Three types of fatigue tests for an annealed carbon steel containing carbon of 0.42%were carried out on smooth specimens and specimens with a small blind hole in order to investigate the fatigue crack growth law.A sim...Three types of fatigue tests for an annealed carbon steel containing carbon of 0.42%were carried out on smooth specimens and specimens with a small blind hole in order to investigate the fatigue crack growth law.A simple predicting method for crack growth rates has been proposed involving strengthσband the relation between cyclic stress and strain.The validity of proposed method has been confirmed by experiments on several carbon steels with different loadings.展开更多
Fatigue properties of materials by Additive Manufacturing(AM) depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluat...Fatigue properties of materials by Additive Manufacturing(AM) depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluation inevitably requires these factors combined as many as possible, thus resulting in low efficiency and high cost. In recent years, their assessment by leveraging the power of Machine Learning(ML) has gained increasing attentions. A comprehensive overview on the state-of-the-art progress of applying ML strategies to predict fatigue properties of AM materials, as well as their dependence on AM processing and post-processing parameters such as laser power, scanning speed, layer height, hatch distance, built direction, post-heat temperature,etc., were presented. A few attempts in employing Feedforward Neural Network(FNN), Convolutional Neural Network(CNN), Adaptive Network-Based Fuzzy Inference System(ANFIS), Support Vector Machine(SVM) and Random Forest(RF) to predict fatigue life and RF to predict fatigue crack growth rate are summarized. The ML models for predicting AM materials' fatigue properties are found intrinsically similar to the commonly used ones, but are modified to involve AM features. Finally, an outlook for challenges(i.e., small dataset, multifarious features,overfitting, low interpretability, and unable extension from AM material data to structure life) and potential solutions for the ML prediction of AM materials' fatigue properties is provided.展开更多
基金the supports from the Research Foundation for Visiting Scholars of Key Laboratory of Solid Mechanics and FML of Education Ministry,P R Chinathe supports from Japan Society for Promotion of Science
文摘Three types of fatigue tests for an annealed carbon steel containing carbon of 0.42%were carried out on smooth specimens and specimens with a small blind hole in order to investigate the fatigue crack growth law.A simple predicting method for crack growth rates has been proposed involving strengthσband the relation between cyclic stress and strain.The validity of proposed method has been confirmed by experiments on several carbon steels with different loadings.
基金the support from the National Science and Technology Major Project, China (No. J2019IV-0014-0082)the National Key Research and Development Program of China (No. 2022YFB4600700)+1 种基金the National Overseas Youth Talents Program, China, the Research Fund of State Key Laboratory of Mechanics and Control for Aerospace Structures, China (No. MCMS-I-0422K01)a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions, China。
文摘Fatigue properties of materials by Additive Manufacturing(AM) depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluation inevitably requires these factors combined as many as possible, thus resulting in low efficiency and high cost. In recent years, their assessment by leveraging the power of Machine Learning(ML) has gained increasing attentions. A comprehensive overview on the state-of-the-art progress of applying ML strategies to predict fatigue properties of AM materials, as well as their dependence on AM processing and post-processing parameters such as laser power, scanning speed, layer height, hatch distance, built direction, post-heat temperature,etc., were presented. A few attempts in employing Feedforward Neural Network(FNN), Convolutional Neural Network(CNN), Adaptive Network-Based Fuzzy Inference System(ANFIS), Support Vector Machine(SVM) and Random Forest(RF) to predict fatigue life and RF to predict fatigue crack growth rate are summarized. The ML models for predicting AM materials' fatigue properties are found intrinsically similar to the commonly used ones, but are modified to involve AM features. Finally, an outlook for challenges(i.e., small dataset, multifarious features,overfitting, low interpretability, and unable extension from AM material data to structure life) and potential solutions for the ML prediction of AM materials' fatigue properties is provided.
基金Fourth Term of ‘333 Engineering’ Program of Jiangsu Province(Project No.BRA2011116)Youth Foundation of Jiangsu Province(Project No.BK2012095)The Natural Science Foundation of Jiangsu Province of China(Project No.BK2012696)
基金Supported by Youth Foundation of Jiangsu Province(Project No.BK2012095)Special Program for Hadal Science and Technology of Shanghai Ocean University(Project No.HSTRC-T-2013-01)
基金Project (51075106) supported by the National Natural Science Foundation of ChinaProject (10GS12) supported by the Postdoctoral Project of Beijing Aeronautical Science and Technology Research Institute of COMAC
