Heat exchanger dirt growth prediction method based on PCA-GA-RBF

Abstract

The invention discloses a heat exchanger dirt growth prediction method based on PCA-GA-RBF. The method comprises the following steps: step 1, constructing an optimal heat exchanger dirt training sample; step 2, constructing a GA-RBF-based artificial neural network prediction model, and determining the number of input layer neurons, the number of hidden layer neurons and the number of output neurons of the RBF artificial neural network prediction model; step 3, optimizing the initial parameter value of the RBF artificial neural network prediction model by using a genetic algorithm to obtain theinitial parameter value of the RBF artificial neural network prediction model; optimizing hidden node center and width parameters of the RBF network by using a genetic algorithm; and step 4, substituting the optimized initial parameter value of the RBF artificial neural prediction model into the RBF artificial neural network prediction model, and adjusting the central position and the weight of the hidden layer node of the RBF by adopting an orthogonal least square method. The method is high in learning speed and high in precision.

Description

technical field [0001] The invention relates to the fouling generation of heat exchangers in the chemical process industry, in particular to a PCA-GA-RBF-based predictive model of fouling growth in heat exchangers. [0002] technical background [0003] Heat exchangers are widely used in the fields of petroleum, chemical industry and power. In actual operation, the heat exchangers inevitably have more or less fouling problems. The existence of fouling will adversely affect the operation of the heat exchangers, especially It is to deteriorate the heat transfer performance of the heat exchanger. At the same time, considering the time-varying nature of the fouling in the heat exchanger (that is, changing with time), the formation of fouling is a long-term accumulation process, which is affected by many factors, such as fluid properties, wall Temperature, temperature gradient between fluid and wall, wall material, surface roughness, fluid velocity, turbulence intensity, shear for...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of existing heat exchanger fouling prediction methods such as low accuracy and slow response time, the present invention provides a heat exchanger fouling prediction model based on PCA-GA-RBF with fast learning speed and high precision

However, due to the ability of distribution, parallelism and fast global search, the genetic algorithm overcomes the defect that the previous dynamic programming method and nonlinear programming solution cannot converge to the real optimal solution.

Images