BP Neural Network Predicting the Rate of Photo-Catalytic Degradation

De Qing Chu; Bao Guang Mao; Li Min Wang

doi:10.4028/www.scientific.net/AMR.554-556.1624

Paper Titles

Preparation and GC/MS Analysis of Maillard Reaction Products of Perinereis aibuhitensis
p.1602

Density Functional Theory Study of Magnesium Surface
p.1609

Theoretical Study on the Properties of Phenol and its Ozonide
p.1613

Theoretical Study of 4,10-Dinitro-2,6,8,12-tetraoxa-4,10-diaza-tetracyclododecane (TEX)
p.1618

BP Neural Network Predicting the Rate of Photo-Catalytic Degradation
p.1624

Detection of High Energy Materials Using Support Vector Classification
p.1628

The Direct Oxidizing Mechanism for the Reaction of Ozone and Phenol: A DFT Study
p.1632

Observation of Field-Free Molecular Orientation by Terahertz Few-Cycle Pulses
p.1637

Synthesis, Characterization and Antitumor Activities of Cis-gallic acid[(1R,2R)-1,2-cyclohexanediamine] Platinum(II)
p.1645

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 554-556BP Neural Network Predicting the Rate of...

BP Neural Network Predicting the Rate of Photo-Catalytic Degradation

Abstract:

The composite photo-catalyst (PW12-TiO₂) was prepared by a sol-gel and hydrothermal technique. According to the experimental data of the four factors and four levels orthogonal experiment, the BPNN model was built to predict the rate of photo-catalytic degradation and the predictable process was achieved through the software of MATLAB 7.1, The results showed that the BPNN can be used to predicting the rate of photo-catalytic degradation.