacity, has embraced a transformative approach to reliability through value-based maintenance (VBM).  

By integrating Seeq’s analytics platform, RWE has created a data-driven maintenance ecosystem that delivers measurable improvements in uptime, cost efficiency, and strategic asset management. This transformation not only addresses the reliability challenges of traditional energy generation but also lays the groundwork for a scalable, future-ready maintenance framework.

The Challenge

“Reliability became a top corporate imperative—emphasized repeatedly by RWE leadership as “reliability, reliability, reliability.” Traditional maintenance strategies—reactive and scheduled—were no longer sufficient for the scale and complexity of RWE’s operations. 

The following are some of the key challenges faced by RWE: 

  •  High cost of failures: Unplanned shutdowns, such as igniter failures, translated into millions in lost generation revenue.
  • Data fragmentation: Data from systems like SAP, PI, and local maintenance records were siloed, impeding effective diagnostics.
  • Issue prioritization: Hundreds of failure modes existed, but there was no clear, data-informed method to determine which to address first.
  • Analytics Capability Gap: Moving from preventative to predictive maintenance required advanced tools and deep engineering insight.

Specific Technical Hurdles

These challenges were most visible in a set of recurring technical pain points across the gas turbine fleet. Each carries consistent consequences: unplanned downtime, lost generation, higher maintenance costs, and can lead to erosion of confidence with grid operators, regulators, and customers. 

  • Stop ratio valve issues: Past leakage failures caused forced turbine shutdowns, each outage resulting in production losses exceeding of approximately £1.3m.
  • Igniter failures: Difficult to detect early during startups, leading to failed starts and unplanned unavailability.
  • Creep life tracking: Manual data imports limited visibility into high-temperature component wear, raising the risk of shortened equipment life and in-service failures.
  • Air inlet filter degradation: Degraded filters created a risk of water ingress into the compressor, which has caused severe damage and multimillion-pound repair costs.

The Solution

RWE’s reliability transformation is enabled by Seeq’s analytics platform, which underpins a real-time fleet-wide framework for predictive maintenance and health scoring. The central concept is the Health Scoring System, which ranks equipment risks by criticality, cost, and historical impact. This ensures maintenance resources are directed to the issues with the greatest business value.

Core Components

  • Integrated dashboards: Role-specific views for operations, engineering, and management that surface real-time alerts from Seeq. These dashboards are directly connected to underlying data and root-cause analysis tools, ensuring the right issues are flagged to the right users for timely action.
  • Health score framework: Models assess and rank failure modes based on risk, historical impact, and cost.
  • Collaborative approach: A collaborative model development process, where engineers define and prototype logic and data scientists implement in Python and Seeq.
  • Bespoke problem-solving: Custom solutions tailored to unit-specific challenges, leveraging internal engineering expertise.

Analytics & Implementation

RWE’s Seeq deployment spans 12+ GT26 units, where custom models are developed to analyze failure modes using a collaborative workflow between domain engineers and data scientists. 

  • Engineering-led model design: Subject matter experts and data scientists co-develop health scoring models.
  • Indicators calculated in Seeq are exported into RWE’s in-house Maintenance Asset Reliability Assistant (MARA) platform, where they feed the health scoring dashboards.
  • Iterative validation: Models evolve iteratively, with direct input from SMEs and historical data analysis to minimize false positives and confirm predictive power.

The Results

RWE has realized the benefits of a value-based maintenance program operating at fleet scale, with Seeq’s analytics at its core.  By surfacing prioritized equipment risks in real-time, the program has prevented costly failures, reduced failed starts, and enabled engineers to move seamlessly from detection to root-cause analysis.  The integration of health scoring dashboards and analytics has turned maintenance decision-making into a continuous data-driven process.

Success Stories

  1. Igniter failure monitoring: Reduced failed starts by identifying igniter degradation before failure.
  2. Creep life monitoring: Delivered real-time visibility of high-temperature component wear, replacing outdated manual analysis.
  3. Filter management optimization: Predicted optimal replacement dates by calculating water ingress risk, preventing compressor damage, and multimillion-pound failure.
  4. Valve leakage prevention: Monitored stop-ratio valve leakage during startup and rundown tests, preventing two major breakdowns since 2021 and avoiding outages costing approximately £1.3m each.

Transformation

  • Reliability leadership: Hundreds of operationalized failure models and 70+ active Seeq data feeds integrated into RWEs MARA platform.
  • Cost reduction: Optimized use of maintenance resources against high-priority interventions.
  • Adoption at scale: More than 50% of all Seeq users are trained experts contributing to model development, refinement, and continuous improvement.
  • Enterprise alignment: Formation of a Reliability, Integrity, Efficiency, Optimization (RIEO) team to coordinate cross-departmental collaboration.
  • Sustainability: Maximized gas fleet availability and efficiency complements renewables expansion.
  • Scalable blueprint: Solutions and models extendable across RWE’s global fleet.

Conclusion

RWE’s value-based maintenance transformation showcases how legacy power generation infrastructure can be revitalized with modern analytics and cross-functional collaboration. With Seeq at the center, supporting technology and cultural enablement, RWE has not only improved plant reliability and maintenance cost-effectiveness but also created a foundation for continued innovation in the energy sector. As energy systems become more complex, RWE’s model stands as a powerful example of how digital integration and engineering excellence can enable a smarter, more sustainable energy future.