艾明曦

研究领域

工业视觉与感知、智能监测与控制

研究概况

云南大学信息学院讲师、硕士生导师，获中南大学控制科学与工程博士学位，期间赴英国埃克塞特大学、芬兰阿尔托大学和德国杜伊斯堡-埃森大学访学。研究方向为基于机器视觉的复杂工业过程智能监测与控制。主持国家自然科学基金青年项目、云南省基础研究计划面上项目、兴滇英才支持计划-青年人才专项及教育部产学合作项目各1项，在学科领域权威期刊发表论文30余篇。入选云南大学青年培优计划、兴滇英才支持计划青年人才。

研究课题

国家自然科学基金：基于分布式视觉感知的矿物浮选过程运行状态分层评价方法(2024.01-2026.12)

兴滇英才支持计划-青年人才专项：基于深层视觉感知的矿物浮选过程药剂量优化控制(2024.01-2028.12)

云南省基础研究计划面上项目：基于分布视觉感知的矿物浮选过程多质量指标协同预测(2024.03-2027.02)

云南大学青年培优计划项目：基于机器视觉的复杂工业过程运行状态智能感知与优化控制(2022.08-2025.08)

云南省重点实验室开放课题：基于多敏感特征的矿物浮选过程加药量自适应控制方法(2023.06-2024.05)

教育部产学合作协同育人项目：面向新工科的物联网感知层课程改革与实践教学模式创新(2025.05-2026.05)

学术成果

代表性论文：

[1] Mingxi Ai, Jin Zhang, Peng Li, Jiande Wu, Zhaohui Tang, Yongfang Xie*. Semi-supervised contrastive learning for flotation process monitoring with uncertainty-aware prototype optimization[J]. Engineering Applications of Artificial Intelligence, 2025, 145: 110222.

[2] Jin Zhang, Mingxi Ai*, Zhaohui Tang, Yongfang Xie, Jiande Wu, Jun Ma. Data-efficient soft sensing learning for flotation process monitoring. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 1-10.

[3] Mingxi Ai, Yongfang Xie*, Zhaohui Tang, Jiande Wu, Peng Li, Jin Zhang. Self-supervised dynamic and static feature representation learning method for flotation monitoring[J]. Powder Technology, 2024, 442: 119866.

[4] Mingxi Ai, Yongfang Xie*, Steven X. Ding, Zhaohui Tang, Weihua Gui. Domain knowledge distillation and supervised contrastive learning for industrial process monitoring[J]. IEEE Transactions on Industrial Electronics, 2022, 70(9): 9452-9462.

[5] Mingxi Ai, Yongfang Xie*, Zhaohui Tang, Jin Zhang, Weihua Gui. Deep learning feature-based setpoint generation and optimal control for flotation processes[J]. Information Sciences, 2021, 578: 644-658. 

[6] Mingxi Ai, Yongfang Xie, Shiwen Xie*, Jin Zhang, Weihua Gui. Fuzzy association rule-based set-point adaptive optimization and control for the flotation process[J]. Neural Computing and Applications, 2020, 32(17): 14019-14029.

[7] Mingxi Ai, Yongfang Xie*, Zhaohui Tang, Jin Zhang, Weihua Gui. Two-stream deep feature-based froth flotation monitoring using visual attention clues[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70: 1-14.

[8] Mingxi Ai, Yongfang Xie, Shiwen Xie*, Fanbiao Li, Weihua Gui. Data-driven-based adaptive fuzzy neural network control for the antimony flotation plant[J]. Journal of the Franklin Institute, 2019, 356(12): 5944-5960.

[9] Mingxi Ai, Yongfang Xie, Shiwen Xie*, Weihua Gui. Shape-weighted bubble size distribution based reagent predictive control for the antimony flotation process[J]. Chemometrics and Intelligent Laboratory Systems, 2019, 192: 103821.

[10] Mingxi Ai, Yongfang Xie*, Degang Xu, Weihua Gui, Chunhua Yang. Data-driven flotation reagent changing evaluation via union distribution analysis of bubble size and shape[J]. Canadian Journal of Chemical Engineering, 2018, 96: 2616-2626.

[11] Mingxi Ai, Peng Li, Jin Zhang*, Yongfang Xie, Zhaohui Tang. Representation-enhanced semi-supervised learning for flotation working condition recognition[C]. The 43rd Chinese Control Conference (CCC 2024), 2024.

[12] Mingxi Ai, Peng Li, Yongfang Xie*, Zhaohui Tang. Flotation feed grade estimation based on spatial-temporal correlation analysis of froth image features[C]. The 34th Chinese Process Control Conference (CPCC 2023), 2023.

[13] Mingxi Ai*, Yongfang Xie, Degang Xu. Reagent predictive control using joint froth image feature for antimony flotation process[C]. IFAC Papersonline, 2018, 51(21): 284-289.

[14] 艾明曦, 孔庆洁, 张进, 许庆, 李鹏, 谢永芳*, 唐朝晖. 基于浅层特征与深层特征融合的浮选工况识别[J/OL]. 控制理论与应用, 2025.（EI 网络首发）

[15] 艾明曦, 许庆, 张进, 孔庆洁, 李鹏, 谢永芳*, 唐朝晖. 基于局部特征增强的浮选过程改进半监督工况识别方法[J/OL]. 控制与决策, 2025.（EI 网络首发）

发明专利：

[1] 艾明曦,孔庆洁,张进,李鹏,谢永芳. 一种基于手工特征和深度学习特征混合学习的浮选过程工况识别方法. 专利号: ZL202410442153.5.

[2] 艾明曦,许庆,张进,李鹏,谢永芳. 知识与数据联合驱动的矿物浮选过程工况识别方法及装置. 申请号: CN202410912077.X.

[3] 艾明曦,李鹏,张进,谢永芳,唐朝晖. 一种矿物浮选精矿品位软测量方法、装置及相关设备.申请号: CN202311184776.9.

[4] 艾明曦,刘潇潇,高莲,李鹏,杨创艳,王瀚铖. 输电线路冰冻灾害检测方法、装置、电子设备及存储介质. 申请号: CN202411152112.9.