Search results

Accurately evaluating fluid flow behaviors and determining permeability for deforming porous media is time-consuming and remains challenging. This paper aims to propose a novel machine-learning method for the rapid estimation of permeability of porous media at different deformation stages constrained by hydro-mechanical coupling analysis.

A convolutional neural network (CNN) is proposed in this paper, which is guided by the results of finite element coupling analysis of equilibrium equation for mechanical deformation and Boltzmann equation for fluid dynamics during the hydro-mechanical coupling process [denoted as Finite element lattice Boltzmann model (FELBM) in this paper]. The FELBM ensures the Lattice Boltzmann analysis of coupled fluid flow with an unstructured mesh, which varies with the corresponding nodal displacement resulting from mechanical deformation. It provides reliable label data for permeability estimation at different stages using CNN.

The proposed CNN can rapidly and accurately estimate the permeability of deformable porous media, significantly reducing processing time. The application studies demonstrate high accuracy in predicting the permeability of deformable porous media for both the test and validation sets. The corresponding correlation coefficients (R²) is 0.93 for the validation set, and the R² for the test set A and test set B are 0.93 and 0.94, respectively.

This study proposes an innovative approach with the CNN to rapidly estimate permeability in porous media under dynamic deformations, guided by FELBM coupling analysis. The fast and accurate performance of CNN underscores its promising potential for future applications.

Advances in artificial intelligence have ushered in new opportunities for marketers in the domain of content generation. We discuss approaches that have emerged to generate text and image content. Drawing on the customer equity framework, we then discuss the potential applications of automated content generation for customer acquisition, relationship development, and customer retention. We conclude by discussing important considerations that businesses must make prior to adopting automated content generation.

This paper aims to explore the commodity transshipment planning among customers, which is commonly observed in production/sales enterprises to save the operational costs.

A mixed integer programming (MIP) model is built and five types of valid inequalities for tightening the solution space are derived. An improved variable neighborhood search (IVNS) algorithm is presented combining the developed multistart initial solution strategy and modified neighborhood local search procedure.

Experimental results demonstrate that: with less decision variables considered, the proposed model can solve more instances compared to the existing model in previous literature. The valid inequalities utilized to tighten the searching space can efficiently help the model to obtain optimal solutions or high-quality lower bounds. The improved algorithm is efficient to obtain optimal or near-optimal solutions and superior to the compared algorithm in terms of solution quality, computational time and robustness.

This research not only can help reduce operational costs and improve logistics efficiency for relevant enterprises, but also can provide guidance for constructing the decision support system of logistics intelligent scheduling platform to cater for centralized management and control.

This paper develops a more compact model and some stronger valid inequalities. Moreover, the proposed algorithm is easy to implement and performs well.

The purpose of this paper is to explore recent national human resource development (NHRD) practices in China through a literature review focusing on programs and activities that represent the roles and interactions among the government, industry and universities.

To effectively consolidate previous work and conceptualize the recent development of the NHRD practices in China, a semi-narrative literature review was used to explore and analyze NHRD-related functions and activities.

Findings from the literature review showed that although the central government still plays a predominant role in China, universities and corporations are increasingly playing a critical role in developing an innovative and skilled workforce. At the regional level, NHRD initiatives in China have been increasingly undertaken by universities, industry and government–industry–university collaborations. The authors also found a disparity between developed and underdeveloped regions in terms of NHRD in China.

This study used the triple helix model as a framework that provides an insightful lens for researchers to examine how various social entities interact with each other and jointly contribute to NHRD. Further case studies are needed to generate evidence-based knowledge to the NHRD literature.

A more systematic NHRD leadership structure at both the national and local level is desired to unleash the potential of bottom-up development and active government–industry–university collaboration. To counter regional divergence in NHRD in China, intra- and cross-regional collaborations are helpful in improving resources distribution and workforce development.

Based on open system theory, this study focused on programs and activities that represent the roles and interactions among the government, industry and university in Chinese NHRD through the lens of the triple helix model. In addition, this study offers a conceptual model of Chinese NHRD to help scholars and practitioners understand the transitional efforts in NHRD.