Research on evaluation model of health state information security protection for automotive braking system based on machine learning

The Long Short-Term Gradient (LSTG) architecture innovatively combines the time series analysis capability of Long short-term memory network (LSTM) with the efficient training strategy of Mini-batch Gradient Descent (MGD). It has brought innovation to the research of health state information security protection evaluation model of automobile brake system based on machine learning. LSTG uses LSTM to capture the time-dependent characteristics of sensor data in automotive braking system, accelerates model iteration through MGD strategy, and significantly improves the training efficiency and evaluation accuracy of the model. Through experimental comparison, LSTG not only greatly enhances the accuracy rate, recall rate and accuracy rate of the model under complex environment, but also proves the reliability and feasibility of the model in the automotive braking system.