| abstract |
The present application relates to the technical field of technical sintering, and provides a method, model and system for identifying sintering production indicators based on multi-source information. image and infrared image, as well as the production parameters of the sintering machine at this moment, and then perform feature extraction on the visible light image and the infrared image to obtain the first feature vector of the visible light image and the second feature vector of the infrared image. After the eigenvalue dimensionality reduction of the second feature vector, feature-level image fusion is performed to obtain dual-source image fusion features, and multi-modal data fusion is performed on the fused dual-source image fusion features and production parameters to obtain multi-modal feature vectors. It contains more factors that affect the key parameters of sinter, and finally uses the multi-modal feature vector as the input to obtain the key parameters of sinter by using the pre-established multi-layer perception model. |