Research on state prediction method of tobacco curing process based on model fusion

Wang, Yichao; Qin, Lang

doi:10.1007/s12652-021-03129-5

Cited by 12 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SPFM improved the model training process was 97.4% of accuracy, 99.7% precision, 99.7% recall, and 99.7% F1-Score. This performance indicates that this model is very good at controlling the tobacco curing process [4].…”

Section: Introductionmentioning

confidence: 71%

Defect classification of radius shaping in the tire curing process using Fine-Tuned Deep Neural Network

Iklima

Rohman

Muwardi

et al. 2022

Sinergi

View full text Add to dashboard Cite

The curing process or vulcanization process is the final stage of the tire manufacturing process, where the properties of the tire compound change from rubber-plastic material to become elastic by forming cross-links in its molecular structure. The green tire is formed in the curing process, which is placed on the bottom mould. The inside of the green tire surrounds the bladder. The top mould will close to carry out the next curing process. In closing the mould, there is a shaping process of forming a green tire placed on the bladder and given a proportional pressure. Improper or abnormal radius shaping results cause seventy percent of product defects. This paper proposed abnormal detection of radius shaping in the curing process using Fine-tuned Deep Neural Network (DNN). Several DNN models have been examined to analyze an optimized DNN model for abnormal detection of radius shaping in the curing process. The fine-tuned DNN architecture has been exported for the curing system. The DNN was trained with a training accuracy of 97.88%, a validation accuracy of 95%, a testing accuracy of 100%, and a loss of 4.93%.

show abstract

Section: Introductionmentioning

confidence: 71%

Defect classification of radius shaping in the tire curing process using Fine-Tuned Deep Neural Network

Iklima

Rohman

Muwardi

et al. 2022

Sinergi

View full text Add to dashboard Cite

show abstract

“…These data will be transmitted to the data processing center for unified processing and formed into a new dataset. The function of a deep learning server is to use these datasets for model training, in order to achieve spectrum prediction [28].…”

Section: B Communication Spectrum State Prediction Based On Cnn-lstm ...mentioning

confidence: 99%

Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference

Tian,

Yu,

Bai

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The continuous development of communication technology and various deep learning models has led to the invention and application of many anti-interference technologies in the field of communication countermeasures. The existing communication interference models have defects such as low anti-interference rate and low accuracy in communication spectrum prediction. To solve these problems, this study attempts to construct a Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and apply it to the communication jamming system for spectrum state prediction. Firstly, the framework of the communication interference system using the USRP RIO radio platform software was designed, and based on it, the communication interference channel was optimized using reinforcement learning Q-learning algorithm. Next, to further predict the signal spectrum state during the communication process, neural networks are utilized to construct a communication spectrum state prediction model.According to the optimization effect of communication interference channel and network spectrum prediction effect tested, the communication model under the Q-learning algorithm can achieve a 100% effective interference probability in fixed communication strategies. The Convolutional Neural Networks-1 Long-Short Term Memory-2 model has a prediction accuracy of 95.2% and can accurately predict changes in the communication spectrum. In summary, the Convolutional Neural Networks-1 Long-Short Term Memory-2 network constructed by this research can provide new solutions and achieve goodresultsfor communication spectrum prediction.

show abstract

“…In the research on the intelligent control of the bulk tobacco flue-curing process, artificial neural network-based approaches were commonly used [6,7]. Wang and Qin [8] built a state prediction fusion model integrating long-short term memory (LSTM) and extreme gradient boosting (XGBoost) to predict the state of the tobacco curing, and make timely adjustments to the curing process. An improved multi-sequence multi-grained cascade forest model was proposed to classify and identify different tobacco drying conditions in [9].…”

Section: Related Workmentioning

confidence: 99%

Modeling of the Bulk Tobacco Flue-Curing Process Using a Deep Learning-Based Method

Yang

2021

IEEE Access

View full text Add to dashboard Cite

The research of the bulk tobacco flue-curing process is helpful to model the intelligent bulk curing system, which is designed to implement the curing procedure without manual operation. An intelligent bulk curing method based on the convolutional neural network (CNN) named TobaccoNet was proposed, which could set the target dry-bulb temperature (TD) and the target wet-bulb temperature (TW) of the bulk curing barn according to the tobacco leaves image. The performance of the TobaccoNet is compared with the traditional manual image feature extraction method, the stacked-sparse-autoencoder (SSAE)-based deep learning method, and the other two methods applied in related references. The test results show that TobaccoNet outperforms the comparison methods in predicting TD and TW. Specifically, the correlation coefficient reaches 0.9965 and 0.9683, the mean relative error is 1.62% and 1.77%, and the root mean squared error achieves 1.061 °C and 0.8581 °C respectively. The promising results demonstrate that the TobaccoNet is effective and reliable for modeling the intelligent bulk tobacco flue-curing process. The influence of different CNN structures on the prediction accuracy of TD and TW was analyzed. From the perspective of the computational complexity and the prediction performance, the proposed sequential CNN structure is more suitable for analyzing bulk tobacco curing in this study.INDEX TERMS Convolutional neural network, bulk tobacco flue-curing, tobacco leaves, deep learning.

show abstract

Research on state prediction method of tobacco curing process based on model fusion

Cited by 12 publications

References 21 publications

Defect classification of radius shaping in the tire curing process using Fine-Tuned Deep Neural Network

Defect classification of radius shaping in the tire curing process using Fine-Tuned Deep Neural Network

Application of Spectrum State Prediction Method Based on CNN-LSTM Network in Communication Interference

Modeling of the Bulk Tobacco Flue-Curing Process Using a Deep Learning-Based Method

Contact Info

Product

Resources

About