Compressor Offline Washing Triggered by Isentropic Efficiency Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current offline washing procedures for compressors in turbine-compressor assemblies are inefficient, costly, and can lead to excessive degradation due to improper frequency of washings, either too frequent or too infrequent.
Innovation Solution
A method utilizing a computer system with temperature and pressure sensors, a predefined thermodynamic model, and a physics-informed neural network to predict compressor isentropic efficiency, determining the need for offline washing based on real-time measurements and historical data, optimizing the washing procedure to prevent excessive wear.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If repeated offline washings are performed at regular intervals to prevent compressor fouling, then the compressor cleanliness is maintained, but the economic cost increases and the compressor may suffer degradation from excessive washings
Solution Approach 1:
The system continuously monitors compressor performance parameters (temperature, pressure, power consumption) and compares actual values against reference values. When the deviation exceeds a threshold indicating fouling, the system triggers a washing operation. This feedback mechanism replaces fixed-schedule washings with condition-based washings, preventing both excessive washings and insufficient maintenance.
Solution Approach 2:
The compressor system performs self-diagnosis by monitoring its own performance parameters. The control unit automatically determines when washing is needed based on real-time data analysis, eliminating the need for external inspection or fixed-schedule maintenance planning. The system serves itself by detecting its own fouling condition and initiating appropriate maintenance actions.
2Productivity
If offline washing is performed frequently to maintain compressor efficiency, then the compressor performance is preserved, but the compressor may suffer degradation from too many washings
Solution Approach 1:
The system uses real-time feedback from performance sensors to determine the exact moment when fouling affects efficiency. By washing only when necessary (when performance deviation exceeds the threshold), the system maintains compressor efficiency without subjecting the compressor to unnecessary washing cycles that could cause degradation from frequent mechanical cleaning.
Solution Approach 2:
Instead of performing complete washing cycles at fixed intervals, the system applies washing action only when the measured performance degradation exceeds a predetermined threshold. This partial action approach ensures washing is performed just enough to restore efficiency without excessive washing that would harm the compressor.
3Ease of operation
If offline washing is performed at fixed intervals regardless of actual fouling condition, then the maintenance schedule is simple, but the compressor may be washed unnecessarily when only slightly fouled
Solution Approach 1:
The system replaces simple fixed-schedule maintenance with condition-based maintenance triggered by real-time feedback from performance sensors. The control unit continuously monitors parameters and automatically triggers washing only when fouling actually occurs, eliminating unnecessary washings while maintaining operational simplicity through automated decision-making.
Solution Approach 2:
The system establishes predetermined reference values and thresholds in advance that define when fouling becomes significant. These pre-configured parameters enable the system to automatically determine when washing is needed without complex real-time analysis, maintaining ease of operation while avoiding unnecessary washings.
Data Source
Figure 1
Figure 2
AI summary
The invention relates to a method for optimizing a procedure for triggering an offline washing of a compressor in a turbine-compressor assembly, the method comprising: - measuring (110) the compressor inlet temperature and the compressor inlet pressure; - receiving (120) a first measured value corresponding to the compressor inlet temperature, and a second measured value corresponding to the compressor inlet pressure; - calculating (121) the compressor isentropic efficiency from the first and second measured values, using a predefined thermodynamic model; - predicting (122) the compressor isentropic efficiency from the first and second measured values, using a predefined mathematical model; - calculating (124) the real time difference between the calculated compressor isentropic efficiency and the predicted compressor isentropic efficiency; - based on the calculated real time difference, providing (128, 130, 132A, 134, 136, 138A, 140, 142A, 142B) at least one decision indicator as to whether or not a compressor offline washing is necessary.