Smart Manufacturing of Pulp and Paper: Advanced Machine Learning Enabled Multi-Objective Control for Energy Efficient Operation of Brownstock Washing
Project Lead: Auburn University
Partners: Rayonier Advanced Materials
Member % Cost Share: 49.6%
CESMII % Cost Share: 50.4%
Duration: 18 Months
Problem Statement
The US pulp and paper industry offers huge opportunity for CESMII to develop and deploy SM technologies to significantly improve the energy efficiency and the global competitiveness of the industry
Project Goal
Radically accelerate the development and adoption of advanced sensors, controls, platforms, and models to enable SM in the US pulp and paper industry. Statistics pattern analysis (SPA) enhanced ML soft sensor (SPA- ML) for entrained air content and the corresponding advanced multi- objective model predictive control (MPC) for defoamer dosing, wash water flow, and washed pulp quality of brownstock washing will be developed, tested and analyzed using data collected from Rayonier Advanced Material Jesup Plant, the largest cellulose specialties manufacturing plant in the world with several sets of brownstock washer lines
Technical Approach
Using SPA framework to build the SPA-ML soft sensor which is then used to enable multi-objective model MPC for brownstock washing and carrying out techno-economic analysis (TEA) to quantify its energy savings and cost benefits.
Deliverables/Outcomes/SM Marketplace
-
Delivered Machine Learning enabled soft sensor algorithms to monitor entrained air content.
-
Delivered multi-objective model predictive control solutions for brownstock washing.
-
Tested and validated the effect of reducing defoamer flow while monitoring entrained air content and drum speed at Rayonier.
-
Developed and deployed a machine learning based soft sensor for entrained air content for pulp and paper manufacturing. The sensor is reusable for modelling and control across a range of manufacturing processes.
-
Developed a soft sensor mathematical model and method for detecting entrained air content.
Potential Impact
Improve washing efficiency by 15% or reduce energy consumption in recovery evaporation in U.S. kraft mills by around 24.6 trillion Btu while reducing defoamer usage by 20%, providing the industry with a unique opportunity to both reduce cost and improve environmental sustainability
Benefits
- Develop and deploy SM solutions to ALL major processes in pulp and paper manufacturing that are reusable for process modeling and control across a wide range of high-energy consumption manufacturing processes, building on the SM Platform core technologies.
- Train several Ph.D. students on SM in the areas of advanced ML sensing, data analytics, and model-based control and optimization of pulp and paper processes in close collaboration with our industry partners throughout this project
