Design of Hypervelocity-Impact Damage Evaluation Technique Based on Bayesian Classifier of Transient Temperature Attributes

With the rapid increasement of space debris on earth orbit, the hypervelocity-impact (HVI) of space debris can cause some serious damages to the spacecraft, which can affect the operation security and reliability of spacecraft. Therefore, the damage detection of the spacecrafts has become an urgent problem to be solved. In this paper, a method is proposed to detect the damage of spacecraft. Firstly, a variable-interval method is proposed to extract the effective information from the infrared image sequence. Secondly, in order to mine the physical meaning of the thermal image sequence, five attributes are used to construct a feature space. After that, a Naive Bayesian classifier is established to mine the information of different damaged areas. Then, a maximum interclass distance function is used choose the representative of each class. Finally, in order to visualize damaged areas, the Canny operator is used to extract the edge of the damage. In the experiment, ground tests are used to simulate hypervelocity impacts in space. Historical data of natural damaged material and artificial damaged material are used to build different classifiers. After that, the effective of classifiers is illustrated by accuracy, F-score and AUC. Then, two different types of materials are detected by proposed method, Independent Component Analysis (ICA) and Fuzzy C-means (FCM). The results show that the proposed method is more accurate than other methods.