Modal‐based identification method of fire damage in reinforced concrete T‐beams using support vector machine and firefly algorithm

Purpose This paper aims to propose a nonlinear model for aeroelastic aircraft that can predict the flight parameters throughout the investigated flight envelopes. Design/methodology/approach A system identification method based on the support vector machine (SVM) is developed and applied to the nonlinear dynamics of an aeroelastic aircraft. In the proposed non-parametric gray-box method, force and moment coefficients are estimated based on the state variables, flight conditions and control commands. Then, flight parameters are estimated using aircraft equations of motion. Nonlinear system identification is performed using the SVM network by minimizing errors between the calculated and estimated force and moment coefficients. To that end, a least squares algorithm is used as the training rule to optimize the generalization bound given for the regression. Findings The results confirm that the SVM is successful at the aircraft system identification. The precision of the SVM model is preserved when the models are excited by input commands different from the training ones. Also, the generalization of the SVM model is acceptable at non-trained flight conditions within the trained flight conditions. Considering the precision and generalization of the model, the results indicate that the SVM is more successful than the well-known methods such as artificial neural networks. Practical implications In this paper, both the simulated and real flight data of the F/A-18 aircraft are used to provide aeroelastic models for its lateral-directional dynamics. Originality/value This paper proposes a non-parametric system identification method for aeroelastic aircraft based on the SVM method for the first time. Up to the author’s best knowledge, the SVM is not used for the aircraft system identification or the aircraft parameter estimation until now.

Download Full-text

A sensing identification method for shearer cutting state based on modified multi-scale fuzzy entropy and support vector machine

Engineering Applications of Artificial Intelligence ◽

10.1016/j.engappai.2018.11.003 ◽

2019 ◽

Vol 78 ◽

pp. 86-101 ◽

Cited By ~ 10

Author(s):

Lei Si ◽

Zhongbin Wang ◽

Xinhua Liu ◽

Chao Tan

Keyword(s):

Support Vector Machine ◽

Fuzzy Entropy ◽

Support Vector ◽

Multi Scale ◽

Identification Method

Download Full-text

Experimental investigation and multi-conditions identification method of centrifugal pump using Fisher discriminant ratio and support vector machine

Advances in Mechanical Engineering ◽

10.1177/1687814019878041 ◽

2019 ◽

Vol 11 (9) ◽

pp. 168781401987804

Author(s):

Guangqi Qiu ◽

Si Huang ◽

Yingkui Gu

Keyword(s):

Support Vector Machine ◽

Principal Component ◽

Domain Analysis ◽

Test System ◽

Support Vector ◽

Centrifugal Pumps ◽

Flow Conditions ◽

Identification Method ◽

Fisher Discriminant ◽

Time Flow

For identifying the operation situations of centrifugal pumps by artificial intelligence, we performed an experiment on multi-flow conditions. The multi-flow conditions were simulated by adjusting an automatic flow-regulating valve installed on outlet pipe, and the vertical vibration signals of 20 flow points at the bearing house were collected by the test system. By time-domain analysis, frequency-domain analysis, information entropy, empirical modal decomposition, and wavelet packet decomposition methods, a comprehensive feature space was constructed. In addition, the optimal features were selected by Fisher discriminant ratio, and the dimensionality of the selected optimal features was reduced with principal component analysis. Finally, support vector machine algorithm was employed to identify the real-time flow condition, and the hyper-parameters of support vector machine classifier model were optimized by a grid search technique. Results show that the vibration test can effectively simulate the operation situation of centrifugal pumps under multi-flow conditions, and the proposed multi-flow conditions identification method has achieved a good identification performance.

Download Full-text