The engine room equipment is an important part of the ship power system. It is of great significance to monitor, analyze and predict the status data of the engine room equipment to ensure the normal operation of the ship power system. Ship engine room is a variety of equipment such as pumps, diesel engine and the shafting of complex electromechanical system. Mostly rotating machinery equipment, the moving parts is much and complicated structure. In order to realize monitoring, analysis, forecast to the running condition of engine room equipment. The analysis and prediction of vibration signal of mechanical equipment is the key issue. For ship shafting vibration data, this paper presents a fault trend prediction method based on improved empirical mode decomposition and enhanced Intermittent unknown input Kalman filter. First, add white noise signals before modal decomposition, which can optimize the decomposability of the signal and avoid modal aliasing. Then, the characteristic curves of the vibration signals were obtained by sequential analysis of the filtered and reconstructed signals. EIIKF method was used to analyze and predict the characteristic curves, and intermittent parameters were added to compensate for the uncertainties caused by some unknown input items. On this basis, fault diagnosis is carried out by fault discrimination model, and fault prediction based on vibration signal of shaft system is realized. The 90-day measured data are verified by this method, and the sensitivity and accuracy of the prediction results are better than those predicted by general modal decomposition and Kalman filter. The effectiveness and superiority of the improved method are verified.
Trend Prediction of the Operating State of Ship Engine Room Equipment Based on EEMD and EIIKF
2021-10-22
3198452 byte
Conference paper
Electronic Resource
English
Ship Traffic Flow Prediction Using EEMD-edRVFL-RF
IEEE | 2024
|A modified unbiased GM(1,1) prediction model based EEMD
IEEE | 2016
|Train wheel size prediction based on EEMD-LSTM model
British Library Conference Proceedings | 2022
|