Distributed photovoltaic module ash deposition evaluation model training method and evaluation method

CN119025915APending Publication Date: 2024-11-26HUIDIAN TECHNOLOGY (SUZHOU) CO LTD
View PDF 0 Cites -1 Cited by

Patent Information

Application Number
CN202411104777.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-26

Smart Images

  • Figure CN119025915A_ABST
    Figure CN119025915A_ABST
Patent Text Reader

Abstract

The invention discloses an evaluation model training method and evaluation method for distributed photovoltaic module ash deposition, which are applied to the field of photovoltaic modules, and comprise the following steps: obtaining training data and ash deposition data of each training sample; the training data comprises air quality, relative humidity, wind speed, precipitation, active power of an inverter and an installation angle of the inverter; clustering the training samples according to the active power of the inverter to obtain clustered training samples; and training the initial ash deposition evaluation model based on the clustered training samples to obtain a trained distributed photovoltaic module ash deposition evaluation model. According to the method, the influence of a distributed scene is considered, the training samples are clustered based on the active power of the inverter, and the soot formation is accurately evaluated according to the clustering result, so that the soot formation evaluation model of the distributed photovoltaic module obtained by training is more accurate and more explanatory, and the accuracy and the reliability of the model are improved. The model can be applied to the dust deposition evaluation of the distributed photovoltaic module, and can also guide the cleaning work of the photovoltaic module.
Need to check novelty before this filing date? Find Prior Art