20.500.12556/DKUM-96684 Manufacturing process quality prediction via temporal knowledge graph reasoning with adaptive multi-scale temporal path fusion and self-attention mechanism To tackle the pronounced temporal dynamics and intricate interdependencies within process manufacturing knowledge, this paper introduces an innovative framework: the Adaptive Multi-Scale Temporal Path Fusion Network (AMTPFNet). The method constructs short-term (high-frequency) and long-term (low-frequency) historical subgraphs to generate multi-scale temporal representations. It also employs a self-attention mechanism for query-aware temporal path modeling, enabling adaptive weight allocation based on varying time spans. Extensive experiments are conducted on benchmark datasets, including ICEWS18, GDELT, WIKI, and YAGO. Additionally, an application analysis is presented using electromechanical fault data. The results demonstrate that AMTPFNet exhibits remarkable effectiveness and robustness in temporal knowledge graph reasoning tasks, achieving MRR scores of 0.914 on YAGO and 0.838 on WIKI. It achieves high efficiency in predicting future production facts and assessing process quality in industrial workflows. Root causes of failures (e.g., insulation, friction) for motor components (stators, rotors) are accurately predicted, demonstrating the framework’s transferability to real-world manufacturing scenarios. Although electromechanical fault data are used as a case study, the framework generalizes to manufacturing quality prediction and is readily transferable to finance, healthcare, and social media analytics. temporal knowledge graph reasoning TKGR multi-scale temporal modeling temporal path fusion self-attention mechanism knowledge graph embedding manufacturing process analytics process quality prediction časovni grafi znanja sklepanje časovno modeliranje true false true Chair of Production Engineering (CPE), University of Maribor Faculty of Mechanical Engineering Angleški jezik Slovenski jezik https://apem-journal.org/ Članek v reviji 2026-01-23 09:50:07 2026-01-23 09:50:07 2026-01-24 03:11:33 0000-00-00 00:00:00 2025 0 0 str. 380-390 no. 3 Vol. 20 Sep. 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2025-08-25 2025-10-13 2025-10-31 658.5 265841667 10.14743/apem2025.3.547 1854-6250 APEM20-3_380-390.pdf APEM20-3_380-390.pdf 1 971E19D8A04F0A1B7EC925DDF3F066C9 c9318003af2bef2dd5f3dfcd6827b9e3dce8d03d4dc1b63b4f45fc02a7b205de c2a9d400-f839-11f0-8c23-00155d00018d https://dk.um.si/Dokument.php?lang=slv&id=202479 https://apem-journal.org/Archives/2025/Abstract-APEM20-3_380-390.html 0 c8c838fd-f839-11f0-8c23-00155d00018d https://dk.um.si/Dokument.php?lang=slv&id=202480 Fakulteta za strojništvo Advances in production engineering & management 0 0 0