The Experts below are selected from a list of 6270 Experts worldwide ranked by ideXlab platform

Dongsheng Jeng - One of the best experts on this subject based on the ideXlab platform.

  • an optimised product unit neural network with a novel pso bp hybrid training algorithm applications to load Deformation analysis of axially loaded piles
    Engineering Applications of Artificial Intelligence, 2013
    Co-Authors: A Ismail, Dongsheng Jeng, Lulu Zhang
    Abstract:

    In general, neural network training is a nonlinear multivariate optimisation problem. Unlike previous studies, in the present study, particle swarm optimisation (PSO) and back-propagation (BP) algorithms were coupled to develop a robust hybrid training algorithm with both local and global search capabilities. To demonstrate the capacity of the proposed model, we applied the model to the predictions of the load-Deformation behaviour of axially loaded piles. This is a soil-structure interaction problem, involving a complex mechanism of load transfer from the pile to the supporting geologic medium. A database of full scale pile loading tests is used to train and validate the product-unit network. The results show that the proposed hybrid learning algorithm simulates the load-Deformation Curve of axially loaded piles more accurately than other BP, PSO, and existing PSO-BP hybrid methods. The network developed using the proposed algorithm also turns out to be more accurate than hyperbolic and t-z models.

Mofreh Saleh - One of the best experts on this subject based on the ideXlab platform.

  • Modified wheel tracker as a potential replacement for the current conventional wheel trackers
    International Journal of Pavement Engineering, 2018
    Co-Authors: Mofreh Saleh
    Abstract:

    AbstractThis research introduces a modified method for the wheel tracker test. Conventionally, the test is conducted by placing asphalt slabs or cylindrical cores in a fully confined steel or polyethylene moulds. The research work undertaken by the author has shown that having the specimen fully confined in all directions by the steel or polyethylene mould would limit or prevent it from lateral (shear) Deformation. It is also well-known that shear related permanent Deformation is identified as the primary cause for high severity rutting. As a result, a new wheel tracker test set-up was designed and manufactured to capture the true material response under the applied load. In the conventional wheel tracker, the large majority of samples will only show the primary stage and very small part of the secondary stage of the permanent Deformation Curve and most of the time the Curve will plateau regardless of the number of cycles applied. Therefore, in the conventional wheel tracker test, the tertiary stage never...

Lulu Zhang - One of the best experts on this subject based on the ideXlab platform.

  • an optimised product unit neural network with a novel pso bp hybrid training algorithm applications to load Deformation analysis of axially loaded piles
    Engineering Applications of Artificial Intelligence, 2013
    Co-Authors: A Ismail, Dongsheng Jeng, Lulu Zhang
    Abstract:

    In general, neural network training is a nonlinear multivariate optimisation problem. Unlike previous studies, in the present study, particle swarm optimisation (PSO) and back-propagation (BP) algorithms were coupled to develop a robust hybrid training algorithm with both local and global search capabilities. To demonstrate the capacity of the proposed model, we applied the model to the predictions of the load-Deformation behaviour of axially loaded piles. This is a soil-structure interaction problem, involving a complex mechanism of load transfer from the pile to the supporting geologic medium. A database of full scale pile loading tests is used to train and validate the product-unit network. The results show that the proposed hybrid learning algorithm simulates the load-Deformation Curve of axially loaded piles more accurately than other BP, PSO, and existing PSO-BP hybrid methods. The network developed using the proposed algorithm also turns out to be more accurate than hyperbolic and t-z models.

A. A. Tashkinov - One of the best experts on this subject based on the ideXlab platform.

Weishun Wang - One of the best experts on this subject based on the ideXlab platform.

  • Finite difference method–based calculation of gravity Deformation Curve for the large-span beam of heavy-duty vertical lathe:
    Advances in Mechanical Engineering, 2016
    Co-Authors: Zhenyu Han, Han Wang, Zhongxi Shao, Hui Jiang, Weishun Wang
    Abstract:

    To solve the problem that gravity Deformation Curve of large-span cast-iron beam analyzed by finite element method simulation is inaccurate due to material imperfection, a discretization calculation considering the inhomogeneity of the material based on finite difference method is proposed. Supposing the flexural rigidity of the beam is different along the length, the continuous beam is discretized into segments based on finite difference method, and equivalent flexural rigidity is presented to characterize the inhomogeneity of the material. Correction model of bending Deformation is constructed to revise the results of finite element method simulation applying equivalent flexural rigidity that could be obtained by combining the discretization model and Deformation data acquired in a simple self-load experiment in which the beam is simply supported without any assembly process. Finally, flowchart of application is presented, and the approach is illustrated through an example from real case. The experiment...

  • finite difference method based calculation of gravity Deformation Curve for the large span beam of heavy duty vertical lathe
    Advances in Mechanical Engineering, 2016
    Co-Authors: Zhenyu Han, Han Wang, Zhongxi Shao, Hui Jiang, Weishun Wang
    Abstract:

    To solve the problem that gravity Deformation Curve of large-span cast-iron beam analyzed by finite element method simulation is inaccurate due to material imperfection, a discretization calculation considering the inhomogeneity of the material based on finite difference method is proposed. Supposing the flexural rigidity of the beam is different along the length, the continuous beam is discretized into segments based on finite difference method, and equivalent flexural rigidity is presented to characterize the inhomogeneity of the material. Correction model of bending Deformation is constructed to revise the results of finite element method simulation applying equivalent flexural rigidity that could be obtained by combining the discretization model and Deformation data acquired in a simple self-load experiment in which the beam is simply supported without any assembly process. Finally, flowchart of application is presented, and the approach is illustrated through an example from real case. The experiment...