The recent advent of deep artificial neural networks has resulted in a dramatic increase in performance for object classification and detection.While pre-trained with everyday objects,we find that a state-of-the-art o...The recent advent of deep artificial neural networks has resulted in a dramatic increase in performance for object classification and detection.While pre-trained with everyday objects,we find that a state-of-the-art object detection architecture can very efficiently be fine-tuned to work on a variety of object detection tasks in a high-power laser laboratory.In this paper,three exemplary applications are presented.We show that the plasma waves in a laser±plasma accelerator can be detected and located on the optical shadowgrams.The plasma wavelength and plasma density are estimated accordingly.Furthermore,we present the detection of all the peaks in an electron energy spectrum of the accelerated electron beam,and the beam charge of each peak is estimated accordingly.Lastly,we demonstrate the detection of optical damage in a high-power laser system.The reliability of the object detector is demonstrated over1000 laser shots in each application.Our study shows that deep object detection networks are suitable to assist online and offline experimental analysis,even with small training sets.We believe that the presented methodology is adaptable yet robust,and we encourage further applications in Hz-level or kHz-level high-power laser facilities regarding the control and diagnostic tools,especially for those involving image data.展开更多
Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available.Early experimental and numerical research in this field was dominated by single-s...Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available.Early experimental and numerical research in this field was dominated by single-shot experiments with limited parameter exploration.However,recent technological improvements make it possible to gather data for hundreds or thousands of different settings in both experiments and simulations.This has sparked interest in using advanced techniques from mathematics,statistics and computer science to deal with,and benefit from,big data.At the same time,sophisticated modeling techniques also provide new ways for researchers to deal effectively with situation where still only sparse data are available.This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics and its important sub-fields of laser-plasma acceleration and inertial confinement fusion.展开更多
In this study,experimental wear losses under different loads and sliding distances of AISI 1020 steel surfaces coated with(wt.%)50FeCrC‐20FeW‐30FeB and 70FeCrC‐30FeB powder mixtures by plasma transfer arc welding w...In this study,experimental wear losses under different loads and sliding distances of AISI 1020 steel surfaces coated with(wt.%)50FeCrC‐20FeW‐30FeB and 70FeCrC‐30FeB powder mixtures by plasma transfer arc welding were determined.The dataset comprised 99 different wear amount measurements obtained experimentally in the laboratory.The linear regression(LR),support vector machine(SVM),and Gaussian process regression(GPR)algorithms are used for predicting wear quantities.A success rate of 0.93 was obtained from the LR algorithm and 0.96 from the SVM and GPR algorithms.展开更多
Discharge plasma parameter measurement is a key focus in low-temperature plasma research.Traditional diagnostics often require costly equipment,whereas electro-acoustic signals provide a rich,non-invasive,and less com...Discharge plasma parameter measurement is a key focus in low-temperature plasma research.Traditional diagnostics often require costly equipment,whereas electro-acoustic signals provide a rich,non-invasive,and less complex source of discharge information.This study harnesses machine learning to decode these signals.It establishes links between electro-acoustic signals and gas discharge parameters,such as power and distance,thus streamlining the prediction process.By building a spark discharge platform to collect electro-acoustic signals and implementing a series of acoustic signal processing techniques,the Mel-Frequency Cepstral Coefficients(MFCCs)of the acoustic signals are extracted to construct the predictors.Three machine learning models(Linear Regression,k-Nearest Neighbors,and Random Forest)are introduced and applied to the predictors to achieve real-time rapid diagnostic measurement of typical spark discharge power and discharge distance.All models display impressive performance in prediction precision and fitting abilities.Among them,the k-Nearest Neighbors model shows the best performance on discharge power prediction with the lowest mean square error(MSE=0.00571)and the highest R-squared value(R^(2)=0.93877).The experimental results show that the relationship between the electro-acoustic signal and the gas discharge power and distance can be effectively constructed based on the machine learning algorithm,which provides a new idea and basis for the online monitoring and real-time diagnosis of plasma parameters.展开更多
A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator.The model was constructed from variational convolutional neural networks,which mapped the resu...A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator.The model was constructed from variational convolutional neural networks,which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum.An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction.It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam.In addition,the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.展开更多
An accurate plasma current profile has irreplaceable value for the steady-state operation of the plasma.In this study,plasma current tomography based on Bayesian inference is applied to an HL-2A device and used to rec...An accurate plasma current profile has irreplaceable value for the steady-state operation of the plasma.In this study,plasma current tomography based on Bayesian inference is applied to an HL-2A device and used to reconstruct the plasma current profile.Two different Bayesian probability priors are tried,namely the Conditional Auto Regressive(CAR)prior and the Advanced Squared Exponential(ASE)kernel prior.Compared to the CAR prior,the ASE kernel prior adopts nonstationary hyperparameters and introduces the current profile of the reference discharge into the hyperparameters,which can make the shape of the current profile more flexible in space.The results indicate that the ASE prior couples more information,reduces the probability of unreasonable solutions,and achieves higher reconstruction accuracy.展开更多
This study investigates the dry reformation of methane(DRM)over Ni/Al_(2)O_(3)catalysts in a dielectric barrier discharge(DBD)non-thermal plasma reactor.A novel hybrid machine learning(ML)model is developed to optimiz...This study investigates the dry reformation of methane(DRM)over Ni/Al_(2)O_(3)catalysts in a dielectric barrier discharge(DBD)non-thermal plasma reactor.A novel hybrid machine learning(ML)model is developed to optimize the plasma-catalytic DRM reaction with limited experimental data.To address the non-linear and complex nature of the plasma-catalytic DRM process,the hybrid ML model integrates three well-established algorithms:regression trees,support vector regression,and artificial neural networks.A genetic algorithm(GA)is then used to optimize the hyperparameters of each algorithm within the hybrid ML model.The ML model achieved excellent agreement with the experimental data,demonstrating its efficacy in accurately predicting and optimizing the DRM process.The model was subsequently used to investigate the impact of various operating parameters on the plasma-catalytic DRM performance.We found that the optimal discharge power(20 W),CO_(2)/CH_(4)molar ratio(1.5),and Ni loading(7.8 wt%)resulted in the maximum energy yield at a total flow rate of∼51 mL/min.Furthermore,we investigated the relative significance of each operating parameter on the performance of the plasma-catalytic DRM process.The results show that the total flow rate had the greatest influence on the conversion,with a significance exceeding 35%for each output,while the Ni loading had the least impact on the overall reaction performance.This hybrid model demonstrates a remarkable ability to extract valuable insights from limited datasets,enabling the development and optimization of more efficient and selective plasma-catalytic chemical processes.展开更多
Wear tests are essential in the design of parts intended to work in environments that subject a part to high wear.Wear tests involve high cost and lengthy experiments,and require special test equipment.The use of mach...Wear tests are essential in the design of parts intended to work in environments that subject a part to high wear.Wear tests involve high cost and lengthy experiments,and require special test equipment.The use of machine learning algorithms for wear loss quantity predictions is a potentially effective means to eliminate the disadvantages of experimental methods such as cost,labor,and time.In this study,wear loss data of AISI 1020 steel coated by using a plasma transfer arc welding(PTAW)method with FeCrC,FeW,and FeB powders mixed in different ratios were obtained experimentally by some of the researchers in our group.The mechanical properties of the coating layers were detected by microhardness measurements and dry sliding wear tests.The wear tests were performed at three different loads(19.62,39.24,and 58.86 N)over a sliding distance of 900 m.In this study,models have been developed by using four different machine learning algorithms(an artificial neural network(ANN),extreme learning machine(ELM),kernel-based extreme learning machine(KELM),and weighted extreme learning machine(WELM))on the data set obtained from the wear test experiments.The R2 value was calculated as 0.9729 in the model designed with WELM,which obtained the best performance among the models evaluated.展开更多
Various types of plasma events emerge in specific parameter ranges and exhibit similar characteristics in diagnostic signals,which can be applied to identify these events.A semisupervised machine learning algorithm,th...Various types of plasma events emerge in specific parameter ranges and exhibit similar characteristics in diagnostic signals,which can be applied to identify these events.A semisupervised machine learning algorithm,the k-means clustering algorithm,is utilized to investigate and identify plasma events in the J-TEXT plasma.This method can cluster diverse plasma events with homogeneous features,and then these events can be identified if given few manually labeled examples based on physical understanding.A survey of clustered events reveals that the k-means algorithm can make plasma events(rotating tearing mode,sawtooth oscillations,and locked mode)gathering in Euclidean space composed of multi-dimensional diagnostic data,like soft x-ray emission intensity,edge toroidal rotation velocity,the Mirnov signal amplitude and so on.Based on the cluster analysis results,an approximate analytical model is proposed to rapidly identify plasma events in the J-TEXT plasma.The cluster analysis method is conducive to data markers of massive diagnostic data.展开更多
Manual monitoring and seam tracking through watching weld pool images in real-time, by naked eyes or by industrial TV, are experience-depended, subjective, labor intensive, and sometimes biased. So it is necessary to ...Manual monitoring and seam tracking through watching weld pool images in real-time, by naked eyes or by industrial TV, are experience-depended, subjective, labor intensive, and sometimes biased. So it is necessary to realize the automation of computer-aided seam tracking. A PAW (plasma arc welding) seam tracking system was developed, which senses the molten pool and the seam in one frame by a vision sensor, and then detects the seam deviation to adjust the work piece motion adaptively to the seam position sensed by vision sensor. A novel molten pool area image-processing algorithm based on machine vision was proposed. The algorithm processes each image at the speed of 20 frames/second in real-time to extract three feature variables to get the seam deviation. It is proved experimentally that the algorithm is very fast and effective. Issues related to the algorithm are also discussed.展开更多
A Langmuir probe plasma diagnostic system was developed to measure the plasma parameters in a PECVD vacuum coating machine. The plasma was a capacitively coupled plasma （CCP） driven by a radio-frequency （RF） power...A Langmuir probe plasma diagnostic system was developed to measure the plasma parameters in a PECVD vacuum coating machine. The plasma was a capacitively coupled plasma （CCP） driven by a radio-frequency （RF） power supply. To avoid the disturbance of radio-frequency field on the Langmuir probe measurement, a passive compensation method was applied. This method allowed the ＇dc＇ component to be passed and measured in the probe circuit. It was found that the electron temperature in the range from 2.7 eV to 6.4 eV decreased with the increase in RF power. The measured plasma density ranged from 8×10^16 m^-3 to 0.85×10^15 m^-3 and increased with the increase in RF power.展开更多
As JET is developing and testing operational scenarios for higher fusion performance,an increase in pulse disruptivity is being observed.On a deeper analysis,we find that several radiative phenomena play an active rol...As JET is developing and testing operational scenarios for higher fusion performance,an increase in pulse disruptivity is being observed.On a deeper analysis,we find that several radiative phenomena play an active role in determining the outcome of the pulse.The analysis is enabled by the use of real-time tomography based on the bolometer diagnostic.Even though plasma tomography is an inverse problem,we use machine learning to train a forward model that provides the radiation profile directly,based on a single matrix multiplication step.This model is used to investigate radiative phenomena including sawtooth crashes,ELMs and MARFE,and their relationship to the radiated power in different regions of interest.In particular,we use realtime tomography to monitor the core region,and to throw an alarm whenever core radiation exceeds a certain threshold.Our results suggest that this measure alone can anticipate a significant fraction of disruptions in the JET baseline scenario.展开更多
基金support by the operating resources of the Centre for Advanced Laser Applications(CALA)support from the Alexander von Humboldt Stiftung+1 种基金support from the BMBF under contract number 05K19WMBsupport from the German Research Agency,DFG Project No.453619281
文摘The recent advent of deep artificial neural networks has resulted in a dramatic increase in performance for object classification and detection.While pre-trained with everyday objects,we find that a state-of-the-art object detection architecture can very efficiently be fine-tuned to work on a variety of object detection tasks in a high-power laser laboratory.In this paper,three exemplary applications are presented.We show that the plasma waves in a laser±plasma accelerator can be detected and located on the optical shadowgrams.The plasma wavelength and plasma density are estimated accordingly.Furthermore,we present the detection of all the peaks in an electron energy spectrum of the accelerated electron beam,and the beam charge of each peak is estimated accordingly.Lastly,we demonstrate the detection of optical damage in a high-power laser system.The reliability of the object detector is demonstrated over1000 laser shots in each application.Our study shows that deep object detection networks are suitable to assist online and offline experimental analysis,even with small training sets.We believe that the presented methodology is adaptable yet robust,and we encourage further applications in Hz-level or kHz-level high-power laser facilities regarding the control and diagnostic tools,especially for those involving image data.
基金The authors acknowledge the use of GPT-3[288](text-davinci-003)in the copy-editing process of this manuscript.
文摘Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available.Early experimental and numerical research in this field was dominated by single-shot experiments with limited parameter exploration.However,recent technological improvements make it possible to gather data for hundreds or thousands of different settings in both experiments and simulations.This has sparked interest in using advanced techniques from mathematics,statistics and computer science to deal with,and benefit from,big data.At the same time,sophisticated modeling techniques also provide new ways for researchers to deal effectively with situation where still only sparse data are available.This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics and its important sub-fields of laser-plasma acceleration and inertial confinement fusion.
文摘In this study,experimental wear losses under different loads and sliding distances of AISI 1020 steel surfaces coated with(wt.%)50FeCrC‐20FeW‐30FeB and 70FeCrC‐30FeB powder mixtures by plasma transfer arc welding were determined.The dataset comprised 99 different wear amount measurements obtained experimentally in the laboratory.The linear regression(LR),support vector machine(SVM),and Gaussian process regression(GPR)algorithms are used for predicting wear quantities.A success rate of 0.93 was obtained from the LR algorithm and 0.96 from the SVM and GPR algorithms.
基金partially supported by National Natural Science Foundation of China(No.52377155)the State Key Laboratory of Reliability and Intelligence of Electrical Equipment(No.EERI-KF2021001)Hebei University of Technology。
文摘Discharge plasma parameter measurement is a key focus in low-temperature plasma research.Traditional diagnostics often require costly equipment,whereas electro-acoustic signals provide a rich,non-invasive,and less complex source of discharge information.This study harnesses machine learning to decode these signals.It establishes links between electro-acoustic signals and gas discharge parameters,such as power and distance,thus streamlining the prediction process.By building a spark discharge platform to collect electro-acoustic signals and implementing a series of acoustic signal processing techniques,the Mel-Frequency Cepstral Coefficients(MFCCs)of the acoustic signals are extracted to construct the predictors.Three machine learning models(Linear Regression,k-Nearest Neighbors,and Random Forest)are introduced and applied to the predictors to achieve real-time rapid diagnostic measurement of typical spark discharge power and discharge distance.All models display impressive performance in prediction precision and fitting abilities.Among them,the k-Nearest Neighbors model shows the best performance on discharge power prediction with the lowest mean square error(MSE=0.00571)and the highest R-squared value(R^(2)=0.93877).The experimental results show that the relationship between the electro-acoustic signal and the gas discharge power and distance can be effectively constructed based on the machine learning algorithm,which provides a new idea and basis for the online monitoring and real-time diagnosis of plasma parameters.
基金supported by UK STFC ST/V001639/1,UK EPSRC EP/V049577/1 and EP/V044397/1Horizon 2020 funding under European Research Council(ERC)Grant Agreement No.682399+1 种基金support from the Royal Society URF-R1221874support from US DOE grant DESC0016804
文摘A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator.The model was constructed from variational convolutional neural networks,which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum.An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction.It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam.In addition,the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.
基金supported by the National MCF Energy R&D Program of China (Nos. 2018 YFE0301105, 2022YFE03010002 and 2018YFE0302100)the National Key R&D Program of China (Nos. 2022YFE03070004 and 2022YFE03070000)National Natural Science Foundation of China (Nos. 12205195, 12075155 and 11975277)
文摘An accurate plasma current profile has irreplaceable value for the steady-state operation of the plasma.In this study,plasma current tomography based on Bayesian inference is applied to an HL-2A device and used to reconstruct the plasma current profile.Two different Bayesian probability priors are tried,namely the Conditional Auto Regressive(CAR)prior and the Advanced Squared Exponential(ASE)kernel prior.Compared to the CAR prior,the ASE kernel prior adopts nonstationary hyperparameters and introduces the current profile of the reference discharge into the hyperparameters,which can make the shape of the current profile more flexible in space.The results indicate that the ASE prior couples more information,reduces the probability of unreasonable solutions,and achieves higher reconstruction accuracy.
基金This project received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No. 813393the funding from the National Natural Science Foundation of China (No. 52177149)
文摘This study investigates the dry reformation of methane(DRM)over Ni/Al_(2)O_(3)catalysts in a dielectric barrier discharge(DBD)non-thermal plasma reactor.A novel hybrid machine learning(ML)model is developed to optimize the plasma-catalytic DRM reaction with limited experimental data.To address the non-linear and complex nature of the plasma-catalytic DRM process,the hybrid ML model integrates three well-established algorithms:regression trees,support vector regression,and artificial neural networks.A genetic algorithm(GA)is then used to optimize the hyperparameters of each algorithm within the hybrid ML model.The ML model achieved excellent agreement with the experimental data,demonstrating its efficacy in accurately predicting and optimizing the DRM process.The model was subsequently used to investigate the impact of various operating parameters on the plasma-catalytic DRM performance.We found that the optimal discharge power(20 W),CO_(2)/CH_(4)molar ratio(1.5),and Ni loading(7.8 wt%)resulted in the maximum energy yield at a total flow rate of∼51 mL/min.Furthermore,we investigated the relative significance of each operating parameter on the performance of the plasma-catalytic DRM process.The results show that the total flow rate had the greatest influence on the conversion,with a significance exceeding 35%for each output,while the Ni loading had the least impact on the overall reaction performance.This hybrid model demonstrates a remarkable ability to extract valuable insights from limited datasets,enabling the development and optimization of more efficient and selective plasma-catalytic chemical processes.
文摘Wear tests are essential in the design of parts intended to work in environments that subject a part to high wear.Wear tests involve high cost and lengthy experiments,and require special test equipment.The use of machine learning algorithms for wear loss quantity predictions is a potentially effective means to eliminate the disadvantages of experimental methods such as cost,labor,and time.In this study,wear loss data of AISI 1020 steel coated by using a plasma transfer arc welding(PTAW)method with FeCrC,FeW,and FeB powders mixed in different ratios were obtained experimentally by some of the researchers in our group.The mechanical properties of the coating layers were detected by microhardness measurements and dry sliding wear tests.The wear tests were performed at three different loads(19.62,39.24,and 58.86 N)over a sliding distance of 900 m.In this study,models have been developed by using four different machine learning algorithms(an artificial neural network(ANN),extreme learning machine(ELM),kernel-based extreme learning machine(KELM),and weighted extreme learning machine(WELM))on the data set obtained from the wear test experiments.The R2 value was calculated as 0.9729 in the model designed with WELM,which obtained the best performance among the models evaluated.
基金supported by the National Magnetic Confinement Fusion Science Program of China(Nos.2018YFE0301104 and 2018YFE0301100)National Natural Science Foundation of China(Nos.12075096 and 51821005)。
文摘Various types of plasma events emerge in specific parameter ranges and exhibit similar characteristics in diagnostic signals,which can be applied to identify these events.A semisupervised machine learning algorithm,the k-means clustering algorithm,is utilized to investigate and identify plasma events in the J-TEXT plasma.This method can cluster diverse plasma events with homogeneous features,and then these events can be identified if given few manually labeled examples based on physical understanding.A survey of clustered events reveals that the k-means algorithm can make plasma events(rotating tearing mode,sawtooth oscillations,and locked mode)gathering in Euclidean space composed of multi-dimensional diagnostic data,like soft x-ray emission intensity,edge toroidal rotation velocity,the Mirnov signal amplitude and so on.Based on the cluster analysis results,an approximate analytical model is proposed to rapidly identify plasma events in the J-TEXT plasma.The cluster analysis method is conducive to data markers of massive diagnostic data.
文摘Manual monitoring and seam tracking through watching weld pool images in real-time, by naked eyes or by industrial TV, are experience-depended, subjective, labor intensive, and sometimes biased. So it is necessary to realize the automation of computer-aided seam tracking. A PAW (plasma arc welding) seam tracking system was developed, which senses the molten pool and the seam in one frame by a vision sensor, and then detects the seam deviation to adjust the work piece motion adaptively to the seam position sensed by vision sensor. A novel molten pool area image-processing algorithm based on machine vision was proposed. The algorithm processes each image at the speed of 20 frames/second in real-time to extract three feature variables to get the seam deviation. It is proved experimentally that the algorithm is very fast and effective. Issues related to the algorithm are also discussed.
基金the Enterprise Postdoctoral Research Fund of Liaoning Province(BSH:2004921032)National Natural Science Foundation of China(No.60774093)
文摘A Langmuir probe plasma diagnostic system was developed to measure the plasma parameters in a PECVD vacuum coating machine. The plasma was a capacitively coupled plasma （CCP） driven by a radio-frequency （RF） power supply. To avoid the disturbance of radio-frequency field on the Langmuir probe measurement, a passive compensation method was applied. This method allowed the ＇dc＇ component to be passed and measured in the probe circuit. It was found that the electron temperature in the range from 2.7 eV to 6.4 eV decreased with the increase in RF power. The measured plasma density ranged from 8×10^16 m^-3 to 0.85×10^15 m^-3 and increased with the increase in RF power.
基金This work has been carried out within the framework of the EUROfusion Consortium and has received funding from the Euratom research and training programme 2014-2018 and 2019-2020 under grant agreement No.633053.The views and opinions expressed herein do not necessarily reflect those of the European Commission.IPFN(Instituto de Plasmas e Fusão Nuclear)received financial support from FCT(Fundação para a Ciência e a Tecnologia)through projects UIDB/50010/2020 and UIDP/50010/2020.The authors are thankful for the granted use of computational resources provided by CCFE/UKAEA at Culham,UK.
文摘As JET is developing and testing operational scenarios for higher fusion performance,an increase in pulse disruptivity is being observed.On a deeper analysis,we find that several radiative phenomena play an active role in determining the outcome of the pulse.The analysis is enabled by the use of real-time tomography based on the bolometer diagnostic.Even though plasma tomography is an inverse problem,we use machine learning to train a forward model that provides the radiation profile directly,based on a single matrix multiplication step.This model is used to investigate radiative phenomena including sawtooth crashes,ELMs and MARFE,and their relationship to the radiated power in different regions of interest.In particular,we use realtime tomography to monitor the core region,and to throw an alarm whenever core radiation exceeds a certain threshold.Our results suggest that this measure alone can anticipate a significant fraction of disruptions in the JET baseline scenario.
