Data driven structural damage assessment using phase space embedding and Koopman operator under stochastic excitations

•This paper proposes a novel data driven structural damage assessment approach.•This new approach is based on phase space embedding and Koopman operator.•High dimensional phase space obtained for damage assessment under stochastic excitations.•Numerical studies on a truss bridge model are conducted to validate the approach.•In-field studies on a real bridge are conducted to validate the proposed approach.