[ad_1]
A brand new hardware-free platform for maximising wind turbine well being and availability – Windscope – launched on 10 October, following a profitable 9-month beta testing section.
The platform, developed by the info science and engineering crew behind industrial AI firm Ada Mode, is designed to convey superior well being monitoring expertise to asset managers and engineers within the wind vitality sector, empowering them to rapidly scale up their predictive upkeep methods and not using a requirement for {hardware} set up.
Turbine monitoring and AI-driven predictive upkeep aren’t new ideas for wind farm house owners and operators as they search to minimise downtime, maximise manufacturing and prolong the operational lifetime of their belongings. Nevertheless, quite a few obstacles proceed to frustrate the ambitions of asset managers to roll out superior well being monitoring approaches throughout their fleets.
“One of many important complications for operators lies in integrating a wide selection of disparate knowledge streams to achieve a full oversight of their generators’ situation and efficiency,” mentioned Joe Donnelly, CEO, Windscope. “That is significantly difficult in multi-technology portfolios, the place bodily Situation Monitoring Programs (CMS) have both been put in as a part of a earlier marketing campaign or have to be put in to help the deployment of a brand new software program platform.”
“One other huge hurdle lies in the best way key efficiency knowledge may be siloed between the turbine producer (OEM), the Impartial Service Supplier (ISP) and the asset supervisor. Lack of collaboration between stakeholders within the O&M course of places a spanner within the works with regards to performing preventative upkeep earlier than failures happen, growing turbine availability, and supporting protected planning of upkeep actions.”
Windscope, constructed by engineers with first-hand expertise managing upkeep programmes throughout each wind and nuclear energy, goals to put the inspiration for a profitable, scalable predictive O&M technique.
The intuitive software program platform requires no extra {hardware}, eliminating the downtime and expense concerned in putting in monitoring gear, whereas being able to making use of AI to current SCADA and CMS methods. Equally, the place work order administration methods exist, Windscope knowledge may be rapidly built-in into current software program methods and interfaces.
As such, the platform may be up and operating in as little as 2 weeks, giving asset administration groups entry to granular insights that allow them to establish rising points, prioritise upkeep actions and report again to their inside and exterior stakeholders. In flip, this enhanced knowledge entry can empower extra collaborative and clear relationships between the asset supervisor, the OEM and the ISP.
For beta person Ventient Power, Windscope proved profitable in figuring out quite a few points together with Gearbox, Convertor/Transformer and Sensor faults, a few of which might not in any other case have been caught earlier than failure. Windscope additionally proved invaluable as a way of reporting turbine situation in day-to-day communication with the engineering crew and ISP – finally decreasing the general burden on the asset supervisor.
Following these profitable trials, Ventient Power is now utilizing Windscope on a long-term foundation to help its preventative upkeep actions at quite a few UK wind farms.
“Managing an unlimited and technologically numerous wind turbine fleet calls for a dynamic method to asset administration. In consequence, we’re persistently enhancing our upkeep methods to optimise our time and assets,” acknowledged John Morris, Head of Asset Administration (UK) at Ventient Power. “We’ve been significantly impressed by Windscope’s component-level monitoring method, which has confirmed very priceless in figuring out and addressing varied rising faults. Moreover, the system has performed a vital position in promptly escalating these points to our engineering crew and ISP.”
[ad_2]