Deep learning with CBAM-based CNN for batch process quality prediction

Abstract

Data-driven quality prediction method has been widely used in product estimation of batch processes. However, the initial conditions of different batches in batch process are different, and the multiphase characteristics and nonlinearity in batch are not conducive to the quality prediction. To solve these problems, a model for batch process quality prediction based on a convolutional neural network (CNN) is proposed. Firstly, in order to enhance data characteristics and reduce model computing time, a maximum information coefficient (MIC) method based on mutual information is used to select variables according to the correlation between process variables and quality variables. Secondly, the quality prediction model of CBAM-CNN based on the attention mechanism is established. On the one hand, an improved convolutional block attention module (CBAM) is added to the CNN. The input feature mapping is re-calibrated to focus on useful feature information and weaken irrelevant redundant information in each sliding window. On the other hand, by introducing an improved convolutional module with double-band skip connection lines, the backpropagation speed of the CBAM-CNN model is increased, which can effectively avoid the occurrence of the overfitting problem. Finally, the data of batch process is used as the input of the prediction model. The superiority and effectiveness of the proposed model are verified by predicting the quality variable of the penicillin fermentation process simulation benchmark and the industrial-scale penicillin fermentation process. It is proved that the proposed model has better generalization performance in the quality prediction of the penicillin fermentation process with different control strategies.

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles

“…Due to their cost-effectiveness, high precision, and robustness, they find extensive applications in the field of autonomous driving. In convolutional neural network (CNN) 15 – 17 , the convolutional kernels extract features while reducing the parameter count. Pooling layers shrink the size of feature maps while retaining essential information.…”

Batch process control based on reinforcement learning with segmented prioritized experience replay

“…The actor networks in SPER-SAC are parameterized DNNs consisting of 4 hidden layers with 256 hidden nodes, therefore the number of nodes in each layer as [12,256,256,2], whose inputs are the vector of process variables listed in table 1 and outputs the set value of the substrate feed flowrate in the form of a Gaussian distribution. In contrast, the number of network nodes in each layer of the critic network is [13,256,256,1], and its input consists of the process variables and the output of the actor network.…”

“…Batch process has traditionally been used to produce relatively few high-value-added products such as fine chemicals, polymers, and pharmaceuticals. With the increasing demand for a wide range of products in the chemical industry, the importance of batch production has grown [1,2]. Due to the remarkable nonlinear dynamic, the operating conditions of batch processes are prone to significant changes under continuous and unknown disturbances, while the range of product quality requirements are extreme narrow in most instances [3,4].…”