Structural damage diagnosis and fine scale finite element intelligence simulation of long span cable stayed bridges

According to the accumulation characteristics presented by the security threat factors existed in building structure, it is relatively difficult to carry out real-time danger monitoring. In addition, the noise and structure will form complex interference and make the real-time monitoring more difficult. Therefore, this paper proposes one bridge structure monitoring algorithm of restricted Boltzmann machine (SDRBM) based on sparse cross-entropy penalty factor. Firstly, the improvement of deep network learning process based on sparse cross-entropy penalty factor and restricted Boltzmann machine (RBM) has effectively resolved the homogenization problems existed in deep network learning process; secondly, the preset rough set is used to make pretreatment for input bridge health signals to achieve complete preservation of data information and balance of effective reduction as well as simplify treatment complexity; finally, the experiment shows that the proposed DRBM bridge structure monitoring algorithm of sparse cross-entropy penalty factor can achieve bridge safety monitoring under the condition of unknown noise and structure.