《A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances》由会员分享，可在线阅读，更多相关《A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances（14页珍藏版）》请在金锄头文库上搜索。
1、A comprehensive overview on signal processing and artificialintelligence techniques applications in classification of powerquality disturbancesSuhail Khokhara,b,n, Abdullah Asuhaimi B. Mohd Zina, Ahmad Safawi B. Mokhtara,Mahmoud PesaranaaFaculty of Electrical Engineering, Universiti Teknologi Malays
2、is (UTM), MalaysiabDepartment of Electrical Engineering, Quaid e Awam University of Engineering, Science and Technology (QUEST) Nawabshah Pakistana r t i c l e i n f oArticle history:Received 11 February 2015Received in revised form14 May 2015Accepted 15 July 2015Available online 3 August 2015Keywor
3、ds:Power quality disturbancesSignal processingArtificial intelligenceOptimization techniquesFeature extractiona b s t r a c tThe increasing trend towards renewable energy sources requires higher power quality (PQ) at thegeneration, transmission and distribution systems. The PQ disturbances are produ
4、ced due to thenonlinear loads, power electronic converters, system faults and switching events. The utilities andconsumers of electric power are expected to acquire ideal voltage and current waveforms at rated powerfrequency. The development of new techniques for the automatic classification of PQ e
5、vents is at presenta major concern. This paper presents a comprehensive literature review on the applications of digitalsignal processing, artificial intelligence and optimization techniques in the classification of PQdisturbances. Various signal processing techniques used for the feature extraction
6、 such as Fouriertransform, wavelet transform, S-transform, Hilbert transform, Gabor transform and their hybrids havebeen reviewed. The artificial intelligent techniques used for the pattern recognition such as artificialneural network, fuzzy logic, support vector machine are reviewed in detail. The
7、optimization techniquesused for the optimal feature selection such as genetic algorithm, particle swarm optimization and antcolony optimization are also reviewed. A comparison of various classification systems is presented intabular form which highlights the important techniques used in the field of
8、 PQ disturbance monitoring.The comparison of research works carried out on the classification of PQ disturbances points out thatmany researchers have focussed on the feature extraction and classification techniques. Only fewauthors have used the feature selection techniques for selecting the best su
9、itable features. This reviewmay be considered a valuable source for researchers as a reference point to explore the opportunities forfurther improvement in the field of PQ classification.& 2015 Elsevier Ltd. All rights reserved.Contents1.Introduction. . . . . . . . . . . . . . . . . . . . . . . . .
10、. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16512.Power quality. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
11、 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16523.Power quality standards . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16524
12、.Feature extraction techniques in power quality. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16524.1.Fourier transform based feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . .
13、. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16534.2.Kalman filter based feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16534.3.W
14、avelet transform based feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16534.3.1.Wavelet transform for disturbances detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
15、 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16544.3.2.Continuous and discrete wavelet transforms for feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16544.3.3.Wavelet packet transform for feature extraction . . . . .
16、 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16544.3.4.Miscellaneous wavelet transforms for feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1654Contents lists available at ScienceDirectjournal homepage: and Sustainable Energy Reviewshttp:/dx.doi.org/10.1016/j.rser.2015.07.0681364-0321/& 2015 Elsevier Ltd. All rights reserved.nCorresponding author at:
