Abstract: A calculation system for predicting a proppant embedding depth based on a shale softening effect is provided, including a sampling test terminal, a scheduling module, a monitoring module, and a calculation module, wherein the scheduling module, the monitoring module, and the calculation module are connected in communication, and the monitoring module is connected to an external operating system through a wireless network, wherein the external operating system is configured to perform a hydraulic fracturing operation and receive a first control signal and/or a second control signal from the monitoring module. The sampling test terminal is configured to test the samples and obtain test data. The scheduling module is configured to determine a target construction parameter.

Abstract: An automatic transport device for cleaning machines includes a transport base. A lifting-lowering assembly and a tray are provided on the transport base. The tray is connected to the transport base through the lifting-lowering assembly, and can be driven by the lifting-lowering assembly to reciprocate in a height direction. A top surface of the tray is provided with a translation assembly for transferring the shelf to the transport platform. A first mounting cavity is provided at each of front and rear ends of the tray. The translation assembly is connected to a side wall of the first mounting cavity. A second mounting cavity is provided at each of right and left ends of the tray. The second mounting cavity is provided with a limiting assembly, a lifting-lowering sensing assembly and a distance sensing assembly. An interactive system is provided in the transport base.

Abstract: An automatic transport device for cleaning machines includes a transport base. A lifting-lowering assembly and a tray are provided on the transport base. The tray is connected to the transport base through the lifting-lowering assembly, and can be driven by the lifting-lowering assembly to reciprocate in a height direction. A top surface of the tray is provided with a translation assembly for transferring the shelf to the transport platform. A first mounting cavity is provided at each of front and rear ends of the tray. The translation assembly is connected to a side wall of the first mounting cavity. A second mounting cavity is provided at each of right and left ends of the tray. The second mounting cavity is provided with a limiting assembly, a lifting-lowering sensing assembly and a distance sensing assembly. An interactive system is provided in the transport base.

Abstract: A device for machine learning is provided, including a first neural network layer, a second neural network layer with a normalization layer arranged in between. The normalization layer is configured to, when the device is undergoing training on a batch of training samples, receive multiple outputs of the first neural network layer for a plurality of training samples of the batch, each output comprising multiple data values for different indices on a first dimension and a second dimension; group the outputs into multiple groups based on the indices on the first and second dimensions; form a normalization output for each group which are provided as input to the second neural network layer. According to the application, the training of a deep convolutional neural network with good performance that performs stably at different batch sizes and is generalizable to multiple vision tasks is achieved, thereby improving the performance of the training.