Airedale, known worldwide for their critical cooling solutions, has worked with data science experts to develop a new family of cloud-enabled products which can be installed in new and existing equipment like air handling units, chillers and precision air conditioners, allowing them to be connected, monitored and analysed via a secured communication channel to the Airedale Cloud Diagnostics servers. Cloud Diagnostics has been developed to be retrofitted with no disruption to service and offers several key benefits that can really lift the pressure off people tasked with keeping HVAC systems running safely and efficiently.
Leak detection
An emerging feature of the predictive maintenance ability of Cloud Diagnostics is a ground-breaking leak detection algorithm. By being able to recognize the operational features and patterns that signal a leak, detection can occur at very low levels, saving a client significant costs and environmental damage. Most leaks are detected today at around 20%, which is when a drop in performance becomes more obvious to facilities personnel, but in tests Airedale Cloud Diagnostics was able to report a suspected leak at 5%. This early detection has huge implications not only on cost savings, but also safety and environmental targets.Live dashboard
The information gathered by Cloud Diagnostics is reported on a live dashboard, which is available on any internet-connected device, and alerts can be delivered immediately via SMS or email. This allows for any issues to be recognized early and responded to immediately, avoiding disruption and expensive call outs. Data aggregation can be configured to report the latest data received as well as extracting KPIs for a comprehensive visual analysis of the unit’s performance. (e.g. chiller average supply water temperature for last 7 rolling days).Predictive Maintenance
Predictive maintenance is the key to optimizing asset management for any critical equipment. HVAC units connected to Cloud Diagnostics are analysed for performance, utilizing many algorithms and machine learning techniques, whereby the unit’s performance is measured on a variety of relevant factors which are all analysed for deviations against “normalized” behaviour, both instantaneously and over time as well.If a drop in performance against operating conditions is detected, this will act as an early warning system for the customer/maintenance team to investigate further. Being able to identify threats and faults in advance of them happening has a huge cost saving benefit, both in terms of emergency repairs, call out fees and downtime costs to the business.