TR
T.O. Rootliep
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Gas Path Analysis on the GEnx-1B Engine with Fewer Gas Path Sensors
MSc. Thesis at KLM Engine Services
The aviation industry is increasingly driven to enhance predictive maintenance capabilities. This thesis addresses component-wise condition monitoring of the GEnx-1B engine with fewer gas path sensors using Gas Path Analysis (GPA). Due to a limited number of gas path sensors, the GPA problem is underdetermined, with more health indicators than available measurements. A novel approach is proposed that restructures the underdetermined problem into multiple solvable subproblems and combines their solutions using weight factors, while incorporating companion engine analysis to detect abnormal degradation. The GPA simulations are performed using GSPy, avoiding the computational cost of optimization-based methods. Results show accurate predictions of component health indicators, with strong performance for high-pressure compressor (HPC) and high-pressure turbine (HPT) degradation, while low-pressure components exhibit higher uncertainty. It also captures maintenance events and predicts abnormal degradation prior to failure using companion engine residuals. Overall, the Component Exclusion Method and Companion Engine Analysis enable health estimation of underdetermined gas path cases (like the GEnx-1B), while avoiding high computational costs.
...
The aviation industry is increasingly driven to enhance predictive maintenance capabilities. This thesis addresses component-wise condition monitoring of the GEnx-1B engine with fewer gas path sensors using Gas Path Analysis (GPA). Due to a limited number of gas path sensors, the GPA problem is underdetermined, with more health indicators than available measurements. A novel approach is proposed that restructures the underdetermined problem into multiple solvable subproblems and combines their solutions using weight factors, while incorporating companion engine analysis to detect abnormal degradation. The GPA simulations are performed using GSPy, avoiding the computational cost of optimization-based methods. Results show accurate predictions of component health indicators, with strong performance for high-pressure compressor (HPC) and high-pressure turbine (HPT) degradation, while low-pressure components exhibit higher uncertainty. It also captures maintenance events and predicts abnormal degradation prior to failure using companion engine residuals. Overall, the Component Exclusion Method and Companion Engine Analysis enable health estimation of underdetermined gas path cases (like the GEnx-1B), while avoiding high computational costs.
Can we Fix it?
Developing an Accurate and Interpretable Residual-Based AI Model for Turbofan Engine Predictive Maintenance
Research aimed at improving engine maintenance practices is vital to ensuring the aviation industry's high safety standards. Both preventive and corrective maintenance approaches result in either higher costs or increased failures. Predictive maintenance aims to achieve an optimal balance by using time series and historical failure data to anticipate future problems and plan engine maintenance activities. While extensive research has been done on the application of AI models for predictive maintenance using simulated datasets, limited research has been done using real world engine data. Simulated datasets lack the complexity of real world systems which undermines the applicability of their findings to real world situations. This paper addresses the gap between theory and industry by utilizing eight years of operating and maintenance data from the GEnx-1B, provided by KLM Engine Services. We expand classic residual based methods with a novel approach, sister engine analysis, to improve the performance of an LSTM-based fault detection model. The data is labeled based on maintenance reports, which provide the most accurate link to the underlying degradation state of an engine. These reports reveal a significant bias toward high pressure turbine degradation in the GEnx-1B. Furthermore, our findings indicate that incorporating sister engine analysis enhances the average F1 score of an AI-based fault detection model by 7.7% and that AI methods outperform the current industry standard when provided with the same input data. The use of physically relevant model features and LIME analysis ensures the model's behavior is interpretable. These results are significant as they help build trust in AI-based solutions for predictive maintenance, which is crucial for their broader adoption.
...
Research aimed at improving engine maintenance practices is vital to ensuring the aviation industry's high safety standards. Both preventive and corrective maintenance approaches result in either higher costs or increased failures. Predictive maintenance aims to achieve an optimal balance by using time series and historical failure data to anticipate future problems and plan engine maintenance activities. While extensive research has been done on the application of AI models for predictive maintenance using simulated datasets, limited research has been done using real world engine data. Simulated datasets lack the complexity of real world systems which undermines the applicability of their findings to real world situations. This paper addresses the gap between theory and industry by utilizing eight years of operating and maintenance data from the GEnx-1B, provided by KLM Engine Services. We expand classic residual based methods with a novel approach, sister engine analysis, to improve the performance of an LSTM-based fault detection model. The data is labeled based on maintenance reports, which provide the most accurate link to the underlying degradation state of an engine. These reports reveal a significant bias toward high pressure turbine degradation in the GEnx-1B. Furthermore, our findings indicate that incorporating sister engine analysis enhances the average F1 score of an AI-based fault detection model by 7.7% and that AI methods outperform the current industry standard when provided with the same input data. The use of physically relevant model features and LIME analysis ensures the model's behavior is interpretable. These results are significant as they help build trust in AI-based solutions for predictive maintenance, which is crucial for their broader adoption.