The Dasanjiang basin group in Northeast China contains more than ten Mesozoic–Cenozoic sedimentary basins. Much evidence shows that they were a unified large-scale depression lacustrine basin in the Early Cretaceous; however, destruction processes and mechanisms after the formation of the unified lacustrine basin are some of the key issues restricting basic research and oil and gas exploration in the Dasanjiang area. In this study, we carried out low-temperature thermochronology and thermal history inversion on samples from the main basins in the Dasanjiang area to finely restore the destruction process of the unified basin. The results show that since the Early Cretaceous, the Dasanjiang area has experienced three major positive tectonic inversions: 100 Ma~90 Ma, 73 Ma~40 Ma, and 23 Ma~5 Ma. The unified basin was destroyed by compression and uplift and gradually disintegrated. The basin gradually changed from initial unified evolution to differential evolution and finally formed the isolated appearance of each basin. The aforementioned three-stage positive tectonic inversion time limits basically corresponded to the changing periods in the movement direction, subduction angle, and movement speed of the paleo–Pacific Ocean plate. It is believed that the movement and reorganization events of the plates on the Pacific side dominated the formation, destruction, and disintegration of the Dasanjiang prototype basin, which was the main dynamic mechanism of the tectonic evolution of the Mesozoic and Cenozoic basins in the study area and Northeast China.
Intelligent diagnosis method has become a new focus for researchers, which can get rid of the dependence of diagnostic experience and prior knowledge. However, in practical application, to deal with the new fault type of mechanical equipment, the number of fault labels of the diagnosis model needs to be increased. We must retrain the whole training model, which is a time-consuming process. To solve this problem, higher requirements are put forward for the generalization ability and universality of the algorithm. In view of the feature extraction advantages of cross-sparse filtering (Cr-SF), which can be regarded as an unsupervised minimum entropy learning method using the maximization of the proxy of sparsity, this paper proposed a parallel network based on Cr-SF. The feature extraction process of each sample is independent, and the feature extraction and classifier training process are separated. Therefore, the most prominent advantage of the proposed method is that when a new fault occurs, it only needs to extract the feature of the new fault separately and then input it to the classifier at the last layer for training. The experimental results show that the proposed method can obtain high accuracy and stability and can significantly improve the adaptability of intelligent fault diagnosis in practical application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.