Online monitoring and fault diagnosing method for mixing and flavouring process of cigarette filament production based on principal component analysis

Abstract

The invention discloses an online monitoring and fault diagnosing method for a mixing and flavouring process of cigarette filament production based on principal component analysis. The online monitoring and fault diagnosing method aims at a problem of incapability of accurately monitoring and diagnosing caused by multiple batches, low time varying speed, unequal data length and high product diversity in key equipment such as tobacco leaf mixer and KAS flabouring machine in the mixing and flavouring process. Firstly, through analyzing the characteristic of the mixing and flavouring process, operation data with batch characteristic, time characteristic and attribute characteristic are expanded in an attribute direction, and a problem of unequal data length is overcome. Secondly, a monitoring model for each cigarette filament product brand is established based on multiple model structures according to a principal component analysis (PCA) method, and T2, SPE accountancy capability and control domain of each brand of monitoring model are computed in an offline manner. Afterwards, the operation data of the mixing and flavouring process are acquired in an online manner, and a corresponding monitoring model is called according to the product brand for computing the T2 and the SPE accountancy capability in the online manner. Finally, fault diagnosis is performed on the control domain in which a random index exceeds that of a normal operation area according to a contribution chart method.

Description

technical field [0001] The invention relates to an on-line monitoring and fault diagnosis technology of a blending and flavoring section in a cigarette shred process, in particular to an on-line monitoring and fault diagnosis method of a shredded leaf blending machine and a flavoring machine. Background technique [0002] my country's tobacco leaf output and cigarette output both rank first in the world, and tobacco taxation accounts for about 8% of the government's fiscal revenue. However, due to the globalization of the tobacco industry, new laws and regulations, and major changes in the external environment in recent years, China Tobacco is facing increasingly severe competitive and social pressures. Under the premise of ensuring product quality, effectively improving the intelligence level and efficient operation of equipment has become the focus of cigarette factories. The level of intelligence refers to the strength of the perception, analysis, reasoning, and decision...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems existing in the prior art, the present invention provides an on-line monitoring and fault diagnosis method for shredded cigarette blending and flavoring section based on principal component analysis. This method introduces the three-dimensional data analysis method oriented to the batch process In the online monitoring and fault diagnosis of the flavoring section, through T 2 The two multivariate statistics of SPE and SPE are used to monitor faults online, and the main process variables that cause faults are determined through the contribution graph method, which better solves the problem of blending and flavoring caused by multiple batches, slow time-varying, unequal length of data, and product diversity. The reliability and accuracy of segment monitoring and diagnosis results are not high

Images