Polymer Reactor shutdown analysis ​

In recent years , chemical processes have necessitated the use of complex facilities and sophisticated settings. If the facilities are shut down unexpectedly, it could harm the environment and and lead to safety hazards due to the chemical substances' properties, as well as a financial loss due to operating costs. As a result, it's critical to avoid an unplanned shutdown by detecting anomalous factors in the process facilities' operation in advance.

To predict symptoms from responses in the petrochemical polypropylene (PP) process reactor and avoid an emergency shutdown (ESD), a data-based anomaly detection model derived from machine learning and deep learning is used.

It is possible to predict anomalies in the petrochemical PP process up to 7 days in advance. Early detection of an emergency shutdown (ESD) reduces operation costs as well as environmental and safety risks.