No abstract

Raman spectroscopy is a widely used technique for organic and inorganic chemical material identification. Throughout the last century, major improvements in lasers, spectrometers, detectors, and holographic optical components have uplifted Raman spectroscopy as an effective device for a variety of different applications including fundamental chemical and material research, medical diagnostics, bio-science, in-situ process monitoring and planetary investigations. Undoubtedly, mathematical data analysis has been playing a vital role to speed up the migration of Raman spectroscopy to explore different applications. It supports researchers to customize spectral interpretation and overcome the limitations of the physical components in the Raman instrument. However, large, and complex datasets, interferences from instrumentation noise and sample properties which mask the true features of samples still make Raman spectroscopy as a challenging tool. Deep learning is a powerful machine learning strategy to build exploratory and predictive models from large raw datasets and has gained more attention in chemical research over recent years. This chapter demonstrates the application of deep learning techniques for Raman signal-extraction, feature-learning and modelling complex relationships as a support to researchers to overcome the challenges in Raman based chemical analysis.

Process analyzers for in-situ monitoring give advantages over the traditional analytical methods such as their fast response, multi-chemical information from a single measurement unit, minimal errors in sample handing and ability to use for process control. This study discusses the suitability of Raman spectroscopy as a process analytical tool for in-situ monitoring of CO2 capture using aqueous monoethanolamine (MEA) solution by presenting its performance during a 3-day test campaign at PACT pilot plant in Sheffield, UK. Two Raman immersion probes were installed on lean and rich streams for real time measurements. A multivariate regression model was used to determine the CO2 loading. The plant performance is described in detail by comparing the CO2 loading in each solvent stream at different process conditions. The study shows that the predicted CO2 loading recorded an acceptable agreement with the offline measurements. The findings from this study suggest that Raman Spectroscopy has the capability to follow changes in process variables and can be employed for real time monitoring and control of the CO2 capture process. In addition, these predictions can be used to optimize process parameters; to generate data to use as inputs for thermodynamic models, plant design and scale-up scenarios.

No abstract

No abstract