Global quality assurance and risk management company DNV has called on the global solar PV industry to opt for predictive maintenance of PV power plants as part of a joint industry project (JIP) which, it claims, will enable to optimize the costs associated with on-site maintenance.
Currently, the industry's focus is on traditional preventive maintenance, which is visiting sites at regular intervals, or on corrective maintenance related to repair works.
As opposed to these, DNV proposes predictive maintenance to be carried out only when a fault is expected and before it occurs. It can help identify parts that require immediate attention, prioritize maintenance tasks and schedule downtime efficiently, all of which can ensure healthy margins for solar power plants operators.
The goal is for the industry to arrive at minimum standards of maintenance logs while developing predictive maintenance models and evaluatinge their performance.
"Standardized practices will foster better communication and more effective decision-making, and the proactive use of advanced predictive models will reduce downtime, minimize breakdowns, and optimizes solar PV systems' lifespan," said CEO of GreenPowerMonitor, a DNV company, and Executive Vice President for Energy Systems at DNV, Juan Carlos Arévalo.
The effort will be based on machine learning with high-quality and standardized maintenance logs.
The maintenance logs being compiled by the industry at present are highly variable with their levels of detail and quality, point out analysts, which make it challenging to train machine learning models to meet acceptable performance standards.
As the global PV industry is forecast to install between 300 GW and 500 GW annually from 2030 onwards, having a standardized preventive maintenance structure will contribute to running a PV plant profitably.
DNV said the JIP will comprise several work packages including coordination, definition of maintenance log standards, implementation at operating PV plants, development of predictive maintenance models based on the logs, and analysis of results – in order to establish a final agreement on the format for maintenance logs.