Research and development of thick plate shape prediction system based on industrial big data by Yufei MA, Changxin LIU, Wei KONG, Jinliang DING

“…Thick plate shape is one of the important indicators to measure the quality of thick plate products.The timely prediction of the final plate shape in production is of great significance for adjusting the operation and control of thick plate production.In actual industrial production, thick plate data has many characteristics, such as multiple coupling information, large amount of redundant information, and multi-source heterogeneity of data.Combining the needs of thick plate shape prediction, a thick plate shape prediction system was designed and developed.The data dump function was used to filter and preprocess the industrial big data to remove the coupling information and redundant variables in the data.LSTM neural network, convolutional neural network and 3D convolutional neural network were used to extract data features from data of different dimensions, and the features were fused based on the maximum mutual information coefficient to establish an integrated learning prediction model, which effectively solved the modeling difficulties caused by multi-source heterogeneous data.The actual industrial data of a domestic thick plate production line was used for verification, and the results showed the effectiveness of the developed system.…”
Get full text

An interpretable deep learning model for the accurate prediction of mean fragmentation size in blasting operations by Baoqian Huan, Xianglong Li, Jianguo Wang, Tao Hu, Zihao Tao

“…SHapley Additive exPlanations (SHAP) analysis revealed that the modulus of elasticity (E) was a key variable influencing the prediction of mean fragmentation size. …”
Get full text

Skin Lesion Image Segmentation Algorithm Based on MC-UNet by Guihua Yang, Bingxing Pan

“…Aiming at the situation of dermatoscopic images with fuzzy lesion boundaries, variable morphology and high similarity to background, this paper proposes a skin lesion segmentation algorithm that achieves higher segmentation accuracy by combining existing convolutional neural network methods. …”
Get full text

A Machine Learning Model for Procurement of Secondary Reserve Capacity in Power Systems with Significant vRES Penetrations by João Passagem dos Santos, Hugo Algarvio

“…The growing investment in variable renewable energy sources is changing how electricity markets operate. …”
Get full text

RDM-YOLO: A Lightweight Multi-Scale Model for Real-Time Behavior Recognition of Fourth Instar Silkworms in Sericulture by Jinye Gao, Jun Sun, Xiaohong Wu, Chunxia Dai

“…Methodologically, Res2Net blocks are first integrated into the backbone network to enable hierarchical residual connections, expanding receptive fields and improving multi-scale feature representation. Second, standard convolutional layers are replaced with distribution shifting convolution (DSConv), leveraging dynamic sparsity and quantization mechanisms to reduce computational complexity. …”
Get full text

Modeling energy consumption indexes of an industrial cement ball mill for sustainable production by Saeed Chehreh Chelgani, Rasoul Fatahi, Ali Pournazari, Hamid Nasiri

“…To fill the gap, this study developed a CL by examining different AI models (Random Forest, Support Vector Regression, Convolutional Neural Network, extreme gradient boosting, CatBoost, and SHapley Additive exPlanations) for modeling energy consumption indexes of a close ball mill circuit in a cement plant to address the effectiveness of operating variables. …”
Get full text

A Hybrid AI Approach for Fault Detection in Induction Motors Under Dynamic Speed and Load Operations by Muhammad Irfan Ishaq, Muhammad Adnan, Muhammad Ali Akbar, Amine Bermak, Nimra Saeed, Maaz Ansar

“…From existing literature, conventional fault diagnosis approaches in an IM struggle to reliably identify fault patterns at different speeds, particularly under variable speed and changing load conditions. To resolve this issue, this paper presents a unique hybrid Convolutional Neural Network (CNN) along with the Long Short Term Memory (LSTM) topology for diagnosing faulty patterns in an IM under loaded and unloaded variable speed settings. …”
Get full text

Unified estimation of rice canopy leaf area index over multiple periods based on UAV multispectral imagery and deep learning by Haixia Li, Qian Li, Chunlai Yu, Shanjun Luo

“…Moreover, the model accuracies (MLP and CNN) before and after variable screening showed noticeable changes. Conducting variable screening contributed to a substantial improvement in the accuracy of rice LAI estimation. …”
Get full text

MSKFaceNet: A Lightweight Face Recognition Neural Network for Low-Power Devices by Peng Zhang, Qinghua Ma, Yi Li, Min Cui

“…First, we propose a novel lightweight convolutional neural network module called MSKFNet. MSKFNet adopts a bottleneck design and introduces variable kernel convolutions from VarKNet, combined with channel shuffle and structural re-parameterization techniques, establishing an efficient CNN module for embedded systems. …”
Get full text

MTAD-TF: Multivariate Time Series Anomaly Detection Using the Combination of Temporal Pattern and Feature Pattern by Q. He, Y. J. Zheng, C.L. Zhang, H. Y. Wang

“…The common limitation of many related studies is that there is only temporal pattern without capturing the relationship between variables and the loss of information leads to false warnings. …”
Get full text

Quantum Integral Inequalities with Respect to Raina’s Function via Coordinated Generalized Ψ-Convex Functions with Applications by Saima Rashid, Saad Ihsan Butt, Shazia Kanwal, Hijaz Ahmad, Miao-Kun Wang

“…In accordance with the quantum calculus, we introduced the two variable forms of Hermite-Hadamard- (HH-) type inequality over finite rectangles for generalized Ψ-convex functions. …”
Get full text

Intelligent recognition method for personnel intrusion hazardous area in fully mechanized mining face by Qinghua MAO, Jiao ZHAI, Xin HU, Yinan SU, Xusheng XUE

“…To address the problems of low accuracy of video AI recognition of personnel intrusion hazardous areas in fully mechanized mining face caused by factors such as variable personnel scales, and dynamic changes of hazardous areas, an intelligent recognition method for personnel intrusion hazardous areas of fully mechanized mining face based on RSCA-YOLOv8s and automatic division of hazardous areas is proposed. …”
Get full text

MSFUnet: A Semantic Segmentation Network for Crop Leaf Growth Status Monitoring by Zhihan Cheng, He Yan

“…The MFF module integrates multi-scale features to improve the model’s capacity for distinguishing overlapping leaf areas, while the EDF module employs extended convolution to accurately capture fine edge details. …”
Get full text

Improved method for a pedestrian detection model based on YOLO by Yanfei LI, Chengyi DONG

“…The proposed method had superior performance in dense agricultural contexts while improving detection capabilities for pedestrian distribution patterns under complex farmland conditions, including variable lighting and mechanical occlusions. The main innovations were: (1) integration of spatial pyramid dilated (SPD) operations with conventional convolution layers to construct SPD-Conv modules, which effectively mitigated feature information loss while enhancing small-target detection accuracy; (2) incorporation of selective kernel attention mechanisms to enable context-aware feature selection and adaptive feature extraction. …”
Get full text

Daily soil temperature prediction using hybrid deep learning and SHAP for sustainable soil management by Meysam Alizamir, Kaywan Othman Ahmed, Salim Heddam, Sungwon Kim, Jeong Eun Lee

“…Furthermore, various configurations of the input variables were examined across seven distinct observational scenarios to identify the most significant predictive factors. …”
Get full text

Research on the Construction of Crossborder e-Commerce Logistics Service System Based on Machine Learning Algorithms by Jinbo Xu, Shibiao Mu

“…The sentiment synthesis word vector is used as the input data structure of the text, the convolutional neural network model and the recurrent neural network model in machine learning are independently designed and constructed, and a shunt is proposed. …”
Get full text

A New Bearing Fault Diagnosis Method Based on Deep Transfer Network and Supervised Joint Matching by Chengyao Liu, Fei Dong, Kunpeng Ge, Yuanyuan Tian

“…Second, a deep transfer convolutional neural network is built by the way of fine-tuning, and the trained network is used to extract deep features from different domains. …”
Get full text

A MFR Work Modes Recognition Method Based on Dual-Scale Feature Extraction by Zhiyuan Li, Xuan Fu, Chengjian Mo, Jianlong Tang, Ronghua Guo, Wenbo Li

“…The recognition method first obtains the variable-length sequence processing capability through pulse sequence segmentation. …”
Get full text

Fault Classification of 3D-Printing Operations Using Different Types of Machine and Deep Learning Techniques by Satish Kumar, Sameer Sayyad, Arunkumar Bongale

“…The ML models such as k-nearest neighbor (KNN), decision tree (DT), extra trees (ET), and random forest (RF) with convolutional neural network (CNN) as a DL model are used to classify the variable operation printing parameters. …”
Get full text

Short-Term Target Maneuvering Trajectory Prediction Using DTW–CNN–LSTM by Haifeng Guo, Jinyi Yang, Xianyong Jing, Peng Zhang

“…Considering the characteristics of high noise, dynamic complexity, and variable data lengths inherent in short-range air combat scenarios, we employ dynamic time warping (DTW) to assess the similarity of 3D trajectory data. …”
Get full text