Qiang Xiong

With the development of prefabricated buildings and the national requirements of promoting green buildings, this paper studies the failure modes and seismic performance of the t-shaped steel tubular recycled concrete column and prefabricated steel beam joint. The concrete filled steel tubular column composed of 100 ^% recycled concrete is selected. The seismic performance of prefabricated cantilever beam segment fully bolted joints, bolt-reinforced joints, steel tubular recycled concrete columns-Z-shaped prefabricated joints and z-shaped joints with upper and lower flange stiffeners designed according to the principle of equal strength design are studied. The failure models and hysteretic curves of four specimens were obtained by numerical simulation. The seismic behavior of cantilever beam joints affected by the number of flange bolts and the shape of cantilever beam joints was analyzed. The results show that the t-shaped steel tubular recycled concrete column-fabricated Z-shaped steel beam joint has good seismic resistance and can realize the outward displacement of the plastic hinge at the beam end. The anti-seismic capability of joints can be significantly enhanced by setting up upper and lower flange stiffeners and web side stiffeners.

Plant leaves can be used to effectively detect plant diseases. However, the number of images of unhealthy leaves collected from various plants is usually unbalanced. It is difficult to detect diseases using such an unbalanced dataset. We used DoubleGAN (a double generative adversarial network) to generate images of unhealthy plant leaves to balance such datasets. We proposed using DoubleGAN to generate high-resolution images of unhealthy leaves using fewer samples. DoubleGAN is divided into two stages. In stage 1, we used healthy leaves and unhealthy leaves as inputs. First, the healthy leaf images were used as inputs for the WGAN (Wasserstein generative adversarial network) to obtain the pretrained model. Then, unhealthy leaves were used for the pretrained model to generate 64*64 pixel images of unhealthy leaves. In stage 2, a superresolution generative adversarial network (SRGAN) was used to obtain corresponding 256*256 pixel images to expand the unbalanced dataset. Finally, compared with images generated by DCGAN (Deep convolution generative adversarial network). The dataset expanded with DoubleGAN, the generated images are clearer than DCGAN, and the accuracy of plant species and disease recognition reached 99.80% and 99.53%, respectively. The recognition results are better than those from the original dataset.