Browsing by Author "Zhang, Jie"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Effect of crack-like defects on the fracture behaviour of Wire + Arc additively manufactured nickel-base Alloy 718
    (Elsevier, 2020-09-11) Seow, Cui Er; Zhang, Jie; Coules, Harry E.; Wu, Guiyi; Jones, Christopher A.; Ding, Jialuo; Williams, Stewart W.
    The fabrication of large components using a high deposition rate, near-net shape process like Wire + Arc Additive Manufacturing (WAAM) is a promising option for many industries, due to the potential for reduction in material wastage and shorter lead times in comparison to conventional methods. Specialist materials like nickel-base superalloys, which are typically used in high temperature and corrosive environments, are particularly attractive options due to their high raw material costs. Although nickel-base Alloy 718 seems well suited to the process due to its good weldability, process-induced defects can arise from unfavourable deposition conditions and elimination of these defects may not always be possible. In WAAM Alloy 718 deposited under such conditions, crack-like defects with planar morphology and hot cracking characteristics were observed. These defects were observable using conventional non-destructive testing techniques and displayed directionality relating to the deposition path. The fracture behaviour of WAAM Alloy 718 containing these defects was “semi-stable” – a mixture of fracture instability and stable crack extension. The apparent fracture toughness of WAAM Alloy 718 containing these defects was found to be anisotropic, which can be attributed to the interaction of the notched crack with pre-existing defects. WAAM Alloy 718 displayed an apparent fracture toughness comparable to that of wrought Alloy 718 when notched perpendicular to the defects; but only half that of wrought when notched parallel to the defects. Therefore, careful consideration of defect orientation and their effects on mechanical properties is important in assessing the fitness-for-service of WAAM Alloy 718
  • Thumbnail Image
    ItemOpen Access
    Federated learning of wireless network experience anomalies using consumer sentiment
    (IEEE, 2023-03-23) Guo, Weisi; Jin, Bailu; Sun, Schyler C.; Wu, Yue; Qi, Weijie; Zhang, Jie
    In wireless networks, consumer experience is important for both short monitoring of the Quality of Experience (QoE) as well as long term customer retainment. Current 4G and 5G networks are not equipped to measure QoE in an automated way, and experience is still reported through traditional customer care and drive-testing. In recent years, large-scale social media analytics has enabled researchers to gather statistically significant data on consumer experience and correlate them to major events such as social celebrations or significant network outages. However, the translational pathway from languages to topic-specific emotions (e.g., sentiment) to detecting anomalies in QoE is challenging. This challenge lies in two issues: (1) the social experience data remains sparsely distributed across space, and (2) anomalies in experience jump across sub-topic spaces (e.g., from data rate to signal strength). Here, we solved these two challenges by examining the spectral space of experience across topics using federated learning (FL) to identify anomalies. This can inform telecom operators to pay attention to potential network demand or supply issues in real time using relatively sparse and distributed data. We use real social media data curated for our telecommunication projects across London and the United Kingdom to demonstrate our results. FL was able to achieve 74-92% QoE anomaly detection accuracy, with the benefit of 30-45% reduce data transfer and preserving privacy better than raw data transfer.
  • Thumbnail Image
    ItemOpen Access
    Inhomogeneous microstructure and fatigue crack propagation of thick-section high strength steel joint welded using double-sided hybrid fiber laser-arc welding
    (Elsevier, 2020-10-13) Feng, Jiecai; Li, Liqun; Chen, Yanbin; Tian, Yingzhong; Sun, Yongle; Zhang, Xuanjun; Zhang, Jie
    The inhomogeneous microstructure and fatigue crack propagation of 30 mm thick-section high strength steel welded joint by double-sided hybrid fiber laser-arc welding were investigated in detail. The results indicated that the average effective grain size of the laser zone was only 1/2 of that of the arc zone, due to the faster cooling rate of the laser resource. The base metal consisted of massive polygonal ferrites and small granular carbides, while fine grained region, the coarse grained region and weld metal were all composed of martensite with a high dislocation density. Compared with the arc zone, the percentage of grain boundaries with high misorientation angle increased 24% for the laser zone, as the average grain size of the laser zone was smaller than that of the arc zone. The results also revealed that the fatigue crack propagation resistance of the welded joint was higher than that of the base metal. Meanwhile, a significant increase in the fatigue crack propagation resistance of the laser zone occurred, as compared with the arc zone, due to the refined grains and the high proportion of the grain boundaries with high misorientation angle (>15°) in the laser zone.