| Work Detail |
The new algorithm monitors the inverter subsystems and sends alarms when maximum and minimum values ??are reached. Analyze data and categorize variables based on historical values.
Researchers at the University of Lisbon (Portugal) have developed a machine learning algorithm that classifies and predicts inverter failures in commercial-scale photovoltaic plants.
The new algorithm monitors, in particular, the inverter subsystems and sends alarms when maximum and minimum values ??are reached. Analyze the data and classify the variables based on historical values.
The scientists identified the types of failures based on the errors obtained in the inverters and the description of the events. Faults include mains faults, mains overvoltage, temporary mains overvoltage, mains undervoltage, undervoltage, temporary AC overcurrent, mains overfrequency, mains underfrequency, mains power failure, excessive eddy current, mains failure. supply, 10 minute mains overvoltage, output overload and unbalanced load of mains device failure.
The group tested the proposed approach on two ground-mounted PV systems with capacities of 140 kW and 590 kW. Both installations use inverters from the German manufacturer SMA. “The variables of each inverter were analyzed and the following types of failure were verified in the case of variable performance, due to inverter errors,” he explained.
The data were characterized using fine tree, medium tree, and thick tree prediction models. In tree-based models, a set of partitioning rules actively divides the feature space into multiple smaller, non-overlapping regions with similar response values.
The academics claim that the proposed algorithm is capable of identifying seasonal variations in inverter failures and the results it provides can be used for reliability analysis. “The data-driven assessment developed in this study indicates that inverter subsystems emerge to categorize failure modes,” they stressed.
They also suggested protecting inverters from inrush and overcurrent automatically by using parallel resonant capacitance clamp circuits. “High power conversion efficiency can be achieved by regenerating the clamp current to the input voltage source,” they concluded.
The novel algorithm was presented in the study “ Machine learning for monitoring and classification in inverters from solar photovoltaic energy plants ,” published in Compass in Solar . |
