Multi-objective optimization of steam and water flow parameters in loose and condition processes

Loosening and conditioning is one of the important processes in cigarette production, which converts tobacco chunks into tobacco leaves through the action of steam and water. Steam and water are the main energy consumption in this process. To achieve energy conservation and consumption reduction in the production process, while ensuring that process indicators such as tobacco moisture and temperature remain unchanged, the flow of steam and water during the production process should be minimized as much as possible. Based on actual working conditions, a combination of Seagull algorithm optimized backpropagation neural network modeling and multi-objective Golden Eagle optimization algorithm was proposed to solve the minimum flow parameters of steam and water. Through experimental comparison and analysis, Seagull algorithm optimized backpropagation neural network compared with genetic algorithm and particle swarm optimization algorithm has good accuracy in establishing such engineering problem models; Compared with the traditional multi-objective particle swarm optimization algorithm and the non dominated sorting genetic algorithm II, the multi-objective Golden Eagle optimization algorithm has more uniform Pareto solution distribution and stronger optimization ability through Hypervolume verification. As the set parameter of steam and water flow, its solution can effectively achieve energy saving and consumption reduction in the actual production process.