Light & Engineering 26 (3)

Volume 26
Date of publication 09/28/2018
Pages 167-173

PDF

Manufacturing Cost Optimization of Photovoltaic Enterprises Based on Neural Network. L&E 26 (3) 2018

Articles authors:

Weiping ZHANG, Shuming LI, Junfeng YU, Yihua MAO

received the Ph.D. degree in computer science from Rostock University, Rostock, Germany. From 2014 to 2016, he was a Research Scientist with the Institute of BCRT in Berlin, Humboldt University, Berlin, Germany. He is currently a Uni-Professor with the School of Information Engineering, Nanchang University, Nanchang, China. His research interests include machine learning, process information management systems and real-time mobile measurements of physiological parameters

Post Dr. She has received Ph.D. degree in Beijing Forestry University in 2013. From 2017 till now, she began her postdoctoral research at Binhai Industrial Technology Research Institute of Zhejiang University. Her research interests include high value utilization of biomass, technology innovation management and commercialization of research findings

received the master’s degree in communication and information system from Beijing Jiaotong University, Beijing, China. He has more than 5 years development and operation experience in the internet industry, particularly in domain name system and routing technology. He is currently an R&D engineer in Binhai Industrial Technology Research Institute of Zhejiang University, Tianjin, China. His research interests include machine learning and data analysis

Ph.D, Professor. He has got Ph.D. degree from Zhejiang University. Now he serves in College of Civil Engineering and Architectural of Zhejiang University. He also serves as the deputy dean of Industrial Technology Research Institute of Zhejiang University and the dean of Binhai Industrial Technology Research Institute of Zhejiang University. His main research fields: the engineering economy and project cost, construction project management, system design and large data analysis technology; enterprise strategy and technology innovation management

Abstract

How to reduce the cost of photovoltaic power generation is the core issue of the survival and development of photovoltaic enterprises. Based on this, the manufacturing cost optimization of photovoltaic enterprises is studied based on neural network. Through the design of cost accounting control of photovoltaic enterprises, a genetic algorithm is proposed to optimize the manufacturing cost of photovoltaic enterprises, which is predicted at the maximum power point of the same photovoltaic power generation system. The results show that the RBF neural network optimized by genetic algorithm not only improves the prediction speed, but also improves the prediction accuracy. Thus, the maximum power point tracking control of photovoltaic power generation can be achieved better, and the manufacturing cost of photovoltaic enterprises can be optimized.

References

1. Baptista D, Abreu S, TraviesoGonzález C, et al. Hardware implementation of an artificial neural network model to predict the energy production of a photovoltaic system. Microprocessors and Microsystems, 2017. V49, pp.77–86.
2. Dumitru C D, Gligor A, Enachescu C. Solar photovoltaic energy production forecast using neural networks. Procedia Technology, 2016. V22, pp.808–815.
3. Kayri I, Gencoglu M T. Predicting power production from a photovoltaic panel through artificial neural networks using atmospheric indicators. Neural Computing & Applications, 2017, pp.1–14.
4. Kane P V, Andhare A B. Application of psychoacoustics for gear fault diagnosis using artificial neural network. Journal of Low Frequency Noise, Vibration and Active Control, 2016. V35, #3, pp.207–220.
5. Zheng M, Horowitz K, Woodhouse M, et al. III‐Vs at scale: a PV manufacturing cost analysis of the thin film vapour–liquid–solid growth mode. Progress in Photovoltaic: Research and Applications, 2016. V24, #6, pp.871–878.
6. Haiying Li, Xian Li, Xinyue Xu, Jun Liu, Bin Ran. Modelling departure time choice of metro passengers with a smart corrected mixed logit model – A case study in Beijing. Transport Policy. 2018, #69, pp.106–121.
7. Moon S, Yoon S G, Park J H. A new lowcost centralized MPPT controller system for multiply distributed photovoltaic power conditioning modules. IEEE Transactions on Smart Grid, 2015. V6, #6, pp.2649–2658.
8. Jain S, Agarwal V. A singlestage grid connected inverter topology for solar PV systems with maximum power point tracking. IEEE transactions on power electronics, 2007. V22, #5, pp.1928–1940.
9. GotiElordi, Aitor; delaCalleVicente, Alberto; GilLarrea, MaraJose, et al. Application of a business intelligence tool within the context of big data in a food industry company. DYNA, 2018. V92, #3, pp. 347–353.
10. Oman S, Leskovar R, Rosi B, et al. Integration of MES and ERP in supply chains: effect assessment in the case of the automotive industry. Tehnički vjesnik, 2017. V24, #6, pp.1889–1896.

Keywords