NB: Extended abstract & full paper attached as PDF

Accumulated fatigue damage is estimated for a mine truck load frame. On-board sensor data and a linear auto-regressive model is used to calculate stress levels at a number of locations. Lasso regression and coherence is used to identify the most important on-board sensors, such as accelerometers and gyroscopes. A rain flow counting technique is then applied to calculate an estimate of the accumulated damage during different drive cycles of the machine. The accumulated damage based on accelerometer and gyroscope signals is validated against damage accumulation calculations from a measured strain signal. Different load levels of the truck, velocity and road conditions are also taken into consideration.