Prediction of Diesel Engine Cylinder Pressure Based on SSA-BiLSTM Model

Aiming at the difficulty of monitoring the instantaneous state of marine diesel engines, from the perspective of diesel engine operation and maintenance management, based on long short-term memory network (LSTM), an SSA-BiLSTM model is proposed to predict the cylinder pressure of marine medium-speed diesel engines. First, singular spectrum analysis (SSA) is used to denoise and extract the main features of the original cylinder pressure data. The bidirectional long short-term memory network (BiLSTM) model is used to capture the algorithm characteristics of one way calculation and error update backpropagation and optimize its hidden layer. Its backpropagation is adjusted dynamically simultaneously, and the variation law of cylinder pressure with the crank angle of the diesel engine is explored to realize the real time prediction of the cylinder pressure of the diesel engine. The prediction results are compared with other models, such as RNN, LSTM, and SSA-BiLSTM. The experimental results show that the SSA-BiLSTM model can effectively predict the cylinder pressure of the medium-speed engine, which can provide a new idea for improving the performance of the medium-speed engine.