Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty

This paper presents a new truck dispatching policy approach that is adaptive given different mining complex configurations in order to deliver supply material extracted by the shovels to the processors. The method aims to improve adherence to the operational plan and fleet utilization in a mining co...

Full description

Bibliographic Details
Main Authors:	Joao Pedro de Carvalho, Roussos Dimitrakopoulos
Format:	Article
Language:	English
Published:	MDPI AG 2021-05-01
Series:	Minerals
Subjects:	truck dispatching mining equipment uncertainties orebody uncertainty discrete event simulation Q-learning
Online Access:	https://www.mdpi.com/2075-163X/11/6/587

id	doaj-8e614e0a50ec4cc3bbc88455e3862d25
record_format	Article
spelling	doaj-8e614e0a50ec4cc3bbc88455e3862d252021-06-01T01:48:12ZengMDPI AGMinerals2075-163X2021-05-011158758710.3390/min11060587Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing UncertaintyJoao Pedro de Carvalho0Roussos Dimitrakopoulos1COSMO—Stochastic Mine Planning Laboratory, Department of Mining and Materials Engineering, McGill University, 3450 University Street, Montreal, QC H3A 0E8, CanadaCOSMO—Stochastic Mine Planning Laboratory, Department of Mining and Materials Engineering, McGill University, 3450 University Street, Montreal, QC H3A 0E8, CanadaThis paper presents a new truck dispatching policy approach that is adaptive given different mining complex configurations in order to deliver supply material extracted by the shovels to the processors. The method aims to improve adherence to the operational plan and fleet utilization in a mining complex context. Several sources of operational uncertainty arising from the loading, hauling and dumping activities can influence the dispatching strategy. Given a fixed sequence of extraction of the mining blocks provided by the short-term plan, a discrete event simulator model emulates the interaction arising from these mining operations. The continuous repetition of this simulator and a reward function, associating a score value to each dispatching decision, generate sample experiences to train a deep Q-learning reinforcement learning model. The model learns from past dispatching experience, such that when a new task is required, a well-informed decision can be quickly taken. The approach is tested at a copper–gold mining complex, characterized by uncertainties in equipment performance and geological attributes, and the results show improvements in terms of production targets, metal production, and fleet management.https://www.mdpi.com/2075-163X/11/6/587truck dispatchingmining equipment uncertaintiesorebody uncertaintydiscrete event simulationQ-learning
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Joao Pedro de Carvalho Roussos Dimitrakopoulos
spellingShingle	Joao Pedro de Carvalho Roussos Dimitrakopoulos Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty Minerals truck dispatching mining equipment uncertainties orebody uncertainty discrete event simulation Q-learning
author_facet	Joao Pedro de Carvalho Roussos Dimitrakopoulos
author_sort	Joao Pedro de Carvalho
title	Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty
title_short	Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty
title_full	Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty
title_fullStr	Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty
title_full_unstemmed	Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty
title_sort	integrating production planning with truck-dispatching decisions through reinforcement learning while managing uncertainty
publisher	MDPI AG
series	Minerals
issn	2075-163X
publishDate	2021-05-01
description	This paper presents a new truck dispatching policy approach that is adaptive given different mining complex configurations in order to deliver supply material extracted by the shovels to the processors. The method aims to improve adherence to the operational plan and fleet utilization in a mining complex context. Several sources of operational uncertainty arising from the loading, hauling and dumping activities can influence the dispatching strategy. Given a fixed sequence of extraction of the mining blocks provided by the short-term plan, a discrete event simulator model emulates the interaction arising from these mining operations. The continuous repetition of this simulator and a reward function, associating a score value to each dispatching decision, generate sample experiences to train a deep Q-learning reinforcement learning model. The model learns from past dispatching experience, such that when a new task is required, a well-informed decision can be quickly taken. The approach is tested at a copper–gold mining complex, characterized by uncertainties in equipment performance and geological attributes, and the results show improvements in terms of production targets, metal production, and fleet management.
topic	truck dispatching mining equipment uncertainties orebody uncertainty discrete event simulation Q-learning
url	https://www.mdpi.com/2075-163X/11/6/587
work_keys_str_mv	AT joaopedrodecarvalho integratingproductionplanningwithtruckdispatchingdecisionsthroughreinforcementlearningwhilemanaginguncertainty AT roussosdimitrakopoulos integratingproductionplanningwithtruckdispatchingdecisionsthroughreinforcementlearningwhilemanaginguncertainty
_version_	1721411489863041024

Integrating Production Planning with Truck-Dispatching Decisions through Reinforcement Learning While Managing Uncertainty

Similar Items