Remaining Life Prediction of Automatic Fare Collection Systems from the Perspective of Sustainable Development: A Sparse and Weak Feature Fault Data-Based Approach

The most effective way to solve urban traffic congestion in mega cities is to develop rail transit, which is also an important strategy for sustainable urban development. Improving the service performance of rail transit equipment is the key to ensuring the sustainable operation of urban rail transit. Automatic fare collection (AFC) is an indispensable system in urban rail transit. AFC directly serves passengers, and its condition directly affects the sustainability and safety of urban rail transit. This study proposes remaining useful life (RUL) prediction framework for AFC systems. Firstly, it proposes the quantification of AFC health state based on health degree, and proposes a health state assessment method based on digital analog fusion, which compensates for the shortcomings of single data-driven or model driven health methods. Secondly, it constructs a multi feature extraction method based on multi-layer LSTM, which can capture long-term temporal dependencies and multi-dimensional feature, overcoming the limitation of low model accuracy because of the weak data features. Then, the SSA-XGBoost model for AFC RUL prediction is proposed, which effectively performs global and local searches, reduces the possibility of overfitting, and improves the accuracy of the prediction model. Finally, we put it into practice of the AFC system of Shanghai Metro Line 10. The experiment shows that the proposed model has an MSE of 0.00111 and MAE of 0.02869 on the test set, while on the validation set, MSE is 0.00004 and MAE is 0.00659. These indicators are significantly better than other comparative models such as XGBoost, random forest regression, and linear regression. In addition, the SSA-XGBoost model also performs well on R-squared, further verifying its effectiveness in prediction accuracy and model fitting.