AI Case Study

A large european integrated electric power company is predicting, diagnosing and reducing equipment failures in conventional power plants with machine learning

A large european integrated electric power company implemented C3 IoT's C3 Predictive Maintenance solution to achieve more accurate predictions of equipment failure and maintenance needs. The technology uses advanced machine learning-based algorithms to monitor instrument signals, track failure modes and detect anomalies in equipment components. The company's 2,640 megawatt conventional coal-fired power plant benefited from the implementation at it improved prognostic lead time and flexibility in scheduling of maintenance tasks and reduced ununplanned, emergency maintenance tasks.

Industry

Utilities

Electricity

Project Overview

"The C3 Predictive Maintenance application was deployed to significantly contribute to these goals through multiple levers:

* Improving prognostic lead time and flexibility in scheduling of maintenance tasks
* Increasing temporal accuracy and localization of asset failure predictions
* Reducing or avoiding unplanned, emergency maintenance tasks
* Maximizing energy production reliability and dispatch commitments.

One of C3 IoT’s SaaS applications, C3 Predictive Maintenance employed advanced machine learning-based algorithms to enhance failure prediction and diagnostic capabilities of plant operators. The application augmented traditional systems by continuously monitoring all instrument signals, tracking complex failure modes, and detecting operating anomalies associated with impending equipment failures for a large range of rotating equipment components.

With the ability to integrate broad sensor data as well as unstructured maintenance, work orders, and operations information, the application gave plant operators a comprehensive and predictive view of the current conditions and emerging maintenance requirements of equipment days and weeks ahead.

Based on this successful deployment, C3 IoT is working with the utility to scale the machine learning-based methods of C3 Predictive Maintenance to a larger set of rotating equipment and systems across the utility’s conventional power plants in Europe, and additional plants worldwide in 2016-2017."

Reported Results

"The company states the following results:

* Improving prognostic lead time and flexibility in scheduling of maintenance tasks
* Increasing temporal accuracy and localization of asset failure predictions
* Reducing or avoiding unplanned, emergency maintenance tasks.
* Maximizing energy production reliability and dispatch commitments."

Technology

Advanced machine learning-based algorithms
"The application augmented traditional systems by continuously monitoring all instrument signals, tracking complex failure modes, and detecting operating anomalies associated with impending equipment failures for a large range of rotating equipment components.

Function

Operations

Field Services

Background

"One of Europe’s largest integrated electric power companies was looking for analytics solutions to reliably forecast equipment failure and improve condition- based maintenance for its coal-fired power plant.

With a diverse array of coal, oil, and gas/CCGT power plants, the utility’s more than 50GW worldwide generating portfolio has been under pressure to streamline global operations and reduce generating costs (both CapEx and operations /maintenance O&M expenses) by 7-10%."

Benefits

Data

Broad sensor data as well as unstructured maintenance, work orders, and operations information