Based on oil monitoring technology to collect friction and wear parameters, the failure modes of key friction pairs in wind turbine gearboxes can be evaluated and classified. However, the collected data of failures caused by friction and wear are generally small, which limits the application of machine learning in the monitoring or evaluation of the critical friction pairs of wind turbine gearboxes. To verify the feasibility of machine learning in this application, algorithms including decision tree (DT), random forest (RF), k-nearest neighbors (k-NN), and support vector machine (SVM) are implemented, in the context of a small dataset of 424 samples of normal, adhesive, fatigue, and cutting wear for outcome classification. Compared with k-NN and SVM, DT and RF perform better on both training and test samples. The two models identified the key factors and their quantified values associated with failure state, including ferromagnetic particles, viscosity, iron content, and external hard particle silicon. The classifiers developed in this work classified failure state with an average accuracy of 96%, thus offering an accurate decision support tool for classification and evaluation of the friction pair wear state of wind turbine gearboxes.
This paper investigates the effect of strain rate on the mechanical deformation and microstructural development of dual-phase AlCrFe2Ni2 high-entropy alloy during quasi-static and dynamic compression processes. It is revealed that the as-cast AlCrFe2Ni2 alloy is composed of a mixture of FCC, disordered BCC, and ordered B2 crystal structure phases. The alloy shows excellent compressive properties under quasi-static and dynamic deformation. The yield strength exceeds 600 MPa while the compressive strength is more than 3000 MPa at the compression rates of 30% under quasi-static conditions. Under dynamic compression conditions, the ultimate compression stresses are 1522 MPa, 1816 MPa, and 1925 MPa with compression strains about 12.8%, 14.7%, and 18.2% at strain rates of 1300 s−1, 1700 s−1 and 2100 s−1, respectively. The dynamic yield strength is approximately linear with strain rate within the specified range and exhibit great sensitivity. The strong localized deformation regions (i.e., adiabatic shear bands (ASBs)) appear in dynamically deformed samples by dynamic recrystallization due to the conflicting processes of strain rate hardening and heat softening.
27 August 2026 in Canadian Metallurgical Quarterly
1. In recent years, driven by the ‘dual carbon’ targets and the impetus of intelligent manufacturing, the low-carbon and intelligent transformation of the energy-intensive and high-emission steel i...
Charging direct reduced iron (DRI) into a blast furnace alters the softening–melting–dripping behavior of mixed burdens; however, the influencing laws and mechanisms remain unclear. In this study, DRI, pellets, and sinter were used as raw materials to systematically investigate the effect of DRI proportion (0–40%) on the softening–melting–dripping behavior of mixed burdens, and the underlying mechanism was revealed by combining XRD, SEM-EDS, and FactSage thermodynamic simulation. The results show that with increasing DRI proportion, the softening–melting behavior of the mixed burden exhibits a regular variation: the softening start temperature decreases, the softening interval widens, and the melting–dripping interval narrows due to an increase in melting start temperature and a decrease in dripping temperature, indicating an overall improvement in softening–melting–dripping performance. Meanwhile, the maximum pressure difference and total characteristic value decrease by 73.3% and 85.2%, respectively, indicating markedly improved permeability of the burden layer. Moreover, the addition of DRI promotes deep reduction of the mixed burden, leading to a decrease in FeO content. FactSage calculations show that the onset temperature of liquid slag formation decreases, and the equilibrium liquid slag fraction at the maximum pressure-difference temperature decreases. The decrease in basicity combined with FeO fluxing leads to a lower softening start temperature, while reduced primary slag formation and the supporting effect of the DRI metallic skeleton jointly improve bed permeability.