Auxiliary anti-sinking decision model generation method and system based on deep learning method

• Main Authors: ZHANG QI, DONG YUXIN, ZHANG YUE, YANG DONGMEI, ZHANG LIGUO, LI HAOYAO, LI ZE
• Format: Patent
• Language: Chinese; English
• Published: 30.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses an auxiliary anti-sinking decision model generation method and system based on a deep learning method, and belongs to the technical field of anti-sinking auxiliary decision, and the method comprises the steps: obtaining cabin region label data and immersion experiment data of a preset ship, including the total time, the filling time of each cabin, and an immersion video; performing frame-by-frame processing on the immersion video of each cabin to obtain a plurality of pictures and time corresponding to each picture, dividing the plurality of pictures and the time corresponding to each picture into two parts, disorganizing the sequence of the pictures in the first part, dividing the pictures into a training set and a test set, and arranging the second part by taking a time axis as a sequence; inputting the training set into a convolutional neural network for training, and inputting the second part of pictures into the trained convolutional neural network to obtain vectorized data; and i