In the internal thread extrusion forming, if the process parameters are not selected properly, the extrusion torque will increase, the extrusion temperature will be too high, or even the tap will break. In order to obtain effective process parameters under certain working conditions, this paper uses a combination of numerical simulation and process experiment to analyze the influence of the bottom hole diameter, extrusion speed, and friction factor on the extrusion torque and extrusion temperature. Through an orthogonal experiment, the significant influence law of different process parameters on the extrusion torque and extrusion temperature was studied, and the order of their influence was determined. Based on the optimal process parameters, numerical simulations and process tests were carried out, and the extrusion effect and related parameters were compared and analyzed. The results show that the extruded thread has clear contour, uniform tooth pitch, complete tooth shape, and good flatness. Compared with before optimization, the maximum extrusion torque has been reduced by 37.15%, the maximum temperature has been reduced by 29.72%, and the extrusion quality has been improved. It shows that the optimized method and optimized process parameters have good engineering practicability.

The extrusion process parameters have a great impact on the quality of the extrusion thread. In order to ensure the extrusion quality and the smooth progress of the extrusion process, a prediction model based on BP-GA neural network is established. The model takes the diameter of the bottom hole, extrusion speed, and friction coefficient as the input layer, and the extrusion torque, extrusion temperature, and tooth height as the output layer. After training the model with sample data, the extrusion internal thread quality prediction is carried out. The results show that the BP-GA neural network prediction model has a high accuracy in predicting the extrusion torque, extrusion temperature and tooth height rate during the cold extrusion of internal threads. The error between the experimental value and the predicted value of the extrusion torque is between 10% and 15%, the experimental value of the extrusion temperature is consistent with the predicted value, and the error between the experimental value and the predicted value of the tooth height rate is less than 5%. The BP-GA neural network prediction model can accurately predict the extrusion temperature, extrusion torque, and tooth height rate, providing a new way for the re-search of internal thread cold extrusion technology.

In order to improve the service life of extrusion taps and reduce their wear, this paper adopted the coating-simulation technology to investigate the influence laws of tool coating type and coating thickness on extrusion torque, extrusion temperature and wear amount. The validity of the numerical simulation results is confirmed through internal thread extrusion experiments. The results showed that the extrusion torque and extrusion temperature of single-layer coating and composite coating showed a tendency of decreasing and then increasing with the increase of the coating thickness; the extrusion torque and extrusion temperature of the double-layer coating increased with the increase of the coating thickness; the wear amount of the three types of coatings increased with the increase of the coating thickness. The TiAlN single coating demonstrates the most pronounced impact on decreasing extrusion torque and temperature (3.82 N·m and 88.4 °C), resulting in a smooth extrusion process. The TiAlN–TiAlN double coating exhibits the lowest wear amount of 0.076 mm. The utilization of numerical simulation proves to be a dependable approach for evaluating the efficacy of tool coatings, and reasonable selection of coating type and thickness can effectively reduce the extrusion torque, extrusion temperature and wear amount.