Why

Machine data generated by mobile machinery is rarely utilised beyond the onboard control network neither analysed for insights by heavy industry, let alone automatically.

Collecting this machine data requires accessibility to the manufacturers communication systems and a physical connection to the onboard communications hardware.

Furthermore, interpreting the recovered machine data requires methodological data management and large data storage capabilities potentially beyond the capabilities of most end customers and service providers.

Identifying the machine activities performed during operation from the multitude of sensor signals would require manual calculation by the end user.

Therefore, to be scalable in heavy industry the recovery, storage and classification of machine data requires an automated workflow and analysis platform to highlight the productivity of mobile fleet by processing and delivering machine information to the end user in real time.

What

Machine data is generated by sensors onboard mobile machinery to communicate the status of measurable sub-systems to the respective control systems and by extension to the human operator.

The digitalisation of heavy industry involves utilising this machine data to improve the efficiency, effectiveness, and productivity of daily operations by providing an overview of a single mobile asset upwards to an entire fleet.

However, retrieved machine data provides limited information without initially prioritising, filtering and processing the data.

How

A process classification algorithm categorises each data point sourced from a mobile asset into the operational process performed by the operator.

For example, a simplified classification algorithm evaluates the value of an input signal to determine if a mobile asset is active or inactive.

These identified activities are coupled with other metrics, for example the fuel consumed, sourced from additional machine signals to quantify insights or Key Performance Indicators (KPI).

These KPIs highlight productivity issues allowing operators, supervisors and machine manufactures to better utilise, plan and monitor machinery activities by quantifying operating behaviour, process bottlenecks and performance benchmarks.