Prediction modeling of cigarette ventilation rate based on genetic algorithm backpropagation (GABP) neural network

The ventilation rate of cigarettes is an important indicator that affects the internal quality of cigarettes. When producing cigarettes, the unit may experience unstable ventilation rates, which can lead to a decrease in cigarette quality and pose certain risks to smokers. By establishing the ventil...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:EURASIP journal on advances in signal processing Ročník 2024; číslo 1; s. 25 - 14
Hlavní autori: Wei, Jiaxin, Wang, Zhengwei, Li, Shufang, Wang, Xiaoming, Xu, Huan, Wang, Xiushan, Yao, Sen, Song, Weimin, Wang, Youwei, Mei, Chao
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 22.02.2024
Springer Nature B.V
SpringerOpen
Predmet:
Artificial neural networks
Back propagation
Back propagation networks
BP neural network
Cigarettes
Design improvements
Design parameters
Engineering
Genetic algorithms
Genetics algorithm
Multiple linear regression
Neural networks
Prediction models
Predictions
Quantum Information Technology
Signal Processing and Machine Learning in Autonomous Systems
Signal,Image and Speech Processing
Spintronics
Stability
Technical services
Tobacco
Ventilation
Ventilation rate
Tobacco
BP neural network
Genetics algorithm
Multiple linear regression
Ventilation rate
ISSN:1687-6180, 1687-6172, 1687-6180
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The ventilation rate of cigarettes is an important indicator that affects the internal quality of cigarettes. When producing cigarettes, the unit may experience unstable ventilation rates, which can lead to a decrease in cigarette quality and pose certain risks to smokers. By establishing the ventilation rate prediction model, guide the design of unit parameters in advance, to achieve the goal of stabilizing unit ventilation rate, improve the stability of cigarette ventilation rate, and enhance the quality of cigarettes. This paper used multiple linear regression networks (MLR), backpropagation neural networks (BPNN), and genetic algorithm-optimized backpropagation (GABP) to construct a model for the prediction of cigarette ventilation rate. The model results indicated that the total ventilation rate was significantly positively correlated with weight ( P  < 0.01), circumference, hardness, filter air permeability, and open resistance. The results showed that the MLR models' (RMSE = 0.652, R 2  = 0.841) and the BPNN models’ (RMSE = 0.640, R 2  = 0.847) prediction ability were limited. Optimization by genetic algorithm, GABP models were generated and exhibited a little better prediction performance (RMSE = 0.606, R 2  = 0.873). The results indicated that the GABP model has the highest accuracy in the prediction of predicting ventilation rate and can accurately predict cigarette ventilation rate. This method can provide theoretical guidance and technical support for the stability study of the ventilation rate of the unit, improve the design and manufacturing capabilities and product quality of short cigarette products, and help to improve the quality of cigarettes.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/s13634-024-01119-1