ترغب بنشر مسار تعليمي؟ اضغط هنا

Embedding Physics Domain Knowledge into a Bayesian Network Enables Layer-by-Layer Process Innovation for Photovoltaics

114   0   0.0 ( 0 )
 نشر من قبل Zekun Ren
 تاريخ النشر 2019
  مجال البحث فيزياء
والبحث باللغة English




اسأل ChatGPT حول البحث

Process optimization of photovoltaic devices is a time-intensive, trial and error endeavor, without full transparency of the underlying physics, and with user-imposed constraints that may or may not lead to a global optimum. Herein, we demonstrate that embedding physics domain knowledge into a Bayesian network enables an optimization approach that identifies the root cause(s) of underperformance with layer by-layer resolution and reveals alternative optimal process windows beyond global black-box optimization. Our Bayesian-network approach links process conditions to materials descriptors (bulk and interface properties, e.g., bulk lifetime, doping, and surface recombination) and device performance parameters (e.g., cell efficiency), using a Bayesian inference framework with an autoencoder-based surrogate device-physics model that is 100x faster than numerical solvers. With the trained surrogate model, our approach is robust and reduces significantly the time consuming experimentalist intervention, even with small numbers of fabricated samples. To demonstrate our method, we perform layer-by-layer optimization of GaAs solar cells. In a single cycle of learning, we find an improved growth temperature for the GaAs solar cells without any secondary measurements, and demonstrate a 6.5% relative AM1.5G efficiency improvement above baseline and traditional black-box optimization methods.



قيم البحث

اقرأ أيضاً

A detailed reflection high-energy electron diffraction analysis shows relevant features of the lattice parameter relaxation of CdSe thin films grown in a layer-by-layer mode onto ZnSe. In situ investigations of different azimuths show a clear lattice parameter oscillation in the 110 azimuth. The lattice parameter has a minimum value ~similar to that of ZnSe! during Se exposure steps, and a higher and increasing lattice parameter during Cd exposure steps. The behavior is ascribed to the formation of CdSe islands during Cd exposure steps. The cumulative effect in CdSe exposure steps is considered to be a consequence of a decrease in the island size with the number of cycles. Actual plastic deformation does occur after 5 ML.
Computational drug discovery provides an efficient tool helping large scale lead molecules screening. One of the major tasks of lead discovery is identifying molecules with promising binding affinities towards a target, a protein in general. The accu racies of current scoring functions which are used to predict the binding affinity are not satisfactory enough. Thus, machine learning (ML) or deep learning (DL) based methods have been developed recently to improve the scoring functions. In this study, a deep convolutional neural network (CNN) model (called OnionNet) is introduced and the features are based on rotation-free element-pair specific contacts between ligands and protein atoms, and the contacts were further grouped in different distance ranges to cover both the local and non-local interaction information between the ligand and the protein. The prediction power of the model is evaluated and compared with other scoring functions using the comparative assessment of scoring functions (CASF-2013) benchmark and the v2016 core set of PDBbind database. When compared to a previous CNN-based scoring function, our model shows improvements of 0.08 and 0.16 in the correlations (R) and standard deviations (SD) of regression, respectively, between the predicted binding affinities and the experimental measured binding affinities. The robustness of the model is further explored by predicting the binding affinities of the complexes generated from docking simulations instead of experimentally determined PDB structures.
We propose a process algebra for link layer protocols, featuring a unique mechanism for modelling frame collisions. We also formalise suitable liveness properties for link layer protocols specified in this framework. To show applicability we model and analyse t
Engineering the energetics of perovskite photovoltaic devices through the deliberate introduction of dipoles to control the built-in potential of the devices offers the opportunity to enhance their performance without the need to modify the active la yer itself. In this work, we demonstrate how the incorporation of molecular dipoles into the bathocuproine (BCP) hole-blocking layer of inverted perovskite solar cells improves the device open-circuit voltage (VOC) and consequently, its performance. We explore a series of four thiaazulenic derivatives that exhibit increasing dipole moments and demonstrate that these molecules can be introduced into the solution-processed BCP layer to effectively increase the built-in potential within the device, without altering any of the other device layers. As a result the VOC of the devices is enhanced by up to 130 mV with larger dipoles resulting in higher VOCs. To investigate the limitations of this approach, we employ numerical device simulations that demonstrate that the highest dipole derivatives used in this work eliminate all limitations on the VOC stemming from the built-in potential of the device.
Embedding entities and relations into a continuous multi-dimensional vector space have become the dominant method for knowledge graph embedding in representation learning. However, most existing models ignore to represent hierarchical knowledge, such as the similarities and dissimilarities of entities in one domain. We proposed to learn a Domain Representations over existing knowledge graph embedding models, such that entities that have similar attributes are organized into the same domain. Such hierarchical knowledge of domains can give further evidence in link prediction. Experimental results show that domain embeddings give a significant improvement over the most recent state-of-art baseline knowledge graph embedding models.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا