SkySpecs’ Horizon CMS Platform Uses AI to Boost Wind Turbine Condition Monitoring
With the launch of SkySpecs’ Horizon CMS platform, wind turbine operators can now unlock the full potential of their fleet data in order to lower O&M cost and focus on optimizing for maximum uptime. The Advanced Condition Monitoring Platform is enhanced with Kaleidoscope AI - a cutting-edge fault detection technology that uses AI for early and robust fault detection of critical drivetrain components like gearboxes, generators and main bearings. The Horizon CMS platform is disrupting the software paradigm that engineers have relied on for over a decade.
Detecting different fault locations on a bearing
We are going to use the popular Bearing Vibration Data Set from Case Western Reserve University as a benchmark to demonstrate how different bearing conditions and faults can be properly correlated to a different operational mode, and ultimately to the automatic identification of healthy and faulty operational conditions.
MultiViz Vibration’s Mode Identification feature is powered by our Automatic Mode Identification (AMI) unsupervised algorithm for multivariate time series analysis. It performs multidimensional data segmentation and clustering in time series data, such as waveform vibration signals. It detects time periods in which the data exhibits a similar behavior and reports these periods as belonging to the same operational mode.
Operational modes are often correlated with typical conditions of an asset, like on/off, load conditions or fault states. Thus, the identification of different modes when the behavior of the machine has remained the same, can point to the appearance of a fault in the machine.
Condition Monitoring via LoRaWAN
LoRaWAN can be a good choice when key factors become particularly important. These factors include wide areas of coverage on an operating site with different buildings, low cost of infrastructure and operation, use of an established standard, and a large number of users and providers. However, LoRaWAN is less suitable for transmitting large amounts of data due to the low bandwidth, the associated low data transmission rate, and the duty cycle regulations in the 868 MHz range. For this reason, additional sensors with embedded AI algorithms are required for sophisticated monitoring applications.
Machine vibration analysis benefits for manufacturers
Vibration analysis allows early detection of wear, fatigue and failure in rotating machinery because vibration occurs in all rotational assets, but generally highlights an issue discovered by higher readings and particular frequencies, mostly as the result of wear and tear but also as a consequence of poor maintenance practices. Vibration builds and leads to equipment failure.
Vibration analysis identifies potential problems and a predicted time to failure (in some cases up to one year in advance of equipment failure) to enable replacement parts to be ordered in a timely way and helping to reduce unexpected downtimes.