Energies

With the steady growth of performance requirements of gas turbines, the optimization design of turbine blade cooling structures has emerged as a critical technical challenge. This paper provides a comprehensive review of the research progress on machine learning methods in the optimization design of turbine blade cooling structures. First, common internal cooling methods for turbine blades are reviewed, including rib turbulated cooling, pin-fin cooling, and impingement cooling. Second, the application and limitations of traditional optimization methods in the optimization design of turbine blade internal cooling structures are analyzed in detail. On this basis, the application of machine learning methods in the optimization design of turbine blade internal cooling structures is comprehensively reviewed, covering mainstream machine learning models such as artificial neural networks, deep learning, generative adversarial networks, and physics-informed neural networks, as well as mainstream optimization algorithms including genetic algorithms, non-dominated sorting genetic algorithms, particle swarm optimization, and simulated annealing. Furthermore, emerging research directions such as data augmentation techniques, temperature field reconstruction, model interpretability, and optimization structure evolution patterns are discussed. The reviewed literature demonstrates that machine learning methods can substantially enhance the efficiency and accuracy of cooling structure optimization, offering robust support for the cooling design of next-generation gas turbines.

Substation pillar-type switchgear structures are important electrical equipment in the power transmission and transformation system. These structures are characterized by a large top mass, low overall stiffness, and low natural vibration frequency, and are prone to fatigue damage under long-term wind loads. At present, studies on wind-induced vibration fatigue of substation disconnect switch structures are relatively limited. In this paper, a numerical model of the substation disconnect switch structure is established on the basis of static tests, and wind loads are determined according to wind tunnel test results. The Weibull distribution model and the mixed distribution model (Weibull distribution + GPD distribution) are adopted to characterize the wind-speed probability distributions in large-scale steady strong-wind regions and typhoon-prone regions, respectively. Fatigue damage calculation and life prediction are carried out for the fatigue-critical positions of the disconnect switch structure. The results show that the windward and leeward M16 bolts at the flange joint suffer fatigue failure within the 50-year design service life. In large-scale steady strong-wind regions, the predicted fatigue lives of the critical M16-① and M16-⑤ bolts are 8.28 years and 8.48 years, respectively; in typhoon-prone regions, their predicted fatigue lives reduce to 0.87 years and 3.01 years, respectively. The research findings can provide a reference for the anti-fatigue design of flange joints for substation disconnect switch structures.

The rapid global expansion of photovoltaic (PV) systems, driven by rising energy demand, is expected to generate substantial module waste at end-of-life, with global PV waste projected to exceed 4 million tonnes by 2030, 50 million by 2040, and 200 million tonnes by 2050. Based on 105 sources identified through a structured, keyword-based Google Scholar search complemented by backward reference screening, this review provides a comparative, literature-based assessment of recycling, second-life applications, and disposal as end-of-life (EoL) management strategies for PV modules, examining the relationship between module structure, waste management pathways, material recovery potential, and the technical and economic limitations of current practices. Recycling offers clear environmental benefits but remains economically constrained in many scenarios by high process costs and the complexity of separating laminated module structures. Second-life application emerges as a complementary strategy, delaying the premature entry of modules retaining residual functionality into the waste stream and enhancing resource efficiency. Nevertheless, landfilling continues to account for the majority of global PV waste despite the availability of more sustainable alternatives, revealing a marked gap between technical potential and field-level practice. Overall, no single approach is sufficient; effective PV waste management requires an integrated strategy combining recycling, second-life applications, and disposal in line with circular economy principles.