Anomaly detection and failure prediction of gas turbines is of great importance for ensuring reliable operation. This work presents a novel approach for anomaly detection based on a data-driven performance digital twin of gas turbine engines. The developed digital twin consists of two parts: uncertain performance digital twin (UPDT) and fault detection capability. UPDT is a probabilistic digital representation of the expected performance behavior of real-world gas turbine engines operating under various conditions. Fault detection capability is developed based on detecting UPDT outputs that have low probability under the training distribution. A novel anomaly measure based on the first Wasserstein distance is proposed to characterize the entire flight data, and a threshold can be applied to this measure to detect anomaly flights. The proposed UPDT with uncertainty quantification is trained with the sensor data from an individual physical reality and the outcome of the UPDT is intended to deliver the health assessment and fault detection results to support operation and maintenance decision-making. The proposed method is demonstrated on a real-world dataset from a typical type of commercial turbofan engine and the result shows that the F1 score reaches a maximum of 0.99 with a threshold of 0.45. The case study demonstrated that the proposed novel anomaly detection method can effectively identify the abnormal samples, and it is also possible to isolate anomalous behavior in a single performance signal, which is helpful for further fault diagnosis once an anomaly is detected.

High-pressure compressor (HPC) blades of aero engines inevitably exhibit various uncertain geometric deviations, which deteriorate engine performance and increase maintenance costs. Although the condition-based maintenance (CBM) strategy is increasingly adopted to reduce costs by tailoring repair actions based on condition monitoring data, maintenance practices often still rely on original equipment manufacturer (OEM) recommendations. To further refine the CBM strategy, this paper proposes an uncertainty quantification method based on the engine performance digital twin (PDT) model to quantify the impact of HPC blade geometric deviations on overall engine performance. The PDT model is developed by coupling computational fluid dynamics simulations with a zero-dimensional performance model using real operating data and is validated for high predictive accuracy. Surrogate models based on support vector regression are employed to efficiently quantify the impact of combined geometric deviations. The results show that combined deviations cause reductions in mass flow, pressure ratio, and efficiency while increasing exhaust gas temperature and specific fuel consumption. The proposed methodology is applied to a CBM scenario to demonstrate its effectiveness. In the real maintenance process, this method enables the prediction of performance after repair, facilitating optimized maintenance strategies.