Search

Accurate measurement of key quality variables is of great significance for evaluating product quality and ensuring production safety. How to extract useful dynamic latent features from complex process data for effective quality prediction is still a difficult and hot topic in soft sensing modeling. The existing soft sensing models based on long short-term memory (LSTM) do not consider the correlation between hidden states of different time steps when extracting dynamic nonlinear features. To solve these problems, a novel bidirectional LSTM network with weighted attention mechanism (WA-BiLSTM) is proposed in this article to improve the prediction performance for dynamic nonlinear industrial processes. In the WA-BiLSTM model, the bidirectional structure of BiLSTM is used to learn the dynamic information of the input sequence. A weighted attention mechanism layer is designed to dynamically extract the correlation information between the hidden states of different batches. In addition, the ratio between the historical hidden states and the current hidden state is adjusted reasonably by assigning adaptive parameters. Finally, the experimental results on a debutanizer column process and an IndPensim process demonstrate the effectiveness and superiority of the proposed method.

Smart hand diagnosis simulates the expert knowledge of hand diagnosis in traditional Chinese medicine and makes a diagnosis through the hand image information. To ensure the correctness of the diagnosis, an adaptive hand image function region segmentation is developed. Firstly, a hand image is acquired by a mobile app and its contour is extracted by multi-threshold segmentation and edge detection after series preprocessing. Secondly, some key feature corner points in the hand contour are detected through the dynamic intersection method, and then the hand image is segmented into 14 function regions, referring to the nine palace figures of hand diagnosis, in which the feature of each region can indicate the sampled people's health status for a specific physical function. The experimental results show that the hand image function regions can be divided successfully and keep the pathological characteristics in good condition. All that prove the segmentation method has good robustness and high accuracy.