Thermal Deformation Defect Prediction for Layered Printing Using Convolutional Generative Adversarial Network

This paper presents a Thermal Deformation defect prediction method for layered printing using Convolutional Generative Adversarial Network (CGAN). Firstly, the original manifold mesh is converted into layered image in Printing Coordinate System (PCS). The trajectory inside layered image with various infill patterns are generated for making comparisons. Inspired by monocular vision and even binocular vision, the mathematical model of thermal defect prediction via infrared thermogram is built via virtual printing of Digital Twins to preset the initial parameters of Artificial Neural Network (ANN). Particularly, the depth convolution is used to extract multi-scale features of layered image. By using transfer learning techniques to identify small sample data, the CGAN is employed to build the nonlinear implicit relations between thermal deformation and multi-scale features. The binocular stereo vision laser scanner is used to determine the actual thermal deformation of the target printed objects. The shape deformation dissimilarity can be succinctly calculated by evaluating the surface profile error via mesh registration between the original source and target mesh model. The proposed method is verified by physical experiments. The experiment proved that the proposed method can deal with the thermal deformation with more optimal parameters, which contributes to performance forward design of irregular complex parts regarding diversified customized requirements.

The evaluation of the bouncing model of caliper pig’s detection arm in subsea gas pipelines

Caliper pigs are widely used for measuring pipeline internal geometry and detecting anomalies, such as dents, wrinkles and flat spots. Due to its excellent transport capacity, caliper pig is more widely used in subsea gas pipelines than smart pig, such as Magnetic Flux Leakage (MFL) pig or Ultrasonic Test (UT) pig. In this article, the bouncing process of detection arm of caliper pig across convex defect is studied. And then, the influence of the collision between the detection arm and deformation defect, as well as the defect shape on the bounce, is discussed. Based on that, a bouncing theoretical model of the detection arm is developed for analyzing the bouncing phenomenon. Furthermore,the bouncing process that the detection arm moves across the convex defect with different velocities and different initial spring forces is studied by experimental method. The bouncing model calculation value is approximately equal with the experimental value, verifying the validity of the bouncing model. The bouncing model has a great significance for caliper pig evaluating the pipeline convex defect.

Influence of Hardening Phase of Coherent and Incoherent Coupling with FCC Matrix on Evolution of Deformation Defect Subsystem and Strain Hardening of Heterophase Alloys

A mathematical model of plastic deformation of dispersion-hardened materials with FCC matrix and strengthening particles having various coupling with the matrix is presented. The model is based on the equations of balance of deformational defects of various types with allowance for their transformation in the process of plastic deformation. The influence of scale characteristics of the strengthening phase, temperature, and strain rate on the evolution of the dislocation subsystem and on strain hardening of an alloy with FCC matrix is investigated.

The Pilot Study on the Defect Prediction and Numerical Simulation in the Superplastic/ Extrusion of Copper Alloy

The aim of the study on the deformation defect is to prevent defects and to improve the quality and to control the deformation. It is important that the preventive measure could be established to advance the scientificity of the product and processing design. In this paper, the reasons of the outer defects such as cracks are analyzed based on the superplasticity of the copper alloy and the process of solid cages in the superplastic extrusion. The prediction and numerical simulation of these typical defects are also carried out using the Deform-3D software grounded on the model of the rigid-visco plastic FEM. The position, time of crack appearance and relation between the strain rate and the defects are also studied. The simulated results are in equivalent agreement with the experiment.