CNN-based Compressor Mass Flow Estimator in Industrial Aircraft Vapor Cycle System

TL;DR

This paper introduces a CNN-based virtual sensor for estimating compressor mass flow in aircraft vapor cycle systems, outperforming traditional polynomial regression models and including a novel segmentation method for dynamic behavior analysis.

Contribution

A novel CNN model for virtual mass flow estimation and a semi-automatic segmentation method for dynamic system analysis are proposed.

Findings

CNN significantly outperforms polynomial regression in MSE and performance metrics.

The segmentation method enables better analysis of dynamic vapor cycle behavior.

The approach provides a lightweight, accurate alternative to physical sensors in aircraft systems.

Abstract

In Vapor Cycle Systems, the mass flow sensor playsa key role for different monitoring and control purposes. However,physical sensors can be inaccurate, heavy, cumbersome, expensive orhighly sensitive to vibrations, which is especially problematic whenembedded into an aircraft. The conception of a virtual sensor, basedon other standard sensors, is a good alternative. This paper has twomain objectives. Firstly, a data-driven model using a ConvolutionalNeural Network is proposed to estimate the mass flow of thecompressor. We show that it significantly outperforms the standardPolynomial Regression model (thermodynamic maps), in terms of thestandard MSE metric and Engineer Performance metrics. Secondly,a semi-automatic segmentation method is proposed to compute theEngineer Performance metrics for real datasets, as the standard MSEmetric may pose risks in analyzing the dynamic behavior of VaporCycle Systems.