Planar perovskite solar cells (PSCs), as a promising photovoltaic technology, have been extensively studied, with strong expectations for commercialization. Improving the power conversion efficiency (PCE) of PSCs is necessary to accelerate their practical application, in which the electron transport layer (ETL) plays a key part. Herein, a single-anchored ligand of phenylphosphonic acid (PPA) is utilized to regulate the chemical bath deposition of a TiO2 ETL, further improving the PCE of planar PSCs. The PPA possesses a steric benzene ring and a phosphoric acid group, which can inhibit the particle aggregation of the TiO2 film through steric hindrance, leading to optimized interface (ETL/perovskite) contact. In addition, the incorporated PPA can induce the upshift of the Fermi-level of the TiO2 film, which is beneficial for interfacial electron transport. As a consequence, the PSCs with PPA-TiO2 achieve a PCE of 24.83%, which is higher than that (24.21%) of PSCs with TiO2. In addition, the unencapsulated PSCs with PPA-TiO2 also exhibit enhanced stability when stored in ambient conditions.
Photovoltaic (PV) power stations are pivotal for the renewable energy transition, yet their operational efficiency is often compromised by defects such as surface dust accumulation and cracks. Traditional manual inspections are labor-intensive and subjective, while conventional monitoring methods struggle with environmental interference. This study proposes YOLO-MSG, a lightweight framework specifically designed for the automated detection of PV module defects during system operation, including normal panels as well as defective conditions such as dusty and cracked panels. The methodology integrates a Multi-Scale Grouped Convolution (MSGC) module for enhanced feature extraction and a Group-Stem Decoupled Head (GSD-Head) to reduce parameter redundancy. Furthermore, a joint optimization strategy involving LAMP and logits-based knowledge distillation is employed to facilitate edge deployment. Experimental results on a specialized PV defect dataset demonstrate that YOLO-MSG achieves a superior balance between detection accuracy and computational cost. Compared to state-of-the-art models like YOLO11 and YOLOv12, YOLO-MSG significantly reduces GFLOPs and parameter count while maintaining highly competitive mean Average Precision (mAP), with improvements of 1.35% in mAP and 2.37% in mAP50-95 over the baseline models. Specifically, the model achieves an average inference speed of 90.30 FPS on the NVIDIA Jetson AGX platform. These findings confirm the algorithm’s industrial viability, providing a robust and efficient solution for the real-time automated maintenance of photovoltaic infrastructures.