PTQ Q2 2024 Issue

Optimising furnace run length in a steam cracker using AI

Case study on improving ethylene furnace run length by leveraging the synergy of digitalisation and artificial intelligence to provide the necessary insights

Surabhi Thorat and Vivek Srinivasan Dorf Ketal Chemical (I) Pvt Ltd Sudarshan Vijayaraghavan Dorf Ketal Chemicals PTE Ltd

E thylene serves as a predominantly petrochemically derived monomer essential for producing plastics, fibres, and various organic chemicals. These end -products find applications across industries such as pack - aging, transportation, construction, and other industrial and consumer markets. Notably, more than half of global ethyl - ene derivative consumption is attributed to non-durable or consumable end uses, especially in packaging. The majority of this consumption is associated with poly - ethylene, a plastic resin that constitutes most ethylene usage. Given its status as one of the largest volume petrochemicals globally, the consumption of ethylene is influenced by eco - nomic and energy cycles. Its extensive and diverse derivative portfolio, covering both non-durable and durable end uses, positions ethylene as a benchmark for gauging the overall performance of the petrochemical industry. Furnace efficiency In the complex realm of ethylene production, furnace efficiency plays a pivotal role in determining overall operational success. However, a significant challenge arises from shortened run lengths, increasing downtime and production costs. This issue is rooted in the increasing tube metal temperature (TMT) of the furnace, a critical factor affecting operational longevity. A decrease in run length in an ethylene furnace due to coke formation and a rise in TMT can result in significant financial losses for several reasons. Here are some potential factors contributing to the financial impact: • Production interruption: Reduced run length means the ethylene furnace is not operating at its optimal capacity for the intended duration. This interruption in production can lead to lower yields of ethylene and other desired products, resulting in lost revenue. • Increased decoking: Coke formation and elevated TMT may call for frequent decoking, resulting in higher energy costs and reduced capacity utilisation rates. Frequent decok - ing can also affect the overall reliability of the tubes, compro - mising the life span of radiant tubes. • Energy consumption: A less efficient furnace may require more energy to maintain the desired operating conditions. Higher energy consumption not only leads to increased operational costs but also contributes to environmental con - cerns if the energy source is not sustainable.

• Impact on selectivity: Inefficient furnace operation, com - bined with a high potential for coking, leads to a critical TMT threshold during mid-run cycles, constraining achiev - able severity levels. Consequently, this limitation adversely affects the overall selectivity for ethylene make. • Market dynamics: In the competitive petrochemical indus - try, delays or interruptions in production can affect a compa- ny’s ability to meet customer demands. This can result in lost market share and potential long-term damage to business relationships. • Increased emission and environmental impact: Poorly optimised furnace operations tend to emit higher levels of greenhouse gases, thereby exacerbating the carbon foot - print, as furnaces are commonly fuelled by fossil fuels. The frequent decoking process also introduces further emissions, compounding an already elevated environmental impact. To mitigate these financial losses, it is crucial for plant operators to implement effective monitoring, maintenance, and operational strategies to prevent or address issues such as coke formation and elevated TMTs in a timely man - ner. Regular inspections, proper decoking procedures, and adherence to best practices in furnace operation can contrib - ute to improved efficiency and extended run lengths. Differentiator Understanding and addressing elevated TMTs is key to overcoming these aforementioned challenges. Dorf Ketal’s proprietary artificial intelligence (AI) solution CokeNil offers solutions to extend run lengths through predictive mainte - nance, optimised process control, and improved fault detec- tion. It is a data-driven, deep domain insight-based solution where every process parameter is evaluated thoroughly in the exploratory data analysis phase to ensure the accuracy of the outcome. It is built on advanced deep learning methods such as long short-term memory (LSTM) networks, Random Forest regression, CatBoost regression, XGBoost regression, and time series algorithms to help the model identify the pat- tern and behaviour of each critical process parameter. CokeNil is a unique AI solution for optimising the furnace run length. This plant’s distributed control system (DCS) feeds live operating conditions (such as naphtha feed com - position, coil outlet temperature, steam-to-hydrocarbon ratio [SHC], temperature, and fuel flow) to the CokeNil. These are

PTQ Q2 2024