Efficient maintenance of highway electromechanical equipment is crucial for
ensuring reliability within intelligent highway infrastructure and optimizing
the allocation of limited maintenance resources. Traditional Remaining Useful
Life (RUL) prediction models frequently face limitations due to the complex and
dynamic operating conditions of such systems, which often hinder their
predictive accuracy and adaptability. To overcome these persistent challenges,
this study introduces an advanced RUL prediction model that integrates a
Bayesian-optimized Convolutional Neural Network (CNN) with a Long Short-Term
Memory (LSTM) network. Initially, the study identifies key health indicators
that effectively represent the degradation of equipment performance over time.
These indicators undergo Spearman correlation analysis to determine their
relevance to equipment capacity, ensuring that only the most pertinent features
are used for model input. The CNN-LSTM model leverages CNN’s spatial pattern
recognition and LSTM’s ability to process temporal sequences, allowing it to
accurately capture performance trends over time and improve long-term
reliability. To further enhance model accuracy, Bayesian optimization is applied
to adjust the model’s hyperparameters automatically, providing an efficient,
tailored solution that aligns with the unique characteristics and operational
demands of highway electromechanical equipment. Validation on the CALCE lithium
battery dataset demonstrated a prediction accuracy exceeding 92%, confirming the
model's feasibility, robustness, and strong potential for real-world application
in highway system maintenance. The study provides valuable insights for
optimizing the operation, management, and maintenance of highway
electromechanical equipment. It supports predictive maintenance strategies that
enhance maintenance scheduling efficiency, extend the lifespan of critical
infrastructure, and effectively reduce operational costs while simultaneously
improving overall system reliability.