Experimental investigation of vibration signal of an industrial tubular ball mill: Monitoring and diagnosing

Review of control and fault diagnosis methods applied to coal mills

“…Several techniques of mill fault diagnosis using signal analysis have been tried [150][151][152][153][154][155][156][157][158][159]. R. J. Nathan and M. P. Norton [150] proposed a predictive maintenance philosophy using vibration signature analysis for the bowl mills, which can provide useful information about wear, failure, and incorrect settings of the milling system components.…”

“…Z.G. Su et al [151] designed a system that record vibration signals and transfer them into energy amplitudes by utilizing wavelet analysis. Using analysis of these vibration characteristics and estimated level of coal mass in the mill, various operational issues of the mill like mill overload, and lack of coal are determined.…”

“…Signal model based FDD methods as presented in [150][151][152][153][154][155][156][157][158][159] are used to detect wear in roller, grinding table, and other mill components. They are also being used to find other problems such as choking, occurring inside the mills.…”

Novel Strategies for Process Monitoring in Power Plant and Their Comparisons

“…The details of the NPLS algorithm can be obtain from the work [3], and the detailed modeling procedure can also refer to [1]. Here the brief summary of NPLS algorithm was illustrated in Tab.2.…”

“…In [1], we have investigated on applying the Vibration Signal (VS) to monitor the level of coal powder, and a nonlinear partial least squares (NPLS) model, taking VS as inputs and level as output, was established at high cost of experiment consumptions. We found that this model can be applied for monitoring level with high accuracy, however, the accuracy can not be maintained at long running time due to lack of sufficient training samples.…”