Additive manufacturing workpiece forming quality monitoring and predicting method based on deep learning

Abstract

The embodiment of the invention discloses an additive manufacturing workpiece forming quality monitoring and predicting method based on deep learning, which comprises the following steps of: acquiring a geometric feature image and a temperature feature image of a molten pool in an additive manufacturing process by using an image acquisition module to obtain geometric feature parameters and temperature feature parameters; by taking the geometric feature parameters as input of a double-flow convolutional neural network, learning hidden corresponding relations among the geometric feature parameters, the temperature feature parameters and the workpiece forming quality, and enabling the hidden corresponding relations among the geometric feature parameters, the temperature feature parameters and the workpiece forming quality to correspond. By the adoption of the method, geometric and temperature characteristic parameters of the molten pool area, the plume area and the splash area are extracted, so that the dynamic monitoring process of the additive manufacturing technology and the forming quality of the workpiece are more comprehensively reflected; by utilizing the double-flow convolutional neural network is used for achieving classification of the forming quality of the workpiece, long-short-term memory neural network is used for predicting the forming quality of the workpiece in advance and correcting process parameters in time, so that the machining time is shortened, and the production quality is improved.

Description

technical field [0001] The invention relates to the technical field of material manufacturing monitoring and prediction, in particular to a method for monitoring and predicting the forming quality of additively manufactured parts based on deep learning. Background technique [0002] Additive manufacturing is an advanced manufacturing technology integrating information technology, new material technology and manufacturing technology. It is known as a representative technology that is expected to produce the "third industrial revolution". Leading technology for pattern development. In the past 20 years, this technology has achieved rapid development and has been widely used in aviation, aerospace, nuclear power, weapons, ships and other fields. However, the current additive manufacturing technology is prone to defects such as cracks, pores, spheroidization, and unfused holes during the processing process, resulting in unstable forming quality of parts and difficulty in ensuri...

AI Technical Summary

Problems solved by technology

However, in the field of additive manufacturing, there are still relatively few systems that combine the monitoring and prediction of the two parts of the characteristics of the part forming quality. The forming quality cannot be guaranteed, nor can it provide a reference for subsequent process compensation, making the repeatability of the additive manufacturing process unstable

Images