Research and Optimization of Process Parameters for Internal Thread Forming Based on Numerical Simulation and Experimental Analysis.

In order to improve the forming quality of extruded thread, finite element analysis and experimental research are combined to reduce the two keys that affect thread quality in the machining process-extrusion torque and extrusion temperature. The effects of different processing parameters on the extrusion torque and temperature are obtained by numerical simulation, including the bottom hole diameter of the workpiece, the machine tool speed, and the lubrication medium. For the purpose of reducing extrusion torque and temperature, the process parameters for internal thread forming are further optimized by orthogonal design. It is determined that when machining the M22 × 2 internal thread on the connecting rod of the marine diesel engine made of 42CrMo4 steel, the bottom hole diameter of the workpiece should be 21.20 mm, the speed of the machine tool should be 40 RPM, and the lubricating medium should be PDMS polydimethylsiloxane coolant. Compared to before optimization, the maximum extrusion torque and the maximum extrusion temperature are reduced by 19.27% and 15.07%, respectively. On the premise of ensuring the thread connection strength, the height of the thread tooth is reduced by 0.052 mm, and the surface condition of the thread is improved. The surface microhardness at the root, top, and side of the thread increases by about 5 HV0.2, and the depth of the hardened layer increases by 0.05 mm. The results show that the quality of the optimized thread is higher.

Attention-based recurrent neural network for influenza epidemic prediction.

BACKGROUND: Influenza is an infectious respiratory disease that can cause serious public health hazard. Due to its huge threat to the society, precise real-time forecasting of influenza outbreaks is of great value to our public. RESULTS: In this paper, we propose a new deep neural network structure that forecasts a real-time influenza-like illness rate (ILI%) in Guangzhou, China. Long short-term memory (LSTM) neural networks is applied to precisely forecast accurateness due to the long-term attribute and diversity of influenza epidemic data. We devise a multi-channel LSTM neural network that can draw multiple information from different types of inputs. We also add attention mechanism to improve forecasting accuracy. By using this structure, we are able to deal with relationships between multiple inputs more appropriately. Our model fully consider the information in the data set, targetedly solving practical problems of the Guangzhou influenza epidemic forecasting. CONCLUSION: We assess the performance of our model by comparing it with different neural network structures and other state-of-the-art methods. The experimental results indicate that our model has strong competitiveness and can provide effective real-time influenza epidemic forecasting.