论文部分内容阅读
Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of realtime fault predictor is designed based on an improved knearest neighbor method, which needs neither the math model of system nor the training data and prior knowledge. It can study and predict while system’s running, so that it can overcome the difficulty of data acquirement. Besides, this predictor has a fast prediction speed, and the false alarm rate and missing alarm rate can be adjusted randomly. The method is simple and universalizable. The result of simulation on fighter F16 proved the efficiency.
Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of realtime fault predictor is designed based on an improved knearest neighbor method, which needs neither the math model of system nor the training data and prior knowledge. It can study and predict while system running, so that it can overcome the difficulty of data acquirement. Besides, this predictor has a fast prediction speed, and the false alarm rate and missing alarm The result of simulation on fighter F16 proved the efficiency.