State prediction for marine diesel engine based on variational modal decomposition and long short-term memory

• DOI: 10.1016/j.egyr.2021.09.185
• Publication Date: 2021-12-06T12:11:43Z
• Authors: Chong Qu; Zhiguo Zhou; Zhiwen Liu; Shuli Jia; Lianfang Wang; Liyong Ma
• Keywords: SIGNAL (programming language)

With the development of unmanned systems, more and attentions are paid to energy power systems data-driven ships. The autonomy ships puts forward urgent requirements for monitoring prediction system Aiming at state marine diesel engine, an improvement method based on variational modal decomposition (VMD) long short-term memory (LSTM) is proposed in this paper. sub signals obtained by decomposing signal be predicted through VMD, resident all with LSTM, reconstruction sum signal. Compared ESN, SVR methods, reduces errors significantly. RE two sensors reduced 49.79% 56.32% respectively, RMSE 34.65% 27.71% respectively. performance better than other it has sufficient accuracy engine.