XYXin Yin

Xin Yin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xin Yin has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Generative artificial intelligence and deep ensemble learning for short-term rockburst prediction in underground engineering using microseismic data

    by Hairui Liu, Peitao Li, Yongqiang Yu, Xin Yin, Zhili Gong, Jianya Xu

    Rockburst is a dynamic geological hazard characterized by the sudden release of elastic strain energy in underground excavations, posing severe threats to personnel safety. Machine learning (machine learning)-based rockburst prediction using microseismic monitoring faces a critical challenge: class imbalance, where strong rockburst events—the most destructive—are severely underrepresented, leading to poor minority-class predictions. To address this, this study proposes a two-step intelligent framework integrating generative artificial intelligence with deep ensemble learning. First, a conditional tabular generative adversarial network synthesizes high-fidelity samples for minority classes, transforming the imbalanced dataset into a balanced one. Second, a deep random forest is constructed on the augmented dataset to learn the nonlinear mapping between six precursory microseismic parameters—cumulative number of events, cumulative energy, cumulative apparent volume, and their rates of change—and rockburst intensity levels. The whale optimization algorithm enables automatic hyperparameter optimization. Validated on 93 rockburst cases from Jinping II Hydropower Station, the CTGAN-DRF framework increases accuracy from 65% to 90% and Kappa coefficient from 0.53 to 0.87 compared with baseline models. F 1 -scores for slight, moderate, and strong rockburst improve by 0.29, 0.28, and 0.39, respectively. Comparative analysis confirms the superiority of the deep ensemble architecture over shallow alternatives. SHAP-based interpretability analysis reveals that cumulative parameters dominate lower-intensity predictions, while event count rate becomes critical for strong rockburst. The proposed framework provides a reliable and interpretable solution for rockburst prediction under class imbalance, with promising applications in underground engineering safety.

  • Open Access

    Influence of Composite Mineral Admixtures and Expansive Agent on the Mechanical Properties, Durability and Microstructure of Cementitious Materials

    by Xuezhen Wang, Xingze Duan, Ruijie Xia, Wei Li, Ju Liu, Zhou Zhou, Ao Yang, Xin Yin, Guohua Song, Kuangyu Dai

    To improve volume stability and durability of cementitious materials, a composite mineral admixture including ground granulated blast furnace slag, fly ash and silica fume was incorporated at a fixed 12% replacement ratio together with varying dosages of an expansive agent (EA). Results show that the composite admixture delays setting while increasing EA shortens setting time. Mechanical properties first increase and then decrease with EA content. The mixture with 6% EA (A4) achieves the best performance, with a 28-day compressive strength of 51.6 MPa. Expansion behavior continuously increases with EA content, but the expansion coefficient peaks near unity at an optimal EA level and then decreases, which indicates effective shrinkage compensation at moderate EA dosages. Durability properties including sulfate resistance and chloride migration resistance follow a similar non-monotonic trend, enhanced at moderate EA levels but degraded at excessive dosages. The A4 mixture exhibits the highest sulfate resistance coefficient and the lowest chloride diffusion coefficient. Microstructural analyses via XRD, EDS, SEM and MIP reveal differences in hydration products and pore structure characteristics among the mixtures. The composite mineral admixtures contribute to pore refinement through hydration and filler effects, while an appropriate EA dosage provides shrinkage compensation and improves microstructural stability. These combined effects reduce harmful pore content and pore connectivity, thereby improving resistance to sulfate and chloride transport. Excessive EA leads to over-expansion, inducing microstructural defects and disrupting pore structure integrity, which ultimately compromises durability. Therefore, durability enhancement of the composite system is governed by a balance between expansion compensation and pore structure refinement, rather than simply the increase in hydration products.

  • Open Access

    Methane Production from Anaerobic Digestion of Sludge Enhanced by Calcium Hypochlorite Treatment with Zero-Valent Iron Regulation

    by Jiawei Hu, Jie Wu, Jinsong Liang, Xin Yin, Yongli Wang, Shaogang Hu

    Calcium hypochlorite (CH) is a strong oxidant that can be utilized to enhance sludge hydrolysis and anaerobic digestion (AD) performance; however, its suppressive effect on methanogens restricts the development of CH treatment technologies. This laboratory-scale study introduced zero-valent iron (ZVI) into a CH-treated sludge AD system to alleviate the adverse effect, thereby synergistically enhancing biomethane production, and the correlation between methane yield and the two key treatment parameters (ZVI and CH dosages) was explored. The experimental results revealed that the best conditions for the ZVI + CH method were 5 g/L of ZVI plus 0.12 g/g of volatile suspended solids (VSSs) of CH, under which the maximum biomethane yield of 275.8 mL/g VSS was achieved, representing increases of 81.5%, 43.2%, and 28.2% over the control, solo ZVI, and solo CH conditions, respectively. More organic matter in the sludge was found to be degraded during AD by the ZVI + CH treatment compared with the control, solo ZVI, or solo CH conditions. An enzyme activity analysis illustrated that the ZVI + CH treatment not only enhanced the bioactivity of anaerobes but also eliminated the suppression of methanogens by CH. A microbial analysis demonstrated that all functional microbes responsible for sludge AD were enriched by the ZVI + CH treatment, with total abundances of 8.41% and 20.58% in the control and ZVI + CH-treated reactors, respectively.