Abstract: Disclosed a method for predicting permeability of a multi-mineral phase digital core based on deep learning. In the present disclosure, a three-dimensional digital core is constructed and a pore structure is randomly generated; after a plurality of multi-mineral digital core images is acquired by performing image segmentation on the three-dimensional digital core, permeability corresponding to each of the multi-mineral digital core images is acquired by simulation using multi-physics field simulation software and a multi-mineral digital core data set is constructed based on the plurality of multi-mineral digital core images and the permeability corresponding to each of the multi-mineral digital core images; an SE-ResNet18 convolutional neural network is constructed and trained with the multi-mineral digital core data set; and an image of a multi-mineral core to be predicted is input into the trained SE-ResNet18 convolutional neural network to determine the permeability of the multi-mineral core.

Abstract: An automatic cleaning device, comprising: a moving platform configured to automatically move on an operation surface; a cleaning module which is provided on the moving platform and comprises a wet-type cleaning module configured to clean at least a part of the operation surface in a wet-type cleaning mode and a dry-type cleaning module configured to clean at least a part of the operation surface in a dry-type cleaning mode; and a floating lifting/lowering structure connected to the dry-type cleaning module and configured to enable the dry-type cleaning module to passively move up and down relative to the moving platform.

Abstract: A cleaning brush for a smart cleaning device, including: a mounting shaft an elastic supporting member, provided with a through hole extending in an axial direction and sleeved onto the mounting shaft through the through hole; and a tubular member, sleeved onto the elastic supporting member and provided with blades integrated with the tubular member, where an adhesive layer is provided between the mounting shaft and the elastic supporting member, as well as between the elastic supporting member and the tubular member respectively, such that the mounting shaft, the elastic supporting member and the tubular member are adhered together.

Abstract: The present disclosure provides a cleaning brush and an intelligent cleaning device. The cleaning brush includes a shaft rod, a cylindrical member and at least one end member. The shaft rod is provided with two first ends which are opposite in an axial direction; the cylindrical member coaxially sleeves the shaft rod and is provided with two second ends which are opposite in an axial direction, and a brush piece is arranged on an outer surface of the cylindrical member; the at least one end member is installed on at least one of the first ends, and the end member is provided with a blocking structure for preventing an entanglement from excessively extending away from the cleaning brush; the end member and the first end are provided with installation structures respectively matching each other; and the second end of the cylindrical member, which corresponds to the end member, covers at least a portion of the end member.

Abstract: The present disclosure relates to the field of smart home technology and proposes a base station and a cleaning robot system. A base station applicable to clean a cleaning mechanism of a cleaning robot includes a cleaning tank, configured to accommodate at least part of the cleaning mechanism and clean the at least part of the cleaning mechanism, the cleaning tank includes a first end face and a second end face, a direction of a connection line between the first end face and the second end face is substantially parallel to an extension direction of the cleaning mechanism. A cleaning robot system is further provided.

Abstract: The present disclosure provides an autonomous robot, configured to perform a cleaning function and an emptying function.