Rotating Machine Vibration Monitoring for False Alarm Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional rotating machine monitoring systems, such as those for gas turbines, often generate false alarms due to fluctuations in steady state conditions, leading to expensive maintenance and lost revenue.
Innovation Solution
A system utilizing multiple vibration sensors and controllers to analyze synchronized amplitude changes across sensors, considering sensor operation, historical data, and operating parameters to accurately identify potentially damaging events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional monitoring systems use steady state or baseline conditions for vibration monitoring, then the system can operate continuously, but false alarms are generated due to fluctuations from temperature changes and ambient conditions
Solution Approach 1:
The system transitions from static baseline comparison to dynamic adaptive monitoring. The monitoring system continuously adjusts its reference conditions based on real-time operating parameters (temperature, load, speed), allowing it to adapt to changing ambient conditions without generating false alarms. This dynamic adaptation enables continuous operation while maintaining high reliability.
Solution Approach 2:
The system changes the monitoring parameters from fixed steady-state values to variable parameters that correlate with operating conditions. By using multiple sensors to monitor vibration, temperature, load, and speed simultaneously, the system adjusts its fault detection thresholds based on the current operating state, eliminating false alarms caused by environmental fluctuations.
2Reliability
If multiple sensors and comprehensive analysis methods are used to improve detection accuracy, then false alarms are reduced, but the device complexity increases
Solution Approach 1:
The controller is designed to perform multiple functions: it monitors vibration from multiple sensors, collects operating parameters (temperature, load, speed), performs synchronized analysis, and generates fault detections. This multi-functional approach consolidates what could be separate complex systems into a single integrated controller, improving detection accuracy without proportionally increasing overall system complexity.
Solution Approach 2:
The system merges multiple sensor inputs and analysis functions into a unified monitoring framework. By combining vibration sensors, temperature sensors, load monitoring, and speed sensing into a single coordinated system with centralized analysis, the patent achieves high detection accuracy while avoiding the complexity of multiple independent monitoring systems.
3Reliability
If false alarms are generated, then maintenance procedures are triggered, but expensive maintenance and lost revenue occur due to gas turbine being taken offline
Solution Approach 1:
The system uses feedback from multiple sensors to continuously verify fault conditions before triggering maintenance alerts. By monitoring vibration synchronization across multiple sensors and cross-referencing with operating parameters, the system provides feedback that confirms actual faults versus false alarm conditions, preventing unnecessary shutdowns and maintaining productivity while ensuring genuine faults are detected.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the accuracy of identifying potentially damaging events, reducing false alarms and minimizing unnecessary maintenance by precisely detecting hazardous conditions in rotating machines.
Implementation Method 1
A plurality of sensors monitor vibrations associated with a rotating machine
Data Source
Figure 1
Figure 2
AI summary
Systems (100) and methods (200) for protecting rotating machines (105) are provided. Measurements data collected by a plurality of sensors (110, 115) may be received (205) by a controller (120) that includes one or more computers. The plurality of sensors (110, 115) may be configured to monitor vibrations associated with the rotating machine (105). Based at least in part upon the measurements data, the controller (120) may determine (240) that a respective amplitude change for at least two of the plurality of sensors (110, 115) exceeds a threshold condition. The controller (120) may also determine (245) that the threshold condition is exceeded for a predetermined period of time. Based at least in part upon determining that the threshold condition is exceeded for a predetermined period of time, the controller (120) may identify (265) an alarm event.