A novel approach to predict shear strength of tilted angle connectors using artificial intelligence techniques

Shear connectors play a prominent role in the design of steel-concrete composite systems. The behavior of shear connectors is generally determined through conducting push-out tests. However, these tests are costly and require plenty of time. As an alternative approach, soft computing (SC) can be used to eliminate the need for conducting push-out tests. This study aims to investigate the application of artificial intelligence (AI) techniques, as sub-branches of SC methods, in the behavior prediction of an innovative type of C-shaped shear connectors, called Tilted Angle Connectors. For this purpose, several push-out tests are conducted on these connectors and the required data for the AI models are collected. Then, an adaptive neuro-fuzzy inference system (ANFIS) is developed to identify the most influencing parameters on the shear strength of the tilted angle connectors. Totally, six different models are created based on the ANFIS results. Finally, AI techniques such as an artificial neural network (ANN), an extreme learning machine (ELM), and another ANFIS are employed to predict the shear strength of the connectors in each of the six models. The results of the paper show that slip is the most influential factor in the shear strength of tilted connectors and after that, the inclination angle is the most effective one. Moreover, it is deducted that considering only four parameters in the predictive models is enough to have a very accurate prediction. It is also demonstrated that ELM needs less time and it can reach slightly better performance indices than those of ANN and ANFIS.

     

AK-GWO: a novel hybrid optimization method for accurate optimum hierarchical stiffened shells

Engineering with Computers - An attempt has been made to propose a novel prediction model based on the Gaussian process regression (GPR) approach. The proposed GPR was used to predict blast-induced...     

Machine learning approach for solving inconsistency problems of Li-ion batteries during the manufacturing stage

The inconsistency in the mass production of lithium-ion battery (LIB) packs stem from the inconsistency in the capacity, voltage and internal resistance of single batteries that compose packs. The inconsistency issue of these battery packs can greatly reduce the output performance of a large power pack. This paper proposed the machine learning approach based on self-organization mapping (SOM) neural networks for establishing the consistency of LIBs. This method comprehensively compares and analyzes the real-LIB parameters (internal resistance, capacity and voltage) data obtained during charging and discharging to form the clusters of similar performing LIBs. Experimental result validated the clustering analysis and it indicates that the performance of clustered battery pack typically precedes than that of original. The capacity of clustered battery pack increased 1.9% compared with brand-new pack. The temperature distribution of the battery pack assembled after screening is consistent. The peak temperature is 4°-5° lower than the ordinary battery, and the temperature fluctuation is reduced by 2.6°. In addition, the application of cluster analysis is expanded and some key research directions are pointed out.     

The Synthesis of New Epoxy Resins and their Physical Properties

A series of homologous bisphenols was synthesized by the reaction of potassium p-hydroxy-benzoate with dichloroalkanes or by the esterification of p-hydroxybenzoic acid with glycols. The studies of the synthesis of the diglycidyl ethers from these bisphenols were carried out by variation of the reaction conditions. The diglycidyl ethers synthesized were cured with hexahydroxyphthalic anhydride or with 4,4'-diaminodiphenylmethane. The effects of chemical structure of the cured resins on their mechanical, thermal, electrical, and adhesive properties were investigated. The results show that there is a good correlation between chemical structure and physical properties of the cured resins. The more the number of oxyethylene units (-O-CH₂-CH₂-) that are incorporated into the bisphenol portion of the network, the more flexible and polar the cured resins become. The increase in the flexibility of the cured resins is manifested by the decrease in the deflection temperature, elastic modulus and the enhancement of the elongation of the resins. The increase in the polarity of polymer results in the enhancement of the electric constant and the better adhesive properties.     

A novel singular node‐based smoothed finite element method (NS‐FEM) for upper bound solutions of fracture problems

It is well known that the lower bound to exact solutions in linear fracture problems can be easily obtained by the displacement compatible finite element method (FEM) together with the singular crack tip elements. It is, however, much more difficult to obtain the upper bound solutions for these problems. This paper aims to formulate a novel singular node‐based smoothed finite element method (NS‐FEM) to obtain the upper bound solutions for fracture problems. In the present singular NS‐FEM, the calculation of the system stiffness matrix is performed using the strain smoothing technique over the smoothing domains (SDs) associated with nodes, which leads to the line integrations using only the shape function values along the boundaries of the SDs. A five‐node singular crack tip element is used within the framework of NS‐FEM to construct singular shape functions via direct point interpolation with proper order of fractional basis. The mix‐mode stress intensity factors are evaluated using the domain forms of the interaction integrals. The upper bound solutions of the present singular NS‐FEM are demonstrated via benchmark examples for a wide range of material combinations and boundary conditions. Copyright © 2010 John Wiley & Sons, Ltd.     

Isolation of human platelet membrane microparticles from plasma and serum

Methods have been developed to isolate human platelet membrane fragments from plasma and serum. Rabbit antibody produced against the human platelet membrane glycoprotein complex, IIb/IIIa, was utilized in an immunoelectrophoretic assay to evaluate the amount of this antigen in various microparticle preparations. The serum concentration of platelet microparticles was more than tenfold greater than that observed for plasma (65 micrograms/ml versus 4.4 micrograms/ml, respectively). Ultrastructural evaluation of either plasma or serum-derived microparticles disclosed a variety of membrane fragments and membrane-bound vesicles with occasional fragments of red blood cells, white blood cells, and platelets. In contrast, microparticle preparations derived from isolated washed platelets after thrombin stimulation contained a heterogeneous array of membrane fragments, vesicles, and granules but no identifiable red cell, white cell, or platelet fragments. Thus, these studies demonstrate that normal human plasma and serum contain platelet membrane fragments that are produced during cell activation. If a similar loss of platelet membranes occurs in vivo following reversible platelet activation, it is possible that the resulting membrane modifications may be of importance in both the structural and functional changes that develop during platelet senescence.     

A superconvergent point interpolation method (SC‐PIM) with piecewise linear strain field using triangular mesh

A superconvergent point interpolation method (SC‐PIM) is developed for mechanics problems by combining techniques of finite element method (FEM) and linearly conforming point interpolation method (LC‐PIM) using triangular mesh. In the SC‐PIM, point interpolation methods (PIM) are used for shape functions construction; and a strain field with a parameter α is assumed to be a linear combination of compatible stains and smoothed strains from LC‐PIM. We prove theoretically that SC‐PIM has a very nice bound property: the strain energy obtained from the SC‐PIM solution lies in between those from the compatible FEM solution and the LC‐PIM solution when the same mesh is used. We further provide a criterion for SC‐PIM to obtain upper and lower bound solutions. Intensive numerical studies are conducted to verify these theoretical results and show that (1) the upper and lower bound solutions can always be obtained using the present SC‐PIM; (2) there exists an α_exact∈(0, 1) at which the SC‐PIM can produce the exact solution in the energy norm; (3) for any α∈(0, 1) the SC‐PIM solution is of superconvergence, and α=0 is an easy way to obtain a very accurate and superconvergent solution in both energy and displacement norms; (4) a procedure is devised to find a α_prefer∈(0, 1) that produces a solution very close to the exact solution. Copyright © 2008 John Wiley & Sons, Ltd.     

A cell‐based smoothed discrete shear gap method (CS‐FEM‐DSG3) based on the C0‐type higher‐order shear deformation theory for dynamic responses of Mindlin plates on viscoelastic foundations subjected to a moving sprung vehicle

A cell‐based smoothed discrete shear gap method (CS‐FEM‐DSG3) based on the first‐order shear deformation theory (FSDT) was recently proposed for static and dynamic analyses of Mindlin plates. In this paper, the CS‐FEM‐DSG3 is extended to the C⁰‐type higher‐order shear deformation plate theory (C⁰‐HSDT) and is incorporated with damping–spring systems for dynamic responses of Mindlin plates on viscoelastic foundations subjected to a moving sprung vehicle. At each time step of dynamic analysis, one four‐step procedure is performed including the following: (1) transformation of the weight of a four‐wheel vehicle into the sprung masses at wheels; (2) dynamic analysis of the sprung mass of wheels to determine the contact forces; (3) transformation of the contact forces into loads at nodes of plate elements; and (4) dynamic analysis of the plate elements on viscoelastic foundations. The accuracy and reliability of the proposed method are verified by comparing its numerical solutions with those of other available numerical results. Copyright © 2014 John Wiley & Sons, Ltd.     

A face‐based smoothed finite element method (FS‐FEM) for 3D linear and geometrically non‐linear solid mechanics problems using 4‐node tetrahedral elements

This paper presents a novel face‐based smoothed finite element method (FS‐FEM) to improve the accuracy of the finite element method (FEM) for three‐dimensional (3D) problems. The FS‐FEM uses 4‐node tetrahedral elements that can be generated automatically for complicated domains. In the FS‐FEM, the system stiffness matrix is computed using strains smoothed over the smoothing domains associated with the faces of the tetrahedral elements. The results demonstrated that the FS‐FEM is significantly more accurate than the FEM using tetrahedral elements for both linear and geometrically non‐linear solid mechanics problems. In addition, a novel domain‐based selective scheme is proposed leading to a combined FS/NS‐FEM model that is immune from volumetric locking and hence works well for nearly incompressible materials. The implementation of the FS‐FEM is straightforward and no penalty parameters or additional degrees of freedom are used. The computational efficiency of the FS‐FEM is found better than that of the FEM. Copyright © 2008 John Wiley & Sons, Ltd.