Fire Control System Fault Prediction Method Based on CAO-SVM

Abstract

With the development of science and technology, the technology of tank fire control system is also being iteratively updated. At this stage, the fire control system shows the characteristics of higher technical content, more complex structure, more advanced control system, and more difficult fault judgment. Aiming at the problems of small amount of signal data and complex composition collected by artillery control system, a model prediction method based on chaotic mapping improved aquila algorithm optimization support vector machine is proposed. The gray correlation degree analysis is carried out through the collected signal data, the original data parameters are screened, and the attributes with higher gray correlation degree are selected to construct the dataset. The improved aquila algorithm of chaos mapping is used to perform parameter optimization on the penalty factor c and kernel function g of the support vector machine, and after the model training is completed, the failure prediction is performed on the test set. The test shows that the improved prediction model has high prediction accuracy, stable performance, low dependence on the number of sample training sets, and strong advantages.