Two-level comprehensive energy-efficiency quantitative diagnosis scheme for ethylene-cracking furnace with multi-working-condition of fault and exception operation

Abstract Because ethylene-cracking furnace accounts for vast majority of energy consumption in ethylene production, energy-efficiency diagnosis of ethylene-cracking furnace is of great significance for improving energy utilization and production operation. In this paper, a two-level comprehensive energy-efficiency diagnosis problem is considered for both furnace level and internal chambers level. Apart from production load and feed composition, fault and exception operation also have influence on energy-efficiency, which leads to a multiple-working-condition energy-efficiency diagnosis problem under fault and exception operation. Therefore, this paper proposes a new energy-efficiency diagnosis scheme for ethylene-cracking furnace. Firstly, a two-level index system is designed to have an overall understanding of energy-efficiency of ethylene-cracking furnace and internal chambers. Secondly, fault and operation diagnosis criteria are established to identify fault samples, exception operation samples, and fault-and-exception-operation samples from inefficient samples after multi-working-condition division. Thirdly, contributions of operation conditions, outputs, and internal chamber are quantified by step-by-step transformation and total differential methods to locate weak links in energy-efficiency. Finally, effectiveness of diagnosis scheme is verified by applying it to a Chinese ethylene plant. Not only are three inefficient types detected, but also contributions of root causes resulting in inefficiency are quantified, which provides energy conservation and efficiency improvement suggestions for decision-makers.

[1]  Lei Xie,et al.  Deep Learning With Tensor Factorization Layers for Sequential Fault Diagnosis and Industrial Process Monitoring , 2020, IEEE Access.

[2]  Chudong Tong,et al.  Sparse Robust Principal Component Analysis with Applications to Fault Detection and Diagnosis , 2019, Industrial & Engineering Chemistry Research.

[3]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[4]  Adel Alblawi,et al.  Fault diagnosis of an industrial gas turbine based on the thermodynamic model coupled with a multi feedforward artificial neural networks , 2020 .

[5]  Zhiqiang Geng,et al.  Performance analysis and optimal temperature selection of ethylene cracking furnaces: A data envelopment analysis cross-model integrated analytic hierarchy process , 2016 .

[6]  ChangKyoo Yoo,et al.  Statistical process monitoring with independent component analysis , 2004 .

[7]  Mohammadreza Tahan,et al.  A multi-nets ANN model for real-time performance-based automatic fault diagnosis of industrial gas turbine engines , 2017 .

[8]  Zhichao Li,et al.  A probabilistic principal component analysis-based approach in process monitoring and fault diagnosis with application in wastewater treatment plant , 2019, Appl. Soft Comput..

[9]  Cheng Shao,et al.  Ethylene cracking furnace TOPSIS energy efficiency evaluation method based on dynamic energy efficiency baselines , 2018 .

[10]  Andrea Lazzaretto,et al.  On the Thermoeconomic Approach to the Diagnosis of Energy System Malfuntions. Part-1 The TADEUS Problem , 2002 .

[11]  Ning Jin,et al.  Energy Efficiency Solutions for Buildings: Automated Fault Diagnosis of Air Handling Units Using Generative Adversarial Networks , 2019, Energies.

[12]  Siliang Lu,et al.  Efficient Data Reduction at the Edge of Industrial Internet of Things for PMSM Bearing Fault Diagnosis , 2021, IEEE Transactions on Instrumentation and Measurement.

[13]  Yan-Lin He,et al.  Energy modeling and saving potential analysis using a novel extreme learning fuzzy logic network: A case study of ethylene industry , 2018 .

[14]  Hongbo Shi,et al.  A Novel Dynamic Weight Principal Component Analysis Method and Hierarchical Monitoring Strategy for Process Fault Detection and Diagnosis , 2020, IEEE Transactions on Industrial Electronics.

[15]  Sheng Chen,et al.  Nonlinear Process Fault Diagnosis Based on Serial Principal Component Analysis , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Diego Cabrera,et al.  Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator , 2020, Applied Sciences.

[17]  Lei Wang,et al.  Modified kernel principal component analysis using double-weighted local outlier factor and its application to nonlinear process monitoring. , 2017, ISA transactions.

[18]  Chanathip Pharino,et al.  Energy, environmental, and economic analysis of energy conservation measures in Thailand's upstream petrochemical industry , 2016 .

[19]  A. Pérez-Navarro,et al.  Diagnosis of a battery energy storage system based on principal component analysis , 2020 .

[20]  Cheng Shao,et al.  Multi-level and multi-granularity energy efficiency diagnosis scheme for ethylene production process , 2019 .

[21]  Li Zhu,et al.  An energy efficiency integration optimization scheme for ethylene production with respect to multiple working conditions , 2019 .

[22]  Jing Wang,et al.  Fault diagnosis of industrial process based on the optimal parametric t-distributed stochastic neighbor embedding , 2020, Science China Information Sciences.

[23]  Youxian Sun,et al.  A novel fault diagnosis method based on optimal relevance vector machine , 2017, Neurocomputing.

[24]  Shengwei Wang,et al.  A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression , 2013 .

[25]  Wei Sun,et al.  PCA-SDG Based Process Monitoring and Fault Diagnosis: Application to an Industrial Pyrolysis Furnace , 2018 .

[26]  Richard Binns,et al.  Cascaded Sagnac Loops Embedded With Two Polarization Maintaining Photonic Crystal Fibers for Highly Sensitive Strain Measurement , 2021, IEEE Transactions on Instrumentation and Measurement.

[27]  F. H. Nordin,et al.  Fault Detection and Diagnosis of Industrial Robot Based on Power Consumption Modeling , 2020, IEEE Transactions on Industrial Electronics.

[28]  Jocelyn Chanussot,et al.  Multimodal hyperspectral remote sensing: an overview and perspective , 2021, Sci. China Inf. Sci..

[29]  Wenwu Wang,et al.  The Band Structures of Zn 1−x Mg x O(In) and the Simulation of CdTe Solar Cells with a Zn 1−x Mg x O(In) Window Layer by SCAPS , 2019 .