A survey on decision support in high-mix low-volume manufacturing

The increasing demand for highly customised products challenges the ability of manufacturing systems to sustain high levels of automation, particularly in high-mix low-volume (HMLV) environments. Although decision support has become a major research area in response to these challenges, existing reviews either focus narrowly on specific methods such as reinforcement learning for scheduling or address HMLV manufacturing without systematically analysing decision support across manufacturing levels. This paper addresses that gap through a survey of 205 publications on decision support in HMLV manufacturing. The survey provides a structured synthesis of how decision support approaches are applied across four hierarchical manufacturing levels: process, line and cell, factory, and enterprise and supply chain. The reviewed studies are analysed through four research questions addressing: (1) the key drivers motivating decision support in HMLV manufacturing, (2) the optimisation objectives pursued, (3) the technologies and methods employed, and (4) the evaluation practices and limitations reported. The analysis reveals a rapid growth in research activity over the past decade, with a strong methodological concentration around scheduling problems, which account for 69.8% of the reviewed literature, while areas such as logistics and supply chain (6.3%) and quality and maintenance (2.9%) remain comparatively underexplored. Reinforcement learning, graph neural networks, digital twins, and metaheuristic optimisation emerge as dominant technologies and methods, within dynamic scheduling contexts. The findings show that current research is concentrated on simulation-based scheduling optimisation, with comparatively limited attention to cross-level decision support, industrial validation, human-centred decision-making, and integrated decision-support architectures spanning multiple manufacturing levels. Based on these findings, the survey identifies key research gaps and outlines future directions for decision support in HMLV manufacturing. These findings should be considered alongside the search and screening process, which relies primarily on broad HMLV, manufacturing, and decision-support terminology and may therefore under-represent research using specialised, industry-specific terminology.

Authors

Institutions

Publication Details

Journal
Frontiers in Manufacturing Technology
Published
2026-11-12
DOI
https://doi.org/10.3389/fmtec.2026.1905224
Primary Topic
Scheduling and Optimization Algorithms
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A survey on decision support in high-mix low-volume manufacturing

Samra Yousaf, Peter Gorm Larsen, Casper Schou, Lukas Esterle et al.
Frontiers in Manufacturing Technology
Scheduling and Optimization Algorithms
article

A survey on decision support in high-mix low-volume manufacturing

Samra Yousaf, Peter Gorm Larsen, Casper Schou, Lukas Esterle, Rasmus Skovhus Lunding, Jan Corfixen Sørensen, Martin Braas, Filip Džigurski, Jannik Fibiger, Malthe Tøttrup Birkebæk, Mikkel Ejsing Skov Petersen
article en

Abstract

The increasing demand for highly customised products challenges the ability of manufacturing systems to sustain high levels of automation, particularly in high-mix low-volume (HMLV) environments. Although decision support has become a major research area in response to these challenges, existing reviews either focus narrowly on specific methods such as reinforcement learning for scheduling or address HMLV manufacturing without systematically analysing decision support across manufacturing levels. This paper addresses that gap through a survey of 205 publications on decision support in HMLV manufacturing. The survey provides a structured synthesis of how decision support approaches are applied across four hierarchical manufacturing levels: process, line and cell, factory, and enterprise and supply chain. The reviewed studies are analysed through four research questions addressing: (1) the key drivers motivating decision support in HMLV manufacturing, (2) the optimisation objectives pursued, (3) the technologies and methods employed, and (4) the evaluation practices and limitations reported. The analysis reveals a rapid growth in research activity over the past decade, with a strong methodological concentration around scheduling problems, which account for 69.8% of the reviewed literature, while areas such as logistics and supply chain (6.3%) and quality and maintenance (2.9%) remain comparatively underexplored. Reinforcement learning, graph neural networks, digital twins, and metaheuristic optimisation emerge as dominant technologies and methods, within dynamic scheduling contexts. The findings show that current research is concentrated on simulation-based scheduling optimisation, with comparatively limited attention to cross-level decision support, industrial validation, human-centred decision-making, and integrated decision-support architectures spanning multiple manufacturing levels. Based on these findings, the survey identifies key research gaps and outlines future directions for decision support in HMLV manufacturing. These findings should be considered alongside the search and screening process, which relies primarily on broad HMLV, manufacturing, and decision-support terminology and may therefore under-represent research using specialised, industry-specific terminology.

Frontiers in Manufacturing TechnologyVol. 6
University of Southern Denmark (DK), Aarhus University (DK), Aalborg University (DK)
Industry, innovation and infrastructure
Scheduling and Optimization Algorithms
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon