Inference method of SAR equipment task failure cause based on texture feature transformation

Abstract

The invention discloses a SAR equipment task failure reasoning method based on texture feature transformation, which adopts an optimal classification decision tree model and adopts a texture feature transformation method to transform the abnormal image texture feature into its normal image texture feature transformation The difference is normalized, thereby enhancing the accuracy of the optimal classification decision tree model for abnormal image classification. At the same time, modeling based on image texture feature transformation and optimal classification decision tree overcomes the problem of poor training model effect using different terrain SAR image data, and effectively improves the accuracy of SAR equipment task failure cause reasoning.

Description

technical field [0001] The invention belongs to the technical field of SAR equipment support, and more specifically relates to a reasoning method for SAR equipment task failure causes based on texture feature transformation. Background technique [0002] In recent years, with the continuous update of airborne SAR equipment and the continuous injection of high-end technology, airborne SAR equipment tends to be complex, highly integrated and highly intelligent. At the same time, airborne SAR equipment reflects mission failures during use but does not detect obvious hardware failures. Therefore, there is an urgent need for a failure cause reasoning method oriented to mission completion. [0003] Most of the current task failure cause reasoning methods are reasoning methods based on fault diagnosis, which are mainly aimed at locating hardware faults of SAR equipment, and are not suitable for failure cause reasoning requirements for task completion. At the same time, most fault ...

AI Technical Summary

Problems solved by technology

[0003] Most of the current task failure cause reasoning methods are reasoning methods based on fault diagnosis, which are mainly aimed at locating hardware faults of SAR equipment, and are not suitable for failure cause reasoning requirements for task completion.

At the same time, most fault diagnosis methods always try to adjust and optimize the method, while ignoring the importance of features, which makes the algorithm biased towards complexity and low measurement accuracy

Images