人工智能和数据挖掘在发现潜在问题和提高计算效率等方面有较大的优越性。综述了几年来人工智能与数据挖掘等技术应用于电力系统暂态稳定评估所取得的研究成果。对所涉及的主成分分析、遗传算法、粗糙集、信息熵等数据预处理方法，神经网络与支持向量机等分类器，可视化显示等方面的研究成果进行了深入的分析和比较，指出了存在的问题，并对以后的发展方向进行了一定的展望。

Artificial intelligence and data mining possess obvious superiority in finding potential problems during online and offline transient stability assessment (TSA) and improving computational efficiency. In this paper, the progress of the research on applying artificial intelligence and data mining to TSA of power system in recent years is summarized. The research results of data preprocessing methods such as principal component analysis, genetic algorithm, rough set and information entropy concerning with the research on TSA and the pattern recognition methods by neural network and support vector machine as well as visualization display are analyzed and compared in detail; the problems existing in these methods are pointed out, and the development trend of these methods in future is prospected.

[1] Anderson P M，Fouad A A．Power system control and stability [M]．New York：IEEE Press，1994：15-30． [2] Xue Y，Cutsem T V，Ribbens-Pavella M．Extended equal area criterion justifications，generalizations，applications[J]．IEEE Trans on Power Systems，1989，4(2)：44-52． [3] 余贻鑫，王成山．电力系统稳定性理论与方法[M]．北京：科学出版社，1999：10-26． [4] 韩家炜．数据挖掘概念与技术[M]．北京：电子工业出版社，2000：10-12． [5] Sobajic D J，Pao Y H．Artificial neural-net based dynamic security assessment for electric power system[J]．IEEE Trans on Power Systems，1989，4(1)：220-228． [6] 唐巍，陈学允．BP算法应用于电力系统暂态稳定分析的新策略[J]．电力系统自动化，1997，21(3)：47-50． Tang Wei，Chen Xueyun．A new strategy of BP algorithm applying to transient stability analysis of power system[J]．Automation of Electric Power Systems，1997，21(3)：47-50(in Chinese)． [7] 唐巍．神经网络在电力系统暂态稳定分析与控制中的应用[D]．哈尔滨：哈尔滨工业大学，1997． [8] Hobson E G N．Effectiveness of artificial neural networks for first swing stability determination of practical systems[J]．IEEE Trans on Power Systems，1999，9(2)：1062-1068． [9] 戴仁昶，张伯明．基于人工神经网络暂态稳定分析[J]．电力系统自动化，2000，24(12)：1-3． Dai Renchang，Zhang Boming．Transient stability assessment based on ANN[J]．Automation of Electric Power Systems，2000，24(12)：1-3(in Chinese)． [10] Krishna S，Padiyar K R．Transient stability assessment using artificial neural networks[C]．Proceedings of IEEE International Conference on Industrial Technology，India，2000． [11] 顾雪平，曹绍杰，张文勤．人工神经网络和短时仿真结合的暂态安全评估故障筛选方法[J]．电力系统自动化，1999，23(8)：16-19． Gu Xueping，Tso S K，Zhang Wenqin．Integration of ANNs and short-duration numerical simulation for contingency screening of transient security assessment[J]．Automation of Electric Power Systems，1999，23(8)：16-19(in Chinese)． [12] 张琦，韩祯祥，曹绍杰，等．用于暂态稳定评估的人工神经网络输入空间压缩方法[J]．电力系统自动化，2000，25 (2)：32-35． Zhang Qi，Han Zhenxiang，Tso S K，et al．Input dimension reduction in neural network training for transient stability assessment [J]．Automation of Electric Power Systems，2000，25(2)：32-35(in Chinese)． [13] 顾雪平，曹绍杰，张文勤．基于神经网络暂态稳定评估方法的一种新思路[J]．中国电机工程学报，2000，20(4)：77-82． Gu Xueping，Tso S K，Zhang Wenqin．New framework for transient stability assessment based on neural networks [J]．Proceedings of the CSEE，2000，20(4)：77-82(in Chinese)． [14] Amjady N．Transient stability assessment by a new artificial neural network[C]．IEEE Power Engineering Society Winter Meeting． Singapore，2000． [15] 刘玉田，林飞．基于相角测量技术和模糊径向基网络的暂态稳定性预测[J]．中国电机工程学报，2000，20(2)：45-48． Liu Yutian，Lin Fei．Application of PMU and fuzzy radial basis function network to power system transient stability prediction[J]．Proceedings of the CSEE，2000，20(2)：45-48(in Chinese)． [16] Bahbah A G，Girgis A A．New method for generators’ angles and angular velocities prediction for transient stability assessment of multimachine power systems using recurrent artificial neural network[J]．IEEE Trans on Power Systems，2004，19(2)：1015-1022． [17] 周伟，陈允平．自组织映射神经网络用于暂态稳定性分析的研究[J]．电力系统自动化，2002，26(15)：33-38． Zhou Wei，ChenYunping．Self-organizing mapping (SOM) neural networks for power system transient stability assessment [J]．Automation of Electric Power Systems，2002，26(15)：33-38(in Chinese)． [18] 顾雪平，曹绍杰．神经网络在暂态稳定评估中应用的研究述评[J]．华北电力大学学报，2003，30(4)：11-16． Gu Xueping，Tso S K．Research overview of neural- network applications to transient stability assessment of power systems [J]．Journal of North China Electric Power University，2003，30(4)：11-16(in Chinese)． [19] 王成山，曹旌，陈光远．基于聚类分析的电力系统暂态稳定故障筛选[J]．电网技术，2005，29(15)：18-22． Wang Chengshan，Cao Jing，Chen Guangyuan．Power system transient stability contingency screening based on clustering analysis[J]．Power System Technology，2005，29(15)：18-22(in Chinese)． [20] 曹曼．基于遗传模拟退火算法的暂态稳定评估特征选择[D]．北京：华北电力大学，2006． [21] 于之虹，郭志忠．遗传算法在暂态稳定评估输入特征选择中的应用[J]．继电器，2004，32(1)：16-20． Yu Zhihong，Guo Zhizhong．Feature selection based on genetic algorithm for transient stability assessment[J]．Relay，2004，32(1)：16-20(in Chinese)． [22] 仇向东，禹成七，龚仁敏．基于人工神经网络与遗传算法的暂态稳定评估[J]．华北电力大学学报，2002，29(3)：48-51． Qiu Xiangdong，Yu Chengqi，Gong Renmin．Transient stability assessment method based on back propagation algorithm and genetic algorithm[J]．Journal of North China Electric Power University，2002，29(3)：48-51(in Chinese)． [23] 于之虹，郭志忠．改进主成分分析法用于暂态稳定评估的输入特征选择[J]．电力自动化设备，2003，23(8)：17-20． Yu Zhihong，Guo Zhizhong．Improved principal component analysis to feature selection for transient stability assessment[J]．Electric Power Automation Equipment，2003，23(8)：17-20(in Chinese)． [24] 于之虹，郭志忠．基于数据挖掘理论的电力系统暂态稳定评估[J]．电力系统自动化，2003，27(8)：45-48． Yu Zhihong，Guo Zhizhong．A novel approach for transient stability assessment based on data mining theory[J]．Automation of Electric Power Systems，2003，27(8)：45-48(in Chinese)． [25] 向丽萍，王晓红，王建，等．基于支持向量机的暂态稳定分类中的特征选择[J]．继电器，2007，35(9)：33-37． Xiang Liping，Wang Xiaohong，Wang Jian，et al．Feature selection for SVM based transient stability classification[J]．Relay，2007，35(9)：33-37(in Chinese)． [26] 李军，刘艳，顾雪平．基于信息熵的属性离散化算法在暂态稳定评估中的应用[J]．电力系统自动化，2005，29(8)：26-31． Li Jun，Liu Yan，Gu Xueping．An entropy-based discretization method applied in transient stability assessment[J]．Automation of Electric Power Systems，2005，29(8)：26-31(in Chinese)． [27] 方怡，王建，王晓茹．电力系统暂态稳定评估的关联规则挖掘[J]．电力建设，2008，29(2)：83-86． Fang Yi，Wang Jian，Wang Xiaoru．Association rule mining for power system transient stability evaluation[J]．Electric Power Construction， 2008，29(2)：83-86(in Chinese)． [28] 刘菁．基于模糊理论与人工神经网络的暂态稳定评估方法[D]．上海：上海交通大学，2007． [29] 陈磊，刘天琪，文俊．基于二进粒子群优化算法的暂态稳定评估特征选择[J]．继电器，2007(1)：31-36． Chen Lei，Liu Tianqi，Wen Jun．Feature selection based on binary particle swarm optimization for transient stability assessment [J]．Relay，2007(1)：31-36(in Chinese)． [30] 许涛，贺仁睦，王鹏，等．基于统计学习理论的电力系统暂态稳定评估[J]．中国电机工程学报，2003，23(11)：51-55． Xu Tao，He Renmu，Wang Peng，et al．Power system transient stability assessment based on statistic learning theory[J]．Proceedings of the CSEE，2003，23(11)：51-55(in Chinese)． [31] 马骞，杨以涵，刘文颖，等．多输入特征融合的组合支持向量机电力系统暂态稳定评估[J]．中国电机工程学报，2005，25(6)：17-23． Ma Qian，Yang Yihan，Liu Wenying，et al．Power system transient stability assessment with combined SVM method mixing multiple input features[J]．Proceedings of the CSEE，2005，25(6)：17-23(in Chinese)． [32] Moulin L S，Silva A P A ，El-Sharkawi M A，et al．Support vector machines for transient stability analysis of large-scale power systems [J]．IEEE Trans on Power Systems，2004，19(2)：818-825． [33] Wang X H，Wu S T，Li Q Z，et al．V-SVM for transient stability assessment in power systems[J]．Proceedings of Autonomous Decentralized Systems，2005：356-363． [34] Izzri A W N，Mohamed A，Yahya I．A new method of transient stability assessment in power systems using LS-SVM[C]．The 5th Student Conference on Research and Development，Malaysia，2007． [35] Du Z G，Niu L，Zhao J G．Power system on-line transient stability assessment based on relevance vector learning mechanism [C]．International Power Engineering Conference，Singapore，2007． [36] 黄辉，舒乃秋，李自品，等．基于信息融合技术的电力系统暂态稳定评估[J]．中国电机工程学报，2007，27(16)：19-23． Huang Hui，Shu Naiqiu，Li Zipin，et al．Power system transient stability assessment based on information fusion technology [J]．Proceedings of the CSEE，2007，27(16)：19-23(in Chinese)． [37] 汤必强，邓长虹，刘丽芳．复合神经网络在电力系统暂态稳定评估中的应用[J]．电网技术，2004，28(15)：63-66． Tang Biqiang，Deng Changhong，Liu Lifang．Application of compound neural network in power system transient stability assessment[J]．Power System Technology，2004，28(15)：63-66(in Chinese)． [38] 李亦宁．电力系统暂态稳定评估结果的可视化研究[D]．成都：西南交通大学，2007． [39] Wang T W，Guan L，Zhang Y．A modified pattern recognition algorithm and its application in power system transient stability assessment [C]．IEEE Power and Energy Society General Meeting- Conversion and Delivery of Electrical Energy in the 21st Century，2008． [40] Frederic H，Vaithianathan V．Transient stability assessment with unstable limit cycle approximation[J]．IEEE Trans on Power Systems， 1999，14(2)：667-677． [41] Sawhney H，Jeyasurya B．A feed-forward artificial neural network with enhanced feature selection for power system transient stability assessment[J]．Electric Power Systems Research，2006，76(12)：1047-1054． [42] Ferreira W P，Silveira M D C G，Lotufo A P，et al．Transient stability analysis of electric energy systems via a fuzzy art-artmap neural network[J]．Electric Power Systems Research，2006，76(6-7)：466-475． [43] Mjady N，Majedi S F．Transient stability prediction by a hybrid intelligent system[J]．IEEE Trans on Power Systems，2007，22(3)：1275-1283．