Search

Processes or products are typically complex systems with numerous interrelated procedures and interdependent components. This results in complex relationships between responses and input factors, as well as complex nonlinear correlations among multiple responses. If the two types of complex correlations in the quality design cannot be properly dealt with, it will affect the prediction accuracy of the response surface model, as well as the accuracy and reliability of the recommended optimal solutions. In this paper, we combine kernel trick-based kernel principal component analysis, spline-based Bayesian semiparametric additive model, and normal boundary intersection-based evolutionary algorithm to address these two types of complex correlations. The effectiveness of the proposed method in modeling and optimisation is validated through a simulation study and a case study. The results show that the proposed Bayesian semiparametric additive model can better describe the process relationships compared to least squares regression, random forest regression, and support vector basis regression, and the proposed multi-objective optimisation method performs well on several indicators mentioned in the paper. [ABSTRACT FROM AUTHOR]

It is widely accepted that an effective carrier-selective contact is indispensable for high performance crystalline silicon (c-Si) solar cells. However, the properties of these carrier-selective contact materials significantly differ from c-Si in terms of band gap, work function, lattice constant. Consequently, this gives rise to challenges such as band discontinuity and suspended bonds at the interface, which subsequently impact the specific carrier transport process and potentially lead to a reduction primarily in the fill factor at the device level. Titanium nitride (TiN) and titanium oxynitride (TiOxNy) have been employed as an electron-selective contact in both c-Si and perovskite solar cells, demonstrating their effectiveness in enhancing the performance of these devices. Based on the detailed characterizations of the band alignment, the carrier transport mechanisms are analyzed using multiple models, and the theoretical results are basically self-consistent through the verification of variable temperature experiments. These analytical methods can also provide solutions for analyzing the band structure and transport mechanism of diverse heterojunctions, ultimately contributing to the design and optimization of semiconductor heterojunction devices. Carrier-selective contact technology plays a critical role in achieving high-performance photovoltaic devices, but intrinsic limitations within this widely used technology limit further advances in efficiency. Using a combination of experimental characterization, theoretical modeling, and variable temperature experiments, the authors investigate carrier transport mechanisms in silicon heterojunction solar cells and determine that thermal emission dominates the carrier transport process in TiN/n-Si heterojunction. [ABSTRACT FROM AUTHOR]

The conventional approaches to constructing Prediction Intervals (PIs) always follow the principle of 'high coverage and narrow width'. However, the deviation information has been largely neglected, making the PIs unsatisfactory. For high-risk forecasting tasks, the cost of forecast failure may be prohibitive. To address this, this work introduces a multi-objective loss function that includes Prediction Interval Accumulation Deviation (PIAD) within the Lower Upper Bound Estimation (LUBE) framework. The proposed model can achieve the goal of 'high coverage, narrow width, and small bias' in PIs, thus minimizing costs even in cases of prediction failure. A salient feature of the LUBE framework is its ability to discern uncertainty without explicit uncertainty labels, where the data uncertainty and model uncertainty are learned by Deep Neural Networks (DNN) and a model ensemble, respectively. The validity of the proposed method is demonstrated through its application to the prediction of carbon prices in China. Compared with conventional uncertainty quantification methods, the improved interval optimization method can achieve narrower PI widths. [ABSTRACT FROM AUTHOR]