Multi-parameter self-adaptive detection model for curvature of aluminum material

According to the method, a multi-parameter self-adaptive detection model for the bending degree of the aluminum profile is provided, aluminum profile data are obtained and preprocessed, the number of categories and sample dimensions are determined, a fixed-length sample set is obtained, and the fixed-length sample set is divided into a training set and a test set; performing feature extraction on the preprocessed data; inputting the features into a long short-term memory network to obtain a detection model; enabling the detection model to predict the training set, continuously executing the active learning process, and stopping until the detection model reaches a preset accuracy rate or a preset number of iterations; and inputting the test set into the detection model to detect the performance of the detection model. The detection model provided by the invention can continuously adapt to new fault types and maintain an efficient recognition rate in a changing actual working environment; the deep learning mode