掘进机动载荷识别方法

基金项目:

国家高技术研究发展计划（863计划）资源环境技术领域重大项目(2012AA06A405)

A dynamic load identification method of roadheader

1.
State Grid Shanxi Electric Power Research Institute, Taiyuan 030001, China；2.State Grid Taiyuan Power Supply Company, Taiyuan 030012, China；3.State Grid Shanxi Economic and Technological Research

摘要: 针对掘进机工作时负载多变、动载荷实时识别难度大等问题，提出了一种基于多神经网络与证据理论相融合的掘进机动载荷识别方法。该方法采用RBF神经网络，分别对掘进机振动信号垂直、水平、轴向分量进行初步处理，然后采用D-S证据融合理论，对RBF神经网络处理所得的初步结果进行融合诊断，实现掘进机动载荷的实时识别。实例分析结果表明，该方法对于掘进机动载荷的识别准确率达88%。
- 掘进机 /
- 动载荷识别 /
- 截割速度调整 /
- 多神经网络 /
- 证据理论
Abstract: For problems of varied roadheader loads and difficult real-time identification of dynamic load during roadheader working, a dynamic load identification method of roadheader was proposed which was based on multi neural networks and evidence theory. In the method, vertical, horizontal and axial components of vibration signal are analyzed separately by use of RBF neural network, then preliminary results from RBF neural network are fused by use of D-S evidence fusion theory, so as to identify dynamic load of roadheader real-timely. The analysis of actual example show that accuracy rate of dynamic load identification of roadheader achieves 88%.
- roadheader /
- dynamic loading identification /
- adjustment of cutting speed /
- multi neural networks /
- evidence theory