Inflatable Wing Design Parameter Optimization Using Orthogonal Testing and Support Vector Machines

The robust parameter design method is a traditional approach to robust experimental design that seeks to obtain the optimal combination of factors/levels. To overcome some of the defects of the inflatable wing parameter design method, this paper proposes an optimization design scheme based on orthogonal testing and support vector machines （SVMs）. Orthogonal testing design is used to estimate the appropriate initial value and variation domain of each variable to decrease the number of iterations and improve the identification accuracy and efficiency. Orthogonal tests consisting of three factors and three levels are designed to analyze the parameters of pressure, uniform applied load and the number of chambers that affect the bending response of inflatable wings. An SVM intelligent model is established and limited orthogonal test swatches are studied. Thus, the precise relationships between each parameter and product quality features, as well the signal-to-noise ratio （SNR）, can be obtained. This can guide general technological design optimization.

Field study on performance of new technique of geosynthetic-reinforced and pile-supported embankment at bridge approach

Vehicle bumps at a bridge approach caused by the differential settlement between a bridge and an adjacent backfill embankment are one of the most difficult problems in geotechnical engineering. Large vehicle bumps make drivers uncomfortable and cause large impact loads on vehicles and the bridge abutment. A new ground-improvement technique called fixed-geosynthetic-reinforced and pile-supported embankment(FGT embankment) was developed and used to alleviate vehicle bumps at a trial bridge-approach site located in central China. To distribute the differential settlement between the bridge and adjacent backfill embankment over a long transition zone, the following three techniques were used at the trial bridge-approach site:(a) the FGT embankment,(b) conventional geosynthetic-reinforced and pile-supported embankment(CT embankment), and(c) geosynthetic-reinforced embankment without piles(GR embankment). The performance of all three techniques in the field trial was investigated by field measurements involving earth pressure cells, geosynthetic deformation sensors, and settlement gauges. The FGT and CT embankments exhibited better performance than the GR embankment. Compared with the CT embankment, the FGT embankment was more effective at ground improvement. At an elevation of 4.0 m from the base of the embankment, the pressures below the geosynthetic were smaller than those above the geosynthetic at the closest measurement point. The difference between the pressures between above and below the geosynthetic tended to increase with the embankment height.