摘要
球磨机是磨矿工业的关键设备,合理的球磨机负荷参数是其长期稳定运行的必要条件。球磨机筒体振动和振声信号蕴含了丰富的负荷信息,但是筒体振动和振声时域特征难以提取,频域的高维共线性导致磨机负荷模型复杂、泛化性差。通过SiPLS(synergy interval PLS)方法选择与磨机负荷参数密切相关的振动和振声频谱特征,建立磨机负荷模型参数预报模型。结合MATLAB丰富的函数资源和C#.net强大的可视化编程优势,开发实现了具有频谱特征选择、特征模型建立和负荷参数预报等功能的球磨机信号特征选择仿真实验平台。系统测试结果表明该系统能够有效选择与磨矿浓度、填充率和料球比相关的筒体振动和振声信号频谱特征,基于频谱特征的磨机负荷参数预报泛化性能提高。
Ball mill plays an important role in the grinding process. The rational parameters setting of ball mill load is important to ensure the ball mill long-term stable operation. Vibration and acoustic signal of shell contain plenty of information about mill load. It is difficult to select the feature of them in time domain, Frequency spectrum is high dimensionality and colinearity, Models based on it are complex and with a low generalization. The feature frequency bands of vibration and acoustical which are directly relevant to the parameters of ball mill load were selected by Synergy lnterval Partial Least Squares regression （SiPLS） and built models on them. The experimental platform combines the strengths of MATLAB with the benefits of C#.net to implement the functions of frequency feature selection, feature modeling and load parameters prediction. Test results show that the platform selects the frequency spectrum feature effectively, and the generalization of mill load models is improved.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2014年第3期638-642,共5页
Journal of System Simulation
基金
国家自然科学基金(61203102)
