scholarly journals A state-of-art method for solar irradiance forecast via using fisheye lens

2020 ◽  
Author(s):  
Lei Chen ◽  
Yangluxi Li
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Solar Irradiance ◽  
Weather Condition ◽  
Neutral Network ◽  
Fisheye Lens ◽  
Network Method ◽  
Forecast Function ◽  
State Of Art ◽  
Irradiance Forecast

Abstract The purpose of this investigation is to enable the solar irradiance forecast function implementing a common camera devise instead of specialized instrument thereby serve for other researches. Development of various simulated tools requires higher accuracy surrounding weather condition data. Previous studies mainly focus on the improvement of precision for professional monitor equipment i.e. total sky imager, which is limited to the scope of users. In this research, a fisheye lens graph is rectified following a particular algorithm based on the image forming principle. Moreover, solar irradiance prediction adopts the advanced BP neutral network method being proved to be valid. Final results indicate that after rectifying the special perspective images under fisheye direction, colour threshold configuration could remarkably recognize the cloud image. The conclusion shows that common camera fisheye lens coupled with BP neural network successfully predict the solar irradiance.

scholarly journals An Unified Method of Exploration-Based Air Quality Prediction

2020 ◽  
Vol 8 (6) ◽  
pp. 4705-4708
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Bp Neural Network ◽  
Quality Index ◽  
Weather Condition ◽  
Air Quality Index ◽  
Air Quality Prediction ◽  
Large Current ◽  
New Information ◽  
Neural Network Algorithm

Data mining is the application of examining large current databases in sequence to create new information. It is a classification of artificial intelligence build on the concept that systems can get from data, analyze patterns and make judgment with minimal human intervention. The forecast of air quality is done with analyzing the AQI (Air Quality Index) of the atmosphere in different areas. These predictions are done using the BP Neural network Algorithm in which the data of the gases like CO2, CO, SO2, O3, NO2, PM2.5 etc. is first classified in the system, and then the normality is checked by comparison of each gases with the normality. But the prediction cannot be fully excepted because it doesn’t consider the outside weather condition of the atmosphere. This paper uses the ANN (Artificial Neural Network) technique along with BP Neural Network which analysis the weather condition of the atmosphere along with the data of the polluted gases. This paper predict more efficient air quality index of the atmosphere.

Fault Diagnosis of Large Rotors Based on Wavelet Packet Neural Network

2014 ◽  
Vol 722 ◽  
pp. 363-366
Author(s):  
You Juan Zheng ◽  
Ping Liao ◽  
Cai Long Qin ◽  
Yu Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Test Bench ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Network Method ◽  
Spectrum Characteristic ◽  
Fault Information

Using wavelet packet neural network method which is consist of wavelet packet and BP neural network to diagnose large rotors by vibration signal .Firstly , according to the spectrum characteristic of large rotors’ common vibration fault ,using the improved wavelet packet method to compute the energy of the spectrum that can reflect the fault information .And then make the feature vector as the input to establish a model of improved wavelet packet neural network for fault diagnosis . Collect the data of five working conditions from the test bench , establish a improved wavelet packet neural network model, and then use the model to diagnose fault. The experimental results show that this method improves the accuracy obviously and calculate fast.

scholarly journals Position Measurement Based on Fisheye Imaging

Proceedings ◽  
2019 ◽  
Vol 15 (1) ◽  
pp. 38
Author(s):  
Xianjing Li ◽  
Kun Li ◽  
Yanwen Chen ◽  
ZhongHao Li ◽  
Yan Han
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Imaging System ◽  
Large Angle ◽  
Image Features ◽  
Position Measurement ◽  
Fisheye Lens ◽  
Position Information ◽  
Object Distance ◽  
Nonlinear Imaging

For the omnidirectional measurement, the collected images of large-angle fisheye lens need to be corrected and spliced before next procedure, which is complicated and inaccurate. In this paper, a direct position measurement method based on fisheye imaging is proposed for large-angle imaging without any image correcting and splicing. A nonlinear imaging system of fisheye lens is used to acquire the sequence images based on its distortion model, and the critical distortion features of the sequence images are extracted, which contains the position information. And a BP neural network is trained with the extracted image features of previous standard experimental dataset. Finally, the trained BP neural network is employed to measure the object’s distance. Experimental results demonstrate show that the proposed method achieves simple close-object distance measurement with high robustness and a measurement error of ±0.5cm. The proposed method overcomes the shortcomings of conventional measurement methods and expands the fisheye applications filed for omnidirectional measurement.

Creep Behavior Prediction Research of T92 Steel Based on BP Neural Network

2013 ◽  
Vol 467 ◽  
pp. 203-207
Author(s):  
Jian Liu
Keyword(s):  
Neural Network ◽  
Creep Behavior ◽  
Bp Neural Network ◽  
Network Theory ◽  
Experimental Results ◽  
Behavior Prediction ◽  
Forecast Precision ◽  
Network Method ◽  
Simulation Results ◽  
Neural Network Theory

Based on the BP neural network theory, the creep rate prediction model of T92 steel was established under multiple stress levels. Obtained the experimental results and using the model, the experimental results were trained. The results show that the simulation results match the measured results well with a high forecast precision. The BP neural network method can serve as research on T92 steel creep behavior.

Nursing Scheme Based on Back Propagation Neural Network and Probabilistic Neural Network in Chronic Kidney Disease

2020 ◽  
Vol 10 (2) ◽  
pp. 416-421 ◽  
Author(s):  
Xuxia Ying ◽  
Bibo Tang ◽  
Canxin Zhou
Keyword(s):  
Neural Network ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Bp Neural Network ◽  
Probabilistic Neural Network ◽  
Back Propagation ◽  
Model Errors ◽  
Neural Network Method ◽  
Network Method ◽  
Case Data

Objective: The purpose of graded care for chronic kidney disease is to share expert experience, so that doctors can more accurately diagnose chronic kidney disease, so that patients with chronic kidney disease can understand their condition in time and collect case data. The collected case data is established into a data warehouse, the data quality is evaluated, and the BP neural network method is used for data mining to analyze the data. Methods: The paper studied BP neural network and probabilistic neural network (PNN), and used 75% of the samples to compare the models. The model errors were analyzed including maximum, minimum, expectation, variance and running time to get Adaboost. The accuracy and robustness of the -PNN model and the IGABP model are good. Results: BP neural network model and probabilistic neural network method can achieve higher application of graded care for chronic kidney disease. The method is capable of quickly predicting disease grading and providing a standardized treatment care regimen. The method realizes the main functions of querying, managing, and collecting data of medical records. Conclusion: The external expansion function of BP neural network and probabilistic neural network can achieve accurate data analysis, which can effectively improve the diagnosis time and grade prediction accuracy of chronic kidney disease, and provide opinions for graded nursing.

Weld Pool Weld Width Prediction Based on Artificial Neural Network

2013 ◽  
Vol 462-463 ◽  
pp. 171-174
Author(s):  
Xiao Gang Liu ◽  
Le Ting Liu
Keyword(s):  
Neural Network ◽  
Weld Pool ◽  
Bp Neural Network ◽  
Arc Welding ◽  
Welding Process ◽  
Pool Shape ◽  
Weld Width ◽  
Network Method ◽  
Weld Pool Shape

In the COgas shielded arc welding, the weld pool forms is closely related to the quality of welding,but weld pool shape is affected by the welding process parameters. By using BP neural network to predict weld puddle weld width, the results show that the experimental data are very close, thus indicating that prediction of weld width through this network method is very effective.

Performance Prediction of Pre-Corroded Aluminum Alloy Using Genetic Algorithm-Neural Network and Fuzzy Neural Network

2008 ◽  
Vol 33-37 ◽  
pp. 1283-1288 ◽  
Author(s):  
Chao Hua Fan ◽  
Yu Ting He ◽  
Hong Peng Li ◽  
Feng Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Aluminum Alloy ◽  
Aluminum Alloys ◽  
Performance Prediction ◽  
Bp Neural Network ◽  
Fuzzy Neural Network ◽  
Neural Network Method ◽  
Network Method ◽  
Fuzzy Neural

Genetic algorithm is introduced in the study of network authority values of BP neural network, and a GA-NN algorithm is established. Based on this genetic algorithm-neural network method, a predictive model for fatigue performances of the pre-corroded aluminum alloys under a varied corrosion environmental spectrum was developed by means of training from the testing dada. At the same time, a fuzzy-neural network method is established for the same purpose. The results indicate that genetic algorithm-neural network and fuzzy-neural network can both be employed to predict the underlying fatigue performances of the pre-corroded aluminum alloy precisely.

Sign in / Sign up

Export Citation Format

Share Document