The photovoltaic (PV) module is a key technological advancement in renewable energy. When the PV modules fail, the overall generating efficiency will decrease, and the power system’s operation will be influenced. Hence, detecting the fault type when the PV modules are failing becomes important. This study proposed a hybrid algorithm by combining the symmetrized dot pattern (SDP) with a convolutional neural network (CNN) for PV module fault recognition. Three common faults are discussed, including poor welding, breakage, and bypass diode failure. Moreover, a fault-free module was added to the experiment for comparison. First, a high-frequency square signal was imported into the PV module, and the original signal was captured by the NI PXI-5105 high-speed data acquisition (DAQ) card for the hardware architecture. Afterward, the signal was imported into the SDP for calculation to create a snowflake image as the image feature for fault diagnosis. Finally, the PV module fault recognition was performed using CNN. There were 3200 test data records in this study, and 800 data records (200 data records of each fault) were used as test samples. The test results show that the recognition accuracy was as high as 99.88%. It is better than the traditional ENN algorithm, having an accuracy of 91.75%. Therefore, while capturing the fault signals effectively and displaying them in images, the proposed method accurately recognizes the PV modules’ fault types.
Faults in solar photovoltaic (PV) modules often result from component damage, leading to voltage fluctuations and decreased stability in the power system. In this study, the original voltage signals of different PV modules show little variation. Therefore, a solution that combines symmetrized dot pattern (SDP) and AlexNet for fault detection in PV modules was proposed. This solution investigates three common faults: poor welding, cracking, and bypass diode failure, which can be applied to fault-free modules. First, a high-frequency signal was input into the PV module, and the raw signal was captured using an NI PXI-5105 high-speed data acquisition card. Next, we used SDP to process the signal and create images with specific snowflake-like features. These images were used as a basis for fault diagnosis. Finally, deep-learning algorithms were used to perform status detection on the PV module. This research also used 3200 training samples and 800 test samples (200 for each type) to evaluate a new method for diagnosing faults in PV modules. The results show that the accuracy of the new method reached 99.8%, surpassing traditional convolutional neural networks (CNN) and extension neural networks (ENN), whose accuracies were 99.5% and 91.75%, respectively. Furthermore, this study compares the proposed method with more traditional numerical fault diagnosis methods. SDP effectively extracts fault signals and presents them as images. With AlexNet used for fault identification, the method excels in accuracy, training time, and testing time, thereby enhancing the stability and reliability of future energy systems.