Optimization of tobacco drying process control based on reinforcement learning

Abstract Drying is an important procedure in tobacco production. The current PID based drying suffers from issues such as overheating or inconsistent control of the amount of moisture content. In order to boost quality assurance, reinforcement learning has been employed in this paper to facilitate dynamic configuration of dryer. A novel actor-critic based intelligent system is built on top of the current PID control. The new data-centric approach collects environment and machine states, incorporates historical production data and learns temperature adjustment strategies. Compared to automatic PID control and manual intervention, the introduced intelligence proves to be remarkably more effective to govern the drying and control the moisture content level with consistent performance. The proposed method provides new insights into precision achievement in industrial control process.

• Publication year

  2020

• Venue

  Drying Technology

• Publication date

  2020-01-06

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1080/07373937.2019.1633662
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Prediction of energy and exergy of mushroom slices drying in hot air impingement dryer by artificial neural network

  2020cited by this paper
• Effect of high-humidity hot air impingement blanching (HHAIB) and drying parameters on drying characteristics and quality of broccoli florets

  2019cited by this paper
• Artificial intelligence: Is it a good fit for drying?

  2018cited by this paper
• Real-time monitoring of milk powder moisture content during drying in a spouted bed dryer using a hybrid neural soft sensor

  2018cited by this paper
• Evaluation of the air-borne ultrasound on fluidized bed drying of shelled corn: Effectiveness, grain quality, and energy consumption

  2018cited by this paper
• Intelligent control of a grain drying system using a GA-SVM-IMPC controller

  2018cited by this paper
• Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data

  2018cited by this paper
• Fast drying of cut tobacco in drop tube reactor and its effect on petroleum ether tobacco extracts

  2018cited by this paper
• Cubic-RBF-ARX modeling and model-based optimal setting control in head and tail stages of cut tobacco drying process

  2018cited by this paper
• Modeling of paper mill sewage sludge drying using artificial neural networks: Reduction of the training database through Taguchi’s method

  2017cited by this paper
• PID Heating and Temperature Control Method Based On Dynamic Assignment

  2017cited by this paper
• Desiccant wheel system modeling improvement using multiple population genetic algorithm training of neural network

  2017cited by this paper
• An adaptive neuro-fuzzy approach to bulk tobacco flue-curing control process

  2017cited by this paper
• Energy–exergy–ANN analyses of solar-assisted fluidized bed dryer

  2017cited by this paper
• Low-cost optical approach for noncontact predicting moisture content of apple slices during hot air drying

  2017cited by this paper
• A recurrent self-evolving fuzzy neural network predictive control for microwave drying process

  2016cited by this paper
• Effect of two-stage dehydration on retention of characteristic flavor components of flue-cured tobacco in rotary dryer

  2016cited by this paper
• Experimental and Numerical Investigation of the Heat and Mass Transfer for Cut Tobacco During Two-Stage Convective Drying

  2015cited by this paper
• Control of the Moisture Content of Milk Powder Produced in a Spouted Bed Dryer Using a Grey-Box Inferential Controller

  2015cited by this paper
• Study on the Effect of Cut Tobacco Drying on the Pyrolysis and Combustion Properties

  2014cited by this paper
• Fuzzy-PID Control Application in Temperature Automation Control System of Tunnel Kiln

  2013cited by this paper
• Action recognition with discriminative mid-level features

  2012cited by this paper
• Model-Free reinforcement learning with continuous action in practice

  2012cited by this paper
• A Hough transform-based voting framework for action recognition

  2010cited by this paper
• Drying process of tobacco leaves by using a fuzzy controller

  2005cited by this paper
• PID control system analysis, design, and technology

  2005cited by this paper
• Validation of a Model of an Expanding Superheated Steam Flash Dryer for Cut Tobacco Based on Processing Data

  2004cited by this paper
• Dynamic Characteristics of Solids Transportation in Rotary Dryers

  2003cited by this paper
• OnActor-Critic Algorithms

  2003cited by this paper
• Simple analytic rules for model reduction and PID controller tuning

  2003cited by this paper
• Random Forests

  2001cited by this paper
• The future of PID control

  2000cited by this paper
• Policy Gradient Methods for Reinforcement Learning with Function Approximation

  1999cited by this paper
• Reinforcement Learning: An Introduction

  1998cited by this paper
• An analysis of temporal-difference learning with function approximation

  1997cited by this paper
• Reinforcement Learning: A Survey

  1996cited by this paper
• DRYING OF TOBACCO PARTICLES IN A MOBILISED BED

  1994cited by this paper
• Neuronlike adaptive elements that can solve difficult learning control problems

  1983cited by this paper

• Prior knowledge enhanced graph attention network for real-time anomaly detection in tobacco drying processes

  2026cites this paper
• Application of zonal and segmented temperature control technology in rotary drum dryers: Platform design and experimental analysis for tobacco drying

  2026cites this paper
• Microwave drying characteristics of high-moisture tobacco based on a multi-physics model

  2026cites this paper
• Adaptive Tuning of Dynamic Matrix Control for Uncertain Industrial Systems With Deep Reinforcement Learning

  2025cites this paper
• An Interpretable Prediction Method for Tobacco Drying Process Based on CGTNN

  2025cites this paper
• Energy flow field analysis of comas tower dryer based on CFD simulation and experimentation

  2025cites this paper
• A hybrid method based optimal FOPID parameters for air heater temperature and humidity control system in industrial drying application

  2025cites this paper
• Modeling of HDT pneumatic drying machine for moisture control

  2025cites this paper
• How to support decision making with reinforcement learning in hierarchical chemical process control?

  2025cites this paper
• Model-based reinforcement learning with adversarial discriminative domain adaptation

  2025cites this paper
• AI-enhanced freeze-drying: Research progress and application prospects

  2025cites this paper
• RLGBS: Reinforcement Learning-Guided Beam Search for process optimization in a paper machine dryer section

  2025cites this paper
• Improvement of the tobacco drying process based on the combination of IQGA-ELM and Bayesian-optimized hysteresis-regulated sliding mode control strategy

  2025cites this paper
• Applications of Machine Learning Models in Agricultural Product Drying: A Comprehensive Review of Advances, Challenges, and Prospects

  2025cites this paper
• Research on Intelligent Control of Moisture at Loose Rehumidification Outlets Based on Big Data Analysis

  2025cites this paper
• Evolution of Drying Process Modeling: From Mathematical Foundations to Machine Learning‐Driven Prediction and Control

  2025cites this paper
• Double-Loop-Optimization-Based Joint Parameter Tuning for Dynamic Matrix Control With Validation in Intelligent Cigarette Drying Process

  2024cites this paper
• An improved AO algorithm optimized PID rectification model for wind speed and wind pressure regulation in video cabinet of tobacco sorting machine

  2024cites this paper
• Prediction of Tobacco Moisture Content Based on Improved Support Vector Regression Model

  2024cites this paper
• Construction of mathematical model of tobacco roaster based on mechanism analysis

  2024cites this paper
• Enhancing prior-knowledge-based control with deep attention neural network for outlet moisture content of cut-tobacco

  2024cites this paper
• Construction of water content prediction model for tobacco roaster based on back propagation neural network

  2024cites this paper
• An adaptive optimization method toward batch-wise variable set point of outlet moisture content for the tobacco drying process

  2023cites this paper
• Experimental study on condensate heat transfer coefficient of multi-channel cylinder dryer integrated with Bayesian-optimized machine learning prediction

  2023cites this paper
• Analysis of energy consumption of tobacco drying process based on industrial big data

  2023cites this paper
• Influences of cold atmospheric plasma pretreatment on drying kinetics, structural, fractional and chemical characteristics of tobacco leaves

  2022cites this paper
• The Tobacco Leaf Redrying Process Parameter Optimization Based on IPSO Hybrid Adaptive Penalty Function

  2022cites this paper
• Adaptive online learning for system identification and in-advance optimization under long feedback delay and concept drift in cigarette production

  2022cites this paper
• An intelligent moisture prediction method for tobacco drying process using a multi-hierarchical convolutional neural network

  2021cites this paper
• Uncertainty-Aware Data-driven Tobacco Loosening and Conditioning Process Moisture Prediction and Control Optimization

  2021cites this paper
• Structure Optimization of Outlet Uniformity for a Comas Tower Dryer

  2021cites this paper
• Deep multi-sequence multi-grained cascade forest for tobacco drying condition identification

  2021cites this paper
• Intelligent monitoring, predicting, and control technology of food drying: Recent advances, challenges, and future prospects

  year unknowncites this paper