Data Driven Modeling of Electrical Automation Competency Development for Emerging Engineering Workforce
Data and Metadata · 21.05.2026 · 5 · 1466
DOI: 10.56294/dm20261466 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 21.05.2026. Verfasst von Yunlong Zhang. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The fast rate of industrial digitalization, intelligent manufacturing, and intelligent control systems has altered the competency needs of the new generation of engineering workforce in electrical automation. Rigid training models based on conventional training that tend to be curriculum focused and non-dynamic may find it difficult to keep up with the dynamic industry requirements.
Methods
This study suggests modeling and evaluating competency development in electrical automation education and workforce training with Intelligent Data-driven Automation Competency Engine (InDACE). The methodology has five key steps: Data Acquiring, Data Pre-processing, Competency Modelling, Predictive Analytics, Adaptive Feedback Optimisation. First, data from various educational and industrial resources such as academic transcript, laboratory experiment score, project assessment, internship assessment, certification result, attendance record, and feedback from supervisors in the industry is gathered and quantified. The data gathered are cleaned, standardized and normalized to eliminate inconsistencies and enhance the analytical reliability. Further feature extraction and dimensionality reduction techniques are employed to find the relevant indicators of competency. The competency framework is then developed and is multidimensional: technical automation skills, system integration, analytical problem solving and professional skills (communication, teamwork, adaptability, etc.). Weighted performance indicators are used for each competency dimension, determined by industry needs and expert opinion. Various machine learning algorithms such as Random Forest, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANN) are applied for classification and prediction problems to analyse competency progression. Statististical modelling and clustering are used to determine learning patterns and competency deficits and student performance clusters.
Results
This proposed InDACE framework was validated with the data from 420 electrical automation students and 85 early-career professionals. In the prediction of competency and gap identification, the applied model with the best prediction accuracy was Random Forest, with Precision, Recall and F1-score of 93.4%, 92.6% and 93.0%, respectively. The correlation analysis revealed that there is a good correlation between the laboratory performance and internship outcomes (r = 0.87, p
Zitieren
APA
Zhang, Y. (2026). Data Driven Modeling of Electrical Automation Competency Development for Emerging Engineering Workforce. Data and Metadata, 5, 1466. https://doi.org/10.56294/dm20261466
Vancouver
Zhang Y. Data Driven Modeling of Electrical Automation Competency Development for Emerging Engineering Workforce. Data and Metadata. 2026;5:1466. doi:10.56294/dm20261466
BibTeX
@article{Zhang2026,
author = {Zhang, Yunlong},
title = {Data Driven Modeling of Electrical Automation Competency Development for Emerging Engineering Workforce},
journal = {Data and Metadata},
year = {2026},
volume = {5},
pages = {1466},
doi = {10.56294/dm20261466}
}
EUVIMED