Modifying Wind Speed Data of Manual Observation Sequence to Automatic Observation Sequence Using a PSO-Based Neural Network

2011 ◽  
Vol 187 ◽  
pp. 688-692
Author(s):  
Xia Xiao ◽  
Hong Chao Zuo ◽  
Wen Yu Zhang ◽  
Ju Jie Wang
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Optimization Technique ◽  
Weather Data ◽  
Percentage Error ◽  
Observation Data ◽  
Data Sequence ◽  
Wind Speed Data ◽  
Observation Sequence ◽  
Particle Swarm Optimization Technique

Recently, manual observation sequence has been gradually replaced by automatic observation sequence. The difference between manual observation sequence and automatic observation sequence is somewhat inevitable. This challenges the the homogeneity and the continuity of historical weather data, and influences atmospheric researches and applications. Therefore, based on the understanding of the influence caused by the two observation sequences, how to modify the data sequence of manual observation to automatic observation sequence has become a problem. In this paper, a model, which is a neural network based on the particle swarm optimization technique (PSONN), is established to modify the wind speed data sequence from manual observation to automatic observation. The proposed model achieves 15.6% in mean absolute percentage error (MAPE) compared to manual observation data sequence. For wind speed, it could be a promising candidate for modifying manual observing data sequence to automatic observing data sequence.

The Prediction of SO2 Pollutant Concentration Using a RBF Neural Network

2011 ◽  
Vol 55-57 ◽  
pp. 1392-1396
Author(s):  
Cheng Yuan Wang ◽  
Wen Yu Zhang ◽  
Ju Jie Wang ◽  
Wen Fang Zhao
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Quality Indicators ◽  
Rbf Neural Network ◽  
Management Systems ◽  
Percentage Error ◽  
Nonlinear Phenomena ◽  
Observation Data ◽  
Data Sequence ◽  
The Impact

Air pollution may cause pernicious effects on human health, and is a widespread problem in the world. Air quality management systems have became an important research issue with strong implications for inhabitants’ health. Monitoring and forecasting of air quality indicators plays an important role in the management systems. Artificial intelligent techniques are successfully used in modelling of highly complex and nonlinear phenomena. In this paper, a model, which is radial basis function (RBF) neural network, is established to estimate the impact of meteorological indicators on SO2. The proposed model achieves 9.91% in mean absolute percentage error (MAPE) compared to real observation data sequence. For air quality, it could be a promising candidate for forecasting the air quality indicators data sequence.

scholarly journals Digitization of historical wind speed observations at the Swedish Meteorological and Hydrological Institute

2020 ◽  
Author(s):  
Erik Engström ◽  
Cesar Azorin-Molina ◽  
Lennart Wern ◽  
Sverker Hellström ◽  
Christophe Sturm ◽  
...  
Keyword(s):  
Wind Speed ◽  
Best Practices ◽  
Weather Data ◽  
Climate Data ◽  
Intergovernmental Panel ◽  
Wind Speed Data ◽  
Warming Climate ◽  
The 1960S ◽  
The University

<p>This contribution presents the first work package (WP1) of the project “Assessing centennial wind speed variability from a historical weather data rescue project in Sweden”, funded by FORMAS – A Swedish Research Council for Sustainable Development (ref. 2019-00509); previously reported in EGU2019-17792-1. Under a warming climate, one of the major uncertainties on the causes driving the climate variability of winds over land (i.e., the “stilling” phenomenon and the recent “recovery” since the 2010s) is mainly due to short availability (i.e. since the 1960s) and low quality of observed wind records as stated by the Fifth Assessment Report (AR5) of the Intergovernmental Panel on Climate Change (IPCC).</p><p>In this study we present the first steps of a joint initiative between the Swedish Meteorological and Hydrological Institute (SMHI) and the University of Gothenburg aimed at filling the key gap of short availability and low quality of wind datasets, and improve the limited knowledge on the causes driving wind speed variability in a changing climate across Sweden. The aim of the WP1 is to rescue historical wind speed series available in the old weather archives at SMHI for the 1920s-1930s. 13 stations with daily wind speed data (in meters per second) during the period 1925-1938 have been selected for digitization; i.e., spanning back our records 2 decades more. To get wind observations from paper to screen we will follow the “Guidelines on Best Practices for Climate Data Rescue” of the World Meteorological Organization. Our protocol will consist on (i) designing a template for digitization; (ii) digitizing papers by an imaging process based on scanning and photographs; and (iii) typing numbers of wind speed data into the template. WP2 will ensure the quality and homogeneity of wind speed series rescued.</p>

scholarly journals Análise comparativa da velocidade do vento e da temperatura do ar, entre dados gerados por reanálises meteorológicas e dados observacionais na região de Minas Gerais

2018 ◽  
Vol 40 ◽  
pp. 20
Author(s):  
Mauren Lucila Marques de Morais Micalichen ◽  
Nelson Luís da Costa Dias
Keyword(s):  
Wind Speed ◽  
Air Temperature ◽  
Meteorological Data ◽  
Reanalysis Data ◽  
Minas Gerais ◽  
Data Series ◽  
Continuous Series ◽  
Observation Data ◽  
Alternative Source ◽  
Wind Speed Data

The use of alternative sources of meteorological data has become increasingly common, making it possible to evaluate areas with no long or continuous series of meteorological data. In this context, the main objective of this study is to evaluate the performance of data series from the National Centers for Environmental Prediction / National Center for Atmospheric Research (NCEP/NCAR) for the state of Minas Gerais and verify the possible use of them in the absence of data observations of air temperature and wind speed. The analyzes were performed by comparing observation data from 17 meteorological stations and reanalysis data of the CFSR and CFSV2 models. From the results of the statistical analysis, it is observed that the air temperature reanalysis data presented a good performance in the region of study. However, wind speed data show a weak correlation. These results show that the air temperature data from these reanalyses have the potential to be used as an alternative source of data. Further studies are suggested regarding the use of wind speed data from these reanalyses.

Trajectory planning for flexible Cartesian robot manipulator by using artificial neural network: numerical simulation and experimental verification

Robotica ◽  
2010 ◽  
Vol 29 (5) ◽  
pp. 797-804 ◽  
Author(s):  
Akira Abe
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Trajectory Planning ◽  
Learning Algorithm ◽  
Robot Manipulator ◽  
Optimization Technique ◽  
Point Motion ◽  
Particle Swarm Optimization Technique ◽  
Artificial Neural ◽  
Point To Point

SUMMARYThis paper presents a novel trajectory planning method for a flexible Cartesian robot manipulator in a point-to-point motion. In order to obtain an exact mathematical model, the parameters of the equation of motion are determined from an identification experiment. An artificial neural network is employed to generate the desired base position, and then, a particle swarm optimization technique is used as the learning algorithm, in which the sum of the displacements of the manipulator is chosen as the objective function. We show that the residual vibrations of the manipulator can be suppressed by minimizing the displacement of the manipulator. The effectiveness and validity of the proposed method are demonstrated by comparing the simulation and experimental results.

Sign in / Sign up

Export Citation Format

Share Document