The Neural Network Is Applied Research, Environmental Quality Assessment In The Pore Water Of Kunming Basin

There are many methods on ground water environmental quality assessment at present, such as single factor pollution index method, integrated index assessment, fuzzy mathematics method and gray system evaluation method, etc. Though each of those methods has certain advantage, most of them need to construct subject functions, to confirm the power values of evaluation index and how to confirm them objectively and reasonably. For not only the designs of those subject functions contain certain artificial factors, but also the calculations of power value embody reasonless aspects, as a result much important information will be lost in some circumstance.However,Artificial neural network (ANN) is a math-model simulating biological neural network of human brain using computer. It is extremely useful for solving problems without existing algorithmic solutions or with algorithms that are too complex to implement. And it has been widely applied in many-fields such as processing information, automatic control and pattern recognition and so on. The network consists of layers of parallel processing elements called "neurons". The work principle is similar to the course of environment influenced by external stimulus. So it is applicable that assessing the environmental quality of ground water using ANN. Besides, It can make up for these shortcomings of traditional assessing methods in some certain, Most of which need to construct subject functions and confirm the weights of evaluation index, bringing certain subjective effects to assessment processes and some important in formation lost.The main works of this paper are as follows:Firstly, general methods of the ground water environment quality assessment are studied, and single factor pollution index method and fuzzy comprehensive evaluation method are applied into the pore-water environmental quality assessment of Kunming basin.Secondly, some shortcomings of the classical grey association analysis method are analyzed; besides a grey association analysis method is introduced and is improved.It turns out to be reasonable.Thirdly, the neural network's history of development and the basic principle are studied.Fourthly, the principle, the shortcomings and the improvement of BP network are studied. A new processing method for assessing the swatches is introduced .It proves successful that the method is applied into the pore-water environment quality assessment of Kunming basin.Fifthly, comparing with the results of single factor pollution index method, fuzzy comprehensive evaluation method, grey association analysis improvement method and BP network, BP network shortcomings are discovered, and the method which combined single factor pollution index method with BP network is introduced.