Chengfan Li^1,2, Lan Liu^3,*, Junjuan Zhao¹, Xuefeng Liu⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 429-444, 2022, DOI:10.32604/cmes.2022.019202

Abstract Target detection of small samples with a complex background is always difficult in the classification of remote sensing images. We propose a new small sample target detection method combining local features and a convolutional neural network (LF-CNN) with the aim of detecting small numbers of unevenly distributed ground object targets in remote sensing images. The k-nearest neighbor method is used to construct the local neighborhood of each point and the local neighborhoods of the features are extracted one by one from the convolution layer. All the local features are aggregated by maximum pooling to obtain global feature representation. The classification… More >

Kailei Wang, Mingjing Li^*, Peng Yan, Leiting Dong^*

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 165-197, 2022, DOI:10.32604/cmes.2022.019188

Abstract The main goal of this work is to study the ballistic performance of multi-layered moderately-thick metallic targets. Several target configurations have been considered in this work, with various types of interlayer connection (spaced, contacted and adhesive) and the number of layers (four and eight), and the influence of target configurations on ballistic performance has been studied experimentally and numerically. In the experiments, the targets were impacted by 12.7-mm projectiles at a velocity around 820 m/s. The experimental results show that, with similar total thickness, the contacted and adhesive targets exhibit better ballistic performance than the monolithic targets, and the four-layered targets… More >

Changxing Fan¹, Jihong Chen^2,*, Keli Hu^1,3, En Fan¹, Xiuqing Wang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 477-491, 2022, DOI:10.32604/cmes.2022.019159

Abstract We first propose the normal Pythagorean neutrosophic set (NPNS) in this paper, which synthesizes the distribution of the incompleteness, indeterminacy, and inconsistency of the Pythagorean neutrosophic set (PNS) and normal fuzzy number. We also define some properties of NPNS. For solving the decision-making problem of the non-strictly independent and interacting attributes, two kinds of NPNS Choquet integral operators are proposed. First, the NPNS Choquet integral average (NPNSCIA) operator and the NPNS Choquet integral geometric (NPNSCIG) operator are proposed. Then, their calculating formulas are derived, their properties are discussed, and an approach for solving the interacting multi-attribute decision making based on… More >

Gysbert Basson^1,*, Andrew P. Bassom², Brian Salmon³

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 379-409, 2022, DOI:10.32604/cmes.2022.019112

Abstract Advances in numerical simulation techniques play an important role in helping mining engineers understand those parts of the rock mass that cannot be readily observed. The Material Point Method (MPM) is an example of such a tool that is gaining popularity for studying geotechnical problems. In recent years, the original formulation of MPM has been extended to not only account for simulating the mechanical behaviour of rock under different loading conditions, but also to describe the coupled interaction of pore water and solid phases in materials. These methods assume that the permeability of mediums is homogeneous, and we show that… More >

Haijie Pan, Lirong Zheng^*

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 493-512, 2022, DOI:10.32604/cmes.2022.019069

Abstract The machine learning model converges slowly and has unstable training since large variance by random using a sample estimate gradient in SGD. To this end, we propose a noise reduction method for Stochastic Variance Reduction gradient (SVRG), called N-SVRG, which uses small batches samples instead of all samples for the average gradient calculation, while performing an incremental update of the average gradient. In each round of iteration, a small batch of samples is randomly selected for the average gradient calculation, while the average gradient is updated by rounding of the past model gradients during internal iterations. By suitably reducing the… More >

Meng Da¹, Huiqin Wang^1,*, Ke Wang¹, Zhan Wang²

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 513-527, 2022, DOI:10.32604/cmes.2022.019040

Abstract The properties of the same pigments in murals are affected by different concentrations and particle diameters, which cause the shape of the spectral reflectance data curve to vary, thus influencing the outcome of matching calculations. This paper proposes a spectral matching classification method of multi-state similar pigments based on feature differences. Fast principal component analysis (FPCA) was used to calculate the eigenvalue variance of pigment spectral reflectance, then applied to the original reflectance values for parameter characterization. We first projected the original spectral reflectance from the spectral space to the characteristic variance space to identify the spectral curve. Secondly, the… More >

Ningbo Jing¹, Mingqiao Li¹, Lang Liu^2,*, Yutong Shen¹, Peijiao Yang¹, Xuebin Qin¹

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 465-476, 2022, DOI:10.32604/cmes.2022.018965

Abstract During mine filling, the caking in the pipeline and the waste rock in the filling slurry may cause serious safety accidents such as pipe blocking or explosion. Therefore, the visualization of the inner mine filling of the solid–liquid two-phase flow in the pipeline is important. This paper proposes a method based on capacitance tomography for the visualization of the solid–liquid distribution on the section of a filling pipe. A feedback network is used for electrical capacitance tomography reconstruction. This reconstruction method uses radial basis function neural network fitting to determine the relationship between the capacitance vector and medium distribution error.… More >

Shaowei Wang^1,2, Cong Xu¹, Hao Gu^3,*, Pinghua Zhu¹, Hui Liu¹, Bo Xu⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 97-117, 2022, DOI:10.32604/cmes.2022.018721

Abstract Many concrete dams seriously suffer from long-term seepage dissolution, and the induced mechanical property deterioration of concrete may significantly affect the structural performance, especially the seismic safety. An approach is presented in this paper to quantify the influence of seepage dissolution on seismic performance of concrete dams. To connect laboratory test with numerical simulation, dissolution tests are conducted for concrete specimens and using the cumulative relative leached calcium as an aging index, a deterioration model is established to predict the mechanical property of leached concrete in the first step. A coupled seepage-calcium dissolution-migration model containing two calculation modes is proposed… More >

Yinhuan Yang^1,*, Manfeng Gong¹, Xiaoqun Xia¹, Linzhi Wu^2,3

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 365-378, 2022, DOI:10.32604/cmes.2022.018535

Abstract The mechanical properties of Z-pins reinforced composites adhesively bonded single-lap joints (SLJs) under un-directional tension loading are investigated by experimental and numerical methods. Three kinds of joint configurations, including SLJs with three/two rows of Z-pins and “I” array of Z-pins, are investigated by tension test. The failure modes and mechanism of reinforced joints with different Z-pins numbers and alignment are analyzed, and the comparison is performed for the failure strengths of no Z-pins and Z-pins reinforced joints. According to experimental results, failure modes of three kinds of joints are all mixed failure. It turns out that the Z-pins are pulled… More >

Ruhui Cheng¹, Xiaomeng Yin², Leilei Chen^1,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.1, pp. 445-464, 2022, DOI:10.32604/cmes.2022.018519

Abstract This paper applies a machine learning technique to find a general and efficient numerical integration scheme for boundary element methods. A model based on the neural network multi-classification algorithm is constructed to find the minimum number of Gaussian quadrature points satisfying the given accuracy. The constructed model is trained by using a large amount of data calculated in the traditional boundary element method and the optimal network architecture is selected. The two-dimensional potential problem of a circular structure is tested and analyzed based on the determined model, and the accuracy of the model is about 90%. Finally, by incorporating the… More >