Health status assessment of ship diesel engine method based on LSTM prediction and cloud barycenter model

Objectives In response to the development needs of smart engine rooms on ships, this paper proposes an assessment method for the health status of ship diesel engines based on long short-term memory (LSTM) neural network prediction and cloud gravity center evaluation, aiming to enhance the operational and maintenance capabilities of ship diesel engines. Methods First, the method constructs an evaluation indicator parameter set based on the deviation between LSTM predicted parameters and measured parameters. Then, it uses the analytic hierarchy process to construct parameter weights and employs the cloud gravity center evaluation method to assess the health status of the diesel engine. Finally, tests are conducted using actual ship diesel engine data from the early normal period and the later degradation period. Results The results indicate that the evaluation value of the early normal running state of the diesel engine is 99.94 (healthy), and the evaluation value of the later degradation state is 81.71 (good), achieving the goal of assessing the health status of the diesel engine. Conclusions The proposed method can be used for the health status assessment of ship diesel engines and other power equipment, and it has practical application value.