Browsing by Subject "Gaussian process"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Active learning with generalized sliced inverse regression for high-dimensional reliability analysis
    (Elsevier, 2022-01) Yin, Jianhua; Du, Xiaoping; Mechanical and Energy Engineering, School of Engineering and Technology
    It is computationally expensive to predict reliability using physical models at the design stage if many random input variables exist. This work introduces a dimension reduction technique based on generalized sliced inverse regression (GSIR) to mitigate the curse of dimensionality. The proposed high dimensional reliability method enables active learning to integrate GSIR, Gaussian Process (GP) modeling, and Importance Sampling (IS), resulting in an accurate reliability prediction at a reduced computational cost. The new method consists of three core steps, 1) identification of the importance sampling region, 2) dimension reduction by GSIR to produce a sufficient predictor, and 3) construction of a GP model for the true response with respect to the sufficient predictor in the reduced-dimension space. High accuracy and efficiency are achieved with active learning that is iteratively executed with the above three steps by adding new training points one by one in the region with a high chance of failure.
  • Thumbnail Image
    Item
    Gaussian process-based prognostics of lithium-ion batteries and design optimization of cathode active materials
    (Elsevier, 2022-04-30) Valladares, Homero; Li , Tianyi; Zhu, Likun; El-Mounayri, Hazim; Hashem, Ahmed M.; Abdel-Ghany, Ashraf E.; Tovar, Andres; Mechanical and Energy Engineering, School of Engineering and Technology
    The increasing adoption of lithium-ion batteries (LIBs) in consumer electronics, electric vehicles, and smart grids poses two challenges: the accurate prediction of the battery health to prevent operational impairments and the development of new materials for high-performance LIBs. Characterized by their flexibility and mathematical tractability, Gaussian processes (GPs) provide a powerful framework for monitoring and optimization tasks. This study employs two GP-based techniques: co-kriging surrogate modelling and Bayesian optimization. The GP training data comes from the cycling performance test of five CR2032 cells with Ni contents of 0.0, 0.4, 0.5, 0.6, and 1.0 in their cathode active material Li2NixMn2-xO4. The co-kriging surrogate predicts the capacity degradation profile of a cell by exploiting information from different cells. Bayesian optimization identifies new Ni compositions that can produce cells with high initial specific capacity and large cycle life. The study shows the predictive capabilities of the co-kriging surrogate when correlated data is available. Bayesian optimization predicts that a Ni content of 0.44 produces cells with an initial specific capacity of 103.4 ± 3.8 mAh g−1 and a cycle life of 595 ± 12 cycles. Furthermore, the Bayesian strategy identifies other Ni contents that can improve the overall quality of the current Pareto front.
  • Thumbnail Image
    Item
    Process Design of Laser Powder Bed Fusion of Stainless Steel Using a Gaussian Process-Based Machine Learning Model
    (Springer, 2020) Meng, Lingbin; Zhang, Jing; Mechanical and Energy Engineering, School of Engineering and Technology
    In this work, a Gaussian process (GP)-based machine learning model is developed to predict the remelted depth of single tracks, as a function of combined laser power and laser scan speed in a laser powder bed fusion process. The GP model is trained by both simulation and experimental data from the literature. The mean absolute prediction error magnified by the GP model is only 0.6 μm for a powder bed with layer thickness of 30 μm, suggesting the adequacy of the GP model. Then, the process design maps of two metals, 316L and 17-4 PH stainless steels, are developed using the trained model. The normalized enthalpy criterion of identifying keyhole mode is evaluated for both stainless steels. For 316L, the result suggests that the ΔHhs≥30 criterion should be related to the powder layer thickness. For 17-4 PH, the criterion should be revised to ΔHhs≥25.