Demonstration and validation of constructive initialization method for neural networks to approximate nonlinear functions in engineering mechanics applications

Pei, Jin‐Song; Masri, Sami F.

doi:10.1007/s11071-014-1797-z

Cited by 10 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They explained physical meaning of trained networks' parameters for system identification and damage detection purpose. The approach presented in [27,28] is a continuation of Pei's studies, where they presented a developed initialization procedure and neurons' number selection to approximate nonlinear functions in context of restoring force planes identification.…”

Section: Artificial Neural Network-based Model For Identificationmentioning

confidence: 99%

Identification of the stick and slip motion between contact surfaces using artificial neural networks

et al. 2020

View full text Add to dashboard Cite

The paper presents work related to nonlinear system parameters identification. The research is focused on systems with hysteretic stiffness characteristics. The identification procedure is developed with use of artificial neural networks. The presented method assumes two separate clusters of neural networks, which are supported by additional signal processing block. Such approach gives an advantage over the conventional identification methods due to its small restrictions. The validation process considers structural responses in time and frequency domains as well as the restoring force plane of the dynamic structure. First, verification of the identification method is performed on the numerical simulation of the system with hysteretic stiffness. Next, the identification of the real dynamic system with contact-related nonlinearity is carried out. The steel samples with contacting surfaces were used in the experiment. Electromagnetic shaker was used to excite the structure and enforce a relative shear motion between surfaces in contact. The system response was recorded using the Polytec laser vibrometer.

show abstract

Section: Artificial Neural Network-based Model For Identificationmentioning

confidence: 99%

Identification of the stick and slip motion between contact surfaces using artificial neural networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The nonlinear restoring force is estimated through the displacement and velocity inputs. In Pei et al 147 and Pei and Masri, 148 ANN is used to estimate the displacement and acceleration transmissibility functions as well as the restoring force of a viscous fluid damper. In Ghiasi et al, 149 the ANN and the least square support vector machine (LS-SVM) 150 are employed to detect the damage location and severity.…”

Section: Data Fusion Techniques In Shmmentioning

confidence: 99%

Data fusion approaches for structural health monitoring and system identification: Past, present, and future

Jahanshahi

2018

Structural Health Monitoring

159

View full text Add to dashboard Cite

During the past decades, significant efforts have been dedicated to develop reliable methods in structural health monitoring. The health assessment for the target structure of interest is achieved through the interpretation of collected data. At the beginning of the 21st century, the rapid advances in sensor technologies and data acquisition platforms have led to the new era of Big Data, where a huge amount of heterogeneous data are collected by a variety of sensors. The increasing accessibility and diversity of the data resources provide new opportunities for structural health monitoring, while the aggregation of information obtained from multiple sensors to make robust decisions remains a challenging problem. This article presents a comprehensive review of the recent data fusion applications in structural health monitoring. State-of-the-art theoretical concepts and applications of data fusion in structural health monitoring are presented. Challenges for data fusion in structural health monitoring are discussed, and a roadmap is provided for future research in this area.

show abstract

“…The applicability of data-driven methods, such as machine learning and artificial neural networks (ANNs), has received growing interest in recent years for modeling structural dynamic systems due to their ability to approximate nonlinear functions with good accuracy [18][19][20][21]. Previous studies have focused on predicting time series data for structural health monitoring and fatigue analysis of structures, such as wind turbines subject to nonlinear loading [22], buildings subject to base excitation similar to earthquakes [23], floating structures [24], or engine vibrations [25,26].…”

mentioning

confidence: 99%

Data-Driven Modeling Approach for Mistuned Cyclic Structures

2021

View full text Add to dashboard Cite

A data-driven approach to predict dynamic responses of mistuned cyclic dynamic structures is presented. Nominally cyclic structures such as turbomachinery bladed disks, or blisks, contain deviations from perfect symmetry, called mistuning, which can significantly increase the forced response of the structure subject to periodic excitations. The ability to accurately model the response is crucial for understanding a structure's dynamics during operation, and thus many reduced-order models have been developed. Data-driven approaches, however, are largely unexplored for predicting physical responses of cyclic structures, and are desirable due to their ability to leverage both computational and experimental data. In this paper, two feed-forward neural networks (FFNNs) are trained using physical responses and parameters from an individual sector of the cyclic structure. The desired physical responses of all sectors are predicted via a cyclic coupling procedure. By only using sector-level data, the number of simulations and/or experiments required to generate training data is substantially reduced, and the approach is not restricted to a specific projection basis unlike previous physics-based methods. A lumped mass model (LMM) of a blisk with stiffness mistuning is used to generate computational surrogate data for training and validation. Both FFNNs achieve high prediction accuracy on both training data and unseen test data. For a test case with an unseen mistuning pattern, this approach shows strong agreement with known actual responses. For this test case, prediction errors in the LMM blade tip amplitudes across all sectors are less than 2%, and the amplification factor error is less than 0.2%.

show abstract

Demonstration and validation of constructive initialization method for neural networks to approximate nonlinear functions in engineering mechanics applications

Cited by 10 publications

References 26 publications

Identification of the stick and slip motion between contact surfaces using artificial neural networks

Identification of the stick and slip motion between contact surfaces using artificial neural networks

Data fusion approaches for structural health monitoring and system identification: Past, present, and future

Data-Driven Modeling Approach for Mistuned Cyclic Structures

Contact Info

Product

Resources

About