共查询到18条相似文献,搜索用时 78 毫秒
1.
转炉炼钢是钢铁企业的主要耗氧工序, 预测转炉炼钢的氧气消耗量对氧气系统合理调度、保证生产安全具有重要意义. 考虑到转炉冶炼工况多、钢种数据粒度不统一, 提出一种基于粒度聚类的转炉炼钢氧气消耗量预测方法. 首先, 利用孤立森林异常检测法剔除历史数据库中的异常数据; 接着, 采用皮尔逊相关性分析和互信息相关系数选取相关影响因子, 对不同钢种数据进行信息粒化, 实现数据特征提取和维度统一, 使用模糊C均值(Fuzzy C-means, FCM) 划分工况并建立不同工况下的氧气消耗量预测子模型; 最后, 利用企业的实际生产数据进行实验, 验证所提方法的准确性和有效性. 相似文献
2.
3.
基于PSO优化的SVM预测应用研究* 总被引:5,自引:2,他引:5
支持向量机参数对支持向量机的性能有着重要影响,参数选择问题是支持向量机的重要研究内容。针对此问题,提出一种基于粒子群优化算法的支持向量机参数选择方法。实验结果表明,经粒子群优化算法优化的支持向量机回归模型具有较高的预测精度,粒子群优化算法是选取支持向量机参数的有效方法。 相似文献
4.
5.
基于PLC的转炉吹氧限压控制器 总被引:1,自引:0,他引:1
氧压自动控制是保证转炉炼质量的理想方案,笔者设计了一套转炉吹氧压力限压及信号联锁控制器。详细介绍自动限压的基本工作过程,控制器的软件、硬件设计。 相似文献
6.
7.
本文介绍了基于施耐德Quantum PLC的150t炼钢转炉自动化系统,从该转炉的工艺流程、技术要求和控制策略、系统解决方案和评价以及运行效果等方面进行了较为详细的描述。 相似文献
8.
9.
10.
11.
12.
13.
14.
15.
16.
针对转炉控制中对吹炼终点温度的控制问题,提出了基于混合递阶遗传RBF神经网络(HGA-RBF)的转炉炼钢终点温度预报模型。研究了RBF网络的特点,用递阶遗传算法克服了网络的结构和参数选择的随机性问题;并结合最小二乘法,提高了收敛速度。仿真结果表明,此算法在一定程度上提高了RBF网络的优化收敛速度和训练测试精度。某钢铁公司提供的实际冶炼数据试验。也证明了该模型预报精度较高,对提高生产的质量有重要意义。 相似文献
17.
In this paper, fuzzy modeling for the control of basic oxygen furnace (BOF) processes is proposed. BOF is a widely preferred and effective steel making method due to its higher productivity and considerably low production cost. Therefore, today almost 65% of the total crude steel production in the world is met by using the BOF method. Higher steel output at lower cost is one of the main objectives of modern steel making methods. In order to accomplish this objective, fuzzy modeling was employed in this study in order to control some variables related to the BOF process. Fuzzy modeling and control in BOF promise a solution to the strongly non-linear problems associated with the process, which have so far proven extremely difficult to be solved by conventional control methods. Data set was selected as inputs from the real empirical BOF data in an integrated steel plant based in Turkey. Although there were negligible deviations from the target values, most of the fuzzy results obtained using MATLAB-Fuzzy Logic Toolbox version 5.0 were found to be acceptable. As a result of the application of the proposed modeling, acceptable levels of compatibility were achieved compared to the empirical BOF data and targeted steel composition. The paper indicates how fuzzy logic would be effectively used for improved process control of BOF furnace in steel making industry. 相似文献