共查询到20条相似文献,搜索用时 171 毫秒
1.
2.
3.
4.
冷连轧机轧制力人工神经网络预报 总被引:2,自引:0,他引:2
采用改进的BP网络Levenberg-Marquardt优化算法对冷连轧机轧制力进行快速预报,此网络参量可自适应调整,收敛速度快.冷连轧生产轧制力预报精度大为提高,为冷连轧轧制力预报提供了一条准确高效的新途径. 相似文献
5.
6.
针对不锈钢冷连轧生产工艺,提出动态变形抗力概念,利用四辊可逆冷轧机和Inston高速拉伸实验机进行轧制-拉伸实验,在MMS-200热模拟实验机上测定不锈钢的应力-应变曲线,建立不锈钢动态变形抗力模型。在Hill方程的基础上建立了轧制力显函数模型,并通过变形抗力和摩擦因数的逆向回归计算实现模型的在线自学习。提出了适合轧制力模型的可信度评估方法,引入Theil不等式系数法,依据TIC值定性分析了模型的适用性。最终确立了适合于冷连轧生产的精确的轧制力显函数模型,并将其应用到生产实践中。统计结果表明:冷连轧过程中轧制力的模型计算值与实测值的相对误差小于3.67%,该模型具有良好的计算精度和较好的泛化能力,适合于工业生产实践。 相似文献
7.
8.
五机架冷连轧机轧制人工神经网络预报 总被引:1,自引:1,他引:0
采用改进的BP网络Levenberg-Marquardt优化算法对冷连轧机轧制力进行快速预报,该网络μ参量可自适应调整,收敛速度快。冷连轧生产轧制力预报精度大为提高,为冷连轧轧制力预报提供了一条准确高效的新途径。 相似文献
9.
10.
11.
12.
13.
The rolling force model for cold tandem mill was put forward by using the Elman dynamic recursive network method,based on the actual measured data.Furthermore,a good assumption is put forward,which brings a full universe of discourse self-adjusting factor fuzzy control,closed-loop adjusting,based on error feedback and expertise into a rolling force prediction model,to modify prediction outputs and improve prediction precision and robustness.The simulated results indicate that the method is highly effective and the prediction precision is better than that of the traditional method.Predicted relative error is less than ±4%,so the prediction is high precise for the cold tandem mill. 相似文献
14.
Based on rolling feature of continuous tandem cold rolling mill, such as multi-variable, strong coupling, non-linear, analyze and set the equal relative load, preventing slippage and profile well as the multi-objective optimization goal, BP neural network with self-learning function is adopted to replace traditional rolling force models and then Levenberg-Marquardt algorithm is adopted to predict the rolling force. Then use multi-objective fuzzy theory to solve the problem of multi-objective optimization of tandem cold rolling schedule. With the example of 1370mm tandem cold rolling, the rolling schedule of the common rolling, the single-object optimization design and the multi-objective fuzzy optimization design are compared with each other, optimization result shows the proposed optimization method decreases the value of three objective functions simultaneous. The performance of the optimal rolling schedule is satisfying and it is promising. 相似文献
15.
16.
摘要:轧制力是影响中厚板厚度精度和板型的关键因素。兴澄特钢中厚板轧机二级模型采用传统Sims公式计算轧制力,精度较低。为提高轧制力预报精度,首先基于大量历史生产数据,通过主成分分析法对影响轧制力的因素进行处理和分析,选出权重较大的影响因子;其次选取现场代表钢种进行热模拟压缩实验,在此基础上提出基于极限学习机(ELM)的综合神经网络轧制力预报模型,即先通过化学成分计算出基准变形抗力,再将其作为轧制力神经网络输入变量进行轧制力预报。建模采用10折10次交叉验证确定最佳网络隐层节点数,并用现场实际生产过程数据对网络进行训练与测试。综合神经网络模型投入现场生产,轧制力预报相对误差±10%以内占比提高15.61%,钢板头部厚度命中率提高1.9%。 相似文献
17.
18.
19.
20.
基于人工智能的自适应板形控制 总被引:1,自引:0,他引:1
针对板带材轧制过程是一个复杂的非线性过程及传统板形控制模型的固有缺陷,为了提高冷轧带钢的板形质量和成材率,提出一种基于神经网络模糊推理的自适应板形控制(AI-AFC)方案,并将其引入森吉米尔20辊轧机的板形控制系统。离线仿真结果表明:该系统具有良好的控制性能,可提高板形控制质量。 相似文献