Controller fatigue detection method and system based on BP neural network

Abstract

The invention relates to the field of fatigue detection, and specifically relates to a controller fatigue detection method and system based on a BP neural network. The method comprises the steps: collecting the pulse value and blood pressure value of the controller, and obtaining the diastolic pressure value and systolic pressure value according to the blood pressure value; inputting the pulse value, the diastolic pressure value and the systolic pressure value to a preset trained BP neural network model, and obtaining a PERCLOS value simulation result; and judging that the controller is in a fatigue state if the PERCLOS value simulation result is greater than the fatigue value. According to the invention, the method and system detect the fatigue degree of a person in real time based on the BP neural network through detecting the pulse value and the blood pressure value, enable the real-time fatigue detection to be simpler, and reduce the detection cost.

Description

technical field [0001] The invention relates to the technical field of fatigue detection, in particular to a controller fatigue detection method and system based on BP neural network. Background technique [0002] With the increasing air traffic flow, the workload of air traffic controllers is increasing, and their fatigue level has an important impact on the safety level of air traffic system. ICAO has developed Doc9966 manual of rules and regulations for fatigue risk management. Developed countries in Europe and the United States have successively extended fatigue detection systems or methods for pilots to controller fatigue detection applications. The Civil Aviation Administration of China is guided by ICAO Doc9966, and also clarified the rules of fatigue risk management in the CCAR-121 document. [0003] However, so far, although researchers at home and abroad have proposed a variety of fatigue detection and management methods and systems, these methods mainly have thr...

AI Technical Summary

Problems solved by technology

First, it is highly subjective. For example, a large number of questionnaires are used in fatigue judgment and prediction, and researchers will score according to the testee’s answer results combined with experience to determine the degree of fatigue, which will inevitably be affected by the researcher’s subjective judgment; The second is that it is difficult to carry out real-time detection. A considerable part of the methods being used are to establish fatigue trend prediction charts by observing the performance of the subjects for a long period of time (such as dozens of days in a row), and then judge the fatigue trend in a certain period of time according to the charts. Whether the controller is fatigued during the time

In this way, the current physical condition of the controller is directly ignored, which may have a certain impact on the detection results; third, most of the current existing methods for real-time fatigue detection use the method of collecting and recognizing facial features, which requires high High-precision video detection equipment can shoot controllers at any time, and it does not have an advantage in terms of cost analysis

Images