检索结果-内蒙古大学图书馆

data-driven model for predicting machining cycle time in ultra-precision machining

ADVANCES IN MANUFACTURING 2025年 1-16页

作者： Zhu, Tong Lee, Carman K. M. To, Sandy Suet Hong Kong Polytech Univ Dept Ind & Syst Engn Hung Hom Hong Kong Peoples R China Hong Kong Polytech Univ Dept Ind & Syst Engn State Key Lab Ultraprecis Machining Technol Kowloon Hong Kong Peoples R China

This study aims to present a data-driven method to accurately predict the machining cycle time for an ultra-precision machining (UPM) milling machine, considering the four most common interpolation types in the target machine tool: full-stop linear, non-stop linear, circular, and Bezier interpolation. Regarding these interpolation types, four artificial neural network (ANN) models were developed to predict the machining times for each command line in each numerical control (NC) program. Using the proposed data-driven method, the motion type of each command line in the NC program is first identified. The corresponding features are then extracted from the specific command line, which is considered the input of the model, while the estimated machining time is the output. After training and tunning, all four models achieved extremely high prediction accuracies (>95%), which were further validated through cutting experiments. Moreover, the influence of different feedrates on the machining time prediction accuracy in UPM was explored for the first time, demonstrating the excellent robustness of the proposed models at high feedrate compared with the CAM-based method. This strategy is easily applicable to other CNC machine tools, and the compact structure of the ANN model and its low computation consumption enable its deployment in edge devices. With the addition of more datasets, the accuracy and robustness of the proposed model can be further enhanced.

关键词： data-driven model Ultra-precision machining (UPM) Machining cycle time Interpolation Neural networks

来源：评论

学校读者我要写书评

暂无评论

A data-driven model for time-varying mesh stiffness of small-module powder metallurgy gear pairs with porosity feature

引用

MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES 2025年

作者： Hu, Bo Zhang, Yuanhao Yin, Lairong Dong, Jianxiong Xiao, Zeliang Zhou, Changjiang Changsha Univ Sci & Technol Hunan Prov Key Lab Safety Design & Reliabil Techno Changsha 410114 Peoples R China Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body Changsha Peoples R China

During the process of forming and sintering of powder metallurgy gears, porosity feature inevitably forms. It can reduce weight and improve damping and lubrication but can reduce the time-varying mesh stiffness (TVMS) of gear pairs. This study proposes a data-driven model to evaluate the TVMS of small-module powder metallurgy gear pairs under the weakening effect of pores. Firstly, leveraging the secondary development of finite element software, a finite element contact model for a spur gear pair with porosity feature is established. Then, combining the finite element simulation data with the theoretical formulas from the potential energy method, the data-driven model for the mesh stiffness of powder metallurgy gears with porosity feature is trained by using a feedforward neural network algorithm. Finally, the impact of porosity on the TVMS of gear pairs is investigated. The results indicate that the proposed data-driven model exhibits excellent predictive accuracy and generalization ability for the gear pairs with varying module, tooth numbers, and porosity. Furthermore, pores primarily weaken the TVMS by reducing the resistance ability of tooth bending, axial compression and foundation deformation. The findings are of great significance to the dynamic design and analysis of powder metallurgy gears.

关键词： Small-module gears powder metallurgy gears time-varying mesh stiffness porosity feature neural networks data-driven model

来源：评论

学校读者我要写书评

暂无评论

The role of optimizers in developing data-driven model for predicting lake water quality incorporating advanced water quality model

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 122卷 411-435页

作者： Uddin, Md Galal Bamal, Apoorva Diganta, Mir Talas Mahammad Sajib, Abdul Majed Rahman, Azizur Abioui, Mohamed Olbert, Agnieszka I. Univ Galway Sch Engn Galway Ireland Univ Galway Ryan Inst Galway Ireland Univ Galway MaREI Res Ctr Galway Ireland Univ Galway Ecohydroinformat Res Grp EHIRG Civil Engn Galway Ireland Munster Technol Univ Dept Civil Struct & Environm Engn Sustainable Infrastructure Res & Innovat Grp Cork Ireland Charles Sturt Univ Sch Comp Math & Engn Wagga Wagga Australia Charles Sturt Univ Gulbali Inst Agr Water & Environm Wagga Wagga Australia Ibnou Zohr Univ Fac Sci Dept Earth Sci Geosci Environm & Geomat Lab GEG Agadir Morocco Univ Coimbra Fac Sci & Technol MARE Marine & Environm Sci Ctr Sedimentary Geol Gr Dept Earth Sci Coimbra Portugal

Lake water is considered as one of the most precious freshwater resources for human consumption and thus, it is required to monitor the lake water quality (WQ) to maintain the good water state. For these purposes, the practice of integrating data-driven models in assessing and predicting lake WQ has received wider application. Nevertheless, the optimal performance of the data-driven models depends on the model hyperparameters and hyperparameter optimization techniques have crucial role in this regard. Therefore, the research aimed to assess the impact of various optimization techniques on these prediction models in order to predict the lake WQ. For the purposes of reliable lake water state assessment, this study presents a comprehensive analysis of lake WQ prediction, integrating sophisticated Root Mean Squared (RMS)-Water Quality Index (WQI) model with eight machine learning algorithms (ML), two Artificial Intelligence (AI) techniques, and five optimization methods. Comparing five optimization methods-Grid Search (GS), Random Search (RS), Bayesian Optimization (BO), Optuna (OPT), and Tree-based Pipeline Optimization Tool (TPOT)-revealed their significant influence on model performance and computational efficiency. Based on the analysis, random forest (RF) integrated with TPOT consistently demonstrated robust performance compared to other models, achieving an impressive R2 value of 0.94 during training (Root mean squared error-RMSE= 0.85, Mean squared error-MSE= 0.73, Mean absolute error-MAE= 0.48, and Percentage of absolute bias error-PABE= 2.35), testing (RMSE= 0.43, MSE= 0.18, MAE= 0.15, and PABE= 0.19), and validation (RMSE= 0.96, MSE= 0.96, MAE= 0.823, and PABE= 1.08), indicating its precision in predicting lake WQ. The results reveal that TPOT and OPT show remarkable effectiveness in optimizing the hyperparameter space to enhance model accuracy across various ML/AI model combinations. The research findings suggest that RMS-WQI with RF-TPOT integration model co

关键词： Hyperparameters Optimization techniques Water quality index (WQI) model data-driven model Lake water

来源：评论

学校读者我要写书评

暂无评论

Short-Term Transmission Capacity Prediction of Hybrid Renewable Energy Systems Considering Dynamic Line Rating Based on data-driven model

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2025年第2期61卷 2410-2420页

作者： Su, Yi Tan, Mao Teh, Jiashen Xiangtan Univ Xiangtan 411105 Peoples R China Univ Sains Malaysia USM Gelugor 14300 Penang Malaysia

The output capacity of Hybrid Renewable Energy Systems (HRES) is crucial for dispatching plans and spinning reserve capacity, but it's constrained by renewable energy generator output and transmission tie-line capacity. Considering both dynamic line rating for tie-lines and the entire HRES is beneficial due to their susceptibility to micro weather conditions. Unfortunately, considering them collectively for capacity forecasting involves long-term regular fluctuations and short-term uncertainty changes in weather factors, which reduces prediction accuracy. Thus, a novel data-driven model is introduced in this paper to address the aforementioned issue. Initially, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to segment the capacity sequence into high-, medium-, and low-frequency components. Subsequently, the high-frequency component, characterized by wind-induced randomness, is predicted using Newton-Raphson-Based Optimizer (NRBO) - Bidirectional Gated Recurrent Unit (BiGRU);the medium-frequency component, reflecting seasonal regularities, is forecasted using Seasonal Autoregressive Integrated Moving Average (SAIMA);and the smooth and periodic low-frequency component is anticipated using Multivariable Linear Regression (MLR). Finally, the predictions from these models are combined to derive the ultimate predictive value. Case studies demonstrate that comprehensive consideration of transmission tie-lines equipped with DLR, as well as HRES, can enhance the external output capability of HRES, especially during periods of abundant wind resources. The proposed data-driven model can capture high-frequency fluctuations, medium-frequency periodicity, and low-frequency trends in capacity to enhance prediction accuracy.

关键词： Predictive models Wind speed Renewable energy sources Meteorological factors Accuracy Optimization Wind forecasting Fluctuations Couplings Prediction algorithms data-driven model dynamic line rating hybrid renewable energy system short-term prediction

来源：评论

学校读者我要写书评

暂无评论

Susceptibility risk assessment of oil and gas pipeline geological hazards in mountainous areas based on data-driven model

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 151卷

作者： Yang, Yuxiang Wang, Benji Cen, Xiao Shao, Bowen Zhu, Baikang Yang, Jin Hong, Bingyuan Henan Polytech Univ Sch Resources & Environm Jiaozuo 454003 Peoples R China China Univ Petr Coll Safety & Ocean Engn Beijing 102249 Peoples R China Zhejiang Expressway Petr Dev Co Ltd Hangzhou 310000 Zhejiang Peoples R China Zhejiang Ocean Univ Natl & Local Joint Engn Res Ctr Harbor Oil & Gas S Sch Petrochem Engn & Environm Zhejiang Key Lab Petrochem Environm Pollut Control Zhoushan 316022 Peoples R China Zhejiang ENN Energy Dev Co Ltd Hangzhou 311200 Zhejiang Peoples R China

Geological hazards are recognized as causing significant damage to oil and gas pipelines, often resulting in catastrophic loss of life and property and hindering societal progress. In this study, a data-driven evaluation model is developed by integrating the Information Value method (IVM) with a Back Propagation Neural Network (BPNN) to assess the susceptibility of geological hazards in mountainous oil and gas pipelines. The IVM is used to identify non-hazardous areas, optimizing sample selection and reducing training errors, while the BPNN is employed to determine the weights of evaluation indicators, enhancing accuracy. First, an evaluation index system is proposed that comprehensively considers the natural geographical conditions and main disaster types. Next, non-disaster areas are located using the IVM and combined with disaster-prone areas to form the sample data. The sample data is then input into a BPNN for training, and the weights of each evaluation index are obtained from the trained network. Finally, a susceptibility risk assessment model is developed based on the derived weights and information values to accurately evaluate the susceptibility of pipeline geological hazards. A pipeline in China's Zhejiang Province's mountainous region is used as an illustration. Compared to the single IVM model and the single BPNN model, the receiver operator characteristic curve shows that the proposed method achieves significant improvements in the area under the curve by 9.8 % and 11.2 %, respectively, indicating a high level of evaluation accuracy. This study provides a reliable approach for assessing geological hazard susceptibility, offering scientific support for pipeline planning and hazard mitigation in oil and gas operations.

关键词： Oil and gas pipelines Geological hazards Susceptibility data-driven model Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Using recurrent neural networks to build a data-driven model of an autonomous underwater vehicle

引用

Transportation Research Procedia 2025年 83卷 417-424页

作者： Maciej Szymkowiak Polish Naval Academy Inz˙yniera Jana Smidowicza 69 Gdynia 81-127 Poland

This paper describes an approach to preparing a data-driven model for simulating the behavior of an autonomous underwater vehicle (AUV), using recurrent neural networks (RNNs). The main task of the research system was to process data containing states and control signals in such a way as to then enable the start of the learning process of selected types of artificial neural networks. In the conversion process, the data are transformed into time sequences that will constitute the training set for Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. Artificial neural network models, based on the above-mentioned architectures, were tested on the validation set to determine the discrepancy in prediction accuracy compared to real data. The obtained results were analyzed which allowed to evaluate the proposed solutions and draw conclusions.

关键词： Autonomous Underwater Vehicle (AUV) data-driven model Recurrent Neural Networks (RNN) Long Short-Term Memory (LSTM) Gated Recurrent Unit (GRU)

来源：评论

学校读者我要写书评

暂无评论

data-driven model as a post-process for daily streamflow prediction in ungauged basins

引用

Heliyon 2025年第4期11.0卷 e42512页

作者： Choi, Jeonghyeon Kim, Sangdan Forecast and Contral Division Nakdong River Flood Control Office Ministry of Environment 1233-88 Nakdongnam-ro Saha-gu Busan 49300 South Korea Division of Earth Environmental System Science (Major in Environmental Engineering) Pukyong National University 45 Yongso-ro Nam-gu Busan 48513 South Korea

Streamflow prediction in ungauged basins (PUB) remains a significant challenge in water resource planning and management. Although recent studies have proposed various approaches to reduce prediction errors using data-driven models (DDMs), further efforts are needed to improve applicability and accuracy of predictions in ungauged basins. This study proposes a framework that utilizes DDM as a post-processor to enhance the PUB performance of process-based models (PBMs) or DDMs and investigates its applicability. For this purpose, the Parsimonious EcoHydrologic model (PEHM) was selected as a PBM, and Long Short-Term Memory (LSTM) and Random Forest (RF) were chosen as DDMs. We tested the proposed approach on 28 basins in Korea, which were assumed to be ungauged. First, PEHM and LSTM were used separately to predict streamflow in ungauged basins. Subsequently, RF was employed as the main DDM for post-processing, and the post-processing effects of LSTM were also examined. The results in this study demonstrate the potential value of various post-processing approaches in improving streamflow prediction in ungauged basins. © 2025 The Authors

关键词： data-driven model Hybrid model Post-process Process-based model Streamflow prediction in ungauged basins

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Rules data-driven Equivalent model with Multi-gradient Learning for Discrete-Time Nearly Optimal Control

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2025年第1期27卷 1-12页

作者： Treesatayapun, C. Walailak Univ Fac Engn 222 Thaiburi Nakhon Si Thammarat 80161 Thailand CINVESTAV IPN Dept Robot & Adv Mfg Mexico City Mexico

A behavior of switchable control directions is investigated for the non-holonomic robotic system considered as a class of unknown nonlinear discrete-time systems. The data-driven equivalent model is established by a multi-input fuzzy rule emulated network and the multi-gradient learning law is developed to tune all adjustable parameters. Thereafter, the nearly optimal controller is derived using the dynamics of the equivalent model and the closed-loop performance is analyzed through rigorous mathematical analysis. The experimental system is constructed to validate the effectiveness of the proposed scheme and the advantage of the multi-gradient approach.

关键词： data-driven model Optimal control Discrete-time systems Multi-gradient learning Non-holonomic robot

来源：评论

学校读者我要写书评

暂无评论

data-driven model for maintenance decision support: A case study of railway signalling systems

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART F-JOURNAL OF RAIL AND RAPID TRANSIT 2016年第1期230卷 220-234页

作者： Morant, Amparo Larsson-Kraik, Per-Olof Kumar, Uday Lulea Univ Technol Lulea Railway Res Ctr SE-97187 Lulea Sweden Trafikverket Lulea Sweden

Signalling systems ensure the safe operation of the railway network. Their reliability and maintainability directly affect the capacity and availability of the railway network, in terms of both infrastructure and trains, as a line cannot be fully operative until a failure has been repaired. The purpose of this paper is to propose a data-driven decision support model that integrates the various parameters of corrective maintenance data and to study maintenance performance by considering different reliability, availability, maintainability and safety parameters. This model is based on failure analysis of historical events in the form of corrective maintenance actions. It has been validated in a case study of railway signalling systems and the results are summarised. The model allows the creation of maintenance policies based on failure characteristics, as it integrates the information recorded in the various parameters of the corrective maintenance work orders. The model shows how the different failures affect the dependability of the system: the critical failures indicate the reliability of the system, the corrective actions give information about the maintainability of the components, and the relationship between the corrective maintenance times measures the efficiency of the corrective maintenance actions. All this information can be used to plan new strategies of preventive maintenance and failure diagnostics, reduce the corrective maintenance and improve the maintenance performance.

关键词： Railway signalling systems decision support model data-driven model failure analysis maintenance corrective maintenance dependability case study reliability availability maintainability and safety data integration

来源：评论

学校读者我要写书评

暂无评论

data-driven model assessment: A comparative study for ship response determination

引用

OCEAN ENGINEERING 2024年 314卷

作者： La Ferlita, Alessandro Ley, Jens Qi, Yan Schellin, Thomas E. Di Nardo, Emanuel El Moctar, Ould Ciaramella, Angelo Univ Duisburg Essen Inst Ship Technol Ocean Engn & Transport Syst Duisburg North Rhine Wes Germany Germany Dev Ctr Ship Technol & Transport Syst DST Oststr 77 D-47057 Duisburg Germany Univ Naples Parthenope Dept Sci & Technol I-80133 Naples Italy

Several machine learning approaches to determine ship responses via data-driven models have been applied. Input features and parameters used relied on time-series analyses obtained from computational-fluid-dynamics approach. As inputs into the data-driven model, the heave and pitch motions of a ship advancing in irregular, i.e., natural seaway were considered. By using different models in the framework of machine learning, required computation for the associated ship motions may be avoided, thus reducing the computational effort to forecast ship motions. Comparative predictions with numerical simulations revealed that the deep-neural-network method for training in auto-machine-learning instructions yielded the highest accuracy in heave motion, resulting in a non-normalized mean-absolute-error of 0.74, against the corresponding error of 1.07 from numerical computations, whereas the method trained with the tree-based models (the extreme gradient boosting and the Hist gradient boosting regressor) predicted less accurate motions for the tested ship. The model trained with the random forest regressor exhibited an error of 1.10. Numerical simulation based on a field method proved to be the most suitable choice for pitch motion. Despite the few samples available to train the regressors, results demonstrated that the measured data was sufficient to assess the developed data-driven model for ship response determination.

关键词： data-driven model Artificial intelligence Ship motion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：