Soft measurement prediction method of water quality of total nitrogen

Abstract

The invention relates to the field of environmental monitoring, and discloses a soft measurement prediction method of water quality of total nitrogen. The method comprises the following steps that: data values of a plurality of water quality monitoring indicators in to-be-tested water environment are obtained, each water quality monitoring indicator has a plurality of obtained data values, at least one of the plurality of water quality monitoring indicators is TN, a number of water quality monitoring indicators are selected from the water monitoring indicators out of the TN, data values of theselected water quality monitoring indicators form a data sample set, the data sample set is divided into a training set and a test set, a fuzzy neural network algorithm is used for training the training set, a TN soft measurement model is obtained; the test set is used for testing the TN soft measurement model to obtain a test result; the model execution and the model test are repeated until theobtained test result meets a preset condition, and the TN soft measurement model meeting the preset condition is set as a final soft measurement model. The obtained model has accurate predicting effects, and reduces water quality soft measurement prediction cost of the TN.

Description

technical field [0001] The invention relates to the field of environmental monitoring, in particular to the water quality soft measurement prediction technology of total nitrogen. Background technique [0002] As we all know, my country's water resources are very scarce, and the per capita share is only 1 / 4 of the world's average level. At the same time, there are serious water pollution problems, such as water pollution, water eutrophication, urban black and odorous water bodies, groundwater pollution, etc. make water resource problems more prominent. In rural areas, nearly 96% of my country's rural sewage, about 8 to 9 billion t / a, has not been treated, causing serious rural environmental pollution and river and sea basin pollution. In cities, black and smelly water bodies have become an urban disease, and almost all cities have no pollution. One survived. Most rivers in China are polluted to varying degrees. It is urgent to alleviate the shortage of water resources, inc...

AI Technical Summary

Problems solved by technology

However, since the sewage treatment system is a complex biochemical treatment system, which is a typical nonlinear, multivariable, unstable, and large time-delay system, with many and uncertain interference factors, it is difficult to directly develop and improve online monitoring instruments, and Monitoring costs (one-time input and reagent costs) are high and difficult to reduce

Images