面向轮胎制造企业的能耗优化方法研究

发布时间：2018-10-31 20:56

【摘要】：随着能源价格的不断上涨和环境问题的日益突出,传统制造业的发展正受到能源成本和环境问题的双重制约。轮胎制造业是高耗能、高污染的企业,通过降低生产过程中的能源消耗来减少能耗成本是企业进行成本控制的有效手段之一。生产调度作为生产管理的重要组成部分,是企业实现节能减排的潜在方向。针对轮胎密炼车间的机器调度优化策略未考虑能耗因素的问题,建立了基于影响因子的能耗优化模型,该模型将总完成时间和能耗成本作为构成要素,以这两个要素的综合成本作为求解目标,同时,加入影响因子表示生产中对时间和能耗成本的关注程度。对于已建立的能耗优化模型,本文设计了一种改进的自适应遗传算法(Another Adaptive Genetic Algorithm, AAGA)对调度优化问题进行求解。AAGA算法在分析“早熟”原因的基础上,提出对每一代群体个体差异程度进行评价的方法,然后根据该评价指标在种群进化过程中动态地调整每一代群体的交叉和变异概率的上下限。同时,每一代群体中个体的交叉和变异概率根据个体适应性自适应调整。基于上述交叉和变异策略,采用Tillard提供的流水车间数据集进行实验,实验结果表明,AAGA算法能够搜索到更优的解。最后,结合实际生产数据,应用上述所提算法对能耗优化问题进行求解,对比数据表明 AAGA 与 SGA (Simple Genetic Algorithm,SGA)和 AGA (Adaptive Genetic Algorithm,AGA)的应用效果相比具有一定优势。进一步,采用AAGA算法对基于影响因子的能耗优化模型进行验证,说明本文建立的能耗优化模型对影响因子的不同取值,可以达到不同程度的节能效果。
[Abstract]:With the rising of energy price and the increasing of environmental problems, the development of traditional manufacturing industry is restricted by energy cost and environmental problems. Tire manufacturing industry is a high energy consumption and high pollution enterprise. It is one of the effective means to reduce the energy consumption cost by reducing the energy consumption in the production process. As an important part of production management, production scheduling is the potential direction for enterprises to achieve energy saving and emission reduction. Aiming at the problem that the energy consumption factor is not considered in the machine scheduling optimization strategy of tire mill workshop, the energy consumption optimization model based on the influence factor is established. The total completion time and energy consumption cost are taken as the constituent elements in the model. The comprehensive cost of these two elements is taken as the goal to solve the problem. At the same time, the influence factor is added to indicate the degree of attention to the cost of time and energy consumption in production. For the established energy consumption optimization model, an improved adaptive genetic algorithm (Another Adaptive Genetic Algorithm, AAGA) is designed to solve the scheduling optimization problem. The AAGA algorithm is based on the analysis of the causes of precocity. A method for evaluating the degree of individual difference in each generation is proposed, and then the upper and lower limits of crossover and variation probability of each generation are dynamically adjusted according to the evaluation index during the evolution of the population. At the same time, the crossover and mutation probability of each generation is adaptively adjusted according to individual adaptability. Based on the above crossover and mutation strategies, the flow shop data set provided by Tillard is used to experiment. The experimental results show that the AAGA algorithm can find a better solution. Finally, the energy consumption optimization problem is solved by using the proposed algorithm based on the actual production data. The comparison data show that the application effect of AAGA, SGA (Simple Genetic Algorithm,SGA) and AGA (Adaptive Genetic Algorithm,AGA) has some advantages. Furthermore, the AAGA algorithm is used to verify the energy consumption optimization model based on the influence factor, which shows that the energy consumption optimization model established in this paper can achieve different energy saving effects.
【学位授予单位】：西安理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TQ330.8;TP18

【参考文献】