SABIC Global Technologies

The invention relates to a method for producing monoalkylene glycol, the method comprising: a) flowing a feed stream comprising alkylene oxide and water into a first reactor unit; b) subjecting the feed stream, in the first reactor unit, to first reaction conditions to obtain a first effluent comprising monoalkylene glycol, unreacted alkylene oxide and unreacted water, wherein the first reaction conditions in the first reactor unit are non-catalytic reaction conditions; c) flowing at least a portion of the first effluent to a second reactor unit; and d) subjecting said portion of the first effluent, in the second reactor unit, to second reaction conditions to obtain a second effluent comprising monoalkylene glycol, wherein the second reactor unit comprises a reactor comprising a catalyst bed and the second reaction conditions in the second reactor unit are catalytic reaction conditions.

Disclosed here are methods and systems to determine asset status in an industrial plant. Embodiments of the method may include, during operation of an asset positioned at the industrial plant and, iteratively, at each of a plurality of selected time intervals, receiving a plurality of data streams from sensors or devices of the asset. The method may include determining, based on application of each of the plurality of pre-processed data streams received to each of a plurality of trained machine learning models, anomaly scores. The method may include determining, via a plurality of votes based on the anomaly scores, a status for the sensors and/or devices. The method may include, if the status for the sensors and/or devices for the asset indicates an anomaly for a consecutive two or more of the plurality of time intervals, generating a next action notification to indicate the anomaly and prevent unplanned downtime.

A dynamic catalyst lifecycle model is described. In some embodiments, real-time external data associated with a catalyst is captured. Actual operational data associated with a petrochemical plant is obtained and the catalyst is used in chemical processes at the petrochemical plant. A selectivity of the catalyst is continuously predicted under different loads and in real-time using a trained machine learning model. The actual operational data and the real-time external data are used as inputs to the trained machine learning model and the trained machine learning model is trained using an actual selectivity and historical catalyst performance.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …