Smart Manufacturing Overview

Principles

Definition

Smart manufacturing is an interdisciplinary academic concept and methodological approach focused on the comprehensive integration of advanced digital technologies throughout the manufacturing lifecycle. It investigates the design, implementation, and optimization of highly connected, data-driven, and adaptive production systems. This domain seeks to leverage real-time information and intelligent automation to achieve unprecedented levels of efficiency, flexibility, quality, and sustainability in industrial processes.

Ontological type

Core Technologies

Data Analytics Methods

System Architectures

Key developments

Key Figures

Neural Adaptive Manufacturing era

Duncan McFarlane [1] is linked with the University of Cambridge [3] and the Australian Defence Force Academy [4] during this era. His key contribution, Rationales for Holonic Manufacturing Control [7], advanced holonic manufacturing control as a framework for distributed autonomous production units, aligning with the era's emphasis on learning-based planning and autonomous reconfiguration. Weiming Shen [2] is affiliated with the University of Southern California [5] and the University of Calgary [6] during this period. His Learning in Agent-Based Manufacturing Systems [8] illustrated learning-enabled agent-based approaches that supported adaptive control and proactive planning, reflecting the era's focus on neural and computational intelligence in manufacturing.

Cyber-Physical Factory Networks era

Jay Lee [1] is associated with Stanford University [3] and University of Wisconsin–Madison [4] in this era. His key contributions include the paper Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment [6], which demonstrated how analytics-driven services enable predictive maintenance and runtime optimization in cyber-physical factory networks, a hallmark of the era. Shanhu Yang [2] is affiliated with University of Cincinnati [5] in this era. Her collaboration on Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment [6] helped articulate how analytics-driven services enable interoperability and resilience across heterogeneous assets in cyber-physical factory networks, aligning with standards and autonomous coordination in this era.

Digital Twin Manufacturing era

Xun Xu[1], affiliated with National University of Singapore[3] and Fuzhou University[4], has shaped the Digital Twin Manufacturing era (2017–2023) through foundational ideas in smart manufacturing. Xun Xu's key contributions include the papers 'Industry 4.0 and Industry 5.0—Inception, conception and perception'[6] and 'Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues'[7], which articulate the Industry 4.0/5.0 continuum and a Digital Twin–driven reference model that underpins real-time integration and autonomous decision-making in manufacturing. Yuqian Lu[2], at University of Auckland[5], has contributed to the Digital Twin Manufacturing discourse in this era. Lu's co-authored works include the papers 'Industry 4.0 and Industry 5.0—Inception, conception and perception'[6] and 'Digital Twin-driven smart manufacturing: Connotation, reference model, applications and research issues'[7], which collectively advance the digital twin framework enabling closed-loop control, predictive maintenance, and quality optimization in smart manufacturing.