A method of detecting process abnormal signals using an improved method of skewness and kurtosis analysis which are used for fault diagnosis of arotary machine is developed. The method proposed in this study has the advantage of detecting online process abnormal signals in industrial use. It is applied to abnormal detection of the catalyst feed flow in a linear low-density polyethylene plant to confirm the design philosophy. The actual result indicates that the proposed method is effective in detecting abnormal process signals.