Adversarial Transferred Data-Assisted Soft Sensor for Enhanced Multigrade Quality Prediction

Abstract

Although recent transfer learning soft sensors show promising applications in multigrade chemical processes, good prediction performance mainly relies on available target domain data, which is difficult to achieve for a start-up grade. Additionally, only employing a single global model is inadequate to characterize the inner relationship of process variables. A just-in-time adversarial transfer learning (JATL) soft sensing method is developed to enhance multigrade process prediction performance. The distribution discrepancies of process variables between two different operating grades are first reduced by the ATL strategy. Subsequently, by applying the just-in-time learning approach, a similar data set is selected from the transferred source data for reliable model construction. Consequently, with the JATL-based soft sensor, quality prediction of a new target grade is implemented without its own labeled data. Experimental results on two multigrade chemical processes validate that the JATL method can give rise to the improvement of model performance.

Domain Compensation-Assisted Quality Inference Enhancement of Chemical Processes with Distributed Outputs

“…Recently, transfer learning tries to reduce the cost of developing new models by leveraging related knowledge. − The available process with sufficient labeled data is generally denoted as the source domain, while the process to be predicted is considered as the target domain. Recently, Zhang et al introduced a robust Gaussian process domain model for the online modeling of multimode processes .…”

Adaptive Temporal–Spatial Pyramid Variational Autoencoder Model for Multirate Dynamic Chemical Process Soft Sensing Application

“…In a prolonged dynamic process, it is necessary to combine existing dynamic information with similar historical information to adjust the model in real time to obtain the best adaptive soft sensor model. Just-in-time (JIT) learning , methods can identify similar historical data for test data, establish local models, and then achieve better prediction accuracy. Since JIT models can build models based on the target data, they are suitable for complex nonlinear data and multimode processes.…”

“…In chemical processes, the process data often exhibits dynamic temporal characteristics, requiring the establishment of specific soft sensing models. − As a result, deep time-series soft sensing models based on methods such as recurrent neural networks (RNN), long short-term memory networks (LSTM), , Hidden markov models (HMM), , etc., have been developed. Jiang et al built a dynamic temporal dependency model based on the similarities between the short-term load forecasting and the transformer architecture .…”