In this article we give some examples of Custom Analytics realizations using the Alteia Python SDK, over the digital twin of an asset reconstructed in Alteia.

Best Fuel Path for Vehicles in Mines & Quarries

This case illustrates how to integrate industrial machine data with site geospatial data.

“A quarry manager wants to use the most efficient routes on his site to move material from point A to point B” (typically, from the loading area in the pit to the crusher)".

How to solve this optimization issue ?

Using a modelization of the fuel consumption of trucks, and the 3D geospatial data resulting from the modelization of a quarry, it was possible to compute and display as a layer in Alteia the best trajectory along available haul roads that minimizes the overall fuel consumption between two points A and B. Let's examine the successive steps to this result.
Step 1 is to use Alteia built-in analytics for generating the quarry haul roads as an input to this fuel map computation :

• Raw images are captured by drones
• Drones images are processed in 2D or 3D in Alteia (they could be processed outside and ingested as well)
• Alteia detects and extracts the haul roads

Step 2 is to define the fuel consumption between any points, using :

• Vehicle-related data : e.g. rolling resistance, load
• Drone-related data : lengths and elevation differences directly computed from the 3D model hosted in Alteia

def fuel_consumption(load, length, delta_z): 
return max(C_h*(1-RR)*(20000+load)/20000*length + C_v*(20000+load)
/20000*delta_z,0)

Step 3 is the development of a small Python script using the SDK. This script :

• defines the KPI to be generated (fuel consumption)
• calls the haul roads pattern as an input
• calls the SDK functions
• generates a visual map (.tiff)

In conclusion, it was possible to simulate the fuel cost associated to a certain positioning of the crusher versus the loading area