Cigarette loose end rate prediction method and system based on improved gradient improvement decision tree

Abstract

The invention discloses a cigarette loose end rate prediction method based on an improved gradient improvement decision tree, which comprises the following steps: acquiring process parameters of tobacco shreds in the same batch in each process of tobacco shred making and loose end rate data in a final package process, and forming an original data set by the process parameters and the loose end rate data; dividing the original data set based on the original data set in combination with a correlation coefficient analysis method to obtain a key process parameter set; performing normalization processing on the data in the key process parameter set, and performing random division on the normalized data to obtain a training data set and a test data set; on the basis of training samples in the training data set, constructing an improved gradient improvement decision tree model; and inputting the test data set sample into the improved gradient improvement decision tree model, and predicting the cigarette empty head rate. A connection is established between each process parameter of the tobacco shred making process and the index of the cigarette packet vacancy rate, so that more accurate prediction of the cigarette vacancy rate is realized.

Description

technical field [0001] The invention relates to the technical field of cigarette short rate prediction, in particular to a cigarette short rate prediction method and system based on an improved gradient boosting decision tree. Background technique [0002] The crimping process is an important link in cigarette processing, and the quality of its process directly affects the quality and quality of shredded tobacco. However, in the actual production process, there will always be unavoidable cigarette shortfalls, resulting in waste of raw materials and efficiency; at present, the main method to solve the problem of cigarette shortfalls is to improve the cigarette machine itself and try to study the shredded process , but these methods can only be carried out in the form of small batch experiments, and the amount of data obtained is so small that it is impossible to discover more rules and better parameter standards, and cannot achieve the desired optimization effect. Therefore,...

AI Technical Summary

Problems solved by technology

Due to the large number of process parameters in the cigarette production process, the prediction method based on statistical regression takes a long time to calculate, and some important process parameters are often missed in the process of fitting the mathematical model, resulting in poor prediction accuracy

The prediction methods based on machine learning mainly include neural network, K nearest neighbor algorithm, etc. The application research of traditional BP neural network model in prediction has made great progress, but because the neural network model is a black box process, the interpretability of the model is not good. Strong, there are disadvantages such as slow convergence speed and poor generalization ability, and cannot achieve satisfactory prediction results

Images