ConSite Mine has been designed to perform optimisation and predictive maintenance on equipment including trucks, pumps and excavators.
It uses sensors and machine learning in the cloud to provide analysis of equipment operations data, giving remote operators prior warning of significant maintenance issues such as cracks in excavator arms or the failure of hydraulic pumps.
"Service technicians supporting customers can analyse asset health information in real-time using the online dashboard. The technician can pre-order parts and schedule planned maintenance, avoiding the costs and delays of unplanned downtime from failed equipment", said the companies.
The solution also aims at improving overall productivity and safety, by monitoring conditions associated with operator behaviour, equipment location and speed, fuel consumption and other data for each equipment and operator.
For instance, on trucks, it can identify unsafe or inefficient operations such as hard braking, free spinning of tires, over-speeding and running over bumpy haul roads from operating data. Optimisation functions include the ability to tweak certain parameters such as the engine rotating speed and the accelerator responsiveness.
In Hitachi's EX-7 series of 190-800t ultra-large excavators, the software collects data from sensors, analyses cumulative loads of the boom and arm by utilising AI and applied analysis technologies, and predicts the occurrence of cracks.
While the system connects to existing, standard sensors on Hitachi machinery, Wenco provides the IoT digital platform and software technology by which large-volume data are collected and displayed on a customised dashboard for each customer.
Pilots of the technology are underway in Australia, Zambia and Indonesia, with plans for a commercial release in 2021, incorporating customer feedback.