Controller Fatigue Detection Method and System Based on Probability and Statistics Method

Abstract

The invention provides a controller fatigue detection method based on a probability statistics method. The method is as follows: obtain the brain wave of the controller, the brain wave includes slow α wave, α wave, β wave and θ wave; calculate the power percentage of slow α wave, the power ratio of α wave and β wave, the power ratio of θ wave and slow α wave Power ratio; obtain the fatigue detection model based on the probability statistics method, input the power percentage of slow alpha wave, the power ratio of alpha wave to beta wave, and the power ratio of theta wave to slow alpha wave into the fatigue detection model, and obtain the simulation result of PERCLOS value; according to The simulation results of PERCLOS values ​​are used for controller fatigue detection. The controller fatigue detection method and system based on the probability statistics method of the present invention adopts the input of electroencephalogram parameters into the fatigue detection model established based on the probability statistics method, and obtains the PERCLOS value simulation results for fatigue detection. Using brain waves to indirectly reflect the degree of fatigue of people, the brain wave acquisition method is simple, easy to implement, and low in cost.

Description

technical field [0001] The invention relates to the aerospace field, in particular to fatigue detection. 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] Existing technology: So far, researchers at home and abroad have proposed a variety of fatigue detection and management methods and systems. The first method is to collect questionnaires from a large number of subjects for fatigue judgment and p...

AI Technical Summary

Problems solved by technology

In this way, the current physical condition of the controller is directly ignored, which may have a certain impact on the detection results; the third method: most of the currently existing methods suitable for real-time fatigue detection use the method of collecting and recognizing facial features. The method requires high-precision video detection equipment to shoot controllers at any time, and it has no advantages in terms of cost analysis

[0004] Insufficiency of the first method: subject to the subjective influence of the researcher, making the judgment and prediction of the fatigue of the subject inaccurate; shortcoming of the second method: real-time detection cannot be carried out, and a certain period of time can be speculated based on the performance of the subject for a period of time. Whether the controller is fatigued for a period of time, ignoring the current physical condition of the controller, making the fatigue determination and prediction inaccurate; the deficiency of the third method: Although the fatigue status of the controller has been monitored in real time, the realization of this method requires High-precision video detection equipment, high cost, not applicable

[0005] Therefore, the defective in the prior art is: commonly used method adopts the parameter that directly reflects people's fatigue degree to carry out fatigue detection, as: people's facial feature (blink eye closure degree), needs the video detection equipment of high precision, and cost is high, Poor applicability, unable to provide effective fatigue detection for controllers

Images