In this work,we study the impacts of the isospin-independent momentum-dependent interaction(MDI)and near-threshold NN→NΔcross sections(σ_(NN→NΔ))on the nucleonic flow and pion production observables in the ultra-...In this work,we study the impacts of the isospin-independent momentum-dependent interaction(MDI)and near-threshold NN→NΔcross sections(σ_(NN→NΔ))on the nucleonic flow and pion production observables in the ultra-relativistic quantum molecular dynamics(UrQMD)model.With the updated isospin-independent MDI and the near-threshold NN→NΔcross sections in the Ur QMD model,17 observables,which are the directed flow(v_(1))and elliptic flow(v_(2))of neutrons,protons,Hydrogen(H),and charged particles as a function of transverse momentum(p_t∕A)or normalized rapidity(y^(lab)_0),and the observables constructed from them,the charged pion multiplicity(M(π))and its ratio(M(π^(-))∕M(π^(+))),can be simultaneously described at certain forms of symmetry energy.The refinement of the UrQMD model provides a solid foundation for further understanding the effects of the missed physics,such as the threshold effect,the pion potential,and the momentum-dependent symmetry potential.Circumstantial constraints on the symmetry energy at the flow characteristic density 1.2±0.6ρ_(0)and the pion characteristic density 1.5±0.5ρ_(0)were obtained with the current version of UrQMD,and the corresponding symmetry energies were S(1.2ρ_(0))=34±4 MeV and S(1.5ρ_(0))=36±8 MeV,respectively.Furthermore,the discrepancies between the data and the calculated results of v_(2)^(n)and v_(2)^(9)at high p_(t)(rapidity)imply that the roles of the missing ingredients,such as the threshold effect,the pion potential,and the momentum-dependent symmetry potential,should be investigated by differential observables,such as the momentum and rapidity distributions of the nucleonic and pionic probes over a wide beam energy range.展开更多
Prompt radiation emitted during accelerator operation poses a significant health risk,necessitating a thorough search and securing of hazardous areas prior to initiation.Currently,manual sweep methods are employed.How...Prompt radiation emitted during accelerator operation poses a significant health risk,necessitating a thorough search and securing of hazardous areas prior to initiation.Currently,manual sweep methods are employed.However,the limitations of manual sweeps have become increasingly evident with the implementation of large-scale accelerators.By leveraging advancements in machine vision technology,the automatic identification of stranded personnel in controlled areas through camera imagery presents a viable solution for efficient search and security.Given the criticality of personal safety for stranded individuals,search and security processes must be sufficiently reliable.To ensure comprehensive coverage,180°camera groups were strategically positioned on both sides of the accelerator tunnel to eliminate blind spots within the monitoring range.The YOLOV8 network model was modified to enable the detection of small targets,such as hands and feet,as well as larger targets formed by individuals near the cameras.Furthermore,the system incorporates a pedestrian recognition model that detects human body parts,and an information fusion strategy is used to integrate the detected head,hands,and feet with the identified pedestrians as a cohesive unit.This strategy enhanced the capability of the model to identify pedestrians obstructed by equipment,resulting in a notable improvement in the recall rate.Specifically,recall rates of 0.915 and 0.82were obtained for Datasets 1 and 2,respectively.Although there was a slight decrease in accuracy,it aligned with the intended purpose of the search-and-secure software design.Experimental tests conducted within an accelerator tunnel demonstrated the effectiveness of this approach in achieving reliable recognition outcomes.展开更多
The superconducting magnet system of a fusion reactor plays a vital role in plasma confinement,a process that can be dis-rupted by various operational factors.A critical parameter for evaluating the temperature margin...The superconducting magnet system of a fusion reactor plays a vital role in plasma confinement,a process that can be dis-rupted by various operational factors.A critical parameter for evaluating the temperature margin of superconducting magnets during normal operation is the nuclear heating caused by D-T neutrons.This study investigates the impact of nuclear heat-ing on a superconducting magnet system by employing an improved analysis method that combines neutronics and thermal hydraulics.In the magnet system,toroidal field(TF)magnets are positioned closest to the plasma and bear the highest nuclear-heat load,making them prime candidates for evaluating the influence of nuclear heating on stability.To enhance the modeling accuracy and facilitate design modifications,a parametric TF model that incorporates heterogeneity is established to expedite the optimization design process and enhance the accuracy of the computations.A comparative analysis with a homogeneous TF model reveals that the heterogeneous model improves accuracy by over 12%.Considering factors such as heat load,magnetic-field strength,and cooling conditions,the cooling circuit facing the most severe conditions is selected to calculate the temperature of the superconductor.This selection streamlines the workload associated with thermal-hydraulic analysis.This approach enables a more efficient and precise evaluation of the temperature margin of TF magnets.Moreover,it offers insights that can guide the optimization of both the structure and cooling strategy of superconducting magnet systems.展开更多
The sensitivity of the dark photon search through invisible decay final states in low-background experiments relies sig-nificantly on the neutron and muon veto efficiencies,which depend on the amount of material used ...The sensitivity of the dark photon search through invisible decay final states in low-background experiments relies sig-nificantly on the neutron and muon veto efficiencies,which depend on the amount of material used and the design of the detector geometry.This paper presents the optimized design of the hadronic calorimeter(HCAL)used in the DarkSHINE experiment,which is studied using a GEANT4-based simulation framework.The geometry is optimized by comparing a traditional design with uniform absorbers to one that uses different thicknesses at different locations on the detector,which enhances the efficiency of vetoing low-energy neutrons at the sub-GeV level.The overall size and total amount of material used in the HCAL are optimized to be lower,owing to the load and budget requirements,whereas the overall performance is studied to satisfy the physical objectives.展开更多
The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using...The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using the complex momentum representation method applied to deformation and continuum coupling.By examining the evolution of the weakly bound and resonant levels near the Fermi surface,s–d orbital reversals and certain prolate deformations were observed.In addition,by analyzing the evolution of the occupation probabilities and density distributions occupied by valence neutrons,we found that the ground state of15B did not exhibit a halo and the ground states of17B and19B exhibited halos at 0.6≤β2≤0.7 and0.3≤β2≤0.7,respectively.The low-l components in the valence levels that are weakly bound or embedded in the continuous spectrum lead to halo formation.展开更多
Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate wh...Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate when the optimization objectives for an accelerator are equal to or greater than four. Recently, many-objective evolutionary algorithms(MaOEAs)that can solve problems with four or more optimization objectives have received extensive attention. In this study, two diffraction-limited storage ring(DLSR) lattices of the Extremely Brilliant Source(ESRF-EBS) type with different energies were designed and optimized using three MaOEAs and a widely used MOEA. The initial population was found to have a significant impact on the performance of the algorithms and was carefully studied. The performances of the four algorithms were compared, and the results demonstrated that the grid-based evolutionary algorithm(GrEA) had the best performance.Ma OEAs were applied in many-objective optimization of DLSR lattices for the first time, and lattices with natural emittances of 116 and 23 pm·rad were obtained at energies of 2 and 6 GeV, respectively, both with reasonable dynamic aperture and local momentum aperture(LMA). This work provides a valuable reference for future many-objective optimization of DLSRs.展开更多
Scaling analysis is widely used to design scaled-down experimental facilities through which the prototype phenomena can be effectively evaluated.As a new method,dynamic system scaling(DSS)must be verified as a rationa...Scaling analysis is widely used to design scaled-down experimental facilities through which the prototype phenomena can be effectively evaluated.As a new method,dynamic system scaling(DSS)must be verified as a rational and applicable method.A DSS method based on dilation transformation was evaluated using single-phase natural circulation in a simple rectangular loop.The scaled-down cases were constructed based on two parameters—length ratio and dilation number—and the corresponding transient processes were simulated using the Relap5 computational code.The results show that this DSS method can simulate the dynamic flow characteristics of scaled-down cases.The transient deviation of the temperature difference and mass flow rate of the scaled cases decrease with increases in the length ratio and dilation number.The distortion of the transient temperature difference is smaller than that of the mass flow;however,the overall deviation is within a reasonable range.展开更多
The neutron supermirror is an important neutron optical device that can significantly improve the efficiency of neutron transport in neutron guides and has been widely used in research neutron sources.Three types of a...The neutron supermirror is an important neutron optical device that can significantly improve the efficiency of neutron transport in neutron guides and has been widely used in research neutron sources.Three types of algorithms,including approximately ten algorithms,have been developed for designing high-efficiency supermirror structures.In addition to its applications in neutron guides,in recent years,the use of neutron supermirrors in neutronfocusing mirrors has been proposed to advance the development of neutron scattering and neutron imaging instruments,especially those at compact neutron sources.In this new application scenario,the performance of supermirrors strongly affects the instrument performance;therefore,a careful evaluation of the design algorithms is needed.In this study,we examine two issues:the effect of nonuniform film thickness distribution on a curved substrate and the effect of the specific neutron intensity distribution on the performance of neutron supermirrors designed using existing algorithms.The effect of film thickness nonuniformity is found to be relatively insignificant,whereas the effect of the neutron intensity distribution over Q(where Q is the magnitude of the scattering vector of incident neutrons)is considerable.Selection diagrams that show the best design algorithm under different conditions are obtained from these results.When the intensity distribution is not considered,empirical algorithms can obtain the highest average reflectivity,whereas discrete algorithms perform best when the intensity distribution is taken into account.The reasons for the differences in performance between algorithms are also discussed.These findings provide a reference for selecting design algorithms for supermirrors for use in neutron optical devices with unique geometries and can be very helpful for improving the performance of focusing supermirror-based instruments.展开更多
The compact spectrometer for heavy ion experiment(CSHINE)is under construction for the study of isospin chronology via the Hanbury Brown–Twiss(HBT)particle correlation function and the nuclear equation of state of as...The compact spectrometer for heavy ion experiment(CSHINE)is under construction for the study of isospin chronology via the Hanbury Brown–Twiss(HBT)particle correlation function and the nuclear equation of state of asymmetrical nuclear matter.The CSHINE consists of silicon strip detector(SSD)telescopes and large-area parallel-plate avalanche counters,which measure the light charged particles and fission fragments,respectively.In phase I,two SSD telescopes were used to observe 30 MeV/u 40Ar?197Au reactions.The results presented here demonstrate that hydrogen and helium were observed with high isotopic resolution,and the HBT correlation functions of light charged particles could be constructed from the obtained data.展开更多
This paper reports on the design,fabrication,RF measurement,and high-power test of a prototype accelerator—such as 11.424 GHz with 12 cells—and a traveling wave of two halves.It was found that the unloaded gradient ...This paper reports on the design,fabrication,RF measurement,and high-power test of a prototype accelerator—such as 11.424 GHz with 12 cells—and a traveling wave of two halves.It was found that the unloaded gradient reached 103 MV/m during the high-power test and the measured breakdown rate,after 3.17×10^(7) pulses,was 1.62×10^(-4)/pulse/m at 94 MV/m and a 90 ns pulse length.We thus concluded that the high-gradient two-half linear accelerator is cost-effective,especially in high-frequency RF linear acceleration.Finally,we suggest that silverbased alloy brazing can further reduce costs.展开更多
We irradiated pea seeds with neutrons from a ^(252)Cf source and studied the radiation dose effects on various morphological development parameters during the growth of M_(1) generation peas.We found that in the dose ...We irradiated pea seeds with neutrons from a ^(252)Cf source and studied the radiation dose effects on various morphological development parameters during the growth of M_(1) generation peas.We found that in the dose range of 0.51-9.27 Gy,with the increase in neutron-absorbed dose,the morphological development parameters of M_(1) generation peas at the initial seedling stage showed an obvious trend with three fluctuations.With the development of pea,this trend gradually weakened.Further analysis and verification showed that the main trend in the M_(1) generation of pea seeds was an inhibitory effect induced by neutron irradiation and there was a good linear correlation between the inhibitory effect and neutron absorption dose We successfully demonstrated the background removal of mutant plants and defined morphological developmen parameters for peas that match the overall development of plants.Our results will positively impact neutron mutation breeding and automatic agriculture.展开更多
Background:The masses of-2500 nuclei have been measured experimentally;however,>7000 isotopes are predicted to exist in the nuclear landscape from H(Z=1)to Og(Z=118)based on various theoretical calculations.Explori...Background:The masses of-2500 nuclei have been measured experimentally;however,>7000 isotopes are predicted to exist in the nuclear landscape from H(Z=1)to Og(Z=118)based on various theoretical calculations.Exploring the mass of the remaining isotopes is a popular topic in nuclear physics.Machine learning has served as a powerful tool for learning complex representations of big data in many fields.Purpose:We use Light Gradient Boosting Machine(LightGBM),which is a highly efficient machine learning algorithm,to predict the masses of unknown nuclei and to explore the nuclear landscape on the neutron-rich side from learning the measured nuclear masses.Methods:Several characteristic quantities(e.g.,mass number and proton number)are fed into the LightGBM algorithm to mimic the patterns of the residual δ(Z,A)between the experimental binding energy and the theoret-ical one given by the liquid-drop model(LDM),Duflo–Zucker(DZ,also dubbed DZ28)mass model,finite-range droplet model(FRDM,also dubbed FRDM2012),as well as the Weizsacker–Skyrme(WS4)model to refine these mass models.Results:By using the experimental data of 80%of known nuclei as the training dataset,the root mean square devia-tions(RMSDs)between the predicted and the experimental binding energy of the remaining 20%are approximately 0.234±0.022,0.213±0.018,0.170±0.011,and 0.222±0.016 MeV for the LightGBM-refined LDM,DZ model,WS4 model,and FRDM,respectively.These values are approximately 90%,65%,40%,and 60%smaller than those of the corresponding origin mass models.The RMSD for 66 newly measured nuclei that appeared in AME2020 was also significantly improved.The one-neutron and two-neutron separation energies predicted by these refined models are consistent with several theoretical predictions based on various physical models.In addition,the two-neutron separation energies of several newly measured nuclei(e.g.,some isotopes of Ca,Ti,Pm,and Sm)pre-dicted with LightGBM-refined mass models are also in good agreement with the latest experimental data.Conclusions:LightGBM can be used to refine theoretical nuclear mass models and predict the binding energy of unknown nuclei.Moreover,the correlation between the input characteristic quantities and the output can be inter-preted by SHapley additive exPlanations(a popular explainable artificial intelligence tool),which may provide new insights for developing theoretical nuclear mass models.展开更多
The first experimental investigation of the tungsten behavior in ELMy H-mode plasmas with co-/counter neutral beam injection(NBI)and unfavor-able/favorable B t was performed on EAST.Tungsten was found to accumulate ea...The first experimental investigation of the tungsten behavior in ELMy H-mode plasmas with co-/counter neutral beam injection(NBI)and unfavor-able/favorable B t was performed on EAST.Tungsten was found to accumulate easily in ELMy H-mode plasma with co-NBI heating and unfavorable B t.Thus,in this case the tungsten concentration can exceed 10^(-4),resulting in degradation of the plasma confinement and periodic H–L transitions.To reduce the tungsten concentration in steady-state type-I ELMy H-mode operation,counter-NBI is applied to modify the density and temperature and brake the plasma toroidal rotation.The applied counter-NBI decreases the PHZ+E_(r) inward pinch velocity and rever-ses the direction of neoclassical inward convection,thus decreasing the tungsten concentration from-7×10^(-5) to-2×10^(-5) in type-I ELMy H-mode plasma with favorable B_(t).A comparison of the effects of different B_(t) directions on the tungsten behavior also shows that favor-able B_(t) is beneficial for reducing the tungsten concentration in the core plasma.These results imply that counter-NBI with favorable B_(t) can effectively prevent tungsten accu-mulation and expand the operating window for exploring steady-state type-I ELMy H-mode operation of EAST.展开更多
Neutron and gamma ray pulse signal discrimination technology is an essential part of many modern scientific fields,such as biology,geology,radiation imaging,and nuclear medicine.Neutrons are always accompanied by gamm...Neutron and gamma ray pulse signal discrimination technology is an essential part of many modern scientific fields,such as biology,geology,radiation imaging,and nuclear medicine.Neutrons are always accompanied by gamma rays due to their unique penetration characteristic;thus,the development of n-γdiscrimination methods is especially crucial.In the present study,a novel n-γdiscrimination method is proposed that implements a pulse-coupled neural network for n-γdiscrimination.In addition,experiments were conducted on the pulse signals detected by an EJ299-33 plastic scintillator,which is especially suitable for n-γdiscrimination.The proposed method was compared to three other discrimination methods,including the back-propagation neural network(BPNN),the fractal spectrum method,and the charge comparison method,with respect to two aspects:(i)the figure of merit(FoM)and(ii)discrimination time.The experimental results showed that the pulse-coupled neural network(PCNN)has a 26.49%improvement in FoM-value compared to the charge comparison method,a72.80%improvement compared to the BPNN,a 66.24%improvement compared to the fractal spectrum method,and the second-fastest discrimination time of 2.22 s.In conclusion,the PCNN treats the input signal as a whole for analysis and processing,imparting it with an excellent antinoise effect and the ability to process the dynamic information contained in a pulse signal.展开更多
Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated ...Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.展开更多
A compact 15.0-MeV, 1.5-kW electron linear accelerator(LINAC) was successfully constructed to provide an electron beam for the first photoneutron source at the Shanghai Institute of Applied Physics, Shanghai,China. Th...A compact 15.0-MeV, 1.5-kW electron linear accelerator(LINAC) was successfully constructed to provide an electron beam for the first photoneutron source at the Shanghai Institute of Applied Physics, Shanghai,China. This LINAC consists of five main parts: a thermal cathode grid-controlled electron gun, a pre-buncher, a variable-phase-velocity buncher, a light-speed accelerating structure, and a high-power transportation beamline. A digital feedforward radio frequency compensator is adopted to reduce the energy spread caused by the transient beam loading effect. Furthermore, a real-time electron gun emission feedback algorithm is used to keep the beam stable. After months of efforts, all the beam parameters successfully met the requirements of the facility. In this paper, the beam commissioning process and performance of the LINAC are presented.展开更多
Using photons in therapeutic and diagnostic medicine requires accurate computation of their attenuation coefficients in human tissues.The buildup factor,a multiplicative coefficient quantifying the ratio of scattered ...Using photons in therapeutic and diagnostic medicine requires accurate computation of their attenuation coefficients in human tissues.The buildup factor,a multiplicative coefficient quantifying the ratio of scattered to primary photons,measures the degree of violation of the Beer-Lambert law.In this study,the gamma-ray isotropic point source buildup factors,specifically,the energy absorption buildup factor(EABF)and exposure buildup factor,are estimated.The computational methods used include the geometric progression fitting method and simulation using the Geant4(version 10.4)Monte Carlo simulation toolkit.The buildup factors of 30 human tissues were evaluated in an energy range of 0.015-15 MeV for penetration depths up to 100 mean free paths(mfp).At all penetration depths,it was observed that the EABF seems to be independent of the mfp at a photon energy of 1.5 MeV and also independent of the equivalent atomic number(Zeq)in the photon energy range of 1.5-15 MeV.However,the buildup factors were inversely proportional to Zeq for energies below 1.5 MeV.Moreover,the Geant4 simulations of the EABF of water were in agreement with the available standard data.(The deviations were less than 5%.)The buildup factors evaluated in the present study could be useful for controlling human exposure to radiation.展开更多
The neutron yield in the12C(d,n)13N reaction and the proton yield in the12C(d,p)13C reaction have been measured using deuteron beams of energies 0.6-3 MeV.The deuteron beam is delivered from a 4-MeV electrostatic acce...The neutron yield in the12C(d,n)13N reaction and the proton yield in the12C(d,p)13C reaction have been measured using deuteron beams of energies 0.6-3 MeV.The deuteron beam is delivered from a 4-MeV electrostatic accelerator and bombarded on a thick carbon target.The neutrons are detected at 0°,24°,and 48°and the protons at135°in the laboratory frame.Further,the ratio of the neutron yield to the proton yield was calculated.This can be used to effectively recognize the resonances.The resonances are found at 1.4 MeV,1.7 MeV,and 2.5 MeV in the12C(d,p)13C reaction,and at 1.6 MeV and 2.7 MeV in the12C(d,n)13N reaction.The proposed method provides a way to reduce systematic uncertainty and helps confirm more resonances in compound nuclei.展开更多
In this paper, we study how pixel size influences energy resolution for a proposed pixelated detector—a high sensitivity, low cost, and real-time radon monitor based on a Topmetal-Ⅱ^- time projection chamber(TPC). T...In this paper, we study how pixel size influences energy resolution for a proposed pixelated detector—a high sensitivity, low cost, and real-time radon monitor based on a Topmetal-Ⅱ^- time projection chamber(TPC). This monitor was designed to improve spatial resolution for detecting radon alpha particles using Topmetal-Ⅱ^- sensors assembled by a 0.35 lm CMOS integrated circuit process.Owing to concerns that small pixel size might have the side effect of worsening energy resolution due to lower signalto-noise ratio, a Geant4-based simulation was used to investigate the dependence of energy resolution on pixel sizes ranging from 60 to 600 lm. A non-monotonic trend in this region shows the combined effect of pixel size and threshold on pixels, analyzed by introducing an empirical expression. Pixel noise contributes 50 keV full-width at half-maximum energy resolution for 400 lm pixel size at 1–4σ threshold that is comparable to the energy resolution caused by energy fluctuations in the TPC ionization process( ~20 keV). The total energy resolution after combining both factors is estimated to be 54 keV for a pixel size of 400 lm at 1–4σ threshold. The analysis presented in this paper would help choosing suitable pixel size for future pixelated detectors.展开更多
Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in hi...Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in highenergy particle and nuclear physics experiments.The inherent properties of the detector and hardware imply that particles with relatively high energies probably often generate saturated signals.Usually,these saturated signals are discarded during data processing,and therefore,some useful information is lost.Thus,it is worth restoring the saturated signals to their normal form.The mapping from a saturated signal waveform to a normal signal waveform constitutes a regression problem.Given that the scintillator and collection usually do not form a linear system,typical regression methods such as multi-parameter fitting are not immediately applicable.One important advantage of ANNs is their capability to process nonlinear regression problems.To recover the saturated signal,three typical ANNs were tested including backpropagation(BP),simple recurrent(Elman),and generalized radial basis function(GRBF)neural networks(NNs).They represent a basic network structure,a network structure with feedback,and a network structure with a kernel function,respectively.The saturated waveforms were produced mainly by the environmental gamma in a liquid scintillation detector for the China Dark Matter Detection Experiment(CDEX).The training and test data sets consisted of 6000 and 3000 recordings of background radiation,respectively,in which saturation was simulated by truncating each waveform at 40%of the maximum signal.The results show that the GBRF-NN performed best as measured using a Chi-squared test to compare the original and reconstructed signals in the region in which saturation was simulated.A comparison of the original and reconstructed signals in this region shows that the GBRF neural network produced the best performance.This ANN demonstrates a powerful efficacy in terms of solving the saturation recovery problem.The proposed method outlines new ideas and possibilities for the recovery of saturated signals in high-energy particle and nuclear physics experiments.This study also illustrates an innovative application of machine learning in the analysis of experimental data in particle physics.展开更多
基金supported by the National Natural Science Foundation of China(Nos.11875323,12275359,12205377,12335008,U2032145,11790320,11790323,11790325,and 11961141003)the National Key R&D Program of China(No.2018 YFA0404404)+2 种基金the Continuous Basic Scientific Research Project(No.WDJC-2019-13)the China Institute of Atomic Energy(No.YZ222407001301)the Leading Innovation Project of the CNNC(Nos.LC192209000701 and LC202309000201)。
文摘In this work,we study the impacts of the isospin-independent momentum-dependent interaction(MDI)and near-threshold NN→NΔcross sections(σ_(NN→NΔ))on the nucleonic flow and pion production observables in the ultra-relativistic quantum molecular dynamics(UrQMD)model.With the updated isospin-independent MDI and the near-threshold NN→NΔcross sections in the Ur QMD model,17 observables,which are the directed flow(v_(1))and elliptic flow(v_(2))of neutrons,protons,Hydrogen(H),and charged particles as a function of transverse momentum(p_t∕A)or normalized rapidity(y^(lab)_0),and the observables constructed from them,the charged pion multiplicity(M(π))and its ratio(M(π^(-))∕M(π^(+))),can be simultaneously described at certain forms of symmetry energy.The refinement of the UrQMD model provides a solid foundation for further understanding the effects of the missed physics,such as the threshold effect,the pion potential,and the momentum-dependent symmetry potential.Circumstantial constraints on the symmetry energy at the flow characteristic density 1.2±0.6ρ_(0)and the pion characteristic density 1.5±0.5ρ_(0)were obtained with the current version of UrQMD,and the corresponding symmetry energies were S(1.2ρ_(0))=34±4 MeV and S(1.5ρ_(0))=36±8 MeV,respectively.Furthermore,the discrepancies between the data and the calculated results of v_(2)^(n)and v_(2)^(9)at high p_(t)(rapidity)imply that the roles of the missing ingredients,such as the threshold effect,the pion potential,and the momentum-dependent symmetry potential,should be investigated by differential observables,such as the momentum and rapidity distributions of the nucleonic and pionic probes over a wide beam energy range.
文摘Prompt radiation emitted during accelerator operation poses a significant health risk,necessitating a thorough search and securing of hazardous areas prior to initiation.Currently,manual sweep methods are employed.However,the limitations of manual sweeps have become increasingly evident with the implementation of large-scale accelerators.By leveraging advancements in machine vision technology,the automatic identification of stranded personnel in controlled areas through camera imagery presents a viable solution for efficient search and security.Given the criticality of personal safety for stranded individuals,search and security processes must be sufficiently reliable.To ensure comprehensive coverage,180°camera groups were strategically positioned on both sides of the accelerator tunnel to eliminate blind spots within the monitoring range.The YOLOV8 network model was modified to enable the detection of small targets,such as hands and feet,as well as larger targets formed by individuals near the cameras.Furthermore,the system incorporates a pedestrian recognition model that detects human body parts,and an information fusion strategy is used to integrate the detected head,hands,and feet with the identified pedestrians as a cohesive unit.This strategy enhanced the capability of the model to identify pedestrians obstructed by equipment,resulting in a notable improvement in the recall rate.Specifically,recall rates of 0.915 and 0.82were obtained for Datasets 1 and 2,respectively.Although there was a slight decrease in accuracy,it aligned with the intended purpose of the search-and-secure software design.Experimental tests conducted within an accelerator tunnel demonstrated the effectiveness of this approach in achieving reliable recognition outcomes.
基金the National Natural Science Foundation of China(Nos.52222701,52077211,and 52307034).
文摘The superconducting magnet system of a fusion reactor plays a vital role in plasma confinement,a process that can be dis-rupted by various operational factors.A critical parameter for evaluating the temperature margin of superconducting magnets during normal operation is the nuclear heating caused by D-T neutrons.This study investigates the impact of nuclear heat-ing on a superconducting magnet system by employing an improved analysis method that combines neutronics and thermal hydraulics.In the magnet system,toroidal field(TF)magnets are positioned closest to the plasma and bear the highest nuclear-heat load,making them prime candidates for evaluating the influence of nuclear heating on stability.To enhance the modeling accuracy and facilitate design modifications,a parametric TF model that incorporates heterogeneity is established to expedite the optimization design process and enhance the accuracy of the computations.A comparative analysis with a homogeneous TF model reveals that the heterogeneous model improves accuracy by over 12%.Considering factors such as heat load,magnetic-field strength,and cooling conditions,the cooling circuit facing the most severe conditions is selected to calculate the temperature of the superconductor.This selection streamlines the workload associated with thermal-hydraulic analysis.This approach enables a more efficient and precise evaluation of the temperature margin of TF magnets.Moreover,it offers insights that can guide the optimization of both the structure and cooling strategy of superconducting magnet systems.
基金supported by National Key R&D Program of China(Nos.2023YFA1606904 and 2023YFA1606900)National Natural Science Foundation of China(No.12150006)Shanghai Pilot Program for Basic Research-Shanghai Jiao Tong University(No.21TQ1400209).
文摘The sensitivity of the dark photon search through invisible decay final states in low-background experiments relies sig-nificantly on the neutron and muon veto efficiencies,which depend on the amount of material used and the design of the detector geometry.This paper presents the optimized design of the hadronic calorimeter(HCAL)used in the DarkSHINE experiment,which is studied using a GEANT4-based simulation framework.The geometry is optimized by comparing a traditional design with uniform absorbers to one that uses different thicknesses at different locations on the detector,which enhances the efficiency of vetoing low-energy neutrons at the sub-GeV level.The overall size and total amount of material used in the HCAL are optimized to be lower,owing to the load and budget requirements,whereas the overall performance is studied to satisfy the physical objectives.
基金the National Natural Science Foundation of China(Nos.12205001,11935001,and 12204001)the Scientific Research program of Anhui University of Finance and Economics(Nos.ACKYC22080 and ACKYC220801).
文摘The properties of exotic nuclei are the focus of the present research.Two-neutron halo structures of neutron-rich17,19B were experimentally confirmed.We studied the formation mechanism of halo phenomena in17,19B using the complex momentum representation method applied to deformation and continuum coupling.By examining the evolution of the weakly bound and resonant levels near the Fermi surface,s–d orbital reversals and certain prolate deformations were observed.In addition,by analyzing the evolution of the occupation probabilities and density distributions occupied by valence neutrons,we found that the ground state of15B did not exhibit a halo and the ground states of17B and19B exhibited halos at 0.6≤β2≤0.7 and0.3≤β2≤0.7,respectively.The low-l components in the valence levels that are weakly bound or embedded in the continuous spectrum lead to halo formation.
文摘Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate when the optimization objectives for an accelerator are equal to or greater than four. Recently, many-objective evolutionary algorithms(MaOEAs)that can solve problems with four or more optimization objectives have received extensive attention. In this study, two diffraction-limited storage ring(DLSR) lattices of the Extremely Brilliant Source(ESRF-EBS) type with different energies were designed and optimized using three MaOEAs and a widely used MOEA. The initial population was found to have a significant impact on the performance of the algorithms and was carefully studied. The performances of the four algorithms were compared, and the results demonstrated that the grid-based evolutionary algorithm(GrEA) had the best performance.Ma OEAs were applied in many-objective optimization of DLSR lattices for the first time, and lattices with natural emittances of 116 and 23 pm·rad were obtained at energies of 2 and 6 GeV, respectively, both with reasonable dynamic aperture and local momentum aperture(LMA). This work provides a valuable reference for future many-objective optimization of DLSRs.
文摘Scaling analysis is widely used to design scaled-down experimental facilities through which the prototype phenomena can be effectively evaluated.As a new method,dynamic system scaling(DSS)must be verified as a rational and applicable method.A DSS method based on dilation transformation was evaluated using single-phase natural circulation in a simple rectangular loop.The scaled-down cases were constructed based on two parameters—length ratio and dilation number—and the corresponding transient processes were simulated using the Relap5 computational code.The results show that this DSS method can simulate the dynamic flow characteristics of scaled-down cases.The transient deviation of the temperature difference and mass flow rate of the scaled cases decrease with increases in the length ratio and dilation number.The distortion of the transient temperature difference is smaller than that of the mass flow;however,the overall deviation is within a reasonable range.
基金supported by the National Natural Science Foundation of China (Nos. 12027810 and 11322548)
文摘The neutron supermirror is an important neutron optical device that can significantly improve the efficiency of neutron transport in neutron guides and has been widely used in research neutron sources.Three types of algorithms,including approximately ten algorithms,have been developed for designing high-efficiency supermirror structures.In addition to its applications in neutron guides,in recent years,the use of neutron supermirrors in neutronfocusing mirrors has been proposed to advance the development of neutron scattering and neutron imaging instruments,especially those at compact neutron sources.In this new application scenario,the performance of supermirrors strongly affects the instrument performance;therefore,a careful evaluation of the design algorithms is needed.In this study,we examine two issues:the effect of nonuniform film thickness distribution on a curved substrate and the effect of the specific neutron intensity distribution on the performance of neutron supermirrors designed using existing algorithms.The effect of film thickness nonuniformity is found to be relatively insignificant,whereas the effect of the neutron intensity distribution over Q(where Q is the magnitude of the scattering vector of incident neutrons)is considerable.Selection diagrams that show the best design algorithm under different conditions are obtained from these results.When the intensity distribution is not considered,empirical algorithms can obtain the highest average reflectivity,whereas discrete algorithms perform best when the intensity distribution is taken into account.The reasons for the differences in performance between algorithms are also discussed.These findings provide a reference for selecting design algorithms for supermirrors for use in neutron optical devices with unique geometries and can be very helpful for improving the performance of focusing supermirror-based instruments.
基金This work was supported by the National Natural Science Foundation of China(Nos.11875174 and 11961131010)。
文摘The compact spectrometer for heavy ion experiment(CSHINE)is under construction for the study of isospin chronology via the Hanbury Brown–Twiss(HBT)particle correlation function and the nuclear equation of state of asymmetrical nuclear matter.The CSHINE consists of silicon strip detector(SSD)telescopes and large-area parallel-plate avalanche counters,which measure the light charged particles and fission fragments,respectively.In phase I,two SSD telescopes were used to observe 30 MeV/u 40Ar?197Au reactions.The results presented here demonstrate that hydrogen and helium were observed with high isotopic resolution,and the HBT correlation functions of light charged particles could be constructed from the obtained data.
基金supported by the National Natural Science Foundation of China(No.11922504)。
文摘This paper reports on the design,fabrication,RF measurement,and high-power test of a prototype accelerator—such as 11.424 GHz with 12 cells—and a traveling wave of two halves.It was found that the unloaded gradient reached 103 MV/m during the high-power test and the measured breakdown rate,after 3.17×10^(7) pulses,was 1.62×10^(-4)/pulse/m at 94 MV/m and a 90 ns pulse length.We thus concluded that the high-gradient two-half linear accelerator is cost-effective,especially in high-frequency RF linear acceleration.Finally,we suggest that silverbased alloy brazing can further reduce costs.
基金supported by the National Natural Science Foundation of China(Nos.11675069 and 12075106)the Natural Science Foundation of Gansu Province(No.20JR10RA607)the Fundamental Research Funds for the Central Universities of China(No.lzujbky-2020-kb09)。
文摘We irradiated pea seeds with neutrons from a ^(252)Cf source and studied the radiation dose effects on various morphological development parameters during the growth of M_(1) generation peas.We found that in the dose range of 0.51-9.27 Gy,with the increase in neutron-absorbed dose,the morphological development parameters of M_(1) generation peas at the initial seedling stage showed an obvious trend with three fluctuations.With the development of pea,this trend gradually weakened.Further analysis and verification showed that the main trend in the M_(1) generation of pea seeds was an inhibitory effect induced by neutron irradiation and there was a good linear correlation between the inhibitory effect and neutron absorption dose We successfully demonstrated the background removal of mutant plants and defined morphological developmen parameters for peas that match the overall development of plants.Our results will positively impact neutron mutation breeding and automatic agriculture.
基金This work was supported in part by the National Science Foundation of China(Nos.U2032145,11875125,12047568,11790323,11790325,and 12075085)the National Key Research and Development Program of China(No.2020YFE0202002)the"Ten Thousand Talent Program"of Zhejiang Province(No.2018R52017).
文摘Background:The masses of-2500 nuclei have been measured experimentally;however,>7000 isotopes are predicted to exist in the nuclear landscape from H(Z=1)to Og(Z=118)based on various theoretical calculations.Exploring the mass of the remaining isotopes is a popular topic in nuclear physics.Machine learning has served as a powerful tool for learning complex representations of big data in many fields.Purpose:We use Light Gradient Boosting Machine(LightGBM),which is a highly efficient machine learning algorithm,to predict the masses of unknown nuclei and to explore the nuclear landscape on the neutron-rich side from learning the measured nuclear masses.Methods:Several characteristic quantities(e.g.,mass number and proton number)are fed into the LightGBM algorithm to mimic the patterns of the residual δ(Z,A)between the experimental binding energy and the theoret-ical one given by the liquid-drop model(LDM),Duflo–Zucker(DZ,also dubbed DZ28)mass model,finite-range droplet model(FRDM,also dubbed FRDM2012),as well as the Weizsacker–Skyrme(WS4)model to refine these mass models.Results:By using the experimental data of 80%of known nuclei as the training dataset,the root mean square devia-tions(RMSDs)between the predicted and the experimental binding energy of the remaining 20%are approximately 0.234±0.022,0.213±0.018,0.170±0.011,and 0.222±0.016 MeV for the LightGBM-refined LDM,DZ model,WS4 model,and FRDM,respectively.These values are approximately 90%,65%,40%,and 60%smaller than those of the corresponding origin mass models.The RMSD for 66 newly measured nuclei that appeared in AME2020 was also significantly improved.The one-neutron and two-neutron separation energies predicted by these refined models are consistent with several theoretical predictions based on various physical models.In addition,the two-neutron separation energies of several newly measured nuclei(e.g.,some isotopes of Ca,Ti,Pm,and Sm)pre-dicted with LightGBM-refined mass models are also in good agreement with the latest experimental data.Conclusions:LightGBM can be used to refine theoretical nuclear mass models and predict the binding energy of unknown nuclei.Moreover,the correlation between the input characteristic quantities and the output can be inter-preted by SHapley additive exPlanations(a popular explainable artificial intelligence tool),which may provide new insights for developing theoretical nuclear mass models.
基金supported by the National Key R&D Program of China(Nos.2018YFE0311100 and 2017YFE0301205)National Natural Science Foundation of China(Nos.11905146,11775269,11575244,11575249,11575235,11422546,11805133,and U19A20113)+4 种基金Users with Excellence Program of Hefei Science Center,CAS(No.2019HSC-UE014)National Magnetic Confinement Fusion Science Program of China(Nos.2015GB110005,2015GB103003,2015GB101002,and 2015GB103000)Key Research Program of Frontier Sciences,CAS(No.QYZDB-SSWSLH001)CASHIPS Director’s Fund(No.BJPY2019A01)Shenzhen Clean Energy Research Institute.
文摘The first experimental investigation of the tungsten behavior in ELMy H-mode plasmas with co-/counter neutral beam injection(NBI)and unfavor-able/favorable B t was performed on EAST.Tungsten was found to accumulate easily in ELMy H-mode plasma with co-NBI heating and unfavorable B t.Thus,in this case the tungsten concentration can exceed 10^(-4),resulting in degradation of the plasma confinement and periodic H–L transitions.To reduce the tungsten concentration in steady-state type-I ELMy H-mode operation,counter-NBI is applied to modify the density and temperature and brake the plasma toroidal rotation.The applied counter-NBI decreases the PHZ+E_(r) inward pinch velocity and rever-ses the direction of neoclassical inward convection,thus decreasing the tungsten concentration from-7×10^(-5) to-2×10^(-5) in type-I ELMy H-mode plasma with favorable B_(t).A comparison of the effects of different B_(t) directions on the tungsten behavior also shows that favor-able B_(t) is beneficial for reducing the tungsten concentration in the core plasma.These results imply that counter-NBI with favorable B_(t) can effectively prevent tungsten accu-mulation and expand the operating window for exploring steady-state type-I ELMy H-mode operation of EAST.
基金supported by the Key Science and Technology projects of Leshan(No.19SZD117)the Sichuan Science and Technology Program(No.2021JDRC0108)。
文摘Neutron and gamma ray pulse signal discrimination technology is an essential part of many modern scientific fields,such as biology,geology,radiation imaging,and nuclear medicine.Neutrons are always accompanied by gamma rays due to their unique penetration characteristic;thus,the development of n-γdiscrimination methods is especially crucial.In the present study,a novel n-γdiscrimination method is proposed that implements a pulse-coupled neural network for n-γdiscrimination.In addition,experiments were conducted on the pulse signals detected by an EJ299-33 plastic scintillator,which is especially suitable for n-γdiscrimination.The proposed method was compared to three other discrimination methods,including the back-propagation neural network(BPNN),the fractal spectrum method,and the charge comparison method,with respect to two aspects:(i)the figure of merit(FoM)and(ii)discrimination time.The experimental results showed that the pulse-coupled neural network(PCNN)has a 26.49%improvement in FoM-value compared to the charge comparison method,a72.80%improvement compared to the BPNN,a 66.24%improvement compared to the fractal spectrum method,and the second-fastest discrimination time of 2.22 s.In conclusion,the PCNN treats the input signal as a whole for analysis and processing,imparting it with an excellent antinoise effect and the ability to process the dynamic information contained in a pulse signal.
基金the National Natural Science Foundation of China(No.51875209)the Guangdong Basic and Applied Basic Research Foundation(No.2019B1515120060)the Open Funds of State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment。
文摘Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.
基金supported by the Youth Innovation Promotion Association CAS(No.2018300)
文摘A compact 15.0-MeV, 1.5-kW electron linear accelerator(LINAC) was successfully constructed to provide an electron beam for the first photoneutron source at the Shanghai Institute of Applied Physics, Shanghai,China. This LINAC consists of five main parts: a thermal cathode grid-controlled electron gun, a pre-buncher, a variable-phase-velocity buncher, a light-speed accelerating structure, and a high-power transportation beamline. A digital feedforward radio frequency compensator is adopted to reduce the energy spread caused by the transient beam loading effect. Furthermore, a real-time electron gun emission feedback algorithm is used to keep the beam stable. After months of efforts, all the beam parameters successfully met the requirements of the facility. In this paper, the beam commissioning process and performance of the LINAC are presented.
基金supported by the National Plan for Science,Technology and Innovation(MAARIFAH)King Abdulaziz City for Science and Technology,Kingdom of Saudi Arabia,Award Number(12-MED2516-02)
文摘Using photons in therapeutic and diagnostic medicine requires accurate computation of their attenuation coefficients in human tissues.The buildup factor,a multiplicative coefficient quantifying the ratio of scattered to primary photons,measures the degree of violation of the Beer-Lambert law.In this study,the gamma-ray isotropic point source buildup factors,specifically,the energy absorption buildup factor(EABF)and exposure buildup factor,are estimated.The computational methods used include the geometric progression fitting method and simulation using the Geant4(version 10.4)Monte Carlo simulation toolkit.The buildup factors of 30 human tissues were evaluated in an energy range of 0.015-15 MeV for penetration depths up to 100 mean free paths(mfp).At all penetration depths,it was observed that the EABF seems to be independent of the mfp at a photon energy of 1.5 MeV and also independent of the equivalent atomic number(Zeq)in the photon energy range of 1.5-15 MeV.However,the buildup factors were inversely proportional to Zeq for energies below 1.5 MeV.Moreover,the Geant4 simulations of the EABF of water were in agreement with the available standard data.(The deviations were less than 5%.)The buildup factors evaluated in the present study could be useful for controlling human exposure to radiation.
基金partially supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Nos.XDB16 and XDPB09)the National Natural Science Foundation of China(Nos.11890714 and 11421505)the Key Research Program of Frontier Sciences of the CAS(No.QYZDJ-SSW-SLH002)
文摘The neutron yield in the12C(d,n)13N reaction and the proton yield in the12C(d,p)13C reaction have been measured using deuteron beams of energies 0.6-3 MeV.The deuteron beam is delivered from a 4-MeV electrostatic accelerator and bombarded on a thick carbon target.The neutrons are detected at 0°,24°,and 48°and the protons at135°in the laboratory frame.Further,the ratio of the neutron yield to the proton yield was calculated.This can be used to effectively recognize the resonances.The resonances are found at 1.4 MeV,1.7 MeV,and 2.5 MeV in the12C(d,p)13C reaction,and at 1.6 MeV and 2.7 MeV in the12C(d,n)13N reaction.The proposed method provides a way to reduce systematic uncertainty and helps confirm more resonances in compound nuclei.
基金supported by the National Natural Science Foundation of China(No.U1732271)
文摘In this paper, we study how pixel size influences energy resolution for a proposed pixelated detector—a high sensitivity, low cost, and real-time radon monitor based on a Topmetal-Ⅱ^- time projection chamber(TPC). This monitor was designed to improve spatial resolution for detecting radon alpha particles using Topmetal-Ⅱ^- sensors assembled by a 0.35 lm CMOS integrated circuit process.Owing to concerns that small pixel size might have the side effect of worsening energy resolution due to lower signalto-noise ratio, a Geant4-based simulation was used to investigate the dependence of energy resolution on pixel sizes ranging from 60 to 600 lm. A non-monotonic trend in this region shows the combined effect of pixel size and threshold on pixels, analyzed by introducing an empirical expression. Pixel noise contributes 50 keV full-width at half-maximum energy resolution for 400 lm pixel size at 1–4σ threshold that is comparable to the energy resolution caused by energy fluctuations in the TPC ionization process( ~20 keV). The total energy resolution after combining both factors is estimated to be 54 keV for a pixel size of 400 lm at 1–4σ threshold. The analysis presented in this paper would help choosing suitable pixel size for future pixelated detectors.
基金supported by the ‘‘Detection of very low-flux background neutrons in China Jinping Underground Laboratory’’ project of the National Natural Science Foundation of China(No.11275134)
文摘Artificial neural networks(ANNs)are a core component of artificial intelligence and are frequently used in machine learning.In this report,we investigate the use of ANNs to recover the saturated signals acquired in highenergy particle and nuclear physics experiments.The inherent properties of the detector and hardware imply that particles with relatively high energies probably often generate saturated signals.Usually,these saturated signals are discarded during data processing,and therefore,some useful information is lost.Thus,it is worth restoring the saturated signals to their normal form.The mapping from a saturated signal waveform to a normal signal waveform constitutes a regression problem.Given that the scintillator and collection usually do not form a linear system,typical regression methods such as multi-parameter fitting are not immediately applicable.One important advantage of ANNs is their capability to process nonlinear regression problems.To recover the saturated signal,three typical ANNs were tested including backpropagation(BP),simple recurrent(Elman),and generalized radial basis function(GRBF)neural networks(NNs).They represent a basic network structure,a network structure with feedback,and a network structure with a kernel function,respectively.The saturated waveforms were produced mainly by the environmental gamma in a liquid scintillation detector for the China Dark Matter Detection Experiment(CDEX).The training and test data sets consisted of 6000 and 3000 recordings of background radiation,respectively,in which saturation was simulated by truncating each waveform at 40%of the maximum signal.The results show that the GBRF-NN performed best as measured using a Chi-squared test to compare the original and reconstructed signals in the region in which saturation was simulated.A comparison of the original and reconstructed signals in this region shows that the GBRF neural network produced the best performance.This ANN demonstrates a powerful efficacy in terms of solving the saturation recovery problem.The proposed method outlines new ideas and possibilities for the recovery of saturated signals in high-energy particle and nuclear physics experiments.This study also illustrates an innovative application of machine learning in the analysis of experimental data in particle physics.
