Search the digital library catalog

Abstract: This study addresses a critical challenge in industrial big data analytics for smart manufacturing: conventional machine learning methods often fail to account for data discontinuities caused by scrapped defective intermediates in multi-stage production processes, inadvertently treating non-conforming products as qualified during model training. We propose a novel process-aware data analytics framework specifically designed for process industries, featuring: (1) intelligent attribute partitioning based on information flow discontinuity points, and (2) an ensemble modelling approach combining Random Forest and C5.0 Decision Tree algorithms to generate interpretable prediction rules with quantified feature importance rankings. Validated using real-world production data from a Chinese rail steel manufacturer, our methodology demonstrates superior performance by explicitly incorporating process-specific data correlations. The proposed solution effectively mitigates information distortion caused by scrapped intermediates while maintaining operational interpretability – a crucial requirement for industrial implementation. The research results increased the accuracy rate of the test set of the random forest experiment from 88.39 % to 92.69 %, and the accuracy rate of the test set of the decision tree experiment from 71.89 % to 79.15 %. Additionally, the experimental results verify that, compared with the traditional methods, our framework has better applicability in capturing product quality in the manufacturing industry when process attributes are considered.
Keywords: intelligent manufacturing, process industry, industrial data mining, defect prediction, C5.0 decision tree algorithms, random forest, process-oriented analytics, machine learning
Published in DKUM: 21.01.2026; Views: 0; Downloads: 0
Full text (1,47 MB)
This document has many files! More...
This document is also a collection of 1 document!

Abstract: How to evaluate the fuel gas operation (FGO) of various working groups (WGs) and working shifts (WSs) in reheating furnace is still ambiguous problem. In this paper, a novelty time-series FGO evaluation model was proposed. The strategy mainly included: Firstly, the fuel gas per ton steel (FGTS) was calculated in certain time interval; Secondly, the FGTS time-series data set was formulated in statistical period; Thirdly, the FGTS time-series data set was divided according to working schedule; Lastly, the FGO evaluation model was established. Case study showed that: i) The fuel gas operation evaluation results of various WGs in different WSs were accorded with normal distribution; ii) For various WGs, A WG performed best, followed by C WG and D WG. The performance of B WG was the worst due to its violent fluctuation of fuel gas operation evaluation results in three WSs; iii) For different WSs, the day WS and swing WS performed well, whereas the performance of night WS was unsatisfactory. Discussion results showed that the improvement of working skills, working responsibility and working passion, which were effective measure to achieve energy saving in terms of operation, should be enhanced through skills training and the reward and punishment system. Generally, this novelty time-series FGO evaluation method could also be applied to other industrial equipment.
Keywords: Iron industry, steel Industry, fuel gas operation management, FGO evaluation model, reheating furnace, fuel gas per ton steel time-series, working groups
Published in DKUM: 15.01.2026; Views: 0; Downloads: 0
Full text (993,34 KB)
This document has many files! More...
This document is also a collection of 1 document!

Abstract: Purpose – An effective asset management system (AMS) is essential for healthcare organizations looking to maximize value and performance while minimizing risk and cost. This study aims to identify and evaluate the barriers to AMS adoption and evaluate them from a healthcare perspective. Design/methodology/approach – The study is based on a combination of the Delphi method and the analytic hierarchy process (AHP) with 30 participants from various Slovenian healthcare organizations. Through iterative consensus and prioritization, the Delphi-AHP process resulted in 23 validated barriers, ranked according to their perceived importance for AMS implementation. Findings – The resultsidentified key barriersto implementing AMS in healthcare organizations and categorized them into five dimensions: strategic, human resources, contextual, structural and procedural. The highest ranked barriers were deficient leadership, a shortage of qualified personnel and workforce overload. This indicates that strategic alignment and organizational capacity are perceived as the most critical obstacles to adopting AMS. Originality/value – Thisstudy advancesthe existing literature by addressing a critical gap and providing deeper insight into the factors that impede the successful implementation of AMS in healthcare settings, a domain where empirical evidence remains limited.
Keywords: ssset management, healthcare, barriers, organizational resilience, organizational mechanisms, high-tech industry
Published in DKUM: 09.12.2025; Views: 0; Downloads: 0
Full text (2,64 MB)
This document has many files! More...

Abstract: While previous studies have examined sustainable leadership and innovation separately, limited attention has focused on their systemic interconnection. Building on established frameworks, this study adopts a systems perspective to explain how sustainability-oriented leadership mechanisms shape innovation capability across strategic, organizational, and functional levels. Drawing on a single-case study of an information-rich high-tech company, data were collected through semi-structured interviews and internal documentation to examine leadership practices and organizational enablers that foster innovation. The findings show that sustainable leadership strengthens innovation capability by embedding sustainability values into organizational routines, aligning strategic intent with daily learning, and empowering employees to experiment, collaborate, and share knowledge continuously. These feedback-driven processes connect strategic intent with operational learning, enabling organizations to adapt and renew. The study introduces the Systems Framework for Sustainable Innovation Capability (SFSIC), which explains how leadership, culture, and learning interact as interdependent components of innovation capability and organizational resilience. By framing innovation capability as a dynamic, feedback-driven process rather than a fixed set of determinants, the study advances theory by specifying how sustainability-oriented leadership strengthens adaptive capacity within innovation ecosystems. The study offers guidance for building innovation capability and resilience through aligned leadership practices, enabling structures, and feedback-based learning systems.
Keywords: sustainable leadership, innovation capability, systems thinking, organizational resilience, organizational mechanisms, high-tech industry
Published in DKUM: 01.12.2025; Views: 0; Downloads: 1
Full text (600,08 KB)
This document has many files! More...

Abstract: Background/Purpose: This study investigates the mediating role of decision–making performance in the link between software performance and overall business performance in the logistics sector of an emerging economy. As logistics companies increasingly rely on digital infrastructures, understanding how advanced systems contribute to strategic outcomes is critical for sustaining competitiveness. Methods: A conceptual framework was developed integrating ERP systems, big data analytics, and IoT applications. In this model, software performance is positioned as the independent variable, decision–making performance as the mediator, and business performance as the dependent variable. Data were collected from medium- and large–scale logistics firms and analyzed using regression and bootstrapping methods through SPSS and the PROCESS Macro. Results: The findings reveal that software performance significantly improves decision–making performance (β = 0.552, p < 0.01), which in turn has a strong positive effect on business performance (β = 0.817, p < 0.01). The mediation analysis confirms that decision–making performance mediates the effect of software performance on business outcomes. Conclusion: The results highlight the strategic importance of aligning digital capabilities with organizational decision processes. By demonstrating the mediating role of decision–making, the study highlights that the effective use of advanced analytical tools is crucial for optimizing performance and achieving a sustainable competitive advantage in logistics.
Keywords: software performance, decision–making performance, business performance, TMS systems, logistics industry, emerging economy
Published in DKUM: 14.11.2025; Views: 0; Downloads: 11
Full text (1,46 MB)
This document has many files! More...