Improved ELM algorithm-based capillary quality forecasting method

Abstract

The invention relates to an improved ELM algorithm-based capillary quality forecasting method. The method comprises the steps of collecting a plurality of sets of historical field data during the capillary perforation process so as to construct a training set; according to collected field data, determining the input layer, the output layer and the hidden layer of an integrated ELM network; in combination with a plurality of common excitation functions, determining an excitation function of the integrated ELM network in the weight setting manner; optimizing each weight in the excitation function of the integrated ELM network by adopting a genetic algorithm, and obtaining an optimal excitation function; adopting the training set for training the integrated ELM network, and completing the construction of the integrated ELM network; inputting data obtained during the actual production process into each sub-network of the integrated ELM network, and obtaining the output result of each sub-network so as to obtain the output prediction result of the integrated ELM network, namely the quality prediction result of a capillary tube. According to the invention, the rapid performance of an ELM model and the robustness of an integration method are inherited. As a result, the quality of the capillary tube can be forecasted more accurately.

Description

technical field [0001] The invention belongs to the quality prediction technology in the field of regression technology, and in particular relates to a capillary quality prediction method based on an improved ELM algorithm. Background technique [0002] As the first process of seamless steel pipe production, piercing has a very important impact on the quality of steel pipes; the quality problems caused by the piercing process will not be alleviated in the subsequent process, but will cause more serious quality problems of steel pipes; so , the establishment of a capillary quality prediction model using the collected perforation process data has very important guiding significance for the steel rolling process; common prediction methods are mainly based on time series method, Kalman filter method, neural network, support vector machine (SVM), etc.; The prediction results of the time series method are unstable, and its model parameters are difficult to determine; the neural ne...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the capillary quality prediction method in the prior art that the sample data has noise interference and the prediction result of the ELM model is unstable, the present invention proposes a capillary quality prediction method based on the improved ELM algorithm to achieve the purpose of improving the accuracy of capillary prediction

Images