Optimal sensor placement using machine learning

DOI10.1016/J.COMPFLUID.2017.10.002zbMATH Open1390.76808arXiv1609.07885OpenAlexW2963591671MaRDI QIDQ1648618FDOQ1648618

Authors: R. Semaan 

Publication date: 27 June 2018

Published in: Computers and Fluids (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1609.07885

Recommendations

• Optimal sensor placement for variational data assimilation of unsteady flows past a rotationally oscillating cylinder
• Heuristics for Effective Actuator and Sensor Placement in Feedback Flow Control
• Optimal sensor placement via Gaussian quadrature
• Optimal sensor and actuator placement for feedback control of vortex shedding
• Sequentially optimal sensor placement in thermoelastic models for real time applications

zbMATH Keywords

machine learningflow controloptimal sensor placement

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Direct numerical and large eddy simulation of turbulence (76F65) Flow control and optimization for compressible fluids and gas dynamics (76N25)

Cites Work

• Title not available (Why is that?)
• Random forests
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• Unsteady flow sensing and estimation via the gappy proper orthogonal decomposition
• Title not available (Why is that?)
• Optimized sensor placement for urban flow measurement
• Sensor Placement Methodologies for Dynamic Testing
• Optimal placement and gains of sensors and actuators for feedback control

Cited In (8)

• Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping
• Optimization method for sensor planning
• Optimal sensor placement for variational data assimilation of unsteady flows past a rotationally oscillating cylinder
• Sensor placement in nuclear reactors based on the generalized empirical interpolation method
• Sequentially optimal sensor placement in thermoelastic models for real time applications
• Learning-based actuator selection for increased attack resilience of uncertain systems
• Optimal design of sensors via geometric criteria
• POD-based constrained sensor placement and field reconstruction from noisy wind measurements: a perturbation study

Uses Software

• MEGAFLOW
• TAU
• C4.5
• xROM

This page was built for publication: Optimal sensor placement using machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1648618)