Research on Knowledge Reasoning for Ship Operation and Maintenance Based on Digital Twin

Objective With the continuous development of industrial technology, the process of modern ship intelligence continues to advance, the ship's propulsion system, auxiliary power system and other systems have become more and more intelligent, and ship maintenance work has become more and more complex. Different from land equipment, the environment in which the ship is located is more severe, once the problem occurs, it will not only affect the stability of the ship during operation, but also has a huge security risk. Methods This paper focuses on the reasoning method of ship operation and maintenance (O&M) knowledge based on digital twin, analyzing the ship O&M process on the basis of the physical entity of the ship, and constructing a digital twin model of ship O&M from the multi-dimension of "geometry-physics-behavior-rule". Aiming at the early warning information in the ship O&M knowledge model, we utilize the previous ship O&M cases to establish a ship O&M case database containing ship dynamic monitoring data and ship maintenance methods. Based on the ship O&M case database, an improved KD-tree algorithm for ship O&M knowledge reasoning and strategy generation method is proposed, using Gaussian distance weighting for the weighting of neighboring cases, and using whale optimization algorithm to optimize the characteristic attributes of the ship's equipment with the goal of the accuracy of knowledge reasoning. Results Finally, the effectiveness of the proposed method is verified through comparative experiments. The maintenance strategy is verified in the ship digital twin model, and the maintenance strategy is provided for the physical ship through the virtual-real interaction. Conclusion The proposed method is suitable to be applied to the O&M process of ship gas turbines.