A novel recursive modal parameter estimator for operational time-varying structural dynamic systems based on least squares support vector machine and time series model. (March 2020)

• Record Type: Journal Article
• Authors: Kang, Jie; Liu, Li; Zhou, Si-Da; Wang, Da-Yu; Ma, Yuan-Chen
• Is Part Of: Computers & structures. Volume 229(2020)
• Publication Date: 2020-03
• Subjects: Recursive modal parameter estimation -- Linear time-varying structures -- Least squares support vector machine -- Vector time-dependent autoregressive moving average model; Structural engineering -- Data processing -- Periodicals; Electronic data processing -- Structures, Theory of -- Periodicals; 624.171
• DOI: 10.1016/j.compstruc.2019.106173
• Languages: English
• ISSNs: 0045-7949

Abstract

Highlights: A novel recursive modal parameter estimator for time-varying structures is presented. The proposed recursive estimator adapts the least squares support vector machine. The novel estimator is robust to model structure because of structural risk minimization used. Computational cost of the novel estimator is independent of the measurements dimension. A numerical example and a laboratory experiment validate the proposed estimator. Abstract: Modal parameters are practically important for vibration control, structural dynamic design, health monitoring, etc. Presently, the commonly used recursive modal parameter estimators are generally based on the empirical risk minimization principle, and thus can result in overfitting problem easily. This paper presents a novel recursive modal parameter estimator for operational linear time-varying structures based on least squares support vector machine (LSSVM) and vector time-dependent autoregressive moving average model. A sliding-window forgetting mechanism is adapted to fix computational complexity of each update step and enhance tracking capability of the proposed estimator. A numerical example and a laboratory experiment are performed to demonstrate that the proposed structural risk minimization principle based estimator is robust to model structure and its computational complexities are independent of the dimension of output measurements comparing with the existing recursive extended least squares estimator.