Open Access Thesis
Date of Award
In chemical manufacturing plants, numerous types of data are accessible, which could be process operational data (historical or real-time), process design and product quality data, economic and environmental (including process safety, waste emission and health impact) data. Effective knowledge extraction from raw data has always been a very challenging task, especially the data needed for a type of study is huge. Other characteristics of process data such as noise, dynamics, and highly correlated process parameters make this more challenging.
In this study, we introduce an attention-based RNN for multi-step-ahead prediction that can have applications in model predictive control, fault diagnosis, etc. This model consists of an RNN that encodes a sequence of input time series data into a new representation (called context vector) and another RNN that decodes the representation into output target sequence. An attention model integrated to the encoder-decoder RNN model allows the network to focus on parts of the input sequence that are relevant to predicting the target sequence. The attention model is jointly trained with all other components of the model. By having a deep architecture, the model can learn a very complex dynamic system, and it is robust to noise. In order to show the effectiveness of the proposed approach, we perform a comparative study on the problem of catalyst activity prediction, by using conventional machine learning techniques such as Support Vector Regression (SVR).
Moradi Aliabadi, Majid, "Process Data Analytics Using Deep Learning Techniques" (2020). Wayne State University Theses. 761.