An artificial neural network approach for prediction of long-term strength properties of steel fiber reinforced concrete containing fly ash

In this study, an artificial neural network (ANN) model for studying the strength properties of steel fiber reinforced concrete (SFRC) containing fly ash was devised. The mixtures were prepared with 0 wt%, 15 wt%, and 30 wt% of fly ash, at 0 vol.%, 0.5 vol.%, 1.0 vol.% and 1.5 vol.% of fiber, respectively. After being cured under the standard conditions for 7, 28, 90 and 365 d, the specimens of each mixture were tested to determine the corresponding compressive and flexural strengths. The pa- rameters such as the amounts of cement, fly ash replacement, sand, gravel, steel fiber, and the age of samples were selected as input variables, while the compressive and flexural strengths of the concrete were chosen as the output variables. The back propagation learning algorithm with three different variants, namely the Levenberg-Marquardt (LM), scaled conjugate gradient (SCG) and Fletcher-Powell conjugate gradient (CGF) algorithms were used in the network so that the best approach can be found. The results obtained from the model and the experiments were compared, and it was found that the suitable algorithm is the LM algorithm. Furthermore, the analysis of variance (ANOVA) method was used to determine how importantly the experimental parameters affect the strength of these mixtures.

Influence of process parameters on deep drawing of AA6111 aluminum alloy at elevated temperatures

To gain a deep insight into the hot drawing process of aluminum alloy sheet, simulations of cylindrical cup drawing at elevated temperatures were carried out with experimental validation. The influence of four important process parameters, namely,punch velocity, blank holder force(BHF), friction coefficient and initial forming temperature of blank on drawing characteristics(i.e.minimum thickness and thickness deviation) was investigated with the help of design of experiments(DOE), analysis of variance(ANOVA) and analysis of mean(ANOM). Based on the results of ANOVA, it is shown that the blank holder force has the greatest influence on minimum thickness. The importance of punch velocity for thickness deviation is 44.35% followed by BHF of 24.88%,friction coefficient of 15.77% and initial forming temperature of blank of 14.995%. After determining the significance of each factor on forming characteristics, how the individual parameter affects characteristics was further analyzed by ANOM.

A review of 20 years of naive tests of significance for high-dimensional mean vectors and covariance matrices

We introduce the so-called naive tests and give a brief review of the new developments. Naive testing methods are easy to understand and perform robustly, especially when the dimension is large. We focus mainly on reviewing some naive testing methods for the mean vectors and covariance matrices of high-dimensional populations, and we believe that this naive testing approach can be used widely in many other testing problems.

Simultaneous optimization of multiple performance characteristics in WEDM for machining ZC63/SiC_p MMC

Abstract The compliance of an integrated approach, principal component analysis （PCA）, coupled with Tagu chi＇s robust theory for simultaneous optimization of cor related multiple responses of wire electrical discharge machining （WEDM） process for machining SiCp rein forced ZC63 metal matrix composites （MMCs） is investi gated in this work. The WEDM is proven better for its efficiency to machine MMCs among others, while the particulate size and volume percentage of SiCp with the composite are the utmost important factors. These improve the mechanical properties enormously, however reduce the machining performance. Hence the WEDM experiments are conducted by varying the particulate size, volume fraction, pulseon time, pulseoff time and wire tension. In the view of quality cut, the most important performance indicators of WEDM as surface roughness （Ra）, metal removal rate （MRR）, wire wear ratio （WWR）, kerf （Kw） and white layer thickness （WLT） are measured as respon ses. PCA is used as multiresponse optimization technique to derive the composite principal component （CPC） which acts as the overall quality index in the process. Consequently, Taguchi＇s S/N ratio analysis is applied to optimize the CPC. The derived optimal process responses are confirmed by the experimental validation tests results. The analysis of vari ance is conducted to find the effects of choosing process variables on the overall quality of the machined component.The practical possibility of the derived optimal process conditions is also presented using SEM.