Abstract
Model-based predictive maintenance using high-frequency in-flight data requires digital twins that can model the dynamics of their physical twin with high precision. The models of the twins need to be fast and dynamically updatable. Machine learning offers the possibility to address these challenges in modeling the transient performance of aero engines. During transient operation, heat transferred between the engine’s structure and the annulus flow plays an important role. Diabatic performance modeling is demonstrated using non-dimensional transient heat transfer maps and transfer learning to extend turbomachinery transient modeling. The general form of such a map for a simple system similar to a pipe is reproduced by a Multilayer Perceptron neural network. It is trained using data from a finite element simulation. In a next step, the network is transferred using measurements to model the thermal transients of an aero engine. Only a limited number of parameters measured during selected transient maneuvers is needed to generate suitable non-dimensional transient heat transfer maps. With these additional steps, the extended performance model matches the engine thermal transients well.
Highlights
Today, more data sampled at higher frequency is available from engine in-flight operation
The non-dimensional transient heat transfer map derived from finite element method (FEM) simulation for a given step change of Θstep = 1.0 is shown in Figure 4 for sets of parameters Bii, Bio, and θchar
The neural networks representing the non-dimensional transient heat transfer maps of compressor and turbine were implemented into a state of the art gas turbine performance program to model the investigated shaft power engine
Summary
More data sampled at higher frequency is available from engine in-flight operation To use this data for predictive maintenance, online fault diagnostics, and fleet management, digital twins are of paramount importance. During aero gas turbine engine transient operation, significant amounts of heat are transferred between the engine structure and the annulus flow [5,6]. Proposed modeling the heat transfer from the flow to the engine’s structure using nondimensional heat transfer maps. Those maps can be implemented as look-up tables into the underlying performance program to facilitate fast calculations while keeping the required accuracy. The map representing the transient heat transfer of a pipe is generated This data is used to train a neural network. This map can be transferred to match the thermal transients of a small turboshaft engine using measurements from a limited amount of transient maneuvers
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have