球磨机信号分析和关键参数预报系统
Signal Analysis and Key Parameter Prediction System of Ball Mill

作者: 赵立杰 * , 孙华 * , 陈斌 :沈阳化工大学信息工程学院,辽宁 沈阳; 王魏 :大连海洋大学信息工程学院,辽宁 大连;

关键词: 磨机负荷EEMD特征选择软测量混合编程Mill Load EEMD Feature Selection Soft Measurement Mixed Programming

摘要: 为了实现磨矿过程球磨机负荷参数的在线检测,采用MATLAB和C#.net混合编程方式,开发实现了球磨机振动、振声信号分析和关键参数预报的软测量系统。该系统基于集合经验模态分解(Ensemble Empirical Mode Decomposition, EEMD)技术和区间偏最小二乘(interval partial least-squares, iPLS)技术提取与磨机负荷参数密切相关的本征模态函数(intrinsic mode functions, IMF)频域特征,构建基于本征模态函数特征空间的选择性集成模型,实现磨机负荷参数的测量。MATLAB的Deploytool工具将信号EEMD分解、IMF频谱变换、iPLS特征选择、关键参数模型训练和模型预测一系列m函数编译生成DLL程序集合,在C#.net编程环境中,通过调用上述程序实现球磨机信号分析和关键参数预报软件系统的快速开发。系统测试结果表明该系统能够有效选择筒体振动和振声信号IMF频谱特征,系统准确性和可靠性较高,对改进磨矿过程控制和优化具有重要意义。

Abstract: Due to the difficult of the ball mill load to measure directly, we combined matlab language with c#.net programming to develop a signal analysis and key parameters prediction system of ball mill. The vibration and acoustic signals are decomposed a series of Intrinsic Mode Functions (IMFs) by using Ensemble Empirical Mode Decomposition (EEMD). The frequency domain characteristics of the IMFs were chosen based on interval Partial Least-Squares (iPLS) and forecast model of key load parameters were built based on extreme learning machine ensemble modeling. In order to solve the problem of monitoring and estimating the critical parameters of the ball mill’s running state. Use the Deploytool tool of Matlab to compile a series of M function of signal EEMD decomposition, IMF transform spectrum, iPLS feature selection and the  model training and prediction of the key parameters into C#.NET DLL assemblies, and then call them in C#. The software system of signal analysis and key parameters prediction of ball mill is developed, which has the function of signal decomposition, feature selection, model training and parameter prediction. System test results show that the system can effectively select the cylinder vibration and noise signal IMF spectrum characteristics closely related to the ratio of material ball, grinding concentration and filling rate. In addition, the mill load parameters forecasting system based on spectral characteristics has good generalization performance.

文章引用: 赵立杰 , 孙华 , 陈斌 , 王魏 (2016) 球磨机信号分析和关键参数预报系统。 计算机科学与应用, 6, 160-170. doi: 10.12677/CSA.2016.63020

参考文献

[1] 郜峰. 球磨机负荷监测软件平台的设计与开发[D]: [硕士学位论文]. 沈阳: 东北大学. 2010.

[2] Wu, Z. and Huang, N.E. (2011) Ensemble Empirical Mode Decomposition: A Noise-Assisted Data Analysis Method. Advances in Adaptive Data Analysis, 1, 1-41.

[3] 赵立杰, 汤健, 柴天佑. 基于选择性极限学习机集成的磨机负荷软测量[J]. 浙江大学学报: 工学版, 2011(12): 2088-2092.

[4] 庄红林. 王文斌. 范菁. MATLAB与.NET平台接口技术的研究[J]. 云南民族大学学报(自然科学版), 2007, 3(3): 263-266.

[5] Norgaard, L., Saudland, A., Wagner, J., Nielsen, J.P., Munck, L. and Engelsen, S.B. (2000) Interval Partial Least Squares Regression (iPLS): A Comparative Chemo-metric Study with an Example from Near-Infrared Spectroscopy. Applied Spectroscopy, 54, 413-419.

[6] Husmeier, D. (1999) Random Vector Functional Link (RVFL) Networks. In: Husmeier, D., Ed., Random Vector Functional Link (RVFL) Networks, Neural Networks for Conditional Probability Estimation, Springer, London, 87-97.

[7] 冯雪. 基于EEMD的球磨机负荷参数预报方法的研究[D]: [硕士学位论文]. 沈阳: 沈阳化工大学, 2014.

分享
Top