Study on Fault Early Warning of Induced Draft Fan Based on TCN-SDAE Model and Adaptive Dynamic Threshold

ZHU Guoxiong; ZHANG Xiaoning; XU Jian; YAO Jun; NIU Yuguang; WANG Qinghua; LIU Jizhen

doi:10.19805/j.cnki.jcspe.2026.250346

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Study on Fault Early Warning of Induced Draft Fan Based on TCN-SDAE Model and Adaptive Dynamic Threshold

更新时间：2026-07-16

- Study on Fault Early Warning of Induced Draft Fan Based on TCN-SDAE Model and Adaptive Dynamic Threshold
- Chinese Journal of Power Engineering Vol. 46, Issue 7, Pages: 104-112,192(2026)
- 作者机构：
  
  1. 华北电力大学控制与计算机工程学院,北京,102206
  2. 北京怀柔实验室,北京,101400
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2026.250346
  CLC： TK223.2
- Published：2026
- 稿件说明：
移动端阅览
朱国雄, 张效宁, 徐健, 姚珺, 牛玉广, 王庆华, 刘吉臻. 基于TCN-SDAE模型与自适应动态阈值的引风机故障预警研究[J]. 动力工程学报, 2026, 46(7): 104-112,192.
朱国雄, 张效宁, 徐健, 姚珺, 牛玉广, 王庆华, 刘吉臻. 基于TCN-SDAE模型与自适应动态阈值的引风机故障预警研究[J]. 动力工程学报, 2026, 46(7): 104-112,192. DOI： 10.19805/j.cnki.jcspe.2026.250346.

DOI： 10.19805/j.cnki.jcspe.2026.250346

摘要

为提升引风机故障预警的准确性与可靠性

提出一种融合时间卷积网络(TCN)与堆叠降噪自编码器(SDAE)的无监督智能预警方法。该方法创新性地结合TCN的时序建模能力与SDAE的特征压缩优势

基于引风机正常运行数据构建预测模型

采用重构误差的马氏距离衡量状态偏离程度

并结合滑动时间窗口与切比雪夫不等式实现多变量动态阈值设定

有效提升了异常检测的精准性与适应性。为增强判别鲁棒性

设计连续越限机制以抑制瞬时波动干扰;同时引入变量越限热力图

实现对关键异常变量的可视化解释

显著提升了模型结果的可理解性与运维支持价值。在某300 MW燃煤电厂引风机运行场景下的实证研究表明:该方法能够实现故障的早期识别

具备良好的鲁棒性与动态工况适应能力;所提方法可为辅机系统智能监测提供技术支撑

助力智慧电厂的安全稳定运行

具有良好的工程应用前景。

Abstract

To enhance the accuracy and reliability of fault early warning of induced draft fan

an unsupervised intelligent early warning method that integrated temporal convolutional network (TCN) and stacked denoising autoencoder (SDAE) was proposed. By innovatively combining the temporal modeling capability of TCN and the feature abstraction strength of SDAE

a predictive model was constructed using normal operating data of the induced draft fan. Mahalanobis distance of the reconstruction error was used to quantify deviations from expected behavior

and a sliding time window combined with Chebyshev inequality was employed to establish dynamic multivariate warning thresholds

effectively improving precision and adaptability of anomaly detection. To enhance the robustness of identification

a consecutive threshold-exceedance mechanism was designed to suppress transient disturbances. Meanwhile

a variable-level exceedance heatmap was introduced to visualize the degree and evolution of anomalies across monitored features

significantly improving the interpretability and operational relevance of the results. Experimental validation on a 300 MW coal-fired power plant demonstrated that the method enabled timely identification of potential faults and exhibited strong robustness and adaptability. The proposed approach provides a practical solution for intelligent monitoring of auxiliary systems and supports the safe and stable operation of smart power plants

and is promising for engineering application.

关键词

Keywords

references

刘吉臻, 李云鸷, 宋子秋, 等. 灵活智能燃煤发电技术及评价体系[J]. 动力工程学报, 2022, 42(11): 993-1004, 1012. LIU Jizhen, LI Yunzhi, SONG Ziqiu, et al. Flexible and intelligent coal-fired power generation technology and its evaluation system[J]. Journal of Chinese Society of Power Engineering, 2022, 42(11): 993-1004, 1012.

王庆华, 刘吉臻, 樊欢豹, 等. 支撑我国能源转型的灵活燃煤发电新技术: 锅炉系统及汽轮发电机系统[J]. 中国电机工程学报, 2024, 44(18): 7136-7167. WANG Qinghua, LIU Jizhen, FAN Huanbao, et al. Novel technologies of flexible coal-fired power generation to support China energy transition: boiler system and turbine generator system[J]. Proceedings of the CSEE, 2024, 44(18): 7136-7167.

张维, 刘吉臻, 高明明. 基于数据挖掘的循环流化床锅炉辅机故障预警[J]. 动力工程学报, 2019, 39(10): 826-833. ZHANG Wei, LIU Jizhen, GAO Mingming. Early fault warning of auxiliary equipment for circulating fluidized bed boilers based on data mining[J]. Journal of Chinese Society of Power Engineering, 2019, 39(10): 826-833.

HU Di, CHEN Gang, YANG Tao, et al. An artificial neural network model for monitoring real-time parameters and detecting early warnings in induced draft fan[C]//ASME 201813th International Manufacturing Science and Engineering Conference. College Station, USA: ASME, 2018.

CHEN Xiaolong, WANG Peihong, HAO Yongsheng, et al. Evidential KNN-based condition monitoring and early warning method with applications in power plant[J]. Neurocomputing, 2018, 315: 18-32.

LI Yanping, HONG Feng, TIAN Liang, et al. Early warning of critical blockage in coal mills based on stacked denoising autoencoders[J]. IEEE Access, 2020, 8: 176101-176111.

SUN Heng, CHEN Miaomiao, WENG Jian, et al. Anomaly detection for in-vehicle network using CNN-LSTM with attention mechanism[J]. IEEE Transactions on Vehicular Technology, 2021, 70(10): 10880-10893.

THILL M, KONEN W, WANG Hao, et al. Temporal convolutional autoencoder for unsupervised anomaly detection in time series[J]. Applied Soft Computing, 2021, 112: 107751.

ZHANG Chen, HU Di, YANG Tao. Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost[J]. Reliability Engineering & System Safety, 2022, 222: 108445.

田亮, 袁存波. 基于LSTM和证据理论的引风机轴承故障诊断[J]. 动力工程学报, 2023, 43(5): 614-621. TIAN Liang, YUAN Cunbo. Fault diagnosis of induced draft fan bearing based on LSTM and evidence theory[J]. Journal of Chinese Society of Power Engineering, 2023, 43(5): 614-621.

李晓彬, 牛玉广, 葛维春, 等. 基于改进堆叠自编码网络的电站辅机故障预警[J]. 仪器仪表学报, 2019, 40(6): 39-47. LI Xiaobin, NIU Yuguang, GE Weichun, et al. Early fault warning of power plant auxiliary engine based on improved stacked autoencoder network[J]. Chinese Journal of Scientific Instrument, 2019, 40(6): 39-47.

LI Yanping, HONG Feng, TIAN Liang, et al. Condition monitoring and early fault warning of power plant auxiliary equipment using LSTM-SDAE model with an adaptive threshold[J]. Frontiers in Energy Research, 2023, 10: 1037539.

CHEN Hansi, LIU Hang, CHU Xuening, et al. Anomaly detection and critical SCADA parameters identification for wind turbines based on LSTM-AE neural network[J]. Renewable Energy, 2021, 172: 829-840.

蔡源, 吴浩, 唐丹. 基于特征挖掘与改进TCN-BiGRU的光伏功率区间概率预测[J]. 科学技术与工程, 2025, 25(10): 4145-4155. CAI Yuan, WU Hao, TANG Dan. Probabilistic prediction of photovoltaic power interval based on feature mining and improved TCN-BiGRU[J]. Science Technology and Engineering, 2025, 25(10): 4145-4155.

温廷新, 郭晓赛. 基于特征组合的ECA-TCN光伏发电功率预测模型[J]. 太阳能学报, 2024, 45(12): 94-100. WEN Tingxin, GUO Xiaosai. ECA-TCN photovoltaic power prediction model based on feature combination[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 94-100.

VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11: 3371-3408.

马良玉, 孙佳明. 基于SDAE预测模型和改进SSA的NOx排放优化[J]. 中国电机工程学报, 2022, 42(14): 5194-5201. MA Liangyu, SUN Jiaming. NOx emission optimization based on SDAE prediction model and improved SSA[J]. Proceedings of the CSEE, 2022, 42(14): 5194-5201.

YU Jianbo. A selective deep stacked denoising autoencoders ensemble with negative correlation learning for gearbox fault diagnosis[J]. Computers in Industry, 2019, 108: 62-72.

娄建楼, 李燕, 王琦, 等. 基于改进堆栈降噪自编码器的锅炉设备在线监测数据清洗方法[J]. 计算机集成制造系统, 2019, 25(12): 3181-3190. LOU Jianlou, LI Yan, WANG Qi, et al. Cleaning method for online monitoring data of boiler equipment based on improved stacked denoising auto-encoder[J]. Computer Integrated Manufacturing Systems, 2019, 25(12): 3181-3190.

于仙毅, 巫江虹, 高云辉. 基于主成分分析与支持向量机的热泵系统制冷剂泄漏识别研究[J]. 化工学报, 2020, 71(7): 3151-3164. YU Xianyi, WU Jianghong, GAO Yunhui. Research on refrigerant leakage identification for heat pump system based on PCA-SVM models[J]. CIESC Journal, 2020, 71(7): 3151-3164.

王艺霏, 李哲, 周斌, 等. 基于特征变量分析的火电厂引风机故障预警模型研究与应用[J]. 工业控制计算机, 2021, 34(7): 11-13. WANG Yifei, LI Zhe, ZHOU Bin, et al. Research and application of induced draft fan fault early warning model in thermal power plant based on characteristic variable analysis[J]. Industrial Control Computer, 2021, 34(7): 11-13.

雷萌, 吕游, 魏玮, 等. 基于LSTM神经网络与贝叶斯优化的电站风机故障预警[J]. 热能动力工程, 2022, 37(8): 213-220. LEI Meng, LYU You, WEI Wei, et al. Fault warning of power plant fans based on long short-term memory neural network and Bayesian optimization[J]. Journal of Engineering for Thermal Energy and Power, 2022, 37(8): 213-220.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatio-temporal Graph Attention Network-based Fault Warning of Coal Mill

A Boiler Reheater Wall Temperature Prediction Model Based on CNN-BiLSTM-SSA

Prediction of SO2 Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN

Day-ahead Irradiance Forecasting Framework Based on CEEMDAN-KDBSCAN-Informer

Mooring-line Tension Prediction Based on Re-decomposition and Deep Learning

Related Author

NIU Yuguang

XU Jian

DU Ming

YAO Jun

徐世明

何至谦

周怀春

刘洋

Related Institution

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University

江苏省智慧能源技术及装备工程研究中心

华能营口热电有限责任公司

中国矿业大学低碳能源与动力工程学院

Department of Energy and Power Engineering, Tsinghua University

AI问答

⁰