As for the proposed technology by combining the artificial bee colony algorithmthe semi-supervised extreme learning machine (ABC-SSELM), characteristic parameter normalization equations of I-V curves are tuned via low-cost data under normal operation of PV strings. The proposed ABC-SSELM method only needs 1-3 labeled data of the total dataset to save humantime cost. The accuracy of diagnosing various mixed faults can reach more than 99.84,the monitoring of dust accumulation can provide effective cleaning to increase the revenue of the solar PV power generation system.

As our knowledge goes, there are no methods to deal with the problems of PV faulty diagnoses by considering dust impact simultaneously. The proposed ABC-SSELM algorithm can make use of unlabeled historical data,require only 1-3 labeled data of the total dataset. In the hybrid simulationexperiment verification, the average accuracy improvement of the proposed ABC-SSELM is over 69.28 than the extreme learning machine (ELM), over 7.37 than the stage-wise additive modeling using multi-class exponential loss function based on the classificationregression tree (SAMME-CART), over 2.94 than the localglobal consistency (LGC), over 1.26 than the semi-supervised extreme learning machine (SSELM),over 0.42 than the particle-swarm-optimization-based SSELM (PSO-SSELM).

This technology application industry includes photovoltaic system manufacturersmaintenance & management manufacturers. Based on the assumption of the installed capacity of 20GW solar PV power generation systems in 2025the power generation of 3kWh per kilowatt per day, it will create more than 200 million kWh of power generation, the economic benefit exceeding 600 million NTD per year,the carbon reduction benefit exceeding 110,000 tons CO2e per year if the fault diagnosis improves the power generation efficiency by more than 1. This technology has been successfully transferred to an authorized solar PV manufacturer by 500,000 NTD for one year,is currently negotiating with a number of solar PV system manufacturers to do follow-up joint authorization matters.

天使投資人、策略合作夥伴