Turbine Engine Contamination Modeling for Predictive Wash Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional jet engine maintenance schedules do not consider the actual performance and condition of the engine when determining wash events, leading to inefficient cleaning and potential engine performance deterioration.
Innovation Solution
A system utilizing contamination accumulation modeling to assess particulate accumulations within a turbine engine, optimizing wash timings and methods based on sensor data to maximize hardware life and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional fixed maintenance schedules are used for engine washes, then maintenance timing is simple to determine, but engine performance deterioration occurs due to inadequate cleaning optimization
Solution Approach 1:
The system continuously monitors engine performance parameters (such as compressor inlet pressure, turbine outlet temperature, and fuel flow) and feeds this data back to the contamination accumulation model. The model compares actual performance against baseline values to detect contamination levels, enabling dynamic adjustment of wash scheduling based on real engine condition rather than fixed time intervals.
Solution Approach 2:
The contamination accumulation model predicts future contamination levels based on historical performance data and operating conditions. By forecasting when contamination will reach thresholds that require cleaning, the system schedules wash events proactively before significant performance deterioration occurs, rather than reacting to degraded performance.
2Reliability
If frequent engine washes are performed to maintain performance, then engine cleanliness is improved, but maintenance costs and operational downtime increase
Solution Approach 1:
The wash scheduling system transitions from static fixed-interval scheduling to dynamic condition-based scheduling. The contamination accumulation model continuously updates contamination level predictions based on real-time performance monitoring and historical data, adjusting wash timing dynamically to match actual contamination accumulation rates. This allows extending wash intervals when contamination accumulates slowly while scheduling earlier washes when accumulation is rapid.
Solution Approach 2:
The system monitors changes in key performance parameters (pressure ratios, temperatures, fuel consumption) to detect contamination accumulation. By tracking parameter drift from baseline values and correlating it with contamination models, the system determines optimal wash timing based on actual contamination levels rather than arbitrary time or cycle thresholds.
3Measurement precision
If comprehensive sensor monitoring is implemented to track engine conditions, then wash timing accuracy is improved, but system complexity and data processing requirements increase
Solution Approach 1:
The system utilizes existing engine sensors that serve multiple functions - the same sensors monitoring combustion efficiency, turbine performance, and emissions also provide data for contamination accumulation detection. By leveraging multi-functionality of standard engine instrumentation, the system avoids adding dedicated contamination sensors while still achieving accurate contamination monitoring through performance parameter analysis.
Solution Approach 2:
The contamination accumulation model acts as an intermediary that translates complex sensor data from multiple engine parameters into a single contamination level prediction. Rather than directly processing raw sensor signals, the model uses performance parameter deviations as intermediate indicators of contamination, simplifying the relationship between sensor inputs and wash scheduling decisions.
Data Source
AI summary
A wash optimization system and related methods are provided that increase the efficiency and the effectiveness of engine washes. A system comprising at least one processor receives sensor data representing one or more measured parameters of a turbine engine and determines at least one performance parameter based on the sensor data. The at least one performance parameter represents one or more particulate values associated with the turbine engine. The system generates a health state for the turbine engine based on the at least one performance parameter and generates a wash identifier based on the health state of the turbine engine.