Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge

doi:10.1016/j.cjche.2025.07.001

中国化学工程学报 ›› 2025, Vol. 84 ›› Issue (8): 107-116.DOI: 10.1016/j.cjche.2025.07.001

• Full Length Article • 上一篇下一篇

Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge

Xin Wang¹, Shengxu Jin¹, Chengwei Cai³, Junran Luo⁴, Xiangshuai Tan², Yunfei Guo², Zhao Li², Jinghui Gao², Xinlin He², Litao Niu², Yicun Lin², Wei Zhao², Guangjin Chen¹, Chun Deng¹

1. College of Artificial Intelligence, State Key Laboratory of Heavy Oil Processing, China University of Petroleum, Beijing 102249, China;
2. Xi'an Thermal Power Research Institute Co., Ltd., Xi'an 710054, China;
3. Huaneng Dongguan Gas Turbine Thermal Power Co., Ltd., Dongguan 523590, China;
4. China Huaneng Group Co., Ltd. Guangxi Branch, Nanning 530000, China

收稿日期:2025-01-12 修回日期:2025-07-06 接受日期:2025-07-09 出版日期:2025-08-28 发布日期:2025-07-17
通讯作者: Xiangshuai Tan,E-mail:tanxiangshuai@tpri.com.cn;Yunfei Guo,E-mail:174644372@qq.com;Chun Deng,E-mail:chundeng@cup.edu.cn
基金资助:
This work was supported by the Jingneng Shiyan Thermal Power Co., Ltd. (TPRI/TR-CA-006-2023), Huaihe Energy Power Group Co., Ltd. (TPRI/TR-CA-040-2023) and Xi'an Thermal Power Research Institute Co., Ltd. (TPRI/TR-CA-110-2021A/H1).

Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge

Xin Wang¹, Shengxu Jin¹, Chengwei Cai³, Junran Luo⁴, Xiangshuai Tan², Yunfei Guo², Zhao Li², Jinghui Gao², Xinlin He², Litao Niu², Yicun Lin², Wei Zhao², Guangjin Chen¹, Chun Deng¹

1. College of Artificial Intelligence, State Key Laboratory of Heavy Oil Processing, China University of Petroleum, Beijing 102249, China;
2. Xi'an Thermal Power Research Institute Co., Ltd., Xi'an 710054, China;
3. Huaneng Dongguan Gas Turbine Thermal Power Co., Ltd., Dongguan 523590, China;
4. China Huaneng Group Co., Ltd. Guangxi Branch, Nanning 530000, China

Received:2025-01-12 Revised:2025-07-06 Accepted:2025-07-09 Online:2025-08-28 Published:2025-07-17
Contact: Xiangshuai Tan,E-mail:tanxiangshuai@tpri.com.cn;Yunfei Guo,E-mail:174644372@qq.com;Chun Deng,E-mail:chundeng@cup.edu.cn
Supported by:
This work was supported by the Jingneng Shiyan Thermal Power Co., Ltd. (TPRI/TR-CA-006-2023), Huaihe Energy Power Group Co., Ltd. (TPRI/TR-CA-040-2023) and Xi'an Thermal Power Research Institute Co., Ltd. (TPRI/TR-CA-110-2021A/H1).

摘要/Abstract

摘要： Thermal power generation systems have stringent requirements for water and steam quality, i.e., condensate water quality is one of the critical issues. In this paper, we designed a two-layer model based on an autoencoder and expert knowledge to achieve the early warning and causal analysis of condensate water quality abnormalities. An early warning model using an autoencoder model is built based on the historical data affecting the condensate water quality. Next, an analytical model of condensate water quality abnormalities was then developed by combining expert knowledge and trend test algorithms. Two different datasets were used to test the proposed model, respectively. The accuracy of the autoencoder model in the short-period test set is 88.83%, which shows that the early warning model can accurately analyze the condensate water quality data and achieve the purpose of early warning. For the long-time period test set, the model can correctly identify each abnormality and simultaneously indicates the cause of the abnormal condensate water quality. The proposed model can correctly identify abnormal working conditions and it is applicable to other thermal power plants.

关键词: Early warning, Data-driven, Condensate water quality, Abnormality detection, Algorithm, Neural network

Abstract: Thermal power generation systems have stringent requirements for water and steam quality, i.e., condensate water quality is one of the critical issues. In this paper, we designed a two-layer model based on an autoencoder and expert knowledge to achieve the early warning and causal analysis of condensate water quality abnormalities. An early warning model using an autoencoder model is built based on the historical data affecting the condensate water quality. Next, an analytical model of condensate water quality abnormalities was then developed by combining expert knowledge and trend test algorithms. Two different datasets were used to test the proposed model, respectively. The accuracy of the autoencoder model in the short-period test set is 88.83%, which shows that the early warning model can accurately analyze the condensate water quality data and achieve the purpose of early warning. For the long-time period test set, the model can correctly identify each abnormality and simultaneously indicates the cause of the abnormal condensate water quality. The proposed model can correctly identify abnormal working conditions and it is applicable to other thermal power plants.

Key words: Early warning, Data-driven, Condensate water quality, Abnormality detection, Algorithm, Neural network

Xin Wang, Shengxu Jin, Chengwei Cai, Junran Luo, Xiangshuai Tan, Yunfei Guo, Zhao Li, Jinghui Gao, Xinlin He, Litao Niu, Yicun Lin, Wei Zhao, Guangjin Chen, Chun Deng. Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge[J]. 中国化学工程学报, 2025, 84(8): 107-116.

参考文献

[1] O. Mahian, M.R. Mirzaie, A. Kasaeian, S.H. Mousavi, Exergy analysis in combined heat and power systems: a review, Energy Convers. Manag. 226 (2020) 113467.
[2] Y.T. Ling, S.M. Xia, M.Q. Cao, K.R. He, M.K. Lim, A. Sukumar, H.Y. Yi, X.D. Qian, Carbon emissions in China’s thermal electricity and heating industry: an input-output structural decomposition analysis, J. Clean. Prod. 329 (2021) 129608.
[3] K.X. He, T. Wang, F.K. Zhang, X. Jin, Anomaly detection and early warning via a novel multiblock-based method with applications to thermal power plants, Measurement 193 (2022) 110979.
[4] H. Qian, B. Sun, Y.J. Guo, Z.L. Yang, J. Ling, W. Feng, A parallel deep learning algorithm with applications in process monitoring and fault prediction, Comput. Electr. Eng. 99 (2022) 107724.
[5] P. Hundi, R. Shahsavari, Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants, Appl. Energy 265 (2020) 114775.
[6] R. Laubscher, Time-series forecasting of coal-fired power plant reheater metal temperatures using encoder-decoder recurrent neural networks, Energy 189 (2019) 116187.
[7] L.F. Yin, J.X. Xie, Multi-feature-scale fusion temporal convolution networks for metal temperature forecasting of ultra-supercritical coal-fired power plant reheater tubes, Energy 238 (2022) 121657.
[8] J.H. Chen, H.K. Li, D.R. Sheng, W. Li, A hybrid data-driven modeling method on sensor condition monitoring and fault diagnosis for power plants, Int. J. Electr. Power Energy Syst. 71 (2015) 274-284.
[9] J. Yu, J. Yoo, J. Jang, J.H. Park, S. Kim, A novel plugged tube detection and identification approach for final super heater in thermal power plant using principal component analysis, Energy 126 (2017) 404-418.
[10] K. Rostek, L. Morytko, A. Jankowska, Early detection and prediction of leaks in fluidized-bed boilers using artificial neural networks, Energy 89 (2015) 914-923.
[11] G.L. Li, Y.J. Li, C.Y. Fang, J. Su, H.T. Wang, S.D. Sun, G.L. Zhang, J.X. Shi, Research on fault diagnosis of supercharged boiler with limited data based on few-shot learning, Energy 281 (2023) 128286.
[12] N. Indrawan, L.J. Shadle, R.W. Breault, R. Panday, U.K. Chitnis, Data analytics for leak detection in a subcritical boiler, Energy 220 (2021) 119667.
[13] Y.X. Dong, Y. Yao, J.S. Zeng, S.H. Luo, C.H. Gao, Isolation of overtemperature fault in an industrial boiler using tree-structured sparsity-based reconstruction, Ind. Eng. Chem. Res. 61 (19) (2022) 6575-6586.
[14] M.L. Bai, X.S. Yang, J.F. Liu, J. Liu, D.R. Yu, Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers, Appl. Energy 302 (2021) 117509.
[15] M.L. Bai, J.F. Liu, J.H. Chai, X.Y. Zhao, D.R. Yu, Anomaly detection of gas turbines based on normal pattern extraction, Appl. Therm. Eng. 166 (2020) 114664.
[16] N. Basha, C. Kravaris, H. Nounou, M. Nounou, Bayesian-optimized Gaussian process-based fault classification in industrial processes, Comput. Chem. Eng. 170 (2023) 108126.
[17] M. Wang, D.H. Zhou, M.Y. Chen, Y.W. Wang, Anomaly detection in the fan system of a thermal power plant monitored by continuous and two-valued variables, Control Eng. Pract. 102 (2020) 104522.
[18] J.D. Wang, Z.J. Yang, J.J. Su, Y. Zhao, S. Gao, X.K. Pang, D.H. Zhou, Root-cause analysis of occurring alarms in thermal power plants based on Bayesian networks, Int. J. Electr. Power Energy Syst. 103 (2018) 67-74.
[19] C.Z. Huang, X.X. Sheng, Data-driven model identification of boiler-turbine coupled process in 1000 MW ultra-supercritical unit by improved bird swarm algorithm, Energy 205 (2020) 118009.
[20] T. Li, Y.M. Han, Y.Q. Wang, Z.Q. Geng, A self-attention mechanism integrating adaptive double subspace for fault detection in industrial processes, IEEE Trans. Syst. Man Cybern. Syst. 55 (1) (2025) 540-549.
[21] Y.T. Zhang, J.H. Wang, C.L. Li, H.P. Duan, W.H. Wang, Attention-based deep learning models for predicting anomalous shock of wastewater treatment plants, Water Res. 275 (2025) 123192.
[22] Z. Zhang, Y.M. Han, B. Ma, Z.Q. Geng, A time series self-supervised contrastive pretraining method with data augmentation using discrepancy of reconstruction information loss, IEEE Trans. Instrum. Meas. 74 (2025) 2514512.
[23] Y.D. Shu, L. Ming, F.F. Cheng, Z.P. Zhang, J.S. Zhao, Abnormal situation management: Challenges and opportunities in the big data era, Comput. Chem. Eng. 91 (2016) 104-113.
[24] M. aurelio Ranzato, C. Poultney, S. Chopra, Y. Cun, Efficient Learning of Sparse Representations with an Energy-Based Model, in: B. Scholkopf, J. Platt, T. Hoffman (Eds.), Adv. Neural Inf. Process. Syst., MIT Press, 2006.
[25] J.Q. Zhu, F. Deng, J.C. Zhao, J. Chen, Adaptive aggregation-distillation autoencoder for unsupervised anomaly detection, Pattern Recognit. 131 (2022) 108897.
[26] A.S. D. R. Cox, Some quick sign tests for trend in location and dispersion, Biometrika 42 (1/2) (1955) 80-95.

Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge

Two-layer model for the early warning and analysis of condensate water quality abnormalities based on autoencoder and expert knowledge

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Qingyu Wang, Duiping Liu, Yong Lu, Jibin Zhou, Xiangang Ma, Mao Ye. Deep learning approach for morphology classification and particle sizing of industrial methanol-to-olefins (MTO) catalyst[J]. 中国化学工程学报, 2025, 84(8): 1-10.
[2]	Nan Liu, Chunmeng Zhu, Zeng Li, Yunpeng Zhao, Xiaogang Shi, Xingying Lan. Hierarchical framework for predictive maintenance of coking risk in fluid catalytic cracking units: A data and knowledge-driven method[J]. 中国化学工程学报, 2025, 84(8): 35-46.
[3]	Ali Tarik Karagoz, Omar Alqusair, Chao Liu, Jie Li. Advances in conceptual process design: From conventional strategies to AI-assisted methods[J]. 中国化学工程学报, 2025, 84(8): 60-76.
[4]	Dian Zhang, Bo Ouyang, Zheng-Hong Luo. Reaction process optimization based on interpretable machine learning and metaheuristic optimization algorithms[J]. 中国化学工程学报, 2025, 84(8): 77-85.
[5]	Tiantong Zhang, Haolin Cheng, Yao Nian, Jinli Zhang, Qingbiao Li, You Han. Application of generative artificial intelligence in catalysis[J]. 中国化学工程学报, 2025, 84(8): 86-95.
[6]	Zhenhua Yu, Guan Wang, Qingchao Jiang, Xuefeng Yan. Process fault root cause diagnosis through state evolution mapping based on temporal unit shapelets[J]. 中国化学工程学报, 2025, 84(8): 96-106.
[7]	Zhi Ma, Peng Cui, Xu Wang, Lanyu Li, Haoxiang Xu, Adrian Fisher, Daojian Cheng. The integration of artificial intelligence and high-throughput experiments: An innovative driving force in catalyst design[J]. 中国化学工程学报, 2025, 84(8): 117-132.
[8]	Zheyuan Pang, Siying Liu, Yiting Lin, Xiangchen Fang, Honglai Liu, Chong Peng, Cheng Lian. Large language model-based multi-objective modeling framework for vacuum gas oil hydrotreating[J]. 中国化学工程学报, 2025, 84(8): 133-145.
[9]	Zhenhua Yu, Zongyu Yao, Weijun Wang, Qingchao Jiang, Zhixing Cao. SmdaNet: A hierarchical hard sample mining and domain adaptation neural network for fault diagnosis in industrial process[J]. 中国化学工程学报, 2025, 84(8): 146-157.
[10]	Xiaodong Hong, Yudong Shen, Zuwei Liao, Yongrong Yang. Machine-learning-assisted high-throughput computational screening of the n-hexane cracking initiator[J]. 中国化学工程学报, 2025, 84(8): 190-200.
[11]	Yuan Wang, Mengyue Chen, Jingwei Tian, Weidong Zhang, Dahuan Liu. A data-driven predictive model for solubility: A case study of the NaCl-Na₂SO₄-H₂O system[J]. 中国化学工程学报, 2025, 84(8): 254-265.
[12]	Haowei Li, Bingzhu Min, Yaling Gong, Linsheng Li, Xingbao Wang, Yimeng Zhu, Wenying Li. Molecular design of high energy density fuels from coal-to-liquids[J]. 中国化学工程学报, 2025, 84(8): 266-273.
[13]	Zenan Tian, Zhiyu Zhang, Xiang Li, Xinxin Gao, Ziru Ren, Xiaobin Zhang. Evaluation of live Cryo-ECT system for liquid nitrogen-vapor nitrogen flow[J]. 中国化学工程学报, 2025, 82(6): 246-255.
[14]	Zhe Wang, Renchu He, Jian Long. A systematic data-driven modelling framework for nonlinear distillation processes incorporating data intervals clustering and new integrated learning algorithm[J]. 中国化学工程学报, 2025, 81(5): 182-199.
[15]	Xiaoyu Zhou, Erwei Song, Mingmei Wang, Erqiang Wang. Dynamic temperature control of dividing wall batch distillation with middle vessel based on neural network soft-sensor and fuzzy control[J]. 中国化学工程学报, 2025, 79(3): 200-211.