.png){kind=icon}
Return
Collaborative Optimization Framework for the Industrial Thickening–Dewatering Process Based on Mixed Integer Linear Programming
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2023.3305660.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Reducing the economic expenditure on electricity in the thickening-dewatering process is a viable approach to enhancing production efficiency and minimizing energy consumption. However, limited research has been conducted on co-optimization strategies for this process thus far. To address this gap and decrease the energy economic index (EEI) in the thickening-dewatering process, this work introduces a collaborative optimization framework. This work begins by developing a process model capable of simulating the thickening-dewatering process, thereby addressing the issue of insufficient ON-site production data. Leveraging the operational data generated by the process model, data-driven predictive models are constructed to facilitate the formulation of an explicit optimization model. Subsequently, a continuous-time mixed integer linear programming (MILP) problem is established to optimize the process, with the objective of minimizing the EEI while accounting for process safety and electricity price constraints. Finally, the collaborative optimization framework is applied to a gold hydrometallurgy plant, yielding significant improvements. The process achieves a 58.67% reduction in EEI compared with manual operations, alongside a 53.62% reduction in equipment operation time.
Keywords:
Optimization
Collaboration
Process control
Production
Predictive models
Slurries
Task analysis
Batch process
collaborative optimization
ladder electricity prices
mixed integer linear programming (MILP)
thickening-dewatering process
Journal
IF:
5.9
Papers:
2.0W
Citations:
5.8W
Organization
Cited Papers
Image-based thickener mud layer height prediction with attention mechanism-based CNN.png)
ISA TRANSACTIONS
ISA TRANSACTIONSIF6.5
PREAI
ShareSaveShareSaveShareSaveAn effective energy management Layout-Based reinforcement learning for household demand response in digital twin simulationSOLAR ENERGY
SOLAR ENERGYIF6.6
PREAI
ShareSaveShareSave
ShareSaveShareSave
View more