On sensor optimisation for structural health monitoring robust to environmental variations

Abstract. Structural health monitoring (SHM) is often approached from a statistical pattern recognition or machine learning perspective with the aim of inferring state structure using data derived network sensors placed upon it. In this paper, two SHM sensor placement optimisation (SPO) strategies that offer robustness to environmental effects are developed and evaluated. The both involve constructing an objective function (OF) based established damage classification technique locations genetic algorithm (GA). key difference between explored here in whether any sources benign variation deemed be observable not. relative performances demonstrated experimental gathered glider wing tested chamber, different states across series controlled temperatures.