The analysis and simulation of aircraft engine behavior have garnered significant attention in the aeronautical industry, primarily due to its implications for performance, maintenance, safety, and sustainability.Our work successfully showcases the efficacy of utilizing time series data collected from our aircraft engines to construct a digital twin capable of dynamically emulating their real-time behavior.We then introduce a new methodology to model the physical engine's degradation and meticulously monitor its evolution over time.By continuously analyzing the simulated data against real-world performance measurements, our approach offers valuable insights into the engine's long-term behavior and health trajectory.

In recent years, exploring deep generative models for generating time series has garnered significant interest within the research community. These models have found wide-ranging applications in areas such as data augmentation, scenario simulation, and the imputation of missing data. The authenticity of the generated time series has seen remarkable advancements with the integration of recurrent neural networks (RNNs) and generative adversarial networks (GANs). RNNs used to represent the state-of-the-art (SOA) in processing sequence dependencies until the advent of Transformers, which redefined the SOA, especially in Natural Language Processing and Computer Vision. The introduction of a transformer-based GAN represented an innovative step forward, aiming to address the limitations inherent in RNNs. However, this model’s efficacy is constrained when faced with unimodal data distribution assumptions, leading to arbitrary outputs in complex distribution scenarios. This paper introduces a novel Multivariate Time Series Conditional GAN (MTS-CGAN), that leverages transformer-based architectures in generator and discriminator networks. MTS-CGAN conditions the generation process on a specific encoded context (categorical and MTS inputs), enabling one-pass generation of multivariate time series, and accommodating mixed distribution frameworks, outperforming existing models. We evaluate MTS-CGAN using quantitative metrics across multiple multivariate time series datasets. Furthermore, we propose also an innovative adaptation of the Frechet Inception Distance (FID), tailored for time series, to assess the quality of the generated data. This research demonstrates the potential of MTS-CGAN in generating high-fidelity multivariate time series.

Time series clustering is a challenging task due to the specificities of this type of data. Temporal correlation and invariance to transformations such as shifting, warping or noise prevent the use of standard data mining methods. Time series clustering has been mostly studied under the angle of finding efficient algorithms and distance metrics adapted to the specific nature of time series data. Much less attention has been devoted to the general problem of model selection. Clustering stability has emerged as a universal and model-agnostic principle for clustering model selection. This principle can be stated as follows: an algorithm should find a structure in the data that is resilient to perturbation by sampling or noise. We propose to apply stability analysis to time series by leveraging prior knowledge on the nature and invariances of the data. These invariances determine the perturbation process used to assess stability. Based on a recently introduced criterion combining between-cluster and within-cluster stability, we propose an invariance-guided method for model selection, applicable to a wide range of clustering algorithms. Experiments conducted on artificial and benchmark data sets demonstrate the ability of our criterion to discover structure and select the correct number of clusters, whenever data invariances are known beforehand.

A major application of data analytics for aircraft engine manufacturers is engine health monitoring, which consists in improving availability and operation of engines by leveraging operational data and past events. Traditional tools can no longer handle the increasing volume and velocity of data collected on modern aircraft. We propose a generic and scalable pipeline for large-scale analytics of operational data from a recent type of aircraft engine, oriented towards health monitoring applications. Based on Hadoop and Spark, our approach enables domain experts to scale their algorithms and extract features from tens of thousands of flights stored on a cluster. All computations are performed using the Spark framework, however custom functions and algorithms can be integrated without knowledge of distributed programming. Unsupervised learning algorithms are integrated for clustering and dimensionality reduction of the flight features, in order to allow efficient visualization and interpretation through a dedicated web application. The use case guiding our work is a methodology for engine fleet monitoring with a self-organizing map. Finally, this pipeline is meant to be end-to-end, fully customizable and ready for use in an industrial setting.