Solar equipment manufacturers, EPCs and power plant owners and operators commonly face the challenge of keeping their fleet, machinery and other assets working efficiently, while also reducing the cost of maintenance and time-sensitive repairs. Considering the aggressive timelines set for solar-focused organizations, it is crucial to identify the cause of potential faults or failures before they have an opportunity to occur.
By proactively identifying potential issues via artificial intelligence, solar companies can turn equipment sensor data into actionable insights in order to more effectively deploy maintenance services and improve equipment uptime.
Predictive maintenance approach
The underlying architecture of a predictive maintenance model is fairly uniform irrespective of its end applications. The analytics usually reside on a host of IT platforms, but these layers are systematically described as:
- Data acquisition and storage (either on the cloud or at the edge)
- Data transformation — conversion of raw data for machine learning models
- Condition monitoring — alerts based on asset operating limits
- Asset health evaluation — generating diagnostic records based on trend analysis if asset health has already started declining
- Prognostics — generating predictions of failure through machine learning models and estimating remaining life
- Decision support system — recommendations of best actions
- Human interface layer — making all information accessible in an easy-to-understand format
Failure prediction, fault diagnosis, failure-type classification and recommendation of relevant maintenance actions are all a part of predictive maintenance methodology.
As solar customers become increasingly aware of the growing maintenance costs and downtime caused by unexpected machinery failures, predictive maintenance solutions are gaining even more traction. For energy companies in particular, this type of predictive maintenance can serve as a significant competitive advantage in front of customers.
The bigger players have already been using this methodology for more than a decade. Small- and medium-sized companies in the solar sector also can reap its advantages by keeping repair costs low and meeting initial operational costs.
Predictive maintenance is also a step ahead of preventive maintenance. As maintenance work is scheduled at preset intervals, maintenance technicians are informed of the likelihood of parts and components failing during the next work cycle and can take action to minimize downtime.
In addition to the advantages of controlling repair costs, avoiding warranty costs for failure recovery, reducing unplanned downtime and eliminating the causes of failure, predictive maintenance employs non-intrusive testing techniques to evaluate and compute asset performance trends. Additional methods used can include thermodynamics, acoustics, vibration analysis and infrared analysis.
What stakeholders need is a bankable analytics and engineering service partner who can help them leverage data science not only to predict embryonic asset failures, but also to eliminate them and take action in a timely manner.
Sean Otto leads business development for Cyient’s Advanced Analytics team.
The Residential Rooftop Report for the first quarter of 2019 is now available for download. The theme is “Heating Up Sales,” and we’ve teamed up with report sponsor Aurora Solar to examine ways for residential solar installation companies to lower customer acquisition costs, close more leads and overall run a more streamlined, efficient local solar business. Just fill out the form below to access your free report.