Optimal productivity in solar power plants based on machine learning and engineering management

The complexity of solar power plants is constantly increasing. This sophistication includes the increasing number of solar panels installed and the technologies that are employed in the energy conversion systems. The new solar plants require advanced methods to ensure the availability of all the panels. This paper proposes a recurrent convolutional neural network algorithm for detecting failures, reducing the costs and the time of the inspections. The method is aimed to analyze the data provided by an unmanned aerial vehicle fitted with a thermographic camera. This system provides thermographic data and telemetry. A region-based recurrent convolutional neural network is trained by a previously created dataset. Once the neural network is trained, it is used as a hot spot detector. This detector will have employed the telemetry in order to identify the real panel that can be affected.

[1]  N. Panwar,et al.  Role of renewable energy sources in environmental protection: A review , 2011 .

[2]  Mayorkinos Papaelias,et al.  Cracks and welds detection approach in solar receiver tubes employing electromagnetic acoustic transducers , 2018 .

[3]  Benjamin Lev,et al.  Optimal decision-making via binary decision diagrams for investments under a risky environment , 2017, Int. J. Prod. Res..

[4]  Mohsen Elhafsi,et al.  Pricing and capacity planning for product-line expansion and reduction , 2017, Int. J. Prod. Res..

[5]  Mayorkinos Papaelias,et al.  Optimal Dynamic Analysis of Electrical/Electronic Components in Wind Turbines , 2017 .

[6]  Fausto Pedro García Márquez,et al.  Optimal Maintenance Management of Offshore Wind Farms , 2016 .

[7]  B. Lev,et al.  New Pipe Notch Detection and Location Method for Short Distances employing Ultrasonic Guided Waves , 2017 .

[8]  Mayorkinos Papaelias,et al.  Techno-Economical Advances for Maintenance Management of Concentrated Solar Power Plants , 2017 .

[9]  Juan R. Trapero,et al.  A New Ranking Method Approach for Decision Making in Maintenance Management , 2014 .

[10]  Liang Cheng,et al.  A heuristic method for detecting and locating faults employing electromagnetic acoustic transducers , 2017 .

[11]  Fausto Pedro García Márquez,et al.  Economic Viability Analytics for Wind Energy Maintenance Management , 2015 .

[12]  Fausto Pedro García Márquez,et al.  Big Data and Web Intelligence: Improving the Efficiency on Decision Making Process via BDD , 2016 .

[13]  Alberto Pliego Marugán,et al.  Decision making process via binary decision diagram , 2015 .

[14]  Fausto Pedro García Márquez,et al.  Wavelet transforms and pattern recognition on ultrasonic guides waves for frozen surface state diagnosis , 2018 .

[15]  Fausto Pedro García Márquez,et al.  Fuzzy Logic Applied to SCADA Systems , 2017 .

[16]  Fausto Pedro García Márquez,et al.  Economic viability analysis for icing blades detection in wind turbines , 2016 .

[17]  Fausto Pedro García Márquez,et al.  Ice detection using thermal infrared radiometry on wind turbine blades , 2016 .

[18]  Fausto Pedro García Márquez,et al.  Competitiveness based on logistic management: a real case study , 2015, Ann. Oper. Res..

[19]  Fausto Pedro García Márquez,et al.  SCADA and Artificial Neural Networks for Maintenance Management , 2017 .

[20]  Gabi Friesen,et al.  Review of Failures of Photovoltaic Modules , 2014 .

[21]  Fausto Pedro García Márquez,et al.  Recurrent Neural Network and Genetic Algorithm Approaches for a Dual Route Optimization Problem: A Real Case Study , 2013 .

[22]  Fausto Pedro García Márquez,et al.  Machine Learning for Wind Turbine Blades Maintenance Management , 2017 .

[23]  Mayorkinos Papaelias,et al.  Identification of critical components of wind turbines using FTA over the time , 2016 .