Advances in Computer and Materials Scienc Research
2026 International Conference on Image Algorithms, Architecture, Physics, and Mechanical Engineering
Vol. 6 / No. 1 2026 ISSN 3007-9640 26 articles
The 2026 International Conference on Image Algorithms, Architecture, Physics, and Mechanical Engineering (ICIAPME 2026) is dedicated to establishing a high-level international platform for academic exchange and collaboration in the fields of image algorithms, architectural engineering, physics, and mechanical engineering. The conference aims to promote the dissemination of innovative ideas, encourage interdisciplinary integration, and facilitate the sharing of cutting-edge research achievements and practical engineering experience. ICIAPME 2026 provides a forum for researchers, scholars, engineers, and industry professionals to present recent advances in image processing and computational algorithms, architectural design and structural innovation, physical sciences, and mechanical systems and technologies. By fostering dialogue and collaboration among academia, research institutions, and industry, ICIAPME 2026 seeks to bridge theoretical research and practical applications, stimulate technological innovation, and address emerging scientific and engineering challenges. The conference also aims to support the development of intelligent technologies, advanced materials, and sustainable engineering solutions in response to the evolving demands of modern science, industry, and society.
Papers in this issue
26-
pp. 1–8
Research on Building Extraction from Remote Sensing Images based on Deep Learning
Guokuan He, Yuhong Wang, Ping Nie
In this study, the LoveDa dataset is used to carry out experiments. In the data preprocessing stage, the sample size of the dataset is effectively expanded through data enhancement and normalization operations such as rotating, flipping, etc., so that the model can learn more images of buildings with different shapes and angles during the training process. Subsequently, the U-Net network model is trained using the processed dataset, paying close attention to the model's accuracy, F1 value and ot...
-
pp. 9–20
Numerical Analysis of the Effect of Tunnel Span on the Dynamic Response of Tunnel under Strong Stress Waves
Zihan Zhang, Shaoliu Liu
Span significantly impacts tunnel bearing capacity, and this study investigates its influence on the dynamic response of straight-walled arch tunnels under strong ground impact loads. A dynamic finite element model is established to simulate the mechanical behavior of the tunnel under static and dynamic coupling conditions. The plastic zone evolution, peak particle velocity distribution, and tunnel displacement characteristics are analyzed using the dynamic finite element method for a tunnel sub...
-
pp. 21–32
A Dual-Channel Feature Fusion Network of MACNN and Informer for Gearbox Fault Diagnosis under Variable Operating Conditions
Zeyu Yang, Lijie Zhang, Ze Xu, Linfeng Han, Haotian Guo, Jiacheng Xu
To address the difficulty of extracting and identifying gearbox fault features under varying operating conditions in industrial environments, a gearbox fault diagnosis method based on a dual-channel feature extraction and fusion network combining a multi-scale convolutional neural network (MACNN) and an Informer encoder is proposed. First, variational mode decomposition (VMD) and the fast Fourier transform (FFT) are applied to preprocess the raw vibration signals to explore multi-scale character...
-
pp. 33–41
Theoretical Analysis, Practical Defects and Optimization Paths of Coupling Structures Between Blockchain and Federated Learning
Xukai Cui, Hui Wang
Federated learning, featuring "data available but not visible", enables cross-entity collaborative modeling while protecting data privacy. However, its traditional centralized architecture suffers from inherent drawbacks, including single-point failure, lack of trust, and insufficient incentive mechanisms. Blockchain technology, with its decentralization, immutability, and smart contract automation features, provides a targeted technical solution to address these issues. Recent studies have prop...
-
pp. 42–51
Research on Floor Damage Classification of Optimized BP Neural Network Using Genetic Algorithm
Ming Sun, Duo Yang, Xiaolong Jiang, Lei Qian
Floor water inrush accidents are a significant component of mine water disasters, posing a serious threat to coal mine safety and production. Floor water inrush accidents are a significant component of mine water disasters, posing a serious threat to coal mine safety and production. The damage classification serves as a crucial indicator of the severity of floor water inrush accidents. This study outlines the primary control factors influencing floor damage classification. Utilizing a genetic al...
-
pp. 52–58
Particle assembly based on double-sided acoustic holography
Najat Hussain, Yonghao Wen, Zonglin Li, Yuan Zhou, Laixin Huang, Fei Li
Acoustic holography (AH) has emerged as a powerful technique for non-invasive and contactless manipulation of microscopic objects, enabling precise spatial organization in bioassembly and tissue modeling. Compared with a single lens for only phase modulation, using two lenses provides phase and amplitude modulation in acoustic field control, resulting in higher quality holographic images. However, dual-lens configurations suffer from acoustic refraction effects and therefore require precise posi...
-
pp. 59–69
Research on the Bearing Structure Movement of Overburden Strata in Stope under Thick Sandstone Conditions and Its Energy Accumulation and Dissipation Evolution Characteristics
Qingwei Bu, Bin Ma, Zheng Wei, Jiawang Song, Wenxue Gao, Baoping Du, Haipeng Wang, Yuhan Bai, Xuwei Mao, Jian Cao
In response to the complex occurrence of coal bearing strata leading to severe overburden strata instability and mining pressure, especially the instability of thick sandstone roof causing strong dynamic pressure disasters, threatening operational safety, and causing surface damage. This article takes the fully mechanized coal mining face with thick sandstone conditions in the western mining area of Inner Mongolia as the research object, and uses a combination of physical model experiments and n...
-
pp. 70–76
Research on the Evaluation Method of Asphalt Mixture Uniformity Based on Shape-Centre Method
Shuailin Wang, Tuanwei Sun, Jintao Wei, Xuquan Hu, Chenchen Xi, Shoujing Yan, Jiachen Shi, Wei Zhan
In order to control the quality of the project and reduce the impact of asphalt pavement segregation on the early road service life, this paper investigates the asphalt mix paving uniformity. First of all, based on the theory of form-centered method, the article proposes an evaluation method using weighted form-centered distance coefficient of variation to evaluate the uniformity of asphalt mixture. Then, a series of operations such as preprocessing and image segmentation were performed based on...
-
pp. 77–84
A Joint Time-Frequency Scaling Algorithm for Squint SAR Imaging
Liang Ni, Chengshan Yang, Jinqiang Zhang, Yujie Liang
Squint radar imaging is an important working mode for synthetic aperture radar (SAR). To facilitate the accumulation of azimuth energy, range walk correction is commonly applied to straighten the envelopes of the scattering points. However, this process violates the principle of translation invariance, causing azimuth spatial-variant effects in range migrations and Doppler coefficients. Consequently, conventional imaging methods struggle to achieve effective and uniform focusing across the entir...
-
pp. 85–90
Composite-Phase Spin-Multiplexed Metasurface for Multi-Channel Perfect Vortex Vector Beams
Zihan Zhang, Zhengtai Ma, Xianzi Pei, Xiaowei Qin, Yiyang Xie
To meet the increasing demands of high-speed, high-capacity data transmission in 5G commercialization, vortex beams carrying orbital angular momentum (OAM) have emerged as a promising approach for introducing additional multiplexing dimensions. In this work, a spin-multiplexed metasurface based on a composite-phase modulation mechanism is proposed and numerically verified. Rectangular GaAs nanofins enable independent phase control of left- and right-handed circularly polarized light, integrating...
-
pp. 91–99
Research on Underwater Structured Light Three-Dimensional Reconstruction Based on Deep Learning
Yuheng Wang, Haojun Zhang, Lei Lu, Zhilong Su, Wei Pan
Underwater structured light three-dimensional (3D) imaging is essential for applications in underwater exploration and inspection. However, it suffers from stripe brightness attenuation, contrast reduction, and random noise introduction due to absorption, scattering, and refraction across media interfaces, leading to degraded stripe decoding and reconstruction accuracy. This paper presents a diffusion model-based approach for underwater structured light 3D reconstruction. Without altering the co...
-
pp. 100–106
Effects of Near-Field Phase and Amplitude Deviations on the Far-Field Beam Quality of Hexagonally Packed VCSEL Arrays
Baozhuo Jiang, Zhengtai Ma, Shangkun Li, Chengcheng Huang, Huan Zhang, Pengying Chang, Yiyang Xie
Vertical Cavity Surface Emitting Laser (VCSEL) coupled arrays are promising for high-power and high-beam-quality applications. However, optical field coupling among array elements in practical operation induces phase and amplitude non-uniformities that degrade far-field beam quality. In this work, the effects of near-field phase and amplitude non-uniformities on the far-field beam quality of hexagonally packed VCSEL arrays are investigated. Based on Gaussian beam propagation theory, a theoretica...
-
pp. 107–112
Calculation method for braking energy during aircraft aborted takeoff
Fengmin Zheng, Junqiang Bai, Lei Qiao, Yizhen Li
The conventional calculation of braking energy for aircraft is mainly aimed at the landing phase, while there is relatively little research on the calculation method of braking energy for dangerous conditions such as aircraft takeoff suspension. Based on this, combined with the aircraft ground kinematics and dynamics models, and considering the changes in flight parameters during the entire process of releasing the drag parachute during the aircraft's takeoff suspension, according to the princip...
-
pp. 113–123
Effect of Tool Traversing Speed on Microstructure, Interface and Properties of Al/Steel Friction Stir Welding Lap Joints
Linghang Ma, Yijun Liu, Xu Zhang, Guo Chen, Yue Xie, Shikang Gao, Weizhao Sun, Li Zhou
Dissimilar materials of Al/Steel; Friction stir lap welding; Interface; Microstructure; Mechanical properties
-
pp. 124–134
Underactuated Merchant Ship Trajectory Tracking Control with Anti-Interference Capability Based on L1-LOS Guidance and Multi-Parameter PSO-PID Optimization
Xinhao Huang, Yongzheng Li, Biwei Wang, Lin Jiang, Liting Ding, Jiazheng Liu, Zeyu Chen
Aiming at the problems of low response efficiency of large heading deviation and low accuracy of trajectory tracking under complex sea state in trajectory tracking control of underactuated merchant ships, this study proposes an improved L1-LOS(LL) algorithm, which introduces the Line-of-Sight (LOS) guidance algorithm in the curved path scenarios with large heading errors on the basis of traditional L1 algorithm to take advantage of its fast response algorithm to correct the large heading errors ...
-
pp. 135–142
Research on Virtual Reality Motion Sickness Recognition Model Based on 1D-CNN Using EEG Signals
Dongxue Chen, Shuai Wang, Yue Yuan
Virtual Reality technology holds broad application prospects across various fields, but "Virtual Reality Motion Sickness " has emerged as a critical bottleneck restricting its development. This study aims to deeply explore the neural mechanisms of VRMS through Brain-Computer Interface technology. A high-precision Electroencephalogram (EEG) system was employed to collect EEG signals and subjective motion sickness scores from 23 participants before and after exposure to VR scenarios under strictly...
-
pp. 143–150
CLANet: A Hybrid Encoder for EEG Emotion Recognition via Spatiotemporal-Spectral Feature Fusion
Huiwen Chen, Hongyu Liu, Naishi Feng
Human emotion is a core link between cognition, behavior, and physiology, and its accurate recognition is crucial for advancing the development of intelligent human-computer interaction, mental health diagnosis, and other related fields. Current research mostly achieves multi-domain feature fusion through simple concatenation or weighted fusion at the algorithmic level, failing to fully reveal and exploit the feature contribution rates associated with emotional processing. To address the aforeme...
-
pp. 151–160
High-performance, double node charge sharing tolerant storage cell design
Tianwen Li, Shoubing Qi, Hongjin Liu
As device feature sizes shrink, inter-node charge sharing compromises the SEU sensitivity of hardened SRAM cells. By analyzing upset mechanisms in the unhardened cell, Quatrol, LIU, and DICE, a novel SEU hardened 14T cell is proposed. The new design is compared and analyzed in terms of area, delay,static power consumption, and sensitivity to single-event upsets, against state-of-the-art hardened cells. Due to fewer sensitive nodes prone to upsets, the proposed design exhibits superior immunity t...
-
pp. 161–171
Study on the Developmental Characteristics of Water-Conducting Fracture Zones in Multi-Slice Mining of Thick Coal Seams within the Gondwana Stratigraphy
Xuwei Mao, Liang Li, Jian Cao, Xueyi Yu, Lidong Ma, Zhiqiang Zhao
The geological strata of the Barapukuria Coal Mine in Bangladesh are affiliated with the Gondwana Formation. To ensure safe future mining of thick coal seams under aquifers, the development law of the Water-Flowing Fractured Zone (WFZ) during slice extraction was investigated.The development height of the WFZ was predicted via numerical simulation.. Field measurements of the WFZ height were subsequently conducted for each mining slice, and regression analysis was performed to establish a mine-sp...
-
pp. 172–178
Deep Learning–Based Classification of SERS Spectra for Simultaneous Identification of Clenbuterol, Ractopamine and Salbutamol
Tianzhen Yin, Yankun Peng, Yongyu Li
The illicit residue of lean meat agents poses a severe challenge to global food safety, seriously threatening public health. To address the complex and time-consuming nature of traditional detection methods, this study proposes a novel classification method based on a deep learning neural network for Surface-Enhanced Raman Scattering (SERS) spectra, aiming to achieve rapid and accurate identification of three typical lean meat agents: clenbuterol, salbutamol, and ractopamine. Targeting the commo...
-
pp. 179–189
Research on Early-Age Cracking Mechanisms and Control Factors in Continuously Reinforced Concrete Pavements
Shengshu Liu, Fei Huang, Haibing Jin, Guangli Zhou, Hang Gao, Sili Li, Minyi Fu
Continuously Reinforced Concrete Pavement (CRCP) has been widely adopted internationally due to its superior crack resistance and lower maintenance costs. However, research into the early-age cracking mechanisms and control factors of CRCP still presents numerous challenges, such as insufficient studies on crack formation and development patterns, the bond-slip relationship between steel bars and concrete, and the characteristics of interlayer friction.This paper systematically analyzes the infl...
-
pp. 190–200
IoT-Based Quality Control Technology for Concrete Pavement Construction
Fei Huang, Jianguo Zhang, Guangli Zhou, Shengshu Liu, Hang Gao, Sili Li, Minyi Fu
Concrete quality control is a crucial part of concrete construction. It affects not only the workability of fresh concrete and the mechanical performance of concrete structures but also the long-term durability of concrete components. Therefore, choosing effective concrete quality control methods helps improve the construction quality of concrete projects. This paper designs and improves a mixer for the online observation of cement mortar quality. It also introduces an experimental twin-shaft co...
-
pp. 201–206
Study on the Extraction Performance of N,N'-dimethyl-N,N'-dioctyl-3-oxa-diglycolamide for 13 Lanthanides in Sulfuric Acid System
Xuming Chen, Chen Wang, Guoxin Tian
This study investigates the extraction behavior of 13 lanthanide elements (Ln(III)) by N,N'-dimethyl-N,N'-dioctyl-3-oxa-diglycolamide (DMDODGA) in a sulfuric acid medium, using 40/60 (v/v) % octanol/kerosene as the solvent. The effects of aqueous phase sulfuric acid concentration, DMDODGA concentration, and temperature on the distribution ratio were systematically examined. Slope analysis and thermodynamic parameter determination were performed to elucidate the extraction mechanism.
-
pp. 207–217
TikTok as a Cognitive Scaffold: Exploring the Mechanisms of Gen Z's Self-Directed Learning in Algorithm-Driven Informal Spaces
Wei Zhang
This study focuses on an integrated education chain composed of university students, primary and secondary school students affiliated with a university in Shanghai and its education group. It investigates the mechanisms through which the algorithmic architecture of the short video platform TikTok (Douyin) functions as a cognitive scaffold influencing the self-directed learning behaviors of Generation Z. An empirical study was conducted using a mixed-methods approach with a sample of 500 students...
-
pp. 218–229
Structural Optimization of Negative Pressure Regulation Device for Cigarette Separation Wheel of ZL29 Filter Rod Forming Machine Based on Finite Element Analysis of Flow Field
Huai Wang, Wei Tong, Zhifan Duan, Xinran Pu, Heshan Gao, Bingzhe Cui, Wenwen Zhang, Zhenya Wang
This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text. Please make the page settings of your word processor to A4 format (21 x 29,7 cm or 8 x 11 inches); with the margins: bottom 1.5 cm (0.59 in) and top 3 cm (1.18 in), right/left margins must be 2 cm (0.78 in).Structural Optimization of the Negative Pressure Regulation Device for the Cigarette Separation Wheel of the ...
-
pp. 230–239
Research on Underwater Debris Detection Technology Based on YOLO Algorithm
Chaolong Liu, Xiaoting Bu, Shaobo Yang, Aicheng Xiong
Marine debris not only severely pollutes the health and habitat of marine life but also indirectly threatens human life. Deep learning-based target detection algorithms have achieved significant results in underwater debris detection, with the YOLO algorithm being widely used by researchers due to its fast detection speed and high accuracy. However, the underwater environment is complex and variable, and underwater debris detection faces challenges such as low detection accuracy, false negatives...