Dynamic modeling and analysis of the closed-circuit grinding-classification process

Mathematical models of the grinding process are the basis of analysis, simulation and control. Most existent models in- cluding theoretical models and identification models are, however, inconvenient for direct analysis. In addition, many models pay much attention to the local details in the closed-circuit grinding process while overlooking the systematic behavior of the process as a whole. From the systematic perspective, the dynamic behavior of the whole closed-circuit grinding-classification process is consid- ered and a first-order transfer function model describing the dynamic relation between the raw material and the product is established. The model proves that the time constant of the closed-circuit process is lager than that of the open-circuit process and reveals how physical parameters affect the process dynamic behavior. These are very helpful to understand, design and control the closed-circuit grinding-classification process.

Comparative analysis of twelve transfer learning models for the prediction and crack detection in concrete dams,based on borehole images

Disaster-resilient dams require accurate crack detection,but machine learning methods cannot capture dam structural reaction temporal patterns and dependencies.This research uses deep learning,convolutional neural networks,and transfer learning to improve dam crack detection.Twelve deep-learning models are trained on 192 crack images.This research aims to provide up-to-date detecting techniques to solve dam crack problems.The finding shows that the EfficientNetB0 model performed better than others in classifying borehole concrete crack surface tiles and normal(undamaged)surface tiles with 91%accuracy.The study’s pre-trained designs help to identify and to determine the specific locations of cracks.