刘天元

发布者:邓士豪发布时间:2024-04-15浏览次数:10

姓名:刘天元

个人简介20216月毕业于新葡萄8883官网AMG,获工学博士学位;202112月至202312月于香港理工大学从事博士后研究工作;20241月加入新葡萄8883官网AMG。

研究兴趣:工业人工智能、计算视觉、焊接自动化、无损检测、数字孪生、知识图谱等。

Email: tianyuan.liu@dhu.edu.cn


主讲课程:

[1] 数据结构与数据库,智能制造工程专业,大二上学期,专业基础课,48学时

[2] 工业大数据技术/课程设计,智能制造工程专业,大三下学期,专业基础课,32学时


学术服务

[1] 数字孪生青年学者委员会, 委员

[2] Big Data Mining and Analytics (中科院一区, IF 13.6), Young Associate Editor

[3] Pattern Recognition Letters (中科院三区, IF 5.1), Guest Editor

[4] IET Signal Processing (中科院四区, IF 1.7), Academic Editor

[5] Metals (中科院三区, IF 2.9), Topical Advisory Panel Member

[6] Intelligent Automation & Soft Computing (中科院四区, IF 2), Early Career Editorial Board Member

[7] 桂林理工大学学报(中文核心), 青年编委

[8] 电焊机(中国科技核心), 编委

[9] 金属加工-热加工(中文核心遴选), 青年编委

[10] 焊管(中文核心遴选), 青年编委

[11] 2023 NSFC-RGC Conference on Frontiers of Industrial Big Data and Intelligent Systems, Session Chair.

[12] 2024 8th International Conference on Control Engineering and Artificial Intelligence, Session Chair.

[13] IEEE TII, IEEE TASE, IEEE TNNLS, JIM, JMS, JMP, RCIM, ESWA, AEI, JED, IJCIM, NDTE, BDMA30余本国际期刊审稿人。


科研项目

[1] 中央高校自由探索项目,航天结构件激光焊接缺陷可信识别方法研究,主持。

[2] The Hong Kong Polytechnic University Centrally Funded Postdoctoral Fellowship Scheme, Knowledge and data hybrid-driven explainable laser welding defect recognition, 主持。

[3] 科技部重点研发计划港澳台科技创新合作重点专项,Industrial big data-enabled smart maintenance technology for complex equipment, 参与。

[4] 工信部工业互联网创新发展工程,基于边缘计算的固体火箭发动机异地协同制造工厂内集成应用新模式,参与。

[5] 工信部智能制造新模式应用项目,功能性卫生用品智能生产数字化车间,参与。

[6] 上海市科委科技创新行动计划,消化道黏膜下肿瘤影像人工智能标准化检测体系,参与。


学术论文

[1] Tianyuan Liu, Pai Zheng, Jinsong Bao. Deep learning-based welding image recognition: a comprehensive review. Journal of Manufacturing Systems, 2023, 68: 601-625. (JCR Q1, IF 12.1)

[2] Tianyuan Liu, Jiacheng Wang, Xiaodi Huang, et al. 3DSMDA-Net: an improved 3DCNN with separable structure and multi-dimensional attention for welding status recognition. Journal of Manufacturing Systems, 2022, 62: 811-822. (JCR Q1, IF 12.1)

[3] Tianyuan Liu, Hangbin Zheng, Pai Zheng, et al. An expert knowledge-empowered CNN approach for welding radiographic image recognition. Advanced Engineering Informatics, 2023, 56: 101963. (JCR Q1, IF 8.8)

[4] Tianyuan Liu, Hangbin Zheng, Jinsong Bao, et al. An explainable laser welding defect recognition method based on multi-scale class activation mapping. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-12. (JCR Q1, IF 5.6)

[5] Tianyuan Liu, Pai Zheng, Xiaojia Liu. A multiple scale spaces empowered approach for welding radiographic image defect segmentation. NDT and E International, 2023, 139: 102934. (JCR Q1, IF 4.2)

[6] Tianyuan Liu, Pai Zheng, Jinsong Bao, et al. A state-of-the-art survey of welding radiographic image analysis: challenges, technologies and applications. Measurement, 2023, 214: 112821. (JCR Q1, IF 5.6)

[7] Tianyuan Liu, Jinsong Bao, Hangbin Zheng, et al. Learning semantic-specific visual representation for laser welding penetration status recognition. Science China-Technological Sciences, 2022, 65(2): 347-360. (JCR Q1, IF 4.6)

[8] Tianyuan Liu, Pai Zheng, Huabin Chen, et al. An attention-based bilinear feature extraction mechanism for fine-grained laser welding molten pool/keyhole defect recognition. Journal of Manufacturing Processes, 2023, 87: 150-159. (JCR Q2, IF 6.2)

[9] Tianyuan Liu, Jinsong Bao, Junliang Wang, et al. A hybrid CNN–LSTM algorithm for online defect recognition of CO2 welding. Sensors, 2018, 18(12): 4369. (JCR Q2, IF 3.9)

[10] Tianyuan Liu, Jinsong Bao, Junliang Wang, et al. Deep learning for industrial image: challenges, methods for enriching the sample space and restricting the hypothesis space, and possible issue. International Journal of Computer Integrated Manufacturing, 2022, 35(10-11): 1077-1106. (JCR Q2, IF 4.1)

[11] Tianyuan Liu, Jinsong Bao, Junliang Wang, et al. A coarse-grained regularization method of convolutional kernel for molten pool defect identification. ASME Journal of Computing and Information Science in Engineering, 2020, 20(2): 021005. (JCR Q3, IF 3.1)

[12] Tianyuan Liu, Yanan Jiang, Pai Zheng, et al. A framework of cognitive intelligence-enabled welding cyber physical system. 19th IEEE International Conference on Automation Science and Engineering, 2023. (EI)

[13] 刘天元, 鲍劲松, 汪俊亮, . 融合时序信息的激光焊接熔透状态识别方法. 中国激光, 2021, 48(06): 228-238. EI, 卓越计划。

[14] 刘天元, 郑杭彬, 杨长祺, . 面向激光焊接缺陷识别的可解释性深度学习方法. 航空学报, 2022, 43(04): 451-460. EI, 卓越计划。

[15] 刘天元, 鲍劲松, 汪俊亮, . 受限解空间下粗粒度正则化的熔池边缘自适应检测方法. 焊接学报, 2020, 41(12): 49-54. EI, 机械T2级。

[16] Hangbin Zheng, Tianyuan Liu, Jiayu Liu, et al. Visual analytics for digital twin: a conceptual framework and case study. Journal of Intelligent Manufacturing, 2024, 35(4): 1671-1686. (JCR Q1, IF 8.3)

[17] Tianbiao Liang, Tianyuan Liu, Junliang Wang, et al. Causal deep learning for explainable vision-based quality inspection under visual interference. Journal of Intelligent Manufacturing, 2024, https://doi.org/10.1007/s10845-023-02297-9. (JCR Q1, IF 8.3)

[18] Qibing Lv, Tianyuan Liu, Rong Zhang, et al. Generation approach of human-robot cooperative assembly strategy based on transfer learning. Journal of Shanghai Jiaotong University (Science), 2022, 27: 602-613. (EI)

[19] 梁天飚,刘天元,汪俊亮,等。因果推理引导的复杂花纹织物缺陷视觉检测深度学习方法。中国科学技术科学, 2023, 53(7): 1138-1149. EI.


知识产权

[1] 专著. 工业智能-方法与应用, 电子工业出版社, 2022.

[2] 发明专利. 一种基于知识图谱驱动的设备资源配置优化方法. 授权号CN310117, 2020.

[3] 发明专利. 图像生成方法、装置、计算设备及存储介质. 公开号CN116664972A, 2023.

[4] 发明专利. 一种基于EUS的粘膜下肿瘤细粒度分类方法. 公开号CN114067159A, 2022.

[5] 发明专利. 一种面向卷积神经网络的粗粒度参数正则化方法. 公开号CN110413947A, 2019.

[6] 软件著作权. 焊接图像故障识别系统. 证书号11824429, 2023.

[7] 软件著作权. 东华智能制造研究所DR射线检测系统. 证书号5061870, 2020.


荣誉奖励

[1] 新葡萄8883官网AMG优秀毕业生, 2022.

[2] 新葡萄8883官网AMG优秀博士论文, 2022.

[3] 新葡萄8883官网AMG晋江市政府奖学金一等, 2020.

[4] The International Artificial Intelligence Conference, Best Reviewer Award, 2023.

[5] Intelligent Automation & Soft Computing, Outstanding Reviewer Award, 2023.


学术报告

[1] 特邀报告. 基于深度学习的焊接图像分析综述,中国机械工程学会焊接分会青年工作者第六届学术研讨会会议,2024.

[2] 特邀主旨报告. 焊接射线图像分析综述:挑战、技术和应用,射线无损检测技术交流大会,2023.

[3] 特邀主旨报告. 面向激光焊接熔透状态识别具有特定语义的视觉表示学习, 智能焊接与增材制造技术国际论坛, 2022.

[4] 青年报告. Towards cognitive intelligence-enabled digital twin system for welding quality control, The 2nd Digital Twin International Conference, 2022.

[5] 特邀报告. 3DSMDA-Net: an improved 3DCNN with separable structure and multi-dimensional attention for welding status recognition, The 2021 International Workshop on Intelligentized Welding Manufacturing, 2021.

[6] 特邀报告. 深度学习在工业图像分析中的关键问题研究, 能源清洁高效与安全利用学术论坛, 2020.


欢迎机械工程、焊接自动化、计算机科学等相关专业同学联系报考!