Prof. Dr. David Shan-Hill Wong

Co-authors

Following

Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

10 April 2021 in Processes

Journal Article

Development of Robust and Physically Interpretable Soft Sensor for Industrial Distillation Column Using Transfer Learning with Small Datasets

Yu-Da Hsiao

Jia-Lin Kang

David Shan-Hill Wong

In the development of soft sensors for industrial processes, the availability of data for data-driven modeling is usually limited, which led to overfitting and lack of interpretability when conventional deep learning models were used. In this study, the proposed soft sensor development methodology combining first-principle simulations and transfer learning was used to address these problems. Source-domain models were obtained using a large amount of data generated by dynamic simulations. They were then fine-tuned by a limited amount of real plant data to improve their prediction accuracies on the target domain and guaranteed the models with correct domain knowledge. An industrial C4 separation column operating at a refining unit was used as an example to illustrate the effectiveness of this approach. Results showed that fine-tuned networks could obtain better accuracy and improved interpretability compared to a simple feedforward network with or without regularization, especially when the amount of actual data available was small. For some secondary effects, such as interaction gain, its interpretability is mainly based on the interpretability of the corresponding source models.

8 November 2019 in IEEE Transactions on Industrial Informatics

Journal Article

Physically Consistent Soft-Sensor Development Using Sequence-to-Sequence Neural Networks

Soft-sensors attempt to predict key quality variables that are infrequently available using sensor and manipulated variables that are readily available. Since only limited amount labelled data are available, there is always the concern whether underlying physics were captured so that the model can be reasonably extrapolated, A sequence-to-sequence model in the form of a nonlinear state-observer/encoder and predictor/decoder was proposed. The observer can be trained using large amount of unlabeled data, but in a supervised manner in which the process dynamics was tracked. The encoder output and manipulated variables were used to train the quality predictor. The model was applied to product impurity predictions of an industrial column. Results show that good predictions and excellent consistency in the sign of estimated gains can be achieved even with limited amount of data. These findings indicated that the proposed sequence-to-sequence data-driven approach is able to capture the underlying physics of the process.

31 July 2020 in Environments

Journal Article

Multi-Scale Modeling and Study of Aerosol Growth in an Amine-based CO₂ Capture Absorber

A monoethanolamine (MEA) aerosol growth model was developed to quantify the aerosol growth factor in an amine-based CO₂ capture absorber that considers the gas-liquid interactions, and it is empirically validated by measuring the aerosol particle size and concentration. The aerosol growth model, using sucrose as the aerosol nuclei instead of sulfuric acid to prevent the corrosion of the test equipment, accurately predicted that the outlet aerosol size increased to the same level regardless of the sucrose concentration. It also found that particle concentration was the primary factor affecting aerosol growth and amine emissions. We found an inverse relationship between aerosol particle concentration and the aerosol size, while the MEA emissions were proportional to particle concentration.

29 May 2023 in Polymers

Journal Article

A New Continuous Flow Microwave Radiation Process Design for Non-Isocyanate Polyurethane (NIPU)

Non-isocyanate Polyurethane (NIPU) has been known to result from a thermal-ring-opening reaction between bis-cyclic carbonate (BCC) compounds and polyamines. BCC can be obtained from carbon dioxide capture using an epoxidized compound. Microwave radiation has been found to be an alternative process to conventional heating for synthesizing NIPU on a laboratory scale. The microwave radiation process is far more efficient (>1000 times faster) than using a conventional heating reactor. Now, a flow tube reactor has been designed for a continuous and recirculating microwave radiation system for scaling up NIPU. Furthermore, the TOE (Turn Over Energy) of the microwave for a lab batch (24.61 g) reactor was 24.38 kJ/g. This decreased to 8.89 kJ/g with an increase in reaction size of up to 300 times with this new continuous microwave radiation system. This proves that synthesizing NIPU with this newly-designed continuous and recirculating microwave radiation process is not only a reliable energy-saving method, but is also convenient for scale-up, making it a green process.

5 July 2020 in Preprints.org

Preprint

Multi-scale Modeling and Study of Aerosol Growth on Amine-Based CO2 Capture Absorber

In this study, a monoethanolamine aerosol growth model was developed to investigate the aerosol growth factor. Interactions among the internal conditions in an absorber were considered in this aerosol model. Additionally, an experiment was conducted to measure aerosol particle size, for collecting in-house validation data. Sucrose was used as the aerosol nuclei instead of sulfuric acid to prevent the corrosion of equipment used in the experiment. Experimental results showed that the outlet aerosol sizes increased to the same size regardless of the sucrose concentrations. The aerosol growth model was validated using the in-house experimental data. The aerosol growth model efficiently predicted the aerosol size. For investigating aerosol growth effects, particle number concentration was determined to be the primary factor affecting aerosol growth and amine emissions. When the particle number concentration increased, the aerosol size decreased, whereas the MEA emission increased.

About Me

Expertise: • Process System Engineering/Chemical Engineering Thermodynamics/Process Design/Process Control/Unit Operations for Chemical Engineers • Applied Statistics for Chemical Engineers/Application of Data Science and Deep Machine Learning in Chemical Engineering • CO2 capture and utilization Research Intro: Over the last five years, I have conducted research in the following major areas: (1) CO2 capture and utilization (2) Biodegradable polymer materials process and product development and applications (3) Data analytics and artificial intelligence in manufacturing environment Our laboratory has received past and present funding from the National Science and Technology Council (NSTC), Taiwan; the Ministry of Education, Taiwan; and leading manufacturing companies such as China Steel Corporation, Taiwan; Chang Chun Petrochemical Group; Formosa Plastic Petrochemical; China Petrochemical Development Corporation; Yokogawa, Taiwan; Win Coat Corporation; H&H Corporation etc. Looking for collaborators in: • Process System Design and Control in Chemical Engineering • Big Data Analysis and Artificial Intelligence Application in chemical processes, steel plants, power plants, etc. • Deep Learning Application in molecules structure & properties

Prof. Dr. David Shan-Hill Wong

Prof. Dr. David Shan-Hill Wong

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me