Locomotive driver fatigue state monitoring method based on upper body posture

Abstract

The invention provides a locomotive driver fatigue state monitoring method based on an upper body posture. The method is used for solving the problems that in the prior art, the locomotive driver fatigue state judgment accuracy and precision are not high. The invention discloses a locomotive driver fatigue state monitoring method. Comparing the fatigue label sample with the waking label sample; the method comprises the steps of obtaining a fatigue data feature set, inputting the fatigue data feature set into a DBN network to complete RBM training to obtain an optimal parameter value, taking BPNN as a classifier, performing reverse tuning to realize dichotomy so as to construct a DBN-BPNN monitoring model, and inputting monitored original data into the model to complete judgment of the fatigue state of a driver. According to the method, the local optimum and uncertainty of the original BPNN are solved, the method has real-time performance, environmental adaptability, non-contact performance and convenience, the fatigue degree of the locomotive driver is analyzed more accurately, the train safety guarantee is effectively improved, the accident occurrence probability is reduced, and the train operation cost is reduced.

Description

technical field [0001] The invention belongs to the field of train operation and transportation safety, and in particular relates to a method for monitoring the fatigue state of a locomotive driver based on upper body posture. Background technique [0002] With the rapid development of high-speed rail, people have increasingly strict requirements for high-speed rail safety, and locomotive drivers play an important role in train safety. When the locomotive driver is driving the train, the driver's sitting posture and movements are monotonous, and the driver is in a state of high concentration for a long time, so fatigue is inevitable. Motorcycle drivers in a fatigued state have difficulty concentrating and their reaction speed tends to be slow, which will endanger driving safety. Therefore, in the case of not interfering with the normal operation of the train, real-time, fast and accurate monitoring of the fatigue state of the locomotive driver can ensure driving safety. ...

AI Technical Summary

Problems solved by technology

[0004] In order to improve the accuracy and precision of the fatigue state judgment of the locomotive driver and overcome the problem of large errors in the information collection of the locomotive driver in the prior art, the present invention provides a method for monitoring the fatigue state of the locomotive driver based on the posture of the upper body. Accurately judge the fatigue of locomotive drivers, effectively improve train safety, reduce the probability of accidents, and reduce train operating costs

Images