FPGA-Based Smart Sensor for Detection and Classification of Power Quality Disturbances Using Higher Order Statistics

Power quality (PQ) has received the attention of several research groups due to the impact of PQ disturbances (PQDs) and how they affect the operation of the electrical equipment connected to the grid, especially in industrial and healthcare facilities. The monitoring and analysis of PQD are generally performed with specialized measuring equipment, such as power analyzers, based on the standards. However, this equipment is not suited to perform continuous monitoring and classification of PQD, and it cannot be configured to perform further analysis of the monitored signal. Smart sensors, on the other hand, can provide the functionality that the standard equipment cannot, by integrating several signal processing modules that can be reconfigured using a reconfigurable technology, such as field programmable gate arrays (FPGAs). This paper presents the development of an FPGA-based smart sensor that integrates the processing cores of higher order statistics (HOS) to provide a signal analysis aimed to detect and quantify PQD on electrical installations and an artificial neural network to classify the PQD. Experimentation is performed on the electrical installation in hospital facilities. Results from the HOS processing of electrical signals show that these processing methodologies are suitable for the quantification and classification of PQD on electrical installations.

[1]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[2]  K. Shanti Swarup,et al.  High-Speed Fault Classification in Power Lines: Theory and FPGA-Based Implementation , 2009, IEEE Transactions on Industrial Electronics.

[3]  Gang Chen,et al.  A new classification method for transient power quality combining spectral kurtosis with neural network , 2014, Neurocomputing.

[4]  L. Ferrigno,et al.  FPGA-based Measurement Instrument for Power Quality Monitoring according to IEC Standards , 2008, 2008 IEEE Instrumentation and Measurement Technology Conference.

[5]  Juan José González de la Rosa,et al.  An application of the spectral kurtosis to characterize power quality events , 2013 .

[6]  Muhsin Tunay Gençoglu,et al.  An expert system based on S-transform and neural network for automatic classification of power quality disturbances , 2009, Expert Syst. Appl..

[7]  Rene de Jesus Romero-Troncoso,et al.  FPGA-based neural network harmonic estimation for continuous monitoring of the power line in industrial applications , 2013 .

[8]  Kiyoshi Takahashi,et al.  From intelligent sensors to fuzzy sensors , 1994 .

[9]  José Rivera,et al.  Improved Progressive Polynomial Algorithm for Self-Adjustment and Optimal Response in Intelligent Sensors , 2008, Sensors.

[10]  Roque Alfredo Osornio-Rios,et al.  A Hilbert Transform-Based Smart Sensor for Detection, Classification, and Quantification of Power Quality Disturbances , 2013, Sensors.

[11]  Zhao Yang Dong,et al.  Investigation of power quality categorisation and simulating it's impact on sensitive electronic equipment , 2004, IEEE Power Engineering Society General Meeting, 2004..

[12]  Rafael Sandoval-Rodriguez,et al.  Comparison of Compensation Algorithms for Smart Sensors With Approach to Real-Time or Dynamic Applications , 2015, IEEE Sensors Journal.

[13]  Eduardo Cabal-Yepez,et al.  FPGA-Based Online Detection of Multiple-Combined Faults through Information Entropy and Neural Networks , 2010, 2010 International Conference on Reconfigurable Computing and FPGAs.

[14]  Jerry M. Mendel,et al.  Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applications , 1991, Proc. IEEE.

[15]  Basel Alsayyed Ahmad,et al.  Review of power quality monitoring systems , 2015, 2015 International Conference on Industrial Engineering and Operations Management (IEOM).

[16]  Om Prakash Mahela,et al.  A critical review of detection and classification of power quality events , 2015 .

[17]  Faith Chaibva,et al.  Optimization of Salbutamol Sulfate Dissolution from Sustained Release Matrix Formulations Using an Artificial Neural Network , 2010, Pharmaceutics.

[18]  Manali Chaudhari,et al.  Study of Smart Sensors and their Applications , 2014 .

[19]  Bijaya K. Panigrahi,et al.  Power Quality Disturbance Classification Using Fuzzy C-Means Algorithm and Adaptive Particle Swarm Optimization , 2009, IEEE Transactions on Industrial Electronics.

[20]  Ming Zhang,et al.  A Real-Time Power Quality Disturbances Classification Using Hybrid Method Based on S-Transform and Dynamics , 2013, IEEE Transactions on Instrumentation and Measurement.

[21]  Umar,et al.  WSN-Based Smart Sensors and Actuator for Power Management in Intelligent Buildings , 2015 .

[22]  Ivan Nunes da Silva,et al.  Feature Extraction and Power Quality Disturbances Classification Using Smart Meters Signals , 2016, IEEE Transactions on Industrial Informatics.

[23]  Zahra Moravej,et al.  Detection and Classification of Power Quality Disturbances Using Wavelet Transform and Support Vector Machines , 2009 .

[24]  José G. M. S. Decanini,et al.  Detection and classification of voltage disturbances using a Fuzzy-ARTMAP-wavelet network , 2011 .

[25]  Birendra Biswal,et al.  Automatic Classification of Power Quality Events Using Balanced Neural Tree , 2014, IEEE Transactions on Industrial Electronics.

[27]  Yanbo Huang,et al.  Advances in Artificial Neural Networks - Methodological Development and Application , 2009, Algorithms.

[28]  Rene de Jesus Romero-Troncoso,et al.  Voltage drop repercussions in industrial processes due to the interaction of several machines in a manufacturing cell , 2013 .

[29]  Eric Monmasson,et al.  FPGAs in Industrial Control Applications , 2011, IEEE Transactions on Industrial Informatics.

[30]  Rene de Jesus Romero-Troncoso,et al.  Techniques and methodologies for power quality analysis and disturbances classification in power systems: a review , 2011 .

[31]  Bijaya Ketan Panigrahi,et al.  Detection and classification of power quality disturbances using S-transform and modular neural network , 2008 .

[32]  José María Sierra-Fernández,et al.  A novel FPGA-based system for real-time calculation of the Spectral Kurtosis: A prospective application to harmonic detection , 2016 .

[33]  Mahmoud Pesaran,et al.  A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances , 2015 .

[34]  F. N. Belchior,et al.  Comparative analysis of power quality instruments measuring voltage and power , 2014, 2014 16th International Conference on Harmonics and Quality of Power (ICHQP).

[35]  An Braeken,et al.  Sensor Systems Based on FPGAs and Their Applications: A Survey , 2012, Sensors.

[36]  Samir Mekid,et al.  Further Structural Intelligence for Sensors Cluster Technology in Manufacturing , 2006, Sensors (Basel, Switzerland).

[37]  Juan José González de la Rosa,et al.  A novel virtual instrument for power quality surveillance based in higher-order statistics and case-based reasoning , 2012 .