EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Measuring the Performance Impact of Industry 4.0 in Manufacturing SMEs: An Integrated MPI–Explainable Machine Learning Framework

Sercan Demir, Gencay Sarıışık, Nagehan İlhan

Systems · 13.07.2026 · 14 (7) · 833

DOI: 10.3390/systems14070833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Systems, online erschienen am 13.07.2026. Verfasst von Sercan Demir und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 121 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates the performance implications of Industry 4.0 (I4.0) adoption in manufacturing small and medium-sized enterprises (SMEs) through an integrated analytical framework combining transformation modeling, composite performance measurement, and explainable machine learning. A structured dataset of 120 SMEs across five industrial sectors was analyzed to quantify changes in operational, economic, and sustainability-related performance before and after digital transformation. A novel Manufacturing Performance Index (MPI) was developed to capture multidimensional performance outcomes. The results reveal statistically significant improvements across all performance dimensions following I4.0 adoption (p < 0.001). Notable gains include increases in production output, overall equipment effectiveness, and labor productivity, accompanied by reductions in defect rates, machine downtime, production costs, and energy consumption. The MPI increased from 43.86 to 53.22, indicating a substantial overall performance enhancement. High pre–post correlations (r > 0.80) suggest that digital transformation reinforces existing operational capabilities rather than fundamentally altering firm structures. Explainable machine learning analysis identify overall equipment effectiveness, defect rate, production cost, and machine downtime as the most influential drivers of performance. SHAP-based results further reveal nonlinear and heterogeneous effects, indicating that performance gains vary depending on firm-specific conditions and implementation strategies. Additional analyses demonstrate the presence of distinct SME archetypes and confirm that I4.0 acts as a performance amplifier, with benefits distributed unevenly across firms. The proposed framework contributes to the literature by providing a transparent, data-driven approach for quantifying and interpreting digital transformation outcomes. It also provides practical decision support for SMEs seeking to prioritize investments and benchmark performance improvements within Industry 4.0 environments.

Zitieren

APA

Demir, S., Sarıışık, G., & İlhan, N. (2026). Measuring the Performance Impact of Industry 4.0 in Manufacturing SMEs: An Integrated MPI–Explainable Machine Learning Framework. Systems, 14(7), 833. https://doi.org/10.3390/systems14070833

Vancouver

Demir S, Sarıışık G, İlhan N. Measuring the Performance Impact of Industry 4.0 in Manufacturing SMEs: An Integrated MPI–Explainable Machine Learning Framework. Systems. 2026;14(7):833. doi:10.3390/systems14070833

BibTeX
@article{Demir2026,
  author = {Demir, Sercan and Sarıışık, Gencay and İlhan, Nagehan},
  title = {Measuring the Performance Impact of Industry 4.0 in Manufacturing SMEs: An Integrated MPI–Explainable Machine Learning Framework},
  journal = {Systems},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {833},
  doi = {10.3390/systems14070833}
}
Kostenlos starten →