Dust InSMS: Intelligent soiling measurement system for dust detection on solar mirrors using computer vision methods
作者：
Highlights：
• A new method for soiling quantification is proposed based on CNN approach.
• Experimental measurements of a Fresnel solar field are conducted to collect data.
• The innovation, software and hardware of Dust InSMS sensor are described.
• A good agreement is proven during outdoor validation and tests of the Dust InSMS.
• An optimal cleaning scenario is developed based on genetic algorithms.
摘要
•A new method for soiling quantification is proposed based on CNN approach.•Experimental measurements of a Fresnel solar field are conducted to collect data.•The innovation, software and hardware of Dust InSMS sensor are described.•A good agreement is proven during outdoor validation and tests of the Dust InSMS.•An optimal cleaning scenario is developed based on genetic algorithms.
论文关键词：Soiling,Dust accumulation,Dust detection,CSP,CNN,Image processing
论文评审过程：Received 8 February 2022, Revised 16 August 2022, Accepted 19 August 2022, Available online 23 August 2022, Version of Record 27 August 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118646
