Abstract: Provided is a method and system for predicting a hydration reaction degree of cement based on a cycle generative adversarial network (CycleGAN). The method includes the following steps: S1, acquiring a micro-structure image of a cement paste test specimen; S2, establishing a micro-pore structure image dataset; S3, establishing a cement micro-hydration prediction model based on a CycleGAN; and S4, completing prediction based on a final cement micro-hydration prediction model. A deep learning algorithm is applied to micro-hydration prediction of cement. A complex theoretical formula is replaced with a data driven mode. Dependence on ideal hypotheses is reduced, and the accuracy of prediction on micro-hydration of cement is thus improved.

Abstract: A method for detecting road diseases by intelligent cruise via an unmanned aerial vehicle (UAV), the UAV and a detecting system therefor are provided. The method for detecting road diseases by intelligent cruise via UAV, wherein a road disease detection model and a road recognition model based on deep learning network are built in the UAV, wherein the method specifically comprises a step of: automatically flying the UAV on a predetermined route on the actual road determined by the road recognition model, and obtaining road disease test results by the road surface disease detection model. The present invention adopts the road recognition model and road disease detection model based on deep learning network, which can realize automatic cruise and automatic road disease detection, only need to set a predetermined route or area range, which is convenient and fast.

Abstract: A method for stabilizing and lifting a channel board by underwater grouting includes (A) when the channel board is damaged, removing the damaged channel board, cleaning and leveling a gravel layer under the damaged channel board, placing an undamaged channel board installed with first grouting pipes and a second grouting pipe on the gravel layer, wherein multiple geotextile bags are respectively bound to the first grouting pipes; when the channel board is subsided, installing first grouting pipes and a second grouting pipe into first grouting holes and a second grouting hole, respectively; (B) performing a first polymer grouting through the first grouting pipes, and performing a second polymer grouting through the second grouting pipe; (C) cutting off a part of the first grouting pipes the second grouting pipe which are exposed to the channel board, and leveling incisions; and (D) removing excess polymer left on the channel board.

Abstract: A trough plate for constructing a locked polymer anti-seepage wall includes a plate body, a guide tube, a grouting pipe and an anti-blocking head. A construction method of the locked polymer anti-seepage wall includes the steps of positioning an Nth trough plate and then pressing the Nth trough plate into ground, wherein N is a natural number larger than and equal to 1; engaging an (N+1)th trough plate with the Nth trough plate, and then pressing the (N+1)th trough plate into the ground; connecting a grouting pipe of the Nth trough plate with a grouting machine, pulling out the Nth trough plate, and simultaneously grouting through the grouting pipe of the Nth trough plate by the grouting machine; and repeating the steps (B) and (C) till the locked polymer anti-seepage wall is completed, wherein the steps (B) and (C) are repeated every time, N is automatically increased by 1.

Abstract: A method for detecting road diseases by intelligent cruise via an unmanned aerial vehicle (UAV), the UAV and a detecting system therefor are provided. The method for detecting road diseases by intelligent cruise via UAV, wherein a road disease detection model and a road recognition model based on deep learning network are built in the UAV, wherein the method specifically comprises a step of: automatically flying the UAV on a predetermined route on the actual road determined by the road recognition model, and obtaining road disease test results by the road surface disease detection model. The present invention adopts the road recognition model and road disease detection model based on deep learning network, which can realize automatic cruise and automatic road disease detection, only need to set a predetermined route or area range, which is convenient and fast.

Abstract: A method for segmentation of underground drainage pipeline defects based on full convolutional neural network includes steps of: collecting a data set of the underground drainage pipeline defects; processing the data set of the underground drainage pipeline defects; optimizing with a semantic segmentation algorithm; adjusting model hyperparameters; training a model; verifying the model; and testing the model. The method adopts a deep learning algorithm, optimizes the FCN full convolutional neural network, develops a semantic segmentation method suitable for complex and similar defect characteristics of underground drainage pipelines, and adopts real underground drainage pipeline defect detection big data, thereby realizing pixel-level segmentation of the underground drainage pipeline defects and providing better robustness and generality. The detection accuracy and efficiency of the underground drainage pipeline defects are effectively improved.

Abstract: A trough plate for constructing a locked polymer anti-seepage wall includes a plate body, a guide tube, a grouting pipe and an anti-blocking head. A construction method of the locked polymer anti-seepage wall includes the steps of positioning an Nth trough plate and then pressing the Nth trough plate into ground, wherein N is a natural number larger than and equal to 1; engaging an (N+1)th trough plate with the Nth trough plate, and then pressing the (N+1)th trough plate into the ground; connecting a grouting pipe of the Nth trough plate with a grouting machine, pulling out the Nth trough plate, and simultaneously grouting through the grouting pipe of the Nth trough plate by the grouting machine; and repeating the steps (B) and (C) till the locked polymer anti-seepage wall is completed, wherein the steps (B) and (C) are repeated every time, N is automatically increased by 1.

Abstract: A method for stabilizing and lifting a channel board by underwater grouting includes (A) when the channel board is damaged, removing the damaged channel board, cleaning and leveling a gravel layer under the damaged channel board, placing an undamaged channel board installed with first grouting pipes and a second grouting pipe on the gravel layer, wherein multiple geotextile bags are respectively bound to the first grouting pipes; when the channel board is subsided, installing first grouting pipes and a second grouting pipe into first grouting holes and a second grouting hole, respectively; (B) performing a first polymer grouting through the first grouting pipes, and performing a second polymer grouting through the second grouting pipe; (C) cutting off a part of the first grouting pipes the second grouting pipe which are exposed to the channel board, and leveling incisions; and (D) removing excess polymer left on the channel board.