Optimal sensor placement using machine learning

TL;DR

This paper introduces a machine learning-based method for optimal sensor placement that is simple, adaptive, and computationally efficient, demonstrated on flow over an airfoil with promising results.

Contribution

It proposes a novel sensor placement technique using variable importance from machine learning models, improving over traditional and brute-force methods.

Findings

Sensor placement varies with flow conditions and sensor type.

The method outperforms maximum POD modal amplitude and brute-force approaches.

Response function choice has limited impact on placement.

Abstract

A new method for optimal sensor placement based on variable importance of machine learned models is proposed. With its simplicity, adaptivity, and low computational cost, the method offers many advantages over existing approaches. The new method is implemented on the flow over an airfoil equipped with a Coanda actuator. The analysis is based on flow field data obtained from 2D unsteady Reynolds averaged Navier-Stokes (URANS) simulations with different actuation conditions. The optimal sensor locations is compared against the current de-facto standard of maximum POD modal amplitude location, and against a brute force approach that scans all possible sensor combinations. The results show that both the flow conditions and the type of sensor have an effect on the optimal sensor placement, whereas the choice of the response function appears to have limited influence.