Enhanced Procurement and Production Strategies for Chemical Plants: Utilizing Real-Time Financial Data and Advanced Algorithms

This paper presents an implementation of an automated algorithm powered by market and physical data to improve procurement and production of a chemical plant with the goal of improving the overall economics on the entity. Herein, the algorithm is applied to two scenarios that serve as case studies: conversion of natural gas to methanol and crude palm oil to biodiesel. The program anticipates opportunities to increase profit or avoid loss by analyzing the futures market prices for both reagents and the products while considering cost of storage and conversion derived from physical simulations of the chemical process. Analysis conducted on June 11, 2018, in the biodiesel scenario shows that up to 219.28 USD per tonne of biodiesel can be earned by buying contracts for delivery of crude palm oil in July 2018 and selling contracts for delivery of biodiesel in August 2018 which equates to a margin 11.6% higher than in case of the direct trade. Moreover, it is shown that losses of up to 11.3% can be avoided, and therefore, it is shown that there is realistic scope for increasing the profitability of a chemical plant by exploiting the opportunities across different commodity markets in an automated manner. Consequently, such a cyber system can be used to assist eco-industrial parks with supply chain management, production planning, as well as financial risk governance and, in the end, help to establish a long-term strategy. This study is part of a holistic endeavor that applies cyber physical systems to optimize eco-industrial parks so that energy use and emissions are minimized while economic output is maximized.