Particle swarm optimization and support vector machine based soft-measurement method of effluent-volatile fatty acid of anaerobic wastewater treatment system

Abstract

The invention discloses a particle swarm optimization and support vector machine based soft-measurement method of effluent-volatile fatty acid of an anaerobic wastewater treatment system. In order to improve precision and robustness of a model, the particle swarm optimization and a support vector machine are combined in the measurement method. The problem about long retardation tine of measurement equipment is solved through the soft-measurement method, effluent quality of wastewater is truly and comprehensively monitored in real time, and accidental contaminations are prevented; meanwhile, the soft-measurement method can be used for feedback control to achieve optimal control on the anaerobic wastewater treatment system, guidance is provided for monitoring, optimizing and understanding the anaerobic digestion process, some expensive measurement equipment can be substituted, maintenance cost is saved, wastewater treatment cost is lowered, and the soft-measurement method is easy to promote and apply in wastewater treatment engineering and is good in social and economical benefits.

Description

technical field [0001] The invention relates to the technical field of wastewater treatment, in particular to a soft measurement method for volatile fatty acids in effluent from an anaerobic wastewater treatment system. Background technique [0002] With the acceleration of my country's economic development and industrialization process, my country's wastewater discharge has increased year by year, and water pollution control has a long way to go. The anaerobic biological treatment process has the advantages of low power consumption, low sludge output, low demand for nitrogen and phosphorus, can reduce the cost of supplementing nitrogen and phosphorus nutrients, anaerobic digestion can generate bioenergy, etc., making anaerobic biological treatment in It is becoming more and more important and widely used in industrial wastewater treatment. However, the anaerobic digestion process is an extremely complex, nonlinear, and highly uncertain biochemical process. On the one hand...

AI Technical Summary

Problems solved by technology

[0008] Support Vector Machine (SVM) is especially suitable for solving problems such as small samples, nonlinearity, local minimum points, etc., and the training speed is fast, and it has an effective classification strategy for the added metadata set; the SVM model is based on the VC of statistical learning theory. A new intelligent algorithm developed on the basis of the dimensional theory and the principle of structural risk minimization is developed by Corinna Cortes and Vapnik et al. (Cortes C, Vapnik V.1995.Support-Vector networks[J].Machine Learning, 20( 3): 273-297) first put forward, the basic idea is to introduce the concept of kernel function, map the problem of inseparable low-dimensional space to high-dimensional space linearly separable through kernel function, and perform classification or regression processing in high-dimensional space

Images