**Jun. 16 to Jun. 20, 2024**: I attended The 51st IEEE International Conference on Plasma Science (ICOPS) held in Beijing where I organized a special session. In this session, I invited 9 speakers from USA, UK, Japan, and China. In the ICOPS, I also gave an invited talk entitled*Scientific Machine Learning and its Applications to Plasma Science*.*Physics-informed frameworks for low-temperature plasma simulation***May 10 to May 12, 2024**: I attended The 12th National Symposium on Atmospheric-Pressure Plasma and Its Application Technology held in Maanshan, Anhui Province, and gave an invited talk entitled.*Exploration of AI-driven acceleration technology for plasma simulation***Apr. 04, 2024**: We published a paper on visual classification and detection of power inspection images based on federated learning. In this work, a federated learning (FL) based method for processing power inspection images, which allows different data owners to cooperatively train visual classification and detection models without sharing their local images. To improve the training efficiency, we further propose aby adding a momentum term during the aggregation of model weights. We demonstrate the proposed method in three real-world power inspection image datasets for visual classification, object detection and defect detection tasks respectively*Federated Round-level Momentum (FedRM) method*

This paper is now available on IEEE Transactions on Industry Applications.**Dec. 12, 2023**: I visited Institute of Applied Physics and Computational Mathematics, and gave an invited talk entitled.*Application and prospect of artificial intelligence in numerical simulation of low-temperature plasma***Nov. 12 to Nov. 17, 2023**: I attended The 7th Asia-Pacific Conference on Plasma Physics (AAPPS-DPP 2023) held in Nagoya, Japan where I hosted a session asand gave an invited talk entitled*Session Chair*.*Application prospect of AI-driven differentiable plasma modeling***Oct. 27, 2023**: We published a paper on how to design physics-informed neural networks (PINNs) by neural architecture search (NAS). In this work, we proposedto automatically search the optimum neural architecture for solving certain PDEs. We verify the ability of*NAS-PINN*by several numerical experiments including Poisson, Burgers, and Advection equations.*NAS-PINN*

This paper is now available on Journal of Computational Physics.**Oct. 27 to Oct. 29, 2023**: I attended The 5th International Symposium on Plasma and Energy Conversion (iSPEC 2023) held in Nanjing where I hosted a session asand gave an invited talk entitled*Session Chair*.*Radiation transport characteristics in arc plasmas of eco-friendly gases***Jul. 16 to Jul. 28, 2023**: I attended The 2nd Summer Training Course on Data Science for Teachers majoring in Statistics, Data Science, and Big Data Technology in Higher Education Institutions held in Baoshan, Yunnan Province. This course was organized by Tianyuan Mathematical Center in Northwest China. At the graduation ceremony, I spoke as a teacher representative.**May 26 to May 28, 2023**: I attended 2023 4th International Symposium on Insulation and Discharge Computation for Power Equipment (IDCOMPU 2023) held in Wuhan where I gave an invited talk entitled.*Particle condensation in 2T non-LTE plasmas of SF6 replacements***May 12 to May 14, 2023**: I attended 2023 IEEE 6th International Electrical and Energy Conference (CIEEC 2023) held in Hefei where I gave an invited talk entitled.*Design physics-informed neural networks by neural architecture search***Feb. 23, 2023**: I visited Nanjing Center for Applied Mathematics, and gave an invited talk entitled.*Numerical simulation of low-temperature plasma driven by artificial intelligence: problems and challenges***Feb. 03, 2023**: We published a paper on how to accelerate plasma simulation based on physics-informed neural networks (PINNs). In this work we proposed a meta-learning method, namely Meta-PINN, to reduce the training time of PINN-based 1D arc simulation. The results indicate that Meta-PINN is an effective method for accelerating the PINN-based 1D arc simulation. This is an invited paper by the special issue of Journal of Physics D: Applied Physics on*Data Driven Plasma Science*

This paper is now available on Journal of Physics D: Applied Physics.**Dec. 22 to Dec. 29, 2022**: I attended Frontiers in Mathematical Science held in Tsinghua Sanya International Mathematics Forum (TSIMF) and hosted by the world-famous mathematician Prof. Shing-Tung Yau. In this conference, I was invited to give a talk entitledin a session of Applied Mathematics.*Physics-Informed Low-Temperature Plasma Simulation and Its Acceleration Technology***Oct. 12, 2022**: I attended**Online Seminar on Calculation, Verification and Application of Electron-impact Cross Sections**hosted by the Key Laboratory of Plasma Dynamics. In this conference, I was invited to give a talk entitled.*Calculation and Basic Database Construction of Molecular Ionization Cross Sections***Aug. 26 to Aug. 28, 2022**: I attended**2022 National Conference on High Voltage and Discharge Plasmas**held in Hefei where I gave a presentation on the meta-learning-based plasma simulation. Because of this presentation, I was honored an.*Outstanding Oral Report Award***Aug. 16, 2022**: We published a paper on low-temperature plasma simulation based on physics-informed neural networks (PINNs). In this work we proposed two general AI-driven frameworks for low-temperature plasma simulation: Coefficient-Subnet Physics-Informed Neural Network (CS-PINN) and Runge–Kutta Physics-Informed Neural Network (RK-PINN). Based on these two frameworks, we demonstrated preliminary applications in four cases covering plasma kinetic and fluid modeling. The Editors felt that this article is noteworthy, and have chosen it to be promoted as a.*Featured Article*

This paper is now available on Physics of Fluids.**Jul. 31 to Aug. 05, 2022**: I attended The 9th International Congress of Chinese Mathematicians (ICCM2022). In this conference, I was invited by the round table forum with theme of**Mathematics + Industry**to give a talk entitled. Prof. Shing-Tung Yau, the world-famous mathematician, gave a opening speaking in this thematic forum.*Application of AI Technology in Low-Temperature Plasma Simulation***May 27 to May 29, 2022**: I attended**2022 IEEE 5th International Electrical and Energy Conference (CIEEC)**. In this conference, I hosted a session of**Plasma Science Technology and Applications**, and was invited to give a talk entitled.*Accelerate Plasma Simulation by Combining Deep Neural Networks and Runge-Kutta Formalism***May 11, 2022**: We published a paper in Chinese on power tower anomaly detection from Unmanned Aerial Vehicle (UAV) inspection images based on improved generative adversarial network (GAN). In this work we proposed Squeeze-and-Excitation improved fast unsupervised anomaly detection with generative adversarial network (SE-f-AnoGAN) for anomaly detection from UAV power tower inspection images. The experimental results show that the accuracy rate of overall samples is 95.74% and the recall rates of positive and negative samples reach 96.05% and 95.36% respectively.

This paper is now available on Transactions of China Electrotechnical Society.**Feb. 07, 2022**: I attended again Physics informed AI in Plasma Science (PiAI) Seminar hosted by Prof. Satoshi Hamaguchi in Osaka University. In this seminar, I was invited to give an online talk entitled.*Runge-Kutta Physics Informed Neural Network (RK-PINN) for solving plasma PDEs with transient terms***Aug. 04, 2021**: We published a paper on the database of electron-impact ionization cross sections. This is an open database with tabular fitting parameters and an online web system. Currently there are 88 species composed of H, C, N, O, and F in this database. The same methods and basis set are used to ensure consistent ionization cross sections, which could provide plasma community self-consistent ionization cross sections in plasma modeling. All three reviewers highly rated this work and database, saying that “This database is**instrumental and useful to researchers**”, “This database would be**useful for many applications, including plasma modeling**”, and “The fitting parameters can help**speed up the computation of ionization cross section within a plasma physics simulation**.“.

This paper is now available on Physics of Plasmas.**May. 10, 2021**: We published a paper on the numerical study of graphite production in two-temperature non-LTE plasmas of C4F7N and C5F10O mixed with CO2, N2, and O2. This is part of the serial works on eco-friendly SF6 replacements.**The novelty of this work is that we investigate the departure of thermodynamic equilibrium and the corresponding effects on the graphite production in the plasmas of C4F7N, C5F10O, and their mixtures with CO2, N2, and O2.**The results show that neglecting the nonequilibrium effect can lead to a very inaccurate description of graphite condensation in the above plasmas.

This paper is now available on Plasma Processes and Polymers.**Feb. 22, 2021**: I attended Physics informed AI in Plasma Science (PiAI) Seminar hosted by Prof. Satoshi Hamaguchi in Osaka University. In this seminar, I was invited to give an online talk entitled.*A Dual Neural Network Framework for Plasma Simulation***Jul. 30, 2020**: We published a paper on deep learning for thermal plasma simulation. In this paper we propose a deep learning method for solving the partial differential equations in thermal plasma models by constructing a deep feed-forward neural network to surrogate the solution of the model.**This could bring us a new and prospective numerical tool for plasma modeling.**The innovation of this work is highly rated by the reviewers.

This paper is now available on Computer Physics Communications.**Feb. 06, 2020**: We published two serial papers on compositions of two-temperature (2T) plasmas. In these two papers we compare two kinds of methods for calculating 2T plasma composition: the mass action law methods and extremum searching methods. The former methods include the two described by Potapov and van de Sanden et al mass action laws, respectively. The latter methods include those of searching minimum Gibbs free energy and maximum entropy of a plasma system respectively. The entropy maximization method is first reported in this work and has the same power as the commonly used Gibbs free energy minimization method.**We demonstrate both mathematically and numerically that the method of 2T Gibbs free minimization is completely the same as the 2T Potapov mass action law, and the method of 2T entropy maximization is exactly consistent with the 2T van de Sanden et al mass action law if an assumption is used.**We also extend these methods to the calculation of 2T multi-phase plasma composition.

The part I and part II of the serial papers are now available on Journal of Physics D: Applied Physics and Journal of Physics D: Applied Physics respectively.**Nov. 15, 2019**: We published a paper on the electron-impact ionization cross sections of new SF_{6}replacements, including C_{2}F_{4}H_{2}(R134), C_{3}F_{4}H_{2}(HFO1234ze), C_{4}F_{8}, C_{4}F_{7}N, C_{5}F_{10}O, and C_{6}F_{12}O. In this work we propose a new method of combining the Deutsch-Märk (DM) formalism at low electron energy and the Binary-Encounter-Bethe (BEB) formalism at high electron energy by using a dual sigmoid function. The Editors felt that this article is noteworthy, and have chosen it to be promoted as an.*Editor’s Pick*

This paper is now available on Journal of Applied Physics.**Oct. 15, 2019**: We published a paper on an improved method for fast evaluating arc quenching performance of a gas based on 1D arc decaying model. Compared to the previous method, the present method is improved mainly in the three aspects: the thermal recovery stage is featured by the average radial temperature instead of the axial temperature; the criterion of dividing the dielectric recovery stage into the pre- and postdielectric recovery stages is validated by the average electron number density instead of choosing arbitrarily; and the postdielectric recovery stage is characterized by the critical electric field strength E_{cr}instead of the reduced critical electric field strength (E/N)_{cr}.

This paper is now available on Physics of Plasmas.**Sep. 25, 2019**: We published a paper on the calculation of plasma properties and evaluation of arc decaying characteristics for new eco-friendly gas C_{4}F_{7}N mixed with N_{2}and CO_{2}. The plasma properties include compositions, thermodynamic properties, transport coefficients, and net emission coefficients. The arc decaying characteristics were determined based on the 1-D arc decaying model. The results could be helpful to the selection of SF_{6}new eco-friendly replacements as arc quenching medium.

This paper is now available on Plasma Chemistry and Plasma Processing.**Aug. 25 to Aug. 28, 2019**: I attended**19th National Conference on Plasma Science and Technology**held in Dalian where I gave a presentation on the calculation of multi-phase composition of 2T plasmas.**Aug. 21 to Aug. 23, 2019**: I attended**2019 Annual Academic Conference of High Voltage Technical Committee of Chinese Society for Electrical Engineering (CSEE)**held in Shenyang where I gave a presentation on the fast evaluation of arc quenching ability for a gas based on 1-D arc decaying model. During this conference, I was honored a.*Excellent Paper Award***Aug. 21, 2019**: I was invited by the**China Electrotechnical Society**to give a report in the youth salon held in Beijing. The topic of the report is the application of artifical intelligence to predict molecular ionization cross sections.**Jul. 28 to Jul. 31, 2019**: I attended**2019 1st International Symposium on Insulation and Discharge Computation for Power Equipment**held in Xi’an where I gave a presentation on the machine learning based model for predicting molecular ionization cross sections.**May 09, 2019**: We published a paper on fast prediction of electron-impact ionization cross sections of large molecules via machine learning. In this work we propose a machine learning based method to construct a model for predicting Q_{ion}of large molecules without the high-cost ab initio calculation. The reviewers highly rated this work as a very interesting idea and very innovative method.

This paper is now available on Journal of Applied Physics.**Apr. 03, 2019**: We published a paper on evaluation of arc quenching ability for a gas by combining 1-D hydrokinetic modeling and Boltzmann equation analysis. This is a new, time-saving and easy used method for evaluating arc quenching performance. The work was cooperated with Prof. Yann Cressault and Prof. Philippe Teulet from Laboratoire Plasma et Conversion d’Energie (LAPLACE) in France.

This paper is now available on IEEE Transactions on Plasma Science.**Dec. 03, 2018**: I was honoredby*Excellent Peer Reviewer***Journal of Global Energy Interconnection**.**Nov. 25 to Nov. 28, 2018**: I attended**19th Asian Conference on Electrical Discharge**held in Xianyang where I gave a presentation on the calculation of electron-impact ionization cross sections of molecules. Because of this presentation, I was honored a.*Outstanding Oral Report Award***Oct. 19, 2018**: We published a paper on the comparative study of molecular orbital (MO) composition and its effect on electron-impact ionization cross sections. We found that natural atomic orbital (NAO) method is the best choice for the MO composition in calculating the ionization cross section of a molecule

This paper is now available on Physics of Plasmas.**Oct. 12 to Oct. 14, 2018**: I attended**2018 National Conference on High Voltage and Discharge Plasmas**held in Nanjing where I gave a presentation on the electron-impact ionization cross sections of new SF6 replacements. Because of this presentation, I was honored a.*Outstanding Oral Report Award***Sep. 14, 2018**: We published a paper on the calculation of electron-impact ionization cross sections of perﬂuoroketone (PFK) molecules CxF2xO (x = 1-5) based on Binary-Encounter-Bethe (BEB) and Deutsch-Märk (DM) methods. The work was highly acclaimed by the reviewers: “… This is a nice paper on using two different methods, and improving the straightforward implementations by using improved wavefunctions along the way, to calculate electron-impact ionization cross sections for very complex molecules. … I am also impressed with the overall presentation. … The research reported in the manuscript is interesting and useful …”.

This paper is now available on Plasma Sources Science and Technology.**Aug. 24, 2018**: We published a paper on the comparison of the dielectric breakdown properties for different carbon-fluoride insulating gases i.e. CF_{3}I, C_{2}F_{6}, C_{3}F_{8}, and c-C_{4}F_{8}mixed with CO_{2}, N_{2}, and CF_{4}

This paper is now available on AIP Advances.**Mar. 2, 2018**: We published a paper on thermophysical and radiation properties of C_{4}F_{8}-CO_{2}mixtures which are considered as potential SF_{6}replacement. The work was cooperated with Prof. Yann Cressault and Prof. Philippe Teulet from Laboratoire Plasma et Conversion d’Energie (LAPLACE) in France.

This paper is now available on Physics of Plasmas.**Nov. 10 to Nov. 12, 2017**: I attended**2017 China Electrotechnical Society Academic Anuual Conference**held in Changsha where I gave a presentation on net emission coefficients (NEC) of SF_{6}-Cu arc plasma. The paper I submitted to the conference was selected by the committee to be published on Transactions of China Electrotechnical Society.**Jun. 27, 2017**: I joined Southeast University as a lecturer (assistant professor).