Optimal design of structural parameters for shield cutterhead based on fuzzy mathematics and multi-objective genetic algorithm

In order to improve the strength and stiffness of shield cutterhead, the method of fuzzy mathematics theory in combination with the finite element analysis is adopted. An optimal design model of structural parameters for shield cutterhead is formulated,based on the complex engineering technical requirements. In the model, as the objective function of the model is a composite function of the strength and stiffness, the response surface method is applied to formulate the approximate function of objective function in order to reduce the solution scale of optimal problem. A multi-objective genetic algorithm is used to solve the cutterhead structure design problem and the change rule of the stress-strain with various structural parameters as well as their optimal values were researched under specific geological conditions. The results show that compared with original cutterhead structure scheme, the obtained optimal scheme of the cutterhead structure can greatly improve the strength and stiffness of the cutterhead, which can be seen from the reduction of its maximum equivalent stress by 21.2%, that of its maximum deformation by 0.75%, and that of its mass by 1.04%.

Dosimetric evaluation of CR, 3DCRT and two types of IMRT for breast cancer after conservative surgery

Objective: The purpose of this study was to compare the dose distribution and dose volume histogram (DVH) of the planning target volume (PTV) and organs at risk (OARs) among conventional radiation therapy (CR), three-dimensional conformal radiation therapy (3DCRT), two-step intensity-modulated radiation therapy (TS-IMRT) and direct machine parameter optimization intensity-modulated radiation therapy (DMPO-IMRT) after breast-conserving surgery. Methods: For each of 20 randomly chosen patients, 4 plans were designed using 4 irradiation techniques. The prescribed dose was 50 Gy/2 Gy/25 f, 95% of the planning target volume received this dose. The cumulated DVHs and 3D dose distributions of CR, 3DCRT, TS-IMRT and DMPO-IMRT plans were compared. Results: For the homogeneity indices, no statistically significant difference was observed among CR, 3DCRT, TS-IMRT and DMPO-IMRT while the difference of the conformality indices were statistically significant. With regard to the organs at risk, IMRT and 3DCRT showed a significantly fewer exposure dose to the ipsilateral lung than CR in the high-dose area while in the low-dose area, IMRT demonstrated a significant increase of exposure dose to ipsilateral lung, heart and contralateral breast compared with 3DCRT and CR. In addition, the monitor units (MUs) for DMPO-IMRT were approximately 26% more than those of TS-IMRT and the segments of the former were approximately 24% less than those of the latter. Conclusion: Compared with CR, 3DCRT and IMRT improved the homogeneity and conformity of PTV, reduced the irradiated volume of OARs in high dose area but IMRT increased the irradiated volume of OARs in low dose area. DMPO-IMRT plan has fewer delivery time but more MUs than TS-IMRT.

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.