Materials Design Through Batch Bayesian Optimization with Multisource Information Fusion

Couperthwaite, Richard; Molkeri, Abhilash; Khatamsaz, Danial; Srivastava, Ankit; Allaire, Douglas; Arróyave, Raymundo

doi:10.1007/s11837-020-04396-x

Cited by 17 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e underlying infrastructure is shown in Figure 2, including multiple servers, networks, and other hardware components, as well as the various external financial resources of the interconnected devices, such as transportation and weather. We should enable virtualization, network virtualization, and virtualization services through the use of technology to maximize capabilities [14]. e service platform for route optimization of cold chain logistics distribution vehicles realizes the dynamic route optimization of cold chain logistics distribution vehicles through the solution of the optimization model.…”

Section: Application Mode Of Cold Chain Logistics Distribution In Cloudmentioning

confidence: 99%

Application of the Logistics Management System Based on Cloud Computing Technology

Zhang

2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

In order to solve the vehicle routing optimization problem of cold chain logistics distribution, this paper proposes a vehicle routing optimization method of cold chain logistics distribution based on cloud computing technology. This paper analyzes the advantages of processing the real-time routing of distribution vehicles under the cloud computing mode and establishes the application service architecture of vehicle routing optimization in cold chain logistics; under this architecture, multisource real-time traffic information is obtained, the vehicle distribution time and comprehensive cost are analyzed, the vehicle routing optimization model of cold chain logistics distribution is constructed, and the coarse-grained parallel genetic algorithm is used to solve the model in the cloud computing environment. The experimental results show that if W 1 = 0 , W 2 = 1 , the optimal path is 0-6-7-3-1-4-2-8-5, the total cost is 1620 yuan, the total mileage is 72 km, the vehicle driving time is 2.17 hours, and the calculation time is 10.79 s; let W 1 = 1 , W 2 = 0 , the optimal path is 0-5-6-7-2-4-3-1-8, the vehicle travel time is 1.84 hours, the total cost is 1736 yuan, the total mileage is 76 km, and the calculation time is 11.56 s. The optimal path is obtained in the effective time range. Conclusion. The real-time route optimization method of refrigerated vehicles in the cloud computing environment is effective. This method has practical significance to realize fine control of cold chain logistics distribution cost and improve distribution service efficiency.

show abstract

Section: Application Mode Of Cold Chain Logistics Distribution In Cloudmentioning

confidence: 99%

Application of the Logistics Management System Based on Cloud Computing Technology

Zhang

2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

show abstract

“…135) At the same time, Japan is becoming more active in the promotion of data-driven research and the development of materials data platforms. 136) Libraries and platforms 113,128,131,[137][138][139] for analyzing such data have been developed and are becoming powerful tools for the design and development of materials in the future.…”

Section: Libraries For Experimental and Computing Databases And Progr...mentioning

confidence: 99%

Current Status and Future Scope of Phase Diagram Studies

et al. 2023

View full text Add to dashboard Cite

Research on alloy phase diagrams started in the middle of the 19th century and progressed into the laborious and time-consuming process of constructing phase diagrams through experiments and phenomenological calculations with thermodynamic analysis. More recently, phase diagram research has evolved into the computation of theoretical phase diagrams based on first-principles calculations and the development of new materials for high-throughput data-driven types of phase diagrams. This paper discusses the features and problems of each technique using a collection of recent papers, with the aim of describing future problems in this field.

show abstract

“…Thus, a batch BO that ensures a faster learning rate using parallel computer architectures can be chosen as an alternative. , Meanwhile, it has been pointed out that such conventional batch BO does not have a theoretical guarantee on convergence . Hence, in this study, the multi-scale multi-recommendation (MSMR) batch BO, which has been proved to be a more accurate strategy compared to the sequential optimization strategy while guaranteeing convergence, was implemented as illustrated in Figure .…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…Recently, Bayesian optimization (BO), which is used to optimize a function that is expensive to evaluate, has become popular and has been adopted in engineering, especially in parameter estimation. , For instance, BO has mostly been utilized in tuning hyperparameters of computationally expensive machine learning models and even extended to material design and discovery. , This is because BO has proven to be more efficient than a conventional grid or random search, which may take a substantial amount of time to determine various parameters simultaneously. Moreover, BO can optimize an unknown black-box function with a relatively small number of datasets, while the conventional regression-based methods require a number of data points to find an accurate model.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Microstructural Properties of Wormlike Micelles Via a Multi-Scale Multi-Recommendation Batch Bayesian Optimization

Pahari

Moon

Akbulut

et al. 2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Microstructural properties of wormlike micelles (WLMs), which are employed in characterizing the system to predict rheological properties, have long been obtained via elusive experiments such as small-angle neutron scattering. Hence, in this work, a framework to explicitly obtain such properties from macroscopic rheology measurements was developed. Specifically, the parameters of a mesoscopic pointer-based algorithm, which can predict the linear rheology of WLMs were obtained with the aid of a multi-scale multi-recommendation (MSMR) batch Bayesian optimization (BO) methodology. From three case studies, it was observed that the MSMR batch BO was able to obtain a set of parameters, which showed high prediction accuracy, in comparison to a sequential BO. Specifically, it was found that microstructural properties such as persistent length and the diameter of WLMs were successfully predicted by the proposed framework. Hence, this framework can be utilized in characterizing various WLM systems from readily available macroscopic rheological measurements.

show abstract

Materials Design Through Batch Bayesian Optimization with Multisource Information Fusion

Cited by 17 publications

References 24 publications

Application of the Logistics Management System Based on Cloud Computing Technology

Application of the Logistics Management System Based on Cloud Computing Technology

Current Status and Future Scope of Phase Diagram Studies

Estimation of Microstructural Properties of Wormlike Micelles Via a Multi-Scale Multi-Recommendation Batch Bayesian Optimization

Contact Info

Product

Resources

About