This paper presents a novel hybrid intelligent framework with a Biological-AI approach for fault diagnosis of power transformers based on DGA. The proposed model is inspired by Biologically Inspired Survival (BIS) concepts, where the transformer is considered as a patient and its faults are detected based on gas data. The biological component of the system uses the Cox model, which was initially used in medicine to analyze patient survival. This model enables risk assessment and prediction of the failure risk. The AI component of the system also includes three advanced models. First, DNNs are used for learning complex features. Second, gradient boosting trees are employed for nonlinear modeling. Finally, a meta-learning layer is utilized for the intelligent fusion of predictions. Experimental results on 849 real-world examples demonstrate that this hybrid framework achieves an accuracy of 92.3%, representing an improvement of 24.5% over the best traditional method and 5.1% over the best independent AI model.
This review paper explores the diverse applications of nanofluids in the automotive industry, highlighting recent advancements and their implications. Nanofluids, which are engineered colloidal suspensions of nanoparticles in base fluids, have shown significant potential in enhancing the thermal and mechanical performance of automotive systems. The paper systematically reviews the use of nanofluids in various automotive applications, including coolant systems and lubricants. The review begins by examining the role of nanofluids as coolants in car radiators, where they have demonstrated improved heat transfer efficiency compared to conventional coolants. Studies indicate that nanofluids can enhance the thermal conductivity and heat dissipation, leading to better engine performance and fuel efficiency. The paper also discusses the application of nanofluids in lubricants, where they reduce friction and wear, thereby extending the lifespan of engine components. The application of nanofluids in other automotive systems, such as air conditioning, thermoelectrical generator and battery packs have also been thoroughly discussed where their outstanding properties can significantly improve the efficiency of the system. The outcomes of the reviewed studies suggest that nanofluids offer promising benefits in automotive applications, including enhanced thermal management, reduced wear and tear, improved fuel efficiency, and lower emissions. However, the paper also identifies challenges such as the stability of nanofluids, cost implications, and the need for further research to optimize their formulations and applications.
This paper presents a comprehensive multi-criteria group decision-making (MCGDM) framework for evaluating knowledge management (KM) solutions, with a particular focus on the critical success factors (CSFs) that influence organizational efficacy. The approach integrates the MOWSCER and MARCOS methods, operating within an interval type-2 fuzzy sets (IT2FS) framework to address the underlying uncertainty in expert evaluations. Unlike the DEMATEL method, MOWSCER not only considers cause-and-effect relationships but also assigns weights to CSFs, thereby offering a more robust analysis. Additionally, the MARCOS method has been enhanced by applying the border approximation area concept, enabling it not only to assess KM solutions effectively but also to allocate weights to the participating experts, which adds depth to the decision-making process. To manage the inherent ambiguity in human judgments, IT2FSs are employed for greater precision in capturing linguistic variables and subjective opinions. The proposed model’s practical utility is demonstrated through a case study conducted in a steel manufacturing facility, showcasing its capability to pinpoint actionable KM strategies aligned with organizational needs. Sensitivity analysis highlights the importance of expert weighting in the decision-making process, revealing notable shifts when experts 2 and 5 are replaced. The reliability of this methodology has been affirmed through comparative analyses with established approaches from the literature. Among the key KM solutions identified are creating a transparent workflow or open-door policy, developing employees’ awareness of KM, encouraging teamwork, and awarding group-based rewards. The research also explores the managerial and theoretical implications, offering valuable insights into both the academic and practical applications of KM optimization strategies.
This numerical contribution examines the magnetic natural convection within a novel nanoliquid filled-enclosure with wavy wall and trapezoidal heater considering interior heat generation. Numerical solutions are obtained via Finite Element Method. The effectual thermal conductivity and viscosity of nanoliquid are computed by Koo-Kleinstreuer-Li correlations considering the nanoparticle's Brownian motion. Impacts of diverse parameters like heat generation parameter, shape factor of nanoparticles, Hartmann number, nanoparticles concentration, displacement of the trapezoidal heater wall, Rayleigh number, and amplitude of wavy wall on natural convective flow characteristic are perused. The results disclose that the application of an interior heat generation and horizontal magnetic field can be an effectual way in controlling natural convective flow inside the system.
Millions of preterm infants rely on human donor milk, which is collected, processed, and pooled by human milk banks to standardize its macronutrient content for safe consumption. Effective production and distribution planning in human milk banks are critical, particularly in developing countries where the network is still underdeveloped. Addressing the dynamic and uncertain nature of the human milk supply chain requires a flexible and adaptive approach. This study proposes a novel framework integrating data-driven robust optimization with a rolling horizon approach to manage supply and demand uncertainty and improve the network’s responsiveness. A distinctive overlap-controlled coverage model is introduced to ensure equitable access for infants across metropolitan areas. The framework is validated in collaboration with established human milk banks, utilizing weekly operational data streams to dynamically adapt to changing conditions. Results demonstrate that the proposed approach outperforms traditional deterministic models, improving adherence to clinical macronutrient targets by approximately 14.28
