基于PCA和IGWO-SVM的水泥回转窑故障诊断研究

发布时间：2018-01-04 18:02

本文关键词：基于PCA和IGWO-SVM的水泥回转窑故障诊断研究　出处：《中国测试》2017年10期 　论文类型：期刊论文

【摘要】：为实现水泥回转窑故障的精确诊断,提出一种基于主成分分析(PCA)和支持向量机(SVM)的回转窑故障诊断模型。通过引入差分进化(DE)算法的变异、交叉、选择操作来维持种群的多样性,克服灰狼算法易早熟收敛的缺陷,然后采用这种改进的灰狼算法(IGWO)对SVM的惩罚因子c和核函数参数g进行动态的寻优。运用PCA对采集数据进行降维处理,消除非相关因素,降低数据处理难度,然后将特征提取后的数据作为输入建立故障诊断模型,并与普通的SVM建模方法进行比较。实例表明:在有用信息量损失较小的前提下,分类准确率达到96.153 8%,模型构建时间为2.972 0 s,从而验证模型的准确性和高效性。
[Abstract]:In order to realize the accurate diagnosis of cement rotary kiln fault. A rotary kiln fault diagnosis model based on principal component analysis (PCA) and support vector machine (SVM) is proposed. The mutation and crossover of differential evolution algorithm are introduced. Select the operation to maintain the diversity of the population to overcome the gray wolf algorithm is easy to premature convergence defects. Then the improved gray wolf algorithm (IGWOO) is used to dynamically optimize the penalty factor c and kernel function parameter g of SVM. The dimension reduction of collected data is processed by PCA to eliminate non-related factors. The difficulty of data processing is reduced, and then the feature extracted data is used as input to establish fault diagnosis model, and compared with the common SVM modeling method. The example shows that the loss of useful information is small. The accuracy of classification is 96.1538 and the time of constructing the model is 2.9720 s, which verifies the accuracy and efficiency of the model.
【作者单位】：长春工业大学电气与电子工程学院;
【基金】：吉林省科学技术厅计划项目(20150203003SF)
【分类号】：TP18;TQ172.622
【正文快照】： 0引言水泥回转窑作为新型干法生产线上的核心设备,负责完成水泥生料的煅烧[1]。其工作状态会直接影响水泥熟料的质量、产量[2],因而对其故障进行快速精确地诊断就显得尤为重要。通过智能算法建立可靠的故障诊断模型对回转窑进行及时的故障识别,可以克服人工诊断方法的局限性,

【相似文献】