Condition-Based Feedwater Maintenance Using Fault Prognostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Power plants face challenges in detecting and predicting faults in mechanical systems, particularly in feedwater systems, which can lead to unexpected unavailability and reliance on costly secondary systems, impacting efficiency and reliability.
Innovation Solution
A fault detection system utilizing sensors to collect data from mechanical systems, including torque meters, vibration sensors, and temperature sensors, coupled with a computer system and fault detection server, performs automatic fault detection, isolation, and prognostics using data modeling techniques to predict component failures and optimize maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a secondary feedwater system is installed as backup, then system reliability is improved, but device complexity and cost increase
Solution Approach 1:
The system performs preliminary fault detection and prediction by continuously monitoring component health parameters and analyzing trends before actual failure occurs. This allows maintenance to be scheduled in advance, ensuring system availability without requiring standby backup components.
Solution Approach 2:
The feedwater system monitors its own health status through integrated sensors and analytics that detect degradation trends. The system can identify and flag potential failures before they occur, enabling self-diagnosis and predictive maintenance scheduling without external intervention or backup systems.
2Productivity
If continuous monitoring and predictive analytics are implemented, then maintenance scheduling is optimized, but device complexity increases
Solution Approach 1:
The monitoring system is designed to be multi-functional, serving multiple purposes: real-time fault detection, predictive analytics, maintenance scheduling, and component health tracking. This consolidates what could be multiple separate complex systems into a single integrated platform that delivers comprehensive maintenance management capabilities.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application provides methods and systems for automated condition-based maintenance of mechanical systems. Example systems may at least one memory coupled to one or more computer processors that are configured to receive first data from the mechanical system indicative of performance of a first component of the mechanical system, determine, using the first data, a first performance metric for the first component, determine, using the first performance metric, a probability value that a fault has occurred at the first component, and determine, using the probability value, a predicted length of time until failure of the first component.