Download Brochure!
Feel free to fill in the form to download brochure.
Feel free to fill in the form to download brochure.
Department of Research and Development, Jam Petrochemical Company
Measuring polyethylene properties in the laboratory is time-consuming and usually not available in real time, posing significant challenges for controlling product quality in polymerization plants. This research focuses on developing multivariate data-driven soft sensors for online monitoring and prediction of key characteristics. The targeted properties for prediction include the melt flow index (MFI), density, and average particle diameter in the gas-phase fluidized bed reactor, as well as the MFI and flow rate ratio (FRR) in the slurry-phase process. An exhaustive examination using an ensemble learning approach was conducted to determine the importance scores of process variables. Various machine learning (ML) algorithms were trained and validated using datasets from industrial ethylene polymerization plants. The precision of the ML models was improved by splitting the datasets into categories, comprising high and low MFI and FRR, as well as linear low-density and high-density clusters. Then, segmented ML models were developed for each cluster. The results demonstrated that the segmented ML models utilizing optimized Gaussian process regression models with suitable kernel functions and ensemble bagged tree models offered the highest accuracy in predicting the MFI, FRR, and density. Additionally, the comprehensive ML model without clustering, utilizing Gaussian process regression with an isotropic exponential kernel function, proved to be the most effective at predicting the average particle diameter.
Farzad Jani holds a Master’s degree in Chemical Engineering and has over 16 years of extensive experience in polyethylene production and research. He is currently a key member of the R&D department at Jam Petrochemical Company, where his work focuses on polyolefin characterization, structure-property relationships, and the application of advanced technologies. His areas of expertise include machine learning, acoustic emission, signal processing, fiber optic and piezoelectric sensors, as well as innovations in polyolefin production and process control. His work is distinguished by a strong ability to bridge fundamental research with practical industrial applications in the petrochemical sector.
Full name: Farzad Jani
Contact number: 00989126938523
Linked In account: https://www.linkedin.com/in/farzad-jani-663119172/
Session name/ number: Machine Learning/ 1
Category: Poster presentation