HoseProtect - Safe Remote Drilling through Predictive Modeling of Hydraulic Hoses

This project is about modeling flexible hydraulic hoses attached to mining machines and has the goal of predicting hose states under different machine configurations in order to avoid damage during operations. For this, we will implement different modeling techniques from computational physics and machine learning and evaluate their efficacy for preventing hose damage under realistic use-case scenarios for heavy duty mining machines. By accurately modeling the motion of hydraulic hoses we aim at preventing hose damage and supporting remote and autonomous machine operation.

The majority of heavy duty machines used in mining are powered by hydraulic actuators, which neces sitate the use of hoses to carry pressurized fluid from a compressor on the machine to cylinders along the articulated link chain (e.g., along the booms of a drilling rig). While this solution is flexible and robust, the use of hydraulic hoses poses a risk: if a hose is severed due to interaction with another part of the machine, the machine needs to stop and be serviced. Hydraulic hose servicing is one of the major reasons for machine downtime, costing millions in loss of productivity.

In this project we aim at deploying two different techniques: one analytic an d one data-driven, for the task of modeling the behavior of hydraulic hoses. We will use these methods to predict where the hoses on a machine are situated and devise methodology to prevent collisions between machine and hoses. The modules developed in this project will allow an intelligent controller to avoid damage to the hydraulic fluid hoses powering the machine, thereby decreasing the need for machine maintenance and improving the reliability and cost-efficiency of remote and autonomous mining machines.