A Remaining Useful Life Prediction Method of Wet Friction Component Based on Data-Model Interactive Framework

The reliability of wet clutches is critical to the efficient operation of heavy equipment, as the lifespan of the wet friction component directly impacts the clutch’s stable performance. To accurately predict the remaining useful life (RUL) of wet friction components and to address the overfitting and poor robustness often observed in single models, this study proposes an innovative framework that integrates a neural network with a Wiener process model, thereby establishing a novel data–model interaction architecture. The framework gathers multidimensional degradation data from accelerated life tests and uses Particle Swarm Optimization (PSO) and Long Short-Term Memory (LSTM) to derive a composite health index. Subsequently, the composite health index is modeled using the Wiener Degradation Process (Wiener) to estimate the RUL. An objective function based on the prediction error is then defined, and the Adam algorithm adjusts the framework parameters dynamically to minimize this function and improve the RUL prediction accuracy. The prediction results suggest that the mean relative error (MRE) of this model is only 4.47%, confirming its accuracy. This method provides a more reliable RUL prediction solution for wet friction component based on artificial intelligence.