Support vector machines approach to mean particle size of rock fragmentation due to bench blasting prediction

Aiming at the problems of the traditional method of assessing distribution of particle size in bench blasting, a support vector machines （SVMs） regression methodology was used to predict the mean particle size （X50） resulting from rock blast fragmentation in various mines based on the statistical learning theory. The data base consisted of blast design parameters, explosive parameters, modulus of elasticity and in-situ block size. The seven input independent variables used for the SVMs model for the prediction of X50 of rock blast fragmentation were the ratio of bench height to drilled burden （H/B）, ratio of spacing to burden （S/B）, ratio of burden to hole diameter （B/D）, ratio of stemming to burden （T/B）, powder factor （Pf）, modulus of elasticity （E） and in-situ block size （XB）. After using the 90 sets of the measured data in various mines and rock formations in the world for training and testing, the model was applied to 12 another blast data for validation of the trained support vector regression （SVR） model. The prediction results of SVR were compared with those of artificial neural network （ANN）, multivariate regression analysis （MVRA） models, conventional Kuznetsov method and the measured X50 values. The proposed method shows promising results and the prediction accuracy of SVMs model is acceptable.

Relationship Between Grain Yield and Yield Components in Super Hybrid Rice

Chinese super hybrid rice breeding project has developed many new varieties with great yield potential. It is controversial which yield component should be emphasized in super hybrid rice production. The present study was conducted to compare super hybrid rice with common hybrid and super inbred rice and analyze contributions of yield components to grain yield of super hybrid rice under experimental conditions, and evaluate relationships between grain yield and yield components of super hybrid rice in farmer’s paddy fields. Field experiments were done in Changsha, Guidong, and Nanxian, Hunan Province, China, from 2007 to 2009. Eight super hybrid varieties, one common hybrid variety, and one super inbred variety were grown in each location and year. Rice production investigation was undertaken in high-yielding （Guidong）, moderate-yielding （Nanxian）, and low-yielding （Ningxiang） regions of Hunan Province, China, in 2009. Grain yield and yield components were measured in both the field experiments and rice production investigation. Super hybrid rice varieties outyielded common hybrid and super inbred varieties across three locations and years. Yield potential has been increased by 11.4% in super hybrid rice varieties compared with common and super inbred varieties. The higher yield of super hybrid varieties was attributed to improvement in panicle size. Panicles per m2 had the highest positive contribution to grain yield with the exception under yield level of 10.0 to 12.0 t ha-1, and was positively related to grain yield in farmer’s field at all of the high-, moderate-, and low-yielding regions. Our study suggests that panicle per m2 ought to be emphasized in super hybrid rice production.