基于支持向量机的回转窑减速机故障诊断方法分析-analysis of rotary kiln reducer fault diagnosis method based on support vector machine.docxVIP

AbstractCement rotary kiln is the most important equipment of the cement production line, the rotary kiln’s continuous and stable operation is an important way to improve the production efficiency. Whereas the online monitoring and fault diagnosis system of the rotary kiln is only available for parameters of the chemical reaction process, as to supporting wheels and reducer, which also affect the operation state of the rotary kiln, their maintenance is still being carried out manually. Once these devices fail, the companies have to take the maintenance, resulting in large economic losses.The paper aims at the fault diagnosis technology, a module of the “online monitoring and fault diagnosis technology for the key components of cement production line”, By the identification of mechanical equipment’s operation state, we hope to realize the detection of early failure, to quickly determine the cause of failure, and to avoid the failure to expand, thus to provide support for decision making for the smart maintenance of the equipment.The vibration signal analysis techniques are currently the main method for getting the failure information of rotating machinery equipment, the non-stationary and non-linear characteristics of the vibration signal leave the outcomes of traditional analysis methods, such as Fourier transform, wavelet t ransform meaningless. Hilbert-Huang transform decomposes the signal to the intrinsic mode functions, whose instantaneous frequencies are physically meaningful, thus Hilbert-Huang transform is the effective way to analyze non-stationary signals. Hilbert-Huang transform is composed of empirical mode decomposition and Hilbert spectral analysis, with empirical mode decomposition the core of the Hilbert-Huang transform. The paper does an analysis on the adaptive filtering characteristics of the empirical mode decomposition in detail and compares the Hilbert spectrum and the wavelet spectrum.Support vector machines roots its mathematical basis on stat