Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG

Conventional maintenance strategies for port cranes often lack intelligence, flexibility, and global optimization, with insufficient consideration of time awareness. To optimize condition-based maintenance and resource management for crane clusters, this study decouples maintenance decisions for ind...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiao Yao, Daofang Chang, Haitao Song, Congming Wu, Jingsen Huang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10788675/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846118351735095296
author Shiao Yao
Daofang Chang
Haitao Song
Congming Wu
Jingsen Huang
author_facet Shiao Yao
Daofang Chang
Haitao Song
Congming Wu
Jingsen Huang
author_sort Shiao Yao
collection DOAJ
description Conventional maintenance strategies for port cranes often lack intelligence, flexibility, and global optimization, with insufficient consideration of time awareness. To optimize condition-based maintenance and resource management for crane clusters, this study decouples maintenance decisions for individual cranes from the overall cluster resource management. We formulate a decision-making model, incorporating uncertainties in procurement lead times, costs, equipment downtime, and spare parts shortages. To improve the model-solving process, we present the evolutionary multi-head attention critic with adaptive strategy–multi-agent deep deterministic policy gradient (EMACAS-MADDPG) algorithm, an enhanced version of the multi-agent deep deterministic policy gradient (MADDPG) algorithm. This algorithm initially evolves policy network parameters through a genetic algorithm and subsequently refines them using experience buffer data. Furthermore, a multi-head self-attention mechanism is embedded into the critic network, and an adaptive exploration strategy is utilized during action execution. The implementation of the EMACAS-MADDPG algorithm in the joint optimization model significantly reduces the average maintenance cost by 22.37% compared to the original MADDPG and by 51.73% compared to the Independent Proximal Policy Optimization (IPPO) algorithm.
format Article
id doaj-art-7d49d6057ee64f7e8db2f60a626119f3
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-7d49d6057ee64f7e8db2f60a626119f32024-12-18T00:01:30ZengIEEEIEEE Access2169-35362024-01-011218708118709810.1109/ACCESS.2024.351483410788675Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPGShiao Yao0https://orcid.org/0009-0008-3897-8406Daofang Chang1https://orcid.org/0000-0002-7163-7741Haitao Song2Congming Wu3Jingsen Huang4Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai, ChinaLogistics Engineering College, Shanghai Maritime University, Shanghai, ChinaGuangxi Qinzhou Bonded Port Zone Shenggang Wharf Company Ltd., Qinzhou, ChinaGuangxi Qinzhou Bonded Port Zone Shenggang Wharf Company Ltd., Qinzhou, ChinaGuangxi Qinzhou Bonded Port Zone Shenggang Wharf Company Ltd., Qinzhou, ChinaConventional maintenance strategies for port cranes often lack intelligence, flexibility, and global optimization, with insufficient consideration of time awareness. To optimize condition-based maintenance and resource management for crane clusters, this study decouples maintenance decisions for individual cranes from the overall cluster resource management. We formulate a decision-making model, incorporating uncertainties in procurement lead times, costs, equipment downtime, and spare parts shortages. To improve the model-solving process, we present the evolutionary multi-head attention critic with adaptive strategy–multi-agent deep deterministic policy gradient (EMACAS-MADDPG) algorithm, an enhanced version of the multi-agent deep deterministic policy gradient (MADDPG) algorithm. This algorithm initially evolves policy network parameters through a genetic algorithm and subsequently refines them using experience buffer data. Furthermore, a multi-head self-attention mechanism is embedded into the critic network, and an adaptive exploration strategy is utilized during action execution. The implementation of the EMACAS-MADDPG algorithm in the joint optimization model significantly reduces the average maintenance cost by 22.37% compared to the original MADDPG and by 51.73% compared to the Independent Proximal Policy Optimization (IPPO) algorithm.https://ieeexplore.ieee.org/document/10788675/Gantry crane condition-based maintenancerepair resource managementtime-awaremulti-agent reinforcement learning
spellingShingle Shiao Yao
Daofang Chang
Haitao Song
Congming Wu
Jingsen Huang
Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
IEEE Access
Gantry crane condition-based maintenance
repair resource management
time-aware
multi-agent reinforcement learning
title Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
title_full Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
title_fullStr Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
title_full_unstemmed Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
title_short Joint Optimization of Time-Aware Condition-Based Maintenance and Repair Resource Management for Gantry Crane Clusters Based on Improved MADDPG
title_sort joint optimization of time aware condition based maintenance and repair resource management for gantry crane clusters based on improved maddpg
topic Gantry crane condition-based maintenance
repair resource management
time-aware
multi-agent reinforcement learning
url https://ieeexplore.ieee.org/document/10788675/
work_keys_str_mv AT shiaoyao jointoptimizationoftimeawareconditionbasedmaintenanceandrepairresourcemanagementforgantrycraneclustersbasedonimprovedmaddpg
AT daofangchang jointoptimizationoftimeawareconditionbasedmaintenanceandrepairresourcemanagementforgantrycraneclustersbasedonimprovedmaddpg
AT haitaosong jointoptimizationoftimeawareconditionbasedmaintenanceandrepairresourcemanagementforgantrycraneclustersbasedonimprovedmaddpg
AT congmingwu jointoptimizationoftimeawareconditionbasedmaintenanceandrepairresourcemanagementforgantrycraneclustersbasedonimprovedmaddpg
AT jingsenhuang jointoptimizationoftimeawareconditionbasedmaintenanceandrepairresourcemanagementforgantrycraneclustersbasedonimprovedmaddpg