ѧ ѧʿѧλ
Ŀ BPĻѹԤ
Ժ() : 뼼ѧԺ ѧ : GhoulXing ר ҵ: ѧ뼼 ѧ :20xxxxx ָʦ: ɣڣ ύʱ: Ĵʱ: ѧλʱ:
ѧ
BPĻѹ
Ghoulxing
(ѧ ѧ빤ѧԺ 750000)
ժ Ҫ
BP(Back Propagation)һְ洫㷨ѵĶǰ磬ĿǰӦ㷺ģ֮һϢķɡԪϢݸмԪмڲϢ㣬Ϣ任Ϣ仯мΪ߶ṹһ㴫ݵԪϢһһѧϰ̣Ϣ
αҵ˿оϸ㷨ĻԭMablabʵBP㷨BP뵽ѹǿԤľӦУͬʱݽṹ꾡ķھһϵ֤֮ģԤСԤɿڻѹǿȵԤ⡣
ؼʣBP磬㷨ѹmatlab
Prediction of Concrete Compressive Strength based on BP Neural Network
ghoulxing
(ѧ ѧ빤ѧԺ 750000)
ABSTRACT
BP (Propagation Back) neural network is a kind of multilayer feedforward neural network trained by the error back propagation algorithm. It is one of the most widely used neural network models. It consists of two processes, the forward propagation of information and the back propagation of error. Input layer neurons receives the input information from the outside world, and passed to the middle layer neurons; intermediate layer is internal information processing layer and is responsible for the information transform, according to the demand of the information changes, the middle layer can be designed for single hidden layer or multi hidden layer structure; the last hidden layer transfer to output layer neurons, after further processing, to complete a learning forward propagation process, from the output layer output to the outside information processing results.
This graduation design firstly introduces the research background, secondly, it elaborates the basic principle of neural network algorithm. Finally, the mablab software programming realization of the BP neural network algorithm and the BP neural network is introduced to predict the compressive strength of concrete the concrete application in, and make a detailed analysis of the data structure.After a series of verification, the model prediction error is smaller, the prediction results are reliable and can be used for the prediction of the compressive strength of concrete.
Keywords: BP neural network, back propagation algorithm, concrete
compression,matlab