English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper proposes an intelligent algorithm to predict the MBR membrane flux. The algorithm applies the least squares support vector machine (LS-SVM) to the research of MBR simulation prediction, optimize the penalty factor and kernel parameters of LS-SVM model by particle swarm optimization (PSO) for avoiding the blindness of artificial selection parameter. Due to the complexity and cross-cutting of the factors that affect MBR membrane fouling, first of all, we analyze the factors by principal component analysis (PCA), extract the important factors as the LS-SVM input layer, MBR membrane flux as output layer, and then create PSO-LSSVM prediction simulation model. In the end, we get predictive results with the model. By comparing the predicted results with experimental data, the algorithm has higher prediction accuracy for MBR membrane flux. To further verify the effectiveness of the algorithm, we also compare the model with BP neural network model, the results show that the prediction model of PSO-LSSVM has a higher prediction accuracy. Introduction MBR, combining membrane separation technology with biotechnology, is a new technology which is applied in the field of sewage treatment. Large number of experimental studies have shown that MBR membrane fouling severely affect the performance of MBR technology and caused much energy consumption. The most direct consequence of membrane fouling is caused by decrease in flux, so the size of the membrane flux is important to characterize the degree of membrane fouling. Therefore, the study of membrane pollution factors, and the describing membrane fouling process with intelligent simulation model have become a hot topic in today's MBR simulation system. Only when the number of samples tends to infinity, the forecasting methods based on the traditional statistics have good performance in theory. In most practical cases, the number of samples is limited, and even very small. Therefore, these methods are difficult to achieve the desired results. Compared with the traditional statistics, Vapnik et al established statistical learning theory (SLT),which is a theory of specialized research in machine learning rule with the small samples, and provides a unified machine learning problem framework when the sample is limited. Support Vector Machine (SVM) that proposed by Vapnik in 1995 is kind of machine learning methods based on statistical learning theory. With the in-depth study of Vapnik, it is extended to function regression estimation aspects and demonstrate excellent learning performance. SVM parameter selection problem has not been resolved, so the further application of SVM is severely limited .To this end, we propose a method that combines PSO with SVM. We search parameters of SVM with PSO to achieve optimal prediction model. The method is used to establish a least squares support vector machine (LS-SVM) forecasting model. The model is applied on MBR membrane flux predictions. 2nd International Conference on Electrical, Computer Engineering and Electronics (ICECEE 2015) © 2015. The authors Published by Atlantis Press 1030 The Prediction Model of MBR Membrane Fouling Principal Component Analysis(PCA). Principal component analysis (PCA) method is usually used to simplify the process of solving multivariate high-dimensional complex system, it has been effectively applied to the statistical analysis, pattern recognition, image processing and communication technologies. Typically, there are many variables that affect MBR Membrane Fouling, these variables associate with each other, so there will be a measurement of the noise carried, and these variables have different degrees of importance. The workload can be greatly reduced when PCA is used in simulation prediction of MBR, and this also directly improves the effectiveness and reliability of the forecast. Specifically described as follows: (1) Select 6 contamination factors to compose the original input variable matrix: { } = Resistance Pressure Temperature X MLSS COD PH , , , , , (2) Normalize X matrix with Standardized methods of mean zero to obtain a new matrix A: ij ( ) / , 1, 2,... . 1, 2,..., . Where is the number of samples, is the number of components of samples, is the standard deviation of variable ij j ij

The research of least squares support vector machine optimized by particle swarm optimization algorithm in the simulation MBR prediction