Data-Driven Modeling and Cyclic Scheduling for Ethylene Cracking Furnace System with Inventory Constraints

Lin, Xinwei; Zhao, Liang; Du, Wenli; He, Wangli; Qian, Feng

doi:10.1021/acs.iecr.0c06085

Cited by 14 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, DR approaches can be used to predict the RL agent performance by comparing the current input data with the training data 99 . ML models can also serve as modeling components to complete the description of both the stochastic part (uncertainties) 100 and the deterministic part of the process such as predicting product yield given different grades of raw material in ethylene cracking furnaces 101 …”

Section: Ai Research and Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Towards artificial intelligence at scale in the chemical industry

et al. 2022

View full text Add to dashboard Cite

In the Industry 4.0 era, the chemical industry is embracing broad adoption of artificial intelligence (AI) and machine learning (ML) methods. This article provides a holistic view of how the industry is transforming digitally towards AI at scale. First, a historical perspective on how the industry used AI to aid humans in better decision‐making is shown. Then state‐of‐the‐art AI research addressing industrial needs on reliability and safety, process optimization, supply chain, material discovery, and reaction engineering is highlighted. Finally, a vision of the plant of the future is illustrated with critical components of AI‐ready culture, model life cycle management, and renewed role of humans in chemical manufacturing.

show abstract

Section: Ai Research and Applicationsmentioning

confidence: 99%

“…99 ML models can also serve as modeling components to complete the description of both the stochastic part (uncertainties) 100 and the deterministic part of the process such as predicting product yield given different grades of raw material in ethylene cracking furnaces. 101…”

Section: Supply Chainmentioning

confidence: 99%

Towards artificial intelligence at scale in the chemical industry

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Zhang et al 16 considered the operating features of nonhomogeneous last-batch ending times and furnace load makeups, as well as the background air quality during decoking. Lin et al 17 developed a data-driven yield model based on industrial data and incorporated inventory constraints in the scheduling model.…”

Section: Introductionmentioning

confidence: 99%

Two-Level Decoupled Ethylene Cracking Optimization of Batch Operation and Cyclic Scheduling

Zhang

Qiu

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Intelligent ethylene production relies on the coordination of advanced optimization techniques at different decision levels. For ethylene cracking, the occurrence of dynamic drift and the semi-continuous operation mode mean that decision variables at the operation and scheduling levels are coupled and jointly determine the system performance. Therefore, a collaborative operation and scheduling optimization framework is required to improve efficiency and profitability, but this is difficult to develop because of the coupled process variables. This paper proposes a novel decoupling strategy addressing the two-level ethylene optimization problem of batch operation and cyclic scheduling. Specifically, the operation-level optimization consists of a set of nonlinear programming (NLP) models that run in parallel with different feeds, furnaces, and batch run lengths. The resulted optimal batch operation subsequences and average yields are summarized into parameter tables and passed to the upper mixed-integer nonlinear programming (MINLP) model, which further determines the optimal feed allocation sequences and batch timings at the scheduling level. When applied to an industrial scheduling case, the two-level model improves the batch operations significantly, increasing the ethylene and propylene yields by 0.02–1.24 wt % and lengthening the maximum cracking time by 6–9 days for all feed types. Compared with the traditional scheduling model in which the coil outlet temperature (COT) is fixed, an increase of 2.5% in the profit margin is achieved with the use of a multi-time period operation model which allows the COT to vary and the maximum cracking days to lengthen, demonstrating the significant potential of the proposed two-level model for increasing ethylene cracking profit margins.

show abstract

“… 7 Lin et al developed a cyclic scheduling model for an ethylene cracking furnace system with inventory constraints to improve the efficiency of ethylene production. 8 Tarafder et al first applied multiobjective optimization to an industrial ethylene reactor to increase the profits. 9 Nabavi et al solved several multiobjective optimization problems of an industrial LPG thermal cracker, involving maximization of the annual ethylene/propylene production, selectivity, and run period and minimization of severity and total heat duty per year.…”

Section: Introductionmentioning

confidence: 99%

“…The actual control qualities were improved significantly, and the economic benefits were increased by a multiswarm competitive PSO algorithm based on fuzzy C-means clustering . Lin et al developed a cyclic scheduling model for an ethylene cracking furnace system with inventory constraints to improve the efficiency of ethylene production . Tarafder et al first applied multiobjective optimization to an industrial ethylene reactor to increase the profits .…”

Section: Introductionmentioning

confidence: 99%

Life Cycle Assessment and Multiobjective Optimization for Steam Cracking Process in Ethylene Plant

et al. 2022

Self Cite

View full text Add to dashboard Cite

With energy savings and emission reduction becoming national policies in recent years, the environmental impacts of industrial production are more and more critical. Most of the studies have concentrated on the environmental effects of the industrial production process. Little attention has been paid to the energy consumption and pollution emission in extracting, processing, and transporting the feedstock and other secondary materials. An integrated multiobjective optimization framework is proposed for the steam cracking process on the basis of a life cycle assessment and data-driven modeling methods. A multiobjective economic–environmental optimization model is developed on the basis of industrial and simulated data. A multiobjective optimization model combined with energy cost is also developed for comparative study. The nondominated sorting genetic algorithm-II is utilized to solve the problems, and the Pareto front is obtained. An industrial case study is carried out to indicate the effectiveness of the proposed method. The results show that the LCA-based method can better represent the environmental impacts in comparison with the standard energy cost model. Therefore, the proposed method can achieve a better tradeoff between economic benefits and environmental impacts for guiding ethylene production.

show abstract

Data-Driven Modeling and Cyclic Scheduling for Ethylene Cracking Furnace System with Inventory Constraints

Cited by 14 publications

References 34 publications

Towards artificial intelligence at scale in the chemical industry

Towards artificial intelligence at scale in the chemical industry

Two-Level Decoupled Ethylene Cracking Optimization of Batch Operation and Cyclic Scheduling

Life Cycle Assessment and Multiobjective Optimization for Steam Cracking Process in Ethylene Plant

Contact Info

Product

Resources

About