297 • is the loading time at the shovel, • ℎ is the loaded travel time from the loading point to the dumping location, • is the dumping or unloading time, • is the empty return travel time, and • includes operational delays such as queuing, speed fluctuations, and unnecessary braking. Among these components, ℎ , , and are strongly influenced by driver behavior and therefore represent the primary optimization targets of the proposed Automatic Operator Guidance System (AOGS). Haul and return times are directly governed by the vehicle speed profile along the haul road. Let represent the haul road length; the haul time can be expressed as: ℎ =න 1 ( ) 0 where ( )is the truck speed as a function of road position . Variations in speed due to inconsistent driving behavior, excessive braking, or conservative speed selection significantly increase the integral value of ℎ , thereby reducing overall productivity. By reducing speed variance and maintaining operation near the optimal speed envelope, the guidance system minimizes travel time without compromising safety constraints. 2.1 Target Variables The objective of the Automatic Operator Guidance System is to determine an optimal speed profile that minimizes haulage time while satisfying safety, mechanical, and environmental constraints. This problem is formulated as a multiobjective optimization: ∗( )=argmin ( ) ( ℎ ( )+ ( )+ ( )) where: • ∗( )is the recommended optimal speed, • ℎ ( )represents hauling time, • ( )represents energy or fuel consumption, • ( )is a safety-related penalty term, • , , are weighting coefficients. This formulation reflects the trade-off between productivity maximization, fuel efficiency, and safe operation. The adaptive machine learning model is formulated as a multi-target regression problem, aiming to optimize both operational efficiency and productivity. Specifically, two target variables are defined:
RkJQdWJsaXNoZXIy MTM0Mzk2