Although engineers working on structural retrofitting and analysis have access to numerous code provision equations for calculating shear strength in steel fiber-reinforced concrete (SFRC) beams, pinpointing an accura...
详细信息
Although engineers working on structural retrofitting and analysis have access to numerous code provision equations for calculating shear strength in steel fiber-reinforced concrete (SFRC) beams, pinpointing an accurate and practical equation remains a challenge. This paper introduces a novel hybrid machine learning model, PSO-ANN, which combines the characteristics of artificial neural network (ANN) with the particleswarmoptimizer (PSO). A comprehensive experimental database of SFRC beams was assembled for this research. SFRC beam shear capacity was evaluated using this database and the proposed hybrid technique, resulting in an accurate closed-form formula. To assess the accuracy of existing equations, a set of them was also provided. The PSO-ANN equation emerged as a more straightforward but equally accurate alternative than other previously used formulas. The hybrid technique, known as PSO-ANN, demonstrates significant success in estimating the shear capacity of SFRC beams during the design and planning phases of civil engineering projects.
Acoustic telemetry technology for Well Logging While Drilling(LWD) is one promising kind of LWD data transmission technologies. It takes the elastic wave propagating along the drill string as carrier to transmit downh...
详细信息
ISBN:
(纸本)9781479931972
Acoustic telemetry technology for Well Logging While Drilling(LWD) is one promising kind of LWD data transmission technologies. It takes the elastic wave propagating along the drill string as carrier to transmit downhole measurement data up to the ground. However, polluted by the acoustic noises which are produced by drilling rigs and mud circulation, as well as attenuated during the process of propagation, the surface signal is so completely buried in a variety of noises that it is very difficult to be detected. To solve the problem, firstly an efficient wavelet neural network classifier trained by improved particle swarm optimizer algorithm is presented in this paper. Secondly, the classifier is used to find the mapping relation between downhole original data and surface noisy data. Then the surface noisy telemetry signal can be detected intelligently through the relation. Finally, this method has been proved to be good effect through practical application.
particleswarm Optimization (PSO) algorithms, including standard PSO, Stochastic PSO, and Multi-Phase PSO, are applied to solve the time-domain inverse transient radiation problems in the present research. Time-resolv...
详细信息
particleswarm Optimization (PSO) algorithms, including standard PSO, Stochastic PSO, and Multi-Phase PSO, are applied to solve the time-domain inverse transient radiation problems in the present research. Time-resolved transmittance and reflectance signals of four different measuring models serve as the measurement data, which estimate absorption, scattering coefficients, and geometric position within one-dimensional non-homogeneous media by inverse simulation. To check retrieval performances and accuracies of PSO-based approaches, four different inverse transient radiation cases are investigated to deal with one homogeneous layer, two-layer, three-layer, and continuous non-homogenous media. The influences of different searching ranges, swarm sizes, and maximum fly velocities on the fitness function of PSO are discussed. Meanwhile, the effects of measurement errors on the reconstruction accuracy are also investigated. All the results confirm that radiative parameters could be estimated accurately with measurement noise using PSO-based approaches. (C) 2011 Elsevier Ltd. All rights reserved.
In this paper, mathematical model for heat treatment is constructed according to the process requirement of Roller-hearth Normalizing Furnace. Based on the intelligent control theory of neural network and particle swa...
详细信息
ISBN:
(纸本)9781424467129
In this paper, mathematical model for heat treatment is constructed according to the process requirement of Roller-hearth Normalizing Furnace. Based on the intelligent control theory of neural network and particleswarmalgorithms, the improved PSO-ANN model is established and simulated using lots of data acquired from the site. The result indicates the improved PSO-ANN model can raise the precision of plate temperature, predicated speed, and precision of control. It is proved that this model has good application future.
The multi-phase particleswarm optimization (MPPSO) technique is applied to the inverse radiation problem in the present paper. The directional radiative intensities are served as the measurement data to estimate the ...
详细信息
The multi-phase particleswarm optimization (MPPSO) technique is applied to the inverse radiation problem in the present paper. The directional radiative intensities are served as the measurement data to estimate the radiative source term, optical thickness, scattering albedo, and phase function in one-dimensional semitransparent plane-parallel media by the inverse simulation. To check the performance and accuracy in retrieval, a comparison is presented between three PSO methods, i.e. the MPPSO, the standard PSO, and the Stochastic PSO. The results confirm the potential of the proposed approach MPPSO and show its effectiveness and superiority over the other two PSO algorithms. Furthermore, the effects of swarm size, searching space, phase change frequency, and velocity-reinitializing frequency on the convergence velocity and computational accuracy of MPPSO are also investigated. (c) 2007 Elsevier Ltd. All rights reserved.
This paper analyses several currently used computing methods inspired by the nature and concludes their common properties and their disadvantages. It then proposes a more abstract computing model inspired by the natur...
详细信息
ISBN:
(纸本)9783540724834
This paper analyses several currently used computing methods inspired by the nature and concludes their common properties and their disadvantages. It then proposes a more abstract computing model inspired by the nature according to theoretical results on number theory. We also present a good lattice points method based on the number theory for problem solving, of which the discrepancy of the new method is minimized in the sense when the number of points are fixed. This method is dimensional independent and can be used to solve high dimensional problems. A typical algorithm is proposed to apply Genetic algorithm and Immume algorithm. Some comparable examples are given to show the advantages of our new method.
暂无评论