Probabilistic Risk-Based Performance Evaluation of Seismically Base-Isolated Steel Structures Subjected to Far-Field Earthquakes

Intelligent fault diagnosis is a promising tool for processing mechanical big data. It can quickly and efficiently process the collected signals and provide accurate diagnosis results. However, rotating machinery often works under various speed conditions, which makes it difficult to extract fault features. Inspired by speech recognition, the nuisance attribute projection method in speech recognition is introduced into fault diagnosis to solve the problem of feature extraction in variable speed signals. Based on the idea of unsupervised feature learning, the loss function of nuisance attribute projection is added to the loss function of convolutional neural network (CNN) to learn fault features from original data. Health status is classified according to the learned characteristics and projection matrix P. A special designed bearing dataset is employed to verify the effectiveness of the proposed method. The results show that the proposed method has a higher accuracy and a simpler framework, which is superior to the existing methods in bearing fault diagnosis.

Section: Discussionmentioning

confidence: 99%

A Fault Diagnosis Approach for Rolling Bearing Based on Convolutional Neural Network and Nuisance Attribute Projection under Various Speed Conditions

An³

2019

“…Rezaei Rad and Banazadeh [48] presented a comprehensive application of probabilistic soft computing technique in damage determination of steel structure. Ghorbani et al [49] used the MLP and radial basis function ANNs to predict the support pressure, and develop the ground motion curve in an underground structure (circular tunnel).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Developing a Library of Shear Walls Database and the Neural Network Based Predictive Meta-Model

Moradi

Hariri-Ardebili

2019

There is a large amount of useful information from past experimental tests, which are usually ignored in test-setup for the new ones. Variation of assumptions, materials, test procedures, and test objectives make it difficult to choose the right model for validation of the numerical models. Results from different experiments are sometimes in conflict with each other, or have minimum correlation. Furthermore, not all these information are easily accessible for researchers and engineers. Therefore, this paper presents the results of a comprehensive study on different experimental models for steel plate and reinforced concrete shear walls. A unique library of up to 13 parameters (mechanical properties and geometric characteristics) affecting the strength, stiffness and drift ratio of the shear walls are gathered including their sensitivity analysis. Next, a predictive meta-model is developed based on artificial neural network. It is capable of forecasting the responses for any desired shear wall with good accuracy. The proposed network can be used to as an alternative to the nonlinear numerical simulations or expensive experimental test.

“…The material of the stiffened plates was assumed to have a yield stress of 313.6 MPa and a Young's modulus of 205.8 GPa. The material properties are implemented into FE models via modelling by elastic-perfectly plastic formulation and no material hardening effect is considered [11,25]. For ease of description, the stiffened plates are hereafter referred to as 'Xijmn', where X indicates the type of stiffener, i the size of stiffener, j the aspect ratio of a plate, and mn the thickness of plate, respectively, and each of them is defined as follows: For example, F2510 denotes the stiffened plate with flat-bar stiffeners of Size 2, aspect ratio of 5, and thickness of 10 mm.…”

Section: Geometry and Materials Of Stiffened Platesmentioning

confidence: 99%

Numerical Investigation on Ultimate Compressive Strength of Welded Stiffened Plates Built by Steel Grades of S235–S390

Dong

Wang

et al. 2019

The welded stiffened plate is widely used in naval architecture and offshore engineering as a basic structural member. The aim of this study is to investigate the effect of welding residual stress and steel grade on the ultimate strength of stiffened plates under uniaxial compressive load by non-linear finite element analysis. Nineteen stiffened plates built with three types of stiffeners with various column slenderness ratios provided in the ISSC’2000 VI.2 benchmark calculations are employed in the present study. The commercial finite element code ABAQUS is applied to simulate the collapse behavior of the stiffened plates and verified against the benchmark calculations. Fabrication-related imperfections, such as initial deflections and residual stresses, are accounted for in the simulations. The ultimate strength of stiffened plates built in common shipbuilding steels, namely S235, S315, S355 and S390, are investigated by varying the yield strength of materials in the simulation. Analysis of the numerical results shows that the welding residual stress reduces the ultimate strength of stiffened plates, and increase in yield strength of the material can effectively improve the ultimate strength of common ship stiffened plates; and quantitative analyses of their influences have also been performed.