基于改进型鲸鱼优化算法和最小二乘支持向量机的炼钢终点预测模型研究
|
摘要
终点碳含量是决定钢质量的关键因素,是转炉炼钢过程中需要控制的核心变量之一.本文建立了一种基于莱维飞行的鲸鱼优化算法(Levy Whale Optimization Algorithm,LWOA)和最小二乘向量机(Least Squares Support Vector Machine,LSSVM)的钢水终点碳含量综合预测模型.通过莱维飞行代替了传统鲸鱼优化算法(Whale Optimization Algorithm,WOA)参数的随机选择,优化了鲸鱼算法中跳出局部最优的能力;借助改变鲸鱼算法的系数向量收敛方式明显提高了鲸鱼优化算法的泛化能力、预测精度和收敛速度.数据仿真结果表明,所提出的LWOA-LSSVM预测模型,不仅能够克服局部寻优获取全局最优解,而且具有快速的收敛速度和更高的预测精度,得出预测结果的均方根误差、平均绝对误差和平均绝对百分比误差与遗传算法BP神经网络、遗传算法最小二乘支持向量机和传统鲸鱼算法最小二乘支持向量机相比均有着明显提高.同时,通过调整目标命中率和训练输入样本量验证了预测模型具有更好的鲁棒性.
The final carbon content is the key factor in determining the quality of steel,and is one of the core variables to be controlled in the process of converter steel-making.Based on the Levy whale optimization algorithm(LWOA) and least squares support vector machine(LSSVM),a comprehensive prediction model of carbon content at the end of the steel-making process is established.When the random selection of the parameters of the traditional whale optimization algorithm(WOA) is replaced with the Levy flight algorithm,the ability to jump out of the local optimum is optimized.Changing the method of coefficient vector convergence results in improvements to the generalization ability,prediction precision and convergence speed of the WOA.Data simulation results show that the proposed LWOA-LSSVM forecasting model not only overcomes the local optimization to obtain the global optimal solution,but also achieves faster convergence speed and higher prediction accuracy.Prediction results of the model,concerning root mean square error,mean absolute error,and mean absolute percentage error,show noticeable improvements when compared to those of the genetic algorithm and back propagation(BP) neural network,the genetic algorithm and LSSVM,and the traditional WOA and LSSVM.At the same time,through adjustments of the target hit ratio and the number of training sample entries,the prediction model is proven to be more robust than the aforementioned algorithms.
The final carbon content is the key factor in determining the quality of steel,and is one of the core variables to be controlled in the process of converter steel-making.Based on the Levy whale optimization algorithm(LWOA) and least squares support vector machine(LSSVM),a comprehensive prediction model of carbon content at the end of the steel-making process is established.When the random selection of the parameters of the traditional whale optimization algorithm(WOA) is replaced with the Levy flight algorithm,the ability to jump out of the local optimum is optimized.Changing the method of coefficient vector convergence results in improvements to the generalization ability,prediction precision and convergence speed of the WOA.Data simulation results show that the proposed LWOA-LSSVM forecasting model not only overcomes the local optimization to obtain the global optimal solution,but also achieves faster convergence speed and higher prediction accuracy.Prediction results of the model,concerning root mean square error,mean absolute error,and mean absolute percentage error,show noticeable improvements when compared to those of the genetic algorithm and back propagation(BP) neural network,the genetic algorithm and LSSVM,and the traditional WOA and LSSVM.At the same time,through adjustments of the target hit ratio and the number of training sample entries,the prediction model is proven to be more robust than the aforementioned algorithms.
引文
[1] 冯捷,张红文.转炉炼钢生产[M].北京:冶金工业出版社,2006.332-338.
[2] Daniel M.Mass spectrometry for oxygen steelmaking control[J].Steel Times,1997,225(11):439-440.
[3] 温宏愿,赵琦,等.基于炉口辐射和改进神经网络的转炉终点预测模型[J].光学学报,2008,28(11):2131-2135.Wen Hong-yuan,Zhao Qi,et al.Basic-oxygen-furnace endpoint forecasting model based on radiation and modified neural network[J].Acta Optica Sinica,2008,28(11):2131-2135.(in Chinese)
[4] 谢书明,陶钧,柴天佑.基于神经网络的转炉炼钢终点控制[J].控制理论与应用,2003,20(6):903-907.Xie Shu-ming,Tao Jun,Chai Tian-you.BOF steelmaking endpoint control based on neural network[J].Control Theory & Applications,2003,20(6):903-907.(in Chinese)
[5] 程进,王坚.基于多任务学习的炼钢终点预测方法[J].计算机应用,2017,37(3):889-895.Cheng Jin,Wang Jian.Endpoint prediction method for steelmaking based on multi-task learning[J].Journal of Computer Applications,2017,37(3):889-895.(in Chinese)
[6] 吴虎胜,张凤鸣,吴庐山.一种新的群体智能算法——狼群算法[J].系统工程与电子技术,2013,35(11):2430-2438.Wu Hu-sheng,Zhang Feng-ming,Wu Lu-shan.New swarm intelligence algorithm—wolf pack algorithm[J].Systems Engineering and Electronics,2013,35(11):2430-2438.(in Chinese)
[7] 严良涛,李鸣,杨大勇.基于GA-KPLSR的转炉终点碳含量的预测研究[J].控制工程,2017,24(5):923-926.Yan Liang-tao,Li Ming,Yang Da-yong.Prediction of carbon content at end point based on GA-KPLSR in converters[J].Control Engineering of China,2017,24(5):923-926.(in Chinese)
[8] 杨普,杨杰.转炉炼钢终点控制技术现状研究[J].山西冶金,2017,24(4):53-54,57.Yang Pu,Yang Jie.Research onend-point control technology of converter steelmaking[J].Shanxi Metallurgy,2017,24(4):53-54,57.(in Chinese)
[9] 王庆喜,郭晓波.基于莱维飞行的粒子群优化算法[J].计算机应用研究,2016,33(9):2588-2591.Wang Qing-xi,Guo Xiao-bo.Particle swarm optimization algorithm based on Levy flight[J].Application Research of Computers,2016,33(9):2588-2591.(in Chinese)
[10] 牛培峰,吴志良,马云鹏,等.基于鲸鱼优化算法的汽轮机热耗率模型预测[J].化工学报,2017,68(3):1049-1057.Niu Pei-feng,Wu Zhi-liang,Ma Yun-peng,et al.Prediction of steam turbine heat consumption rate based on whale optimization algorthm [J].Ciesc Journal,2017,68(3):1049-1057.(in Chinese)
[11] Seyedali M,Andrew L.The whale optimization algorithm [J].Advances in Engineering Software,2016,95(5):51-67.
[12] Kennedy J,Eberhart R.Particle swarm optimization[A].Proceedings of IEEE International Conference on Neural Networks[C].Perth,Australia:IEEE,1995.1942-1948.
[13] Dorigo M,Maniezzo V.Ant system:optimization by a colony of cooperating agents[J].IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics,1996,26(1):29-41.
[14] Karaboga D.AnIdea Based on Honey Bee Swarm for Numerical Optimization[R].Kayseri Turkey:Erciyes University,2005.1-10.
[2] Daniel M.Mass spectrometry for oxygen steelmaking control[J].Steel Times,1997,225(11):439-440.
[3] 温宏愿,赵琦,等.基于炉口辐射和改进神经网络的转炉终点预测模型[J].光学学报,2008,28(11):2131-2135.Wen Hong-yuan,Zhao Qi,et al.Basic-oxygen-furnace endpoint forecasting model based on radiation and modified neural network[J].Acta Optica Sinica,2008,28(11):2131-2135.(in Chinese)
[4] 谢书明,陶钧,柴天佑.基于神经网络的转炉炼钢终点控制[J].控制理论与应用,2003,20(6):903-907.Xie Shu-ming,Tao Jun,Chai Tian-you.BOF steelmaking endpoint control based on neural network[J].Control Theory & Applications,2003,20(6):903-907.(in Chinese)
[5] 程进,王坚.基于多任务学习的炼钢终点预测方法[J].计算机应用,2017,37(3):889-895.Cheng Jin,Wang Jian.Endpoint prediction method for steelmaking based on multi-task learning[J].Journal of Computer Applications,2017,37(3):889-895.(in Chinese)
[6] 吴虎胜,张凤鸣,吴庐山.一种新的群体智能算法——狼群算法[J].系统工程与电子技术,2013,35(11):2430-2438.Wu Hu-sheng,Zhang Feng-ming,Wu Lu-shan.New swarm intelligence algorithm—wolf pack algorithm[J].Systems Engineering and Electronics,2013,35(11):2430-2438.(in Chinese)
[7] 严良涛,李鸣,杨大勇.基于GA-KPLSR的转炉终点碳含量的预测研究[J].控制工程,2017,24(5):923-926.Yan Liang-tao,Li Ming,Yang Da-yong.Prediction of carbon content at end point based on GA-KPLSR in converters[J].Control Engineering of China,2017,24(5):923-926.(in Chinese)
[8] 杨普,杨杰.转炉炼钢终点控制技术现状研究[J].山西冶金,2017,24(4):53-54,57.Yang Pu,Yang Jie.Research onend-point control technology of converter steelmaking[J].Shanxi Metallurgy,2017,24(4):53-54,57.(in Chinese)
[9] 王庆喜,郭晓波.基于莱维飞行的粒子群优化算法[J].计算机应用研究,2016,33(9):2588-2591.Wang Qing-xi,Guo Xiao-bo.Particle swarm optimization algorithm based on Levy flight[J].Application Research of Computers,2016,33(9):2588-2591.(in Chinese)
[10] 牛培峰,吴志良,马云鹏,等.基于鲸鱼优化算法的汽轮机热耗率模型预测[J].化工学报,2017,68(3):1049-1057.Niu Pei-feng,Wu Zhi-liang,Ma Yun-peng,et al.Prediction of steam turbine heat consumption rate based on whale optimization algorthm [J].Ciesc Journal,2017,68(3):1049-1057.(in Chinese)
[11] Seyedali M,Andrew L.The whale optimization algorithm [J].Advances in Engineering Software,2016,95(5):51-67.
[12] Kennedy J,Eberhart R.Particle swarm optimization[A].Proceedings of IEEE International Conference on Neural Networks[C].Perth,Australia:IEEE,1995.1942-1948.
[13] Dorigo M,Maniezzo V.Ant system:optimization by a colony of cooperating agents[J].IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics,1996,26(1):29-41.
[14] Karaboga D.AnIdea Based on Honey Bee Swarm for Numerical Optimization[R].Kayseri Turkey:Erciyes University,2005.1-10.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |