| Summary: | 碩士 === 國立臺灣科技大學 === 電子工程系 === 107 === Fault diagnosis of a photovoltaic (PV) system is an essential task for improving its reliability and safety. PV faults at the dc side are difficult to detect by traditional protective devices, which may reduce power conversion efficiency and even lead to safety matters and fire disaster. This thesis investigates intelligent fault diagnostic methods for a PV system. First, optimal faulty features are extracted by analyzing I-V curves from different faults including hybrid faults of a PV system under the standard test condition (STC). Moreover, the trust-region-reflective (TRR) deterministic algorithm combined with the particle-swarm-optimization (PSO) metaheuristic algorithm is proposed to standardize faulty features into the ones under the STC. In addition, a multi-class adaptive boosting (AdaBoost) algorithm, which is the stage-wise additive modeling using multi-class exponential (SAMME) loss function based on the classification and regression tree (CART) as the weak classifier, is utilized to establish the fault diagnostic model. The effectiveness of the fault diagnostic model could long-term maintain by periodically updating the feature standardization equations to standardize the fault features into the ones under the STC. On the other hand, PV systems operating in the outdoor environment are vulnerable to various factors, especially dust impact. I-V characteristics of PV strings under soiling condition are also analyzed in this thesis. Because labeled data for PV systems with specific faults are challenging to record, especially in the large-scale ones, a novel algorithm combining artificial bee colony algorithm and semi-supervised extreme learning machine (ABC-SSELM) is proposed to handle this problem. Combining with the parameter normalization method, the proposed ABC-SSELM algorithm can diagnose PV faults using a small amount of simulated labeled data and historical unlabeled data, which greatly reduces labor cost and time-consuming. Furthermore, the monitoring of dust accumulation can warn power plant owners to clean PV modules in time and increase the power generation benefits. PV systems of 3.51 kWp and 3.9 kWp are used to verify the proposed diagnostic methods. Both numerical simulations and experimental results show the accuracy and reliability of the proposed PV diagnostic technologies.
|
|---|
