Characterizing residual stress on pipework weld repairs using machine learning

核电厂系统是通过使用现代焊接工艺连接压力容器和管道组件而构建的。焊接结构也可能在制造过程中进行焊接修复，以减轻制造缺陷，或在使用过程中进行焊接修复，以保持原始设计寿命或延长寿命。博士项目将审查数据挖掘和机器学习方法的最新发展，确定控制焊接修复残余应力的基线参数，使用数据挖掘方法收集高质量的训练数据，开发/优化合适的机器学习工具，使用挖掘的数据训练工具，验证独立测量的输出，并为工业工程师创建了具有用户友好界面的残余应力表征工具。使用人工神经网络预测焊接件残余应力的一个主要限制是缺乏高质量的测量数据用于训练。拟议的博士项目的创新和挑战将是利用结合测量结果和合成数据的机会，从验证的模拟，以预测/估计残余应力分布在家庭的修复焊件（位于训练数据包络线）。

Nuclear power plant systems are constructed by joining pressure vessels and pipingcomponents using modern welding processes. Welded structures may also be subjected to weld repair eitherduring fabrication to mitigate manufacturing defects, or during service to maintain the original design life, orto provide life extension. The PhD project will review the latest developments in data mining and machine learningmethods, identify baseline parameters controlling residual stresses at weld repairs, collect high qualitytraining data using data mining methods, develop/optimise a suitable machine learning tool, train the toolusing the mined data, validate the outputs against independent measurements, and create residual stresscharacterisation tool with a user-friendly interface for engineers in industry.A major limitation in using ANN for prediction of residual stress in weldments is the shortage of high qualitymeasurement data for training. The innovation and challenge of the proposed PhD project will be to exploitthe opportunity of combining measurement results and synthetic data from validated simulations in orderto predict/estimate residual stress profiles in families of repair weldments (that lie within the training dataparameter envelope).