INDUSTRICS — Industry, Intelligent Systems and Applied Transformation

Editorial Position

A method without a system context is half a contribution

Industrial engineering research lives or dies at the interface between the model and the factory floor, the algorithm and the warehouse, the simulation and the shift schedule. INDUSTRICS requires authors to report not only what the method achieves under controlled conditions, but how it behaves when embedded in a real or realistically simulated operating environment — with its constraints, variability, and human operators.

Contributions that address intelligent manufacturing, industrial AI, digital supply chains, automation systems, or applied transformation of industrial processes are in scope. Purely theoretical work is welcome when the paper specifies the class of industrial systems the theory is designed to serve and the conditions under which it would fail.

Scope & coverage

Industrial AI

Machine learning for industrial performance and optimization, predictive analytics, computer vision for quality inspection, and intelligent decision support.

Smart Manufacturing

Connected operations, predictive maintenance, digital twins, cyber-physical systems, and Industry 4.0 integration frameworks.

Digital Supply Chains

Resilient, data-driven supply chains and logistics systems, demand sensing, inventory optimization, and network design under uncertainty.

Automation & Systems

Control systems, robotics, IIoT, and integrated industrial systems — from sensor networks to enterprise-level orchestration.

Recently published

Volume archive →

Smart Manufacturing

Adaptive scheduling under demand volatility: a deep reinforcement learning approach for mixed-model assembly lines

Reduces average makespan by 12% compared to dispatching rules on a real automotive dataset; validated over 26 weeks of production records.

Y. Chen, R. Müller10 Aug 2026

Digital Supply Chain

Dual-sourcing inventory policies under correlated supply disruptions: a stochastic programming framework

Demonstrates 18% cost reduction over single-source baselines with joint chance constraints; tested on a pharmaceutical cold-chain network.

A. Kapoor, S. Nwosu2 Aug 2026

Industrial AI

Real-time SPC with non-stationary process means: a Bayesian change-point detection method

Outperforms CUSUM and EWMA on detection delay in semiconductor fabrication data with known drift; false alarm rates held constant.

F. Oliveira24 Jul 2026