New artificial neural networks for true triaxial stress state analysis and demonstration of intermediate principal stress effects on intact rock strength

Simulations are conducted using five new artificial neural networks developed herein to demonstrate and investigate the behavior of rock material under polyaxial loading. The effects of the intermediate principal stress on the intact rock strength are investigated and compared with laboratory results from the literature. To normalize differences in laboratory testing conditions, the stress state is used as the objective parameter in the artificial neural network model predictions. The variations of major principal stress of rock material with intermediate principal stress, minor principal stress and stress state are investigated. The artificial neural network simulations show that for the rock types examined, none were independent of intermediate principal stress effects. In addition, the results of the artificial neural network models, in general agreement with observations made by others, show （a） a general trend of strength increasing and reaching a peak at some intermediate stress state factor, followed by a decline in strength for most rock types; （b） a post-peak strength behavior dependent on the minor principal stress, with respect to rock type; （c） sensitivity to the stress state, and to the interaction between the stress state and uniaxial compressive strength of the test data by the artificial neural networks models （two-way analysis of variance; 95% confidence interval）. Artificial neural network modeling, a self-learning approach to polyaxial stress simulation, can thus complement the commonly observed difficult task of conducting true triaxial laboratory tests, and/or other methods that attempt to improve two-dimensional （2D） failure criteria by incorporating intermediate principal stress effects.

The load criteria for ship mechanical noise prediction in low frequencies and experimental validation

The loading method of the external excitations generated by the equipment directly affects the predicted result of the mechanical noise which should be the same under different excitation forms for the given equipment.In this paper,general load criteria are proposed to define forces/moments as the standard form and convert other forms of loads in the low-frequency domain.As the most typical form to charac-terize equipment excitation,acceleration load loading methods for different conditions are investigated.The equivalent formula between ideal accelerations and generalized forces establishes the first load cri-terion.The second load criterion is proposed to address the issue of an average acceleration loading,in which the phase and amplitude distribution are both absent,and cannot apply to the load identification.The upper and lower limits of the mechanical noise can be determined by the vibroacoustic transfer func-tion of the three load models,and the energy-averaged value is used to represent the mechanical noise.Furthermore,the third criterion is used to handle the case where the acceleration load is given by the results of a bench test.According to the equipment source descriptor invariance,the conversion method is achieved between the bench test and the real ship based on the transfer function of a load model,and the mechanical noise is predicted by an equivalent energy method.Finally,a three-parameter method to quantitatively evaluate the well-fitting of experimental and numerical results,and the load criteria are well validated by underwater acoustic experiments of an experimental model.