提出一种基于深度迁移学习与长短期记忆网络相结合的微电网故障诊断方法,可对不同结构的微电网进行故障诊断。首先利用小波包变换提取故障特征组成特征向量作为网络输入;其次,利用源域数据样本对长短期记忆网络故障诊断模型进行预训练,并保存相关参数;然后采用迁移学习将预训练模型中的参数迁移至域自适应网络,得到深度迁移学习与长短期记忆网络相结合的模型;最后根据有标记数据(源域数据)和目标域数据对模型进行微调迁移训练,将单一微电网故障诊断模型迁移至其他不同结构微电网。测试结果表明,该方法能高性能地检测和识别不同结构微电网中任何类型的故障,识别结果均方误差为8.5905×10-5,相比于自适应调整前的长短期记忆网络模型小2个数量级,识别效果更好,诊断精度有明显提高。
Abstract
A microgrid fault diagnosis method based on the combination of deep transfer learning and long-short-term memory network is proposed, which can be used to diagnose microgrids fault with different structures. First, wavelet packet transform is used to extract the feature vectors of fault as the input of the network; second, source domain data samples is used to pre-train the fault diagnosis model built by long short-term memory network, and relevant parameters is saved; Then transfer learning is used to migrate the parameters in the pre-training model to the domain adaptive network to obtain the combination model of deep transfer learning and long-short-term memory network; finally, the model is fine-tuned and migrated according to the labeled data (source domain data) and target domain data, and the single microgrid fault diagnosis model is transferred to other microgrids of different structures. The test results show that the proposed method can detect and identify any type of faults in microgrids of different structures. The mean square error of the identification result is 8.5905×10-5, smaller two orders of magnitude compared with the long-short-term memory network model before adaptive adjustment, the recognition effect is better and the diagnosis accuracy is obviously improved.
关键词
计量学 /
微电网 /
故障识别 /
深度迁移学习 /
长短期记忆网络 /
小波包分解
Key words
metrology /
microgrid /
fault recognition /
deep transfer learning /
long-short-term memory network /
wavelet packet decomposition
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］吴忠强, 戚松岐, 尚梦瑶, 等. 基于优化回声状态网络的微电网等效建模 ［J］. 计量学报, 2021, 42(7): 923-929.
Wu Z Q, Qi S Q, Shang M Y, et al. Equivalent modeling of micro-grid using optimized ESN ［J］. Acta Metrologica Sinica, 2021, 42(7): 923-929.
［2］吴忠强, 刘重阳. 基于IHHO算法的光伏电池工程模型的参数辨识 ［J］. 计量学报, 2021, 42(2): 221-227.
Wu Z Q, Liu C Y. Parameter identification of photovoltaic cell engineering model based on IHHO algorithm ［J］. Acta Metrologica Sinica, 2021, 42(2): 221-227.
［3］刘畅, 卓建坤, 赵东明, 等. 利用储能系统实现可再生能源微电网灵活安全运行的研究综述 ［J］. 中国电机工程学报, 2020, 40(1): 1-18.
Liu C, Zhuo J K, Zhao D M, et al. A review on the utilization of energy storage system for the flexible and safe operation of renewable energy microgrids ［J］. Proceedings of the CSEE, 2020, 40(1): 1-18.
［4］吴忠强, 王国勇, 谢宗奎, 等. 基于IALO算法的蓄电池参数辨识 ［J］. 计量学报, 2021, 42(9): 1206-1213.
Wu Z Q, Wang G Y, Xie Z K, et al. Parameter identification of battery based on IALO algorithm［J］. Acta Metrologica Sinica, 2021, 42(9): 1206-1213.
［5］吴忠强, 王国勇, 谢宗奎, 等. 基于WOA-UKF 算法的锂电池容量与SOC 联合估计 ［J］. 计量学报, 2022, 43(5): 649-656.
Wu Z Q, Wang G Y, Xie Z K, et al. Joint estimation of the capacity and SOC of lithium battery based on WOA-UKF algorithm［J］.Acta Metrologica Sinica, 2022, 43(5): 649-656.
［6］张伟亮, 张辉, 支娜, 等. 环形直流微电网故障分析与保护 ［J］. 电力系统自动化, 2020, 44(24): 105-110.
Zhang W L, Zhang H, Zhi N, et al. Fault analysis and protection of ring DC microgrid ［J］. Automation of Electric Power Systems, 2020, 44(24): 105-110.
［7］Gush T, Bukhari S B A, Haider R, et al. Fault detection and location in a microgrid using mathematical morphology and recursive least square methods ［J］. International Journal of Electrical Power & Energy Systems, 2018, 102: 324-331.
［8］Li X, Dys′ko A, Burt G M. Traveling wave-based protection scheme for inverter-dominated microgrid using mathematical morphology ［J］. IEEE Transactions on Smart Grid, 2014, 5(5): 2211-2218.
［9］Li Y, Gong Y, Jiang B. A novel traveling-wave-based directional protection scheme for MTDC grid with inductive DC terminal ［J］. Electric Power Systems Research, 2018, 157: 83-92.
［10］Aftab M A, Hussain S M S, Ali I, et al. Dynamic protection of power systems with high penetration of renewables: A review of the traveling wave based fault location techniques ［J］. International Journal of Electrical Power & Energy Systems, 2020, 114: 105410.
［11］Abdali A, Mazlumi K, Noroozian R. High-speed fault detection and location in DC microgrids systems using Multi-Criterion System and neural network ［J］. Applied Soft Computing, 2019, 79: 341-353.
［12］Hong Y Y, Cabatac M T A M. Fault detection, classification, and location by static switch in microgrids using wavelet transform and taguchi-based artificial neural network ［J］. IEEE Systems Journal, 2019, 14(2): 2725-2735.
［13］Gush T, Bukhari S B A, Mehmood K K, et al. Intelligent Fault Classification and Location Identification Method for Microgrids Using Discrete Orthonormal Stockwell Transform-Based Optimized Multi-Kernel Extreme Learning Machine ［J］. Energies, 2019, 12(23): 4504.
［14］James J Q, Hou Y, Lam A Y S, et al. Intelligent fault detection scheme for microgrids with wavelet-based deep neural networks ［J］. IEEE Transactions on Smart Grid, 2017, 10(2): 1694-1703.
［15］和敬涵, 罗国敏, 程梦晓, 等. 新一代人工智能在电力系统故障分析及定位中的研究综述 ［J］. 中国电机工程学报, 2020, 40(17): 5506-5516.
He J H, Luo G M, Cheng M X, et al. A research review on application of artificial intelligence in power system fault analysis and location ［J］. Proceedings of the CSEE, 2020, 40(17): 5506-5516.
［16］Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network ［J］. Physica D: Nonlinear Phenomena, 2020, 404: 132306.
［17］杨少波, 刘道伟, 安军, 等. 基于长短期记忆网络的电网动态轨迹趋势预测方法 ［J］. 中国电机工程学报, 2020, 40(9): 2854-2866.
Yang S B, Liu D W, An J, et al. Trend prediction method of power network dynamic trajectory based on long short term memory neural networks ［J］. Proceedings of the CSEE, 2020, 40(9): 2854-2866.
［18］Weiss K, Khoshgoftaar T M, Wang D D. A survey of transfer learning ［J］. Journal of Big data, 2016, 3(1): 1-40.
［19］张雪松, 庄严, 闫飞, 等. 基于迁移学习的类别级物体识别与检测研究与进展 ［J］. 自动化学报, 2019, 45(7): 1224-1243.
Zhang X S, Zhuang Y, Yan F, et al. Status and development of transfer learning based category-level object recognition and detection ［J］. Acta Automatica Sinica, 2019, 45(7): 1224-1243.
［20］Li Y, Sheng H, Cheng Y, et al. State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis ［J］. Applied Energy, 2020, 277: 115504.
基金
河北省自然科学基金(F2020203014)
PDF(178922 KB)
