BP (Back Propagation) neural network algorithm based method for analyzing coating aging

Abstract

The invention provides a BP (Back Propagation) neural network algorithm based method for analyzing coating aging. The method has the advantages of higher flexibility and forecast precision and better hereditability and comprises the processes of signal forward propagation and error backward propagation, wherein in the forward propagation process, an input sample is imported from an input layer and then transmitted to an output layer after the sample is processed through various buried layers layer by layer; if the actual output of an output layer does not accord with an expected output, the process is turned to an error backward propagation stage; in the error backward propagation process, an output error is backwards transmitted to an input layer through the buried layers in a certain form layer by layer, and the error is shared by all units of all the layers so as to obtain error signals of all the units of all the layers, wherein the error signals are used as references for correcting the weight values of all the units; and the weight value adjustment process of all layers of signal forward propagation and error backward propagation is carried out in cycles until network output errors are reduced to an acceptable degree or a preset number of times is finished. The method is characterized in that a momentum item delta W(t)=eta delta X+alpha delta W(t-1) is added, wherein alpha is a momentum factor alpha belonging to the set of (0, 1); the learning rate is adaptively regulated, if a total error E rises after the adjustment of a batch of weight values, eta is equal to beta eta (theta>0), and if the total error E drops after the adjustment of a batch of weight values, eta is equal to theta eta (theta>0); and a steepness factor is introduced, and when an error curve plane enters a flat area, a changed output quantity is set, wherein lambada is the steepness factor, in the flat area, lambada is larger than 1, and after quitting the flat area, lambada is equal to 1.

Description

technical field [0001] The invention relates to the technical field of analysis of coating aging, in particular to an analysis method for coating aging based on a BP neural network algorithm. Background technique [0002] Existing coatings are widely used because of the functions of protecting matrix materials, decoration, signs, and insulation. During the process of processing, storage and use, due to the comprehensive effect of internal and external factors, the performance of the paint gradually deteriorates, so that it finally loses its use value. This phenomenon is called "aging". Aging is an irreversible change. It is impossible to absolutely prevent the aging of paint, but through the study of the aging process, we can gradually understand and master the law of paint aging, and use this law to take appropriate anti-aging measures to delay its aging speed. Improve the aging resistance of the coating to achieve the purpose of prolonging the service life. [0003] The...

AI Technical Summary

Problems solved by technology

Compared with other theoretical modeling, BP neural network is a more practical model; but multi-layer BP network has its own defects: 1) It is easy to form a local minimum instead of a global optimal solution; 2) Many times of training, slow convergence ; 3) There is no theoretical guidance for hidden layer and node selection; 4) Inheritance is poor

Images