Current Location:home > Browse

Institution

1. chinaXiv:202106.00114 [pdf]

RLEPSO:Reinforcement learning based Ensemble particle swarm optimizer

尹世远
Subjects: Computer Science >> Computer Software

Evolution is the driving force behind the evolution of biological intelligence. Learning is the driving force behind human civilization. The combination of evolution and learning can form an entire natural world. Now, reinforcement learning has shown significant effects in many places. However, Currently, researchers in the field of optimization algorithms mainly focus on evolution strategies. And there is very little research on learning. Inspired by these ideas, this paper proposes a new particle swarm optimization algorithm Reinforcement learning based Ensemble particle swarm optimizer (RLEPSO) that combines reinforcement learning. The algorithm uses reinforcement learning for pre-training in the design phase to automatically find a more effective combination of parameters for the algorithm to run better and Complete optimization tasks faster. Besides, this algorithm integrates two robust particle swarm variants. And it sets the weight parameters for different algorithms to better adapt to the solution requirements of a variety of different optimization problems, which significantly improves the robustness of the algorithm. RLEPSO makes a certain number of sub-swarms to increase the probability of finding the global optimum and increasing the diversity of particle swarms. This proposed RLEPSO is evaluated on an optimization test functions benchmark set (CEC2013) with 28 functions and compared with other eight particle swarm optimization variants, including three state-of-the-art optimization algorithms. The results show that RLEPSO has better performance and outperforms all compared algorithms.

submitted time 2021-06-29 Hits10883Downloads726 Comment 0

2. chinaXiv:202011.00129 [pdf]

Precipitation forecasting by large-scale climate indices and machine learning techniques

GHOLAMI ROSTAM,Mehdi ; SADATINEJAD,Seyyed Javad ; MALEKIAN,Arash
Subjects: Geosciences >> Geography

Global warming is one of the most complicated challenges of our time causing considerable tension on our societies and on the environment. The impacts of global warming are felt unprecedentedly in a wide variety of ways from shifting weather patterns that threatens food production, to rising sea levels that deteriorates the risk of catastrophic flooding. Among all aspects related to global warming, there is a growing concern on water resource management. This field is targeted at preventing future water crisis threatening human beings. The very first stage in such management is to recognize the prospective climate parameters influencing the future water resource conditions. Numerous prediction models, methods and tools, in this case, have been developed and applied so far. In line with trend, the current study intends to compare three optimization algorithms on the platform of a multilayer perceptron (MLP) network to explore any meaningful connection between large-scale climate indices (LSCIs) and precipitation in the capital of Iran, a country which is located in an arid and semi-arid region and suffers from severe water scarcity caused by mismanagement over years and intensified by global warming. This situation has propelled a great deal of population to immigrate towards more developed cities within the country especially towards Tehran. Therefore, the current and future environmental conditions of this city especially its water supply conditions are of great importance. To tackle this complication an outlook for the future precipitation should be provided and appropriate forecasting trajectories compatible with this region's characteristics should be developed. To this end, the present study investigates three training methods namely backpropagation (BP), genetic algorithms (GAs), and particle swarm optimization (PSO) algorithms on a MLP platform. Two frameworks distinguished by their input compositions are denoted in this study: Concurrent Model Framework (CMF) and Integrated Model Framework (IMF). Through these two frameworks, 13 cases are generated: 12 cases within CMF, each of which contains all selected LSCIs in the same lead-times, and one case within IMF that is constituted from the combination of the most correlated LSCIs with Tehran precipitation in each lead-time. Following the evaluation of all model performances through related statistical tests, Taylor diagram is implemented to make comparison among the final selected models in all three optimization algorithms, the best of which is found to be MLP-PSO in IMF.

submitted time 2020-11-25 Cooperative journals:《Journal of Arid Land》 Hits3522Downloads654 Comment 0

3. chinaXiv:201903.00239 [pdf]

An experimental study on the influences of water erosion on wind erosion in arid and semi-arid regions

YANG Huimin
Subjects: Geosciences >> Geography

Complex erosion by wind and water causes serious harm in arid and semi-arid regions. The interaction mechanisms between water erosion and wind erosion is the key to further our understanding of the complex erosion. Therefore, in-depth understandings of the influences of water erosion on wind erosion is needed. This research used a wind tunnel and two rainfall simulators to investigate the influences of water erosion on succeeding wind erosion. The wind erosion measurements before and after water erosion were run on semi-fixed aeolian sandy soil configured with three slopes (5°, 10° and 15°), six wind speeds (0, 9, 11, 13, 15 and 20 m/s), and five rainfall intensities (0, 30, 45, 60 and 75 mm/h). Results showed that water erosion generally restrained the succeeding wind erosion. At a same slope, the restraining effects decreased as rainfall intensity increased, which decreased from 70.63% to 50.20% with rainfall intensity increased from 30 to 75 mm/h. Rills shaped by water erosion could weaken the restraining effects at wind speed exceeding 15 m/s mainly by cutting through the fine grain layer, exposing the sand layer prone to wind erosion to airflow. In addition, the restraining effects varied greatly among different soil types. The restraining effects of rainfall on the succeeding wind erosion depend on the formation of a coarsening layer with a crust and a compact fine grain layer after rainfall. The findings can deepen the understanding of the complex erosion and provide scientific basis for regional soil and water conservation in arid and semi-arid regions.

submitted time 2019-03-28 Cooperative journals:《Journal of Arid Land》 Hits16239Downloads2989 Comment 0

4. chinaXiv:201712.00400 [pdf]

A field investigation of wind erosion in the farming–pastoral ecotone of northern China using a portable wind tunnel: a case study in Yanchi County

NAN, Ling; DONG, Zhibao; XIAO, Weiqiang; LI, Chao; XIAO, Nan; SONG, Shaopeng; XIAO, Fengjun; DU, Lingtong
Subjects: Geosciences >> Other Disciplines of Geosciences

The farming–pastoral ecotone in northern China is an extremely fragile ecological zone where wind erosion of cropland and rangeland is easy to occur. In this study, using a portable wind tunnel as a wind simulator, we conducted field simulated wind erosion experiments combined with laboratory analysis to investigate wind erosion of soils in trampled rangeland, non-tilled cropland and tilled cropland in Yanchi County, China. The results showed that compared with rangeland, the cropland had a higher soil water holding capacity and lower soil bulk density. The wind erosion rate of trampled rangeland was much higher than those of non-tilled cropland and tilled cropland. For cropland, the wind erosion rate of the soil after tilling was surprisingly less than that of the soil before tilling. With increasing of wind speed, the volume mean diameter of the eroded sediment collected by the trough in the wind tunnel generally increased while the clay and silt content decreased for all soils. The temporal variation in wind erosion of the trampled rangeland indicated that particle entrainment and dust emission decreased exponentially with erosion time through the successive wind erosion events due to the exhaustion of erodible particles.

submitted time 2017-12-08 Cooperative journals:《Journal of Arid Land》 Hits3185Downloads1317 Comment 0

5. chinaXiv:201711.02284 [pdf]

Lepton identification at particle flow oriented detector for the future e+e- Higgs factories

Dan Yu; Manqi Ruana; Vincent Boudry; Henri Videau
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc.

The lepton identification is essential for the physics programs at high-energy frontier, especially for the precise measurement of the Higgs boson. For this purpose, a Toolkit for Multivariate Data Analysis (TMVA) based lepton identification (LICH1) has been developed for detectors using high granularity calorimeters. Using the conceptual detector geometry for the Circular Electron-Positron Collider (CEPC) and single charged particle samples with energy larger than 2 GeV, LICH identifies electrons/muons with efficiencies higher than 99.5% and controls the mis-identification rate of hadron to muons/electrons to better than 1%/0.5%. Reducing the calorimeter granularity by 1-2 orders of magnitude, the lepton identification performance is stable for particles with E > 2 GeV. Applied to fully simulated eeH/mmH events, the lepton identification performance is consistent with the single particle case: the efficiency of identifying all the high energy leptons in an event, is 95.5-98.5%.

submitted time 2017-11-10 Hits716Downloads372 Comment 0

6. chinaXiv:201711.02297 [pdf]

The low temperature performance of CsI(Na) crystals for WIPMs direct searchesI

Xuan Zhang; Xilei Sun; Junguang Lu; Pin Lv
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc.

Previous studies showed that CsI(Na) crystals have signi cantly di erent wave- forms between alpha and gamma scintillations. In this work, the light yield and PSD capability of CsI(Na) scintillators as a function of the temperature down to 80 K has been studied. As temperature drops, the fast component rises and the slow component decreases. By cooling the CsI(Na) crystals, the light yield of high ionization events are enhanced signi cantly, while the light yield of background gamma events are suppressed. At 110 K, CsI(Na) crystal achieves the optimal balance between low threshold and good background re- jection performance. The di erent responses of CsI(Na) to gamma and alpha at di erent temperatures are explained with self-trapped and activator lumines- cence centers.

submitted time 2017-11-10 Hits1202Downloads637 Comment 0

7. chinaXiv:201711.02322 [pdf]

Tracking in dense environments and its inefficiency measurement using pixel dE/dx

Jason D. Mansour
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc.

We present a measurement of the charged particle reconstruction ine ciency inside of jet cores, using data collected by the ATLAS experiment in 2015 of pp collisions produced at the LHC, at a center-of-mass energy of 13 TeV. The determination of this ine ciency is important for jet energy scale and mass calibration, as well as multiple other performance studies and analyses. A data driven method is used, where the fraction of lost particle tracks is determined from energy deposition dE=dx in the pixel detector. The fraction of lost tracks is found to be less than 5%, which is an improvement since the previous study, and agrees well within systematic uncertainties with a Monte Carlo simulation.

submitted time 2017-11-10 Hits962Downloads493 Comment 0

8. chinaXiv:201706.00800 [pdf]

Stereoscopic PIV Measurements of the Flow Field in a Turbine Cascade

Tian Yangtao; Ma Hongwei; Ma Rong
Subjects: Dynamic and Electric Engineering >> Engineering Thermophysics

This paper presents experimental measurements of the flow field in a Low-speed Turbine Cascade using a stereoscopic particle-image velocimetry (SPIV). During the measurements, a pair of frame-straddling-based CCD cameras were configured at different sides of the laser light sheet, and appropriate tracing particles (DEHS) were employed. The measurements were conducted at the incidence angle of 0 degree and exit Reynolds number of 1.7 x 10(5) with the tip clearance 1.18% of blade chord. The tip flow features, such as the evolution and breakdown of tip leakage vortex, the horseshoe vortex, turbulence characteristics of tip leakage flow, were studied for the flow field analysis. The results showed that the tip leakage flow/vortex mainly dominate flow fields in the tip region. The tip leakage vortex performs as a concentrated vortex before its breaking down and splitting into small vortices. The highest turbulence intensity mainly occurs in the tip region along with the trajectory of tip leakage vortex, and when the vortex breaks down, the turbulence intensity reduces rapidly. Additionally, the SPIV with this configuration also shows an advantage in investigating the flow structures and mechanism inside the turbine cascade.

submitted time 2017-06-26 Cooperative journals:《热科学学报》 Hits14867Downloads1169 Comment 0

9. chinaXiv:201705.00571 [pdf]

Dispersion characterisation of CaCO3 particles in PP/CaCO3 composites

Zhu, YD [Zhu, Y. D.][ 1,2 ]; Allen, GC [Allen, G. C.][ 2 ]; Jones, PG [Jones, P. G.][ 3 ]; Adams, JM [Adams, J. M.][ 4 ]; Gittins, DI [Gittins, D. I.][ 3 ]; Heard, PJ [Heard, P. J.][ 2 ]; Skuse, DR [Skuse, D. R.][ 3 ]
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc.

Polypropylene and calcium carbonate were prepared by melt extrusion in a twin screw extruder or cast- ing in a kneader extruder. The dispersion of CaCO3 particles in PP was analysed through the observation of impact-fracture surface, polished surface, cross-section surface and film using scanning electron microscopy (SEM), focused ion beam (FIB) and optical transmission microscopy (OTM). Only basic infor- mation on particle dispersion was obtained from the investigation of fracture surfaces by SEM and the FIB cross-sections by virtue of the ambiguous phase contrast and the limited area observed. However, the SEM images from polished-surfaces and the film images observed in OTM show the different particle dispersion in different samples. The derived Particle Size Distribution (PSD) curves from OTM images explain the difference of impact strength, demonstrating the relationship between particle dispersion and mechanical properties.

submitted time 2017-05-02 Hits2654Downloads675 Comment 0

10. chinaXiv:201705.00379 [pdf]

Revisiting alpha decay-based near-light-speed particle propulsion

Zhang, WW [Zhang, Wenwu][ 1 ]; Liu, Z [Liu, Zhen][ 1 ]; Yang, Y [Yang, Yang][ 1 ]; Du, SY [Du, Shiyu][ 1 ]
Subjects: Physics >> General Physics: Statistical and Quantum Mechanics, Quantum Information, etc.

Interplanet and interstellar travels require long-term propulsion of spacecrafts, whereas the conventional schemes of propulsion are limited by the velocity of the ejected mass. In this study, alpha particles released by nuclear decay are considered as a potential solution for long-time acceleration. The principle of near-light-speed particle propulsion (NcPP) was elucidated and the stopping and range of ions in matter (SRIM) was used to predict theoretical accelerations. The results show that NcPP by means of alpha decay is feasible for long-term spacecraft propulsion and posture adjustment in space. A practical NcPP sail can achieve a speed 4150 km/s and reach the brink of the solar system faster than a mass equivalent solar sail. Finally, to significantly improve the NcPP sail, the hypothesis of stimulated accel- eration of nuclear decay (SAND) was proposed, which may shorten the travel time to Mars to within 20 days.

submitted time 2017-05-02 Hits1302Downloads813 Comment 0

12345678910  Last  Go  [12 Pages/ 114 Totals]