Abstract The stator cooling water system of a turbine generator must maintain optimal operating conditions to ensure the reliability and safety of the generator. Typically, thermal faults are detected using methods such as shutdown maintenance or temperature difference thresholds, but these methods cannot effectively detect faults in real time while the generator is in operation. To more accurately identify stator thermal faults, this paper proposes a temperature prediction algorithm based on the Transformer architecture. Using the predicted temperatures from multiple measurement points, the future temperature difference is estimated, and a diagnosis model for stator thermal faults is established. To address the issue of limited fault operation data samples, this paper utilizes Gaussian processes with different kernel functions to generate various types of time series, which are then combined with the original data, significantly expanding the training sample space. Finally, experiments are conducted using existing test data. The results indicate that the predictive algorithm proposed in this paper outperforms traditional autoregressive integrated moving average (ARIMA) and long short term memory (LSTM) algorithms. Moreover, the diagnostic model based on this predictive algorithm achieves an accuracy rate of 91.9% in identifying operational states, while also maintaining high precision and recall rates, ensuring low false alarm and missed alarm rates.
[1] 吴笃超. 汽轮发电机定子线棒层间温度和出水温度异常分析与处理[J].通信电源技术, 2021, 38(6): 44-46. [2] KABOLI S, ORAEE H.Heat trap detection in the stator bar of large turbogenerators during the fault of cooling water channels blockage[C]//IECON 2016- 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, 2016: 1501-1506. [3] 钱锋. 发电机水冷定子线圈局部温度异常的故障诊断分析[J].大电机技术, 2004(5): 24-27. [4] 吕伟, 肖爱国. 发电机定子线棒温度异常分析及诊断[J].河南科技, 2021, 40(2): 51-53. [5] RIOUAL M.A thermohydraulic modelling for the stator bars of large turbogenerators: development, validation by laboratory and on site tests[J].IEEE Transactions on Energy Conversion, 1997, 12(1): 1-9. [6] 刘振兴, 尹项根, 张哲, 等. 300MW汽轮发电机定子绕组温度在线监测与故障诊断[J].电力系统自动化, 2002, 26(5): 32-35. [7] BIAN Xu, BAO Shijie.Influence of waterway blockage fault on temperature distribution of stator transposition winding[C]//2022 IEEE 5th International Electrical and Energy Conference (CIEEC), Nanjing, China, 2022, 689-694. [8] 钱锋. 发电机水冷定子线圈局部温度异常的故障诊断分析[J].大电机技术, 2004(5): 24-27. [9] 严璐晗, 林培杰, 程树英, 等. 基于增量学习的CNN- LSTM光伏功率预测[J].电气技术, 2024, 25(5): 31-40. [10] 王步华, 朱劭璇, 熊浩清, 等. 基于长短期记忆神经网络的检修态电网暂态稳定评估方法[J].电气技术, 2023, 24(1): 29-35. [11] 李英顺, 阚宏达, 郭占男, 等. 基于数据预处理和VMD-LSTM-GPR的锂离子电池剩余寿命预测[J].电工技术学报, 2024, 39(10): 3244-3258. [12] 尹杰, 刘博, 孙国兵, 等. 基于迁移学习和降噪自编码器-长短时间记忆的锂离子电池剩余寿命预测[J].电工技术学报, 2024, 39(1): 289-302. [13] 梁郑秋, 郝亮亮, 周艳真, 等. 基于卷积神经网络的核电多相无刷励磁系统旋转整流器故障诊断[J].电工技术学报, 2023, 38(20): 5458-5472. [14] 衣思彤, 刘雅浓, 马耀浥, 等. 基于贝叶斯优化-卷积神经网络-双向长短期记忆神经网络的锂电池健康状态评估[J].电气技术, 2024, 25(5): 1-10. [15] GAO Long, LI Donghui, LI Ding, et al.An improved LSTM based sensor fault diagnosis strategy for the air-cooled chiller system[C]//2019 Chinese Control Conference (CCC), Guangzhou, China, 2019: 4990-4995. [16] YANG Yulei, ZHANG Shuming, SU Kaisen, et al.Early warning of stator winding overheating fault of water-cooled turbogenerator based on SAE-LSTM and sliding window method[J].Energy Reports, 2023, 9: 199-207. [17] CHUNG H W, HOU L, LONGPRE S, et al. Scaling instruction-finetuned language models[EB/OL].2022: arXiv: 2210.11416. http://arxiv.org/abs/2210.11416. [18] XUE H, SALIM F D.PromptCast: a new prompt-based learning paradigm for time series forecasting[J].IEEE Transactions on Knowledge and Data Engineering, 2024, 36(11): 6851-6864. [19] CHOWDHERY A, NARANG S, DEVLIN J, et al. PalM: scaling language modeling with path- ways[EB/OL].2022: arXiv: 2204.02311. http://arxiv. org/abs/2204.02311. [20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL].2017: arXiv preprint arXiv: 1706.03762. http://arxiv.org/abs/1706.03762v2. [21] RAFFEL C, SHAZEER N, ROBERTS A, et al.Exploring the limits of transfer learning with a unified text-to-text transformer[J].Journal of Machine Learning Research, 2020, 21: 1-67. [22] GRUVER N, FINZI M, QIU S, et al. Large language models are zero-shot time series forecasters[EB/OL].2023: arXiv: 2310.07820. http://arxiv.org/abs/2310.07820. [23] JIN Ming, WANG Shiyu, MA Lintao, et al. Time-LLM: time series forecasting by reprogramming large language models[EB/OL].2023: arXiv: 2310.01728. http://arxiv.org/abs/2310.01728. [24] 董海鹰, 王瑞军, 顾瑶琴. 基于自回归求和滑动平均模型的风力发电机轴承寿命预测[J].系统仿真技术, 2017, 13(3): 185-189, 208. [25] CHEN Zaifa, LIU Yancheng, LIU Siyuan.Mechanical state prediction based on LSTM neural netwok[C]// 2017 36th Chinese Control Conference (CCC), Dalian, China, 2017: 3876-3881. [26] 许凯, 富威, 陈世均, 等. 基于LSTM神经网络的汽轮发电机状态监测系统[J].应用科技, 2020, 47(6): 96-100. [27] 刘亚波, 吴秋轩. 基于高斯过程混合模型的时间序列预测算法研究[J].微电子学与计算机, 2021, 38(6): 93-98.
2025, Vol. 26 
