CBS is pleased to announce a new technology Collaboration with Yottaasys –
a leading AI ML Product Company with advanced capabilities to integrate
Computer Vision and
based models to generate actionable business insights and Predictive Maintenance Solution using AI.
CBS, one of Singapore's 50 fastest growing company in 2009, collaborates with Yottaasys AI, an innovative AI products company which uses its Proprietary AML Platform called Superhacker to compute risk scores and can be configured to estimate probability of critical parts failures and raise alerts in advance before an unplanned engine Slowdown/Shutdown.
Both the companies have teamed up to develop a machine learning solution that will improve the situational awareness at ports by analyzing freight, logistic chains and Predictive Maintenance based Solution which can monitor the Health of the Engines in a smarter way and reduce considerable amount of time and cost spent in Maintenance of Vessels.
Both the teams are also looking at utilizing another Proprietary Product of Yottaasys AI, a computer vision based solution called Dhrishti to analyze and monitor cargo and vehicles in port in real time.
The solution can also automate challenging manual analysis, speed up cargo logistics planning, and improve the detection of potential exceptional situations to create better safety awareness.
PREDICTIVE ENGINE MAINTENANCE SOLUTION
Maritime Systems, like ships and all their subsystem, are typically operated in a harsh and largely variable environment.
At the same time, failures in any of the subsystems or components may have a large consequence eg. High Costs (Loss of Revenue), High logistics costs due to remote locations) or environmental impacts. The number of failures in this sector of industry is nowadays typically controlled by performing a lot of preventive maintenance.
By replacing the components in time, failures can be prevented.
However this is a rather expensive policy when the operational profile is largely varying.
The loaded subsystems do not fail. This is a costly process, but it also limits the availability of the system as it must be available for maintenance tasks quite often.
To improve this process, reduce maintenance and logistics costs and at the same time increase the system availability, a better prediction of failures for system operated under specific conditions is required.
Superhacker automates machine learning by and helps you to move beyond typical automated machine learning by building innovative new models from incredibly diverse types of data.
Superhacker consists of broad library of open source and proprietary models from classic regression and complex multiclass classification to the latest deep learning algorithms.
The automated models can work with a variety of data sources including sensor data raw data, tabular data and images.
Reduce unexpected failure by up to 55%
Reduce inventory lead times for spares by up to 28%
Reduce overall maintenance costs by up to 30%
Reduce maintenance interval without compromising on the equipment reliability
The maintenance team can make data-driven decisions
Improve HSSE compliance
Establish clear correlation between events that led to the breakdown, data driven root cause analysis can improve plant reliability.