检索结果-内蒙古大学图书馆

Enhancing understanding of asphalt mixture dynamic modulus prediction through interpretable machine learning method

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Zhang, Ke Min, Zhaohui Hao, Xiatong Henning, Theunis F. P. Huang, Wei Southeast Univ Intelligent Transportat Syst Res Ctr Southeast Univ Rd 2 Nanjing 211189 Peoples R China Southeast Univ Sch Transportat Southeast Univ Rd 2 Nanjing 211189 Peoples R China Univ Auckland Dept Civil & Environm Engn Auckland 1142 New Zealand

Dynamic modulus is a key parameter in pavement design and pavement mechanics analysis. It is essential to accurately predict dynamic modulus and study the relationships between influencing factors and dynamic modulus. In this study, a hybrid prediction model is developed based on Extreme Gradient Boosting (XGBoost) and whale optimization algorithm (WOA). Based on this model, the effects of asphalt binder properties, test condition, asphalt mixture volume parameters, and asphalt mixture gradation on dynamic modulus are analyzed. The contribution of each variable to the model predictions is quantified through Shapley Additive Explanations (SHAP), and the interaction between dynamic modulus and influencing factors is evaluated by Partial Dependence Plot (PDP). The results indicate that the WOA-XGBoost model has excellent accuracy and robustness in predicting dynamic modulus. The three most important factors affecting dynamic modulus prediction results are the complex shear modulus of binder, the test temperature and the asphalt binder viscosity. The increase in dynamic modulus can be achieved through the utilization of asphalt binders characterized by relatively large complex modulus, high viscosity, small phase angle, and high asphalt PG indexes. Reducing the effective binder volume and air voids of the mixture, optimizing the mixture gradation to a suitable level, and increasing the mineral powder content can also lead to the increase of dynamic modulus. Besides, low test temperature and high frequency generally mean a large value of dynamic modulus. This study clarifies the impact of influencing factors on the performance of asphalt mixtures based on machine learning, which lay a foundation for the intelligent design of asphalt mixtures.

关键词： Dynamic modulus of asphalt mixture Extreme Gradient Boosting whale optimization algorithm Influencing factors Shapley Additive Explanations analysis Partial Dependence Plot analysis

来源：评论

学校读者我要写书评

暂无评论

Optimized allocation of water temperature, quality, and quantity for the utilization of geothermal water from deep buried reservoirs

引用

GEOTHERMICS 2024年 119卷

作者： Wang, Xinyi Yuan, Xiaoying Shui, Qingna Qi, Yufeng Deng, Xiaoying Yang, Fang Henan Polytech Univ Inst Resources & Environm Jiaozuo 454000 Henan Peoples R China Ecol & Environm Geol Serv Ctr Henan Prov Bur Geol Zhengzhou 450000 Henan Peoples R China Collaborat Innovat Ctr Coal Safety Prod & Clean & Jiaozuo 454000 Henan Peoples R China Kaifeng City Water Conservat Off Kaifeng 475000 Henan Peoples R China

There is a need to fully utilize the benefits of geothermal water, while avoiding environmental problems in the development process. In this study, the water level, quantity, quality, and temperature of three sub -thermal reservoirs in Kaifeng City urban area, with burial depths of 1600-1800, 1800-2000, and 2000-2200 m, were combined with the local water demand and the actual exploitation and recharge rates, to establish an optimal allocation model of geothermal water considering its temperature, quality, and quantity. The objective function was to minimize the operating cost of the geothermal water supply system, and to overcome the four constraints of the heat supply required to meet the heat demand, single well pumping not exceeding the allowable pumping volume, pumping flow equaling the recharge flow, and water supply meeting the water demand. The model was solved based on the improved whale optimization algorithm and was compared with the results of other algorithms to determine the optimal configuration of geothermal water cascade utilization. The results showed that wells 1, 2, and 3 pumped flow rates of 82.62, 76.54, and 41.17 m3/h for heating, respectively. Additionally, 18.40 m3/h was used for therapeutic bathing, 9.52 m3/h was used for greenhouse cultivation, and 7.74 m3/h was used for fish farming. The lowest operating cost of the geothermal water utilization and recharge system was achieved when wells 4, 5, 6, and 7 were recharged with geothermal water at flows of 41.31, 41.31, 40.88, and 41.17 m3/h, respectively, and well 6 was also recharged with tap water at a flow rate of 35.66 m3/h. Compared with the pre -optimization period, the annual revenue increased by RMB 3.452 million. The study achieved an organic combination of extraction, recharge, and multi -target utilization, which is of great significance for the rational development and utilization of geothermal water and the science -based protection of the resource.

关键词： Geothermal water Temperature and quality separation Gradient utilization whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid information-based PF-WOA algorithm for gas source localization in 3D space

引用

ROBOTICA 2024年第11期42卷 3748-3767页

作者： Wang, Li Ren, Ziyu Fan, Shurui Zhang, Yong Hebei Univ Technol Sch Elect Informat Engn Tianjin Peoples R China Tianjin Univ Commerce Sch Informat Engn Tianjin Peoples R China

In recent years, dangerous gas leakage events occur frequently. Rapid and accurate location of gas leakage sources by mobile robots is the key to avoid the expansion of disasters. In order to solve the problem of discontinuous gas concentration gradient and sparse gas environment in three-dimensional space, particle filter, and whale swarm optimization algorithm are integrated to locate gas source. Firstly, the Z-shape search and comb search are used to locate the plume, and then, the particle filter algorithm is combined with the whale optimization method to guide the particle movement, and the random inertial disturbance term is designed to improve the convergence speed and search accuracy of the algorithm. Experimental results in three-dimensional environment show that the proposed information-driven particle filter whale optimization hybrid algorithm effectively guides the robot in localizing gas source within a certain range, significantly enhancing both the efficiency and accuracy of localization compared to other algorithms.

关键词： gas source localization whale optimization algorithm information entropy particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

An intelligent digital twin model for the battery management systems of electric vehicles

引用

INTERNATIONAL JOURNAL OF GREEN ENERGY 2024年第3期21卷 461-475页

作者： Li, Heng Kaleem, Muaaz Bin Chiu, I-Ju Gao, Dianzhu Peng, Jun Huang, Zhiwu Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Cent South Univ Sch Automat Changsha Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China

Battery management systems (BMS) are crucial for electric vehicles because effective battery management is essential to their safe and reliable operation. However, BMS experience some problems like high cost, reduced space, low efficiency, and high failure rates. This paper proposes an intelligent digital twin model for the BMS which utilized the historical battery data obtained from real driving scenarios to measure, estimate, predict, and diagnose the battery pack states. The digital twin model consists of two parts, one is the state estimation based on the regression model and the second one is the fault diagnosis. The regression model between the variables of BMS is developed using a back propagation neural network (BPNN). Moreover, a whale optimization algorithm (WOA) is utilized to further optimize the parameters of the regression model. A threshold-based fault detection method is applied to diagnose the faults in the BMS. The dataset gathered from an electric vehicle with one year duration is utilized to evaluate the performance of the proposed method. Experiment results verify that the proposed model achieved over 95% prediction accuracy and can effectively diagnose the faults in the BMS.

关键词： Battery management system digital twin electric vehicles neural network whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral prediction model of soil Cu content based on WOA-SPA algorithm

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2024年第18期45卷 6408-6424页

作者： Feng, Xiqin Tian, Anhong Fu, Chengbiao Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming Peoples R China Kunming Univ Sci & Technol Fac Land Resource Engn Kunming Peoples R China

The content of heavy metal Cu in soil is an important indicator for assessing soil quality. However, soil hyperspectral data contain a large amount of redundant data, which can affect the effectiveness of spectral modelling. To address this problem, a combined method based on whale optimization algorithm and Successive Projection algorithm (WOA-SPA) is proposed to select the characteristic bands. And a prediction model of soil heavy metal Cu content was constructed using the partial least squares method. The experimental results show that: (1) The prediction accuracy of soil Cu content using the WOA-PLSR model was higher than that of the SPA-PLSR model, with RPD increased by 0.229, the R2 increased by 0.07, and RMSE decreased by 0.354. (2) Running the WOA and WOA-SPA combination algorithms 30 times respectively to prove the stability of the algorithms, the prediction accuracy of the model constructed based on the WOA-SPA combination algorithm is better than that of the model constructed based on the WOA algorithm as a whole. (3) Compared with the WOA or SPA algorithm alone, the prediction model constructed based on the WOA-SPA algorithm has a better prediction performance, with RPD of 2.259, R2 of 0.804, and RMSE of 2.396 for the prediction set. (4) Comparing the spatial distribution maps of the measured and predicted values, it can be observed that the spatial distribution between the predicted Cu content values based on the combined WOA-SPA algorithm and the measured Cu content values are basically consistent. This study indicates that the WOA-SPA-PLSR model has good stability and prediction accuracy for the prediction of Cu content in soil, which is of great practical significance for the rapid and accurate estimation of heavy metal Cu content in soil. A novel dimensionality reduction method based on WOA-SPA was proposed. The WOA-SPA-PLSR model was constructed, which can accurately and quantitatively predict the content of heavy metal Cu in *** characteristi

关键词： Soil hyperspectral whale optimization algorithm Successive Projection algorithm Cu content of soil selection of characteristic bands

来源：评论

学校读者我要写书评

暂无评论

A novel cascaded trajectory tracking control for UUVs under time-varying disturbances

引用

OCEAN ENGINEERING 2024年 300卷

作者： Chen, Qi Ding, Dan Gan, Wenyang Univ Shanghai Sci & Technol Sch Mech Engn Jungong Rd 516 Shanghai 200093 Peoples R China Shanghai Maritime Univ Logist Engn Coll Haigang Ave 1550 Shanghai 201306 Peoples R China

In this paper, a novel cascaded trajectory tracking control strategy based on the characteristics of kinematics and dynamics is proposed for unmanned underwater vehicles (UUVs) under complex disturbances. A kinematic controller based on an improved model predictive control (MPC) is designed to solve the speed jump problem by considering system constraints. Moreover, an improved whale optimizer with elite strategy (EIWOA) is used to the rolling optimization process of MPC, ensuring that the global best solution is derived by obtaining the elite individuals in the population. Besides, a dynamic controller that consists of an adaptive disturbance observer and a fuzzy integral sliding mode control (ADO-FISMC) is proposed to obtain optimal thrust force under time-varying disturbances. The benefit of ADO lies in that it can estimate time-varying disturbances without specific information about disturbances. The fuzzy logic system is introduced to alleviate the chattering of sliding mode control. The simulation results demonstrate the great tracking performance of the cascaded trajectory tracking controller. The viability of the proposed algorithm is also confirmed by trials conducted in water pools.

关键词： Unmanned underwater vehicles Trajectory tracking whale optimization algorithm Elite strategy Model predictive control Disturbance observer

来源：评论

学校读者我要写书评

暂无评论

A Method for Predicting the Morphology of Multi-track Laser Cladding Coatings Based on WOA-RF

引用

INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING-GREEN TECHNOLOGY 2025年 1-17页

作者： Du, Yanbin Lei, Xin Chen, Hongxi Liang, Qiang Ma, Wensheng Tu, Jian Chongqing Technol & Business Univ Chongqing Key Lab Green Design & Mfg Intelligent E Chongqing 400067 Peoples R China Chongqing Technol & Business Univ Coll Mech Engn Chongqing 400067 Peoples R China Chongqing Pump Ind Co Ltd Chongqing 400033 Peoples R China Chongqing Univ Technol Coll Mat Sci & Engn Chongqing 400054 Peoples R China

The morphology of multi-track laser cladding coatings is influenced by various process parameters, including laser power, scanning speed, and powder feeding rate. Accurate morphology prediction is crucial for optimizing process parameters and enhancing coating performance. A novel prediction framework that integrates the whale optimization algorithm (WOA) with the Random Forest (RF) algorithm (referred to as WOA-RF) is proposed to model the nonlinear relationship between the process parameters involved in laser cladding and the coating morphology. A central composite experiment design (CCD) with 4 factors and 5 levels was designed to carry out the laser cladding experiment, with the 17-4PH as the substrate and the 15-5PH as the cladding powder. The effects of the process parameters of laser cladding (laser power, powder feeding rate, scanning speed, and overlap rate) on the coating morphology characteristics (dilution rate, heat-affected zone area, and surface flatness) were analyzed. The relative importance of each process parameter was assessed by the random forest model. Based on the assessment results, a WOA-RF prediction model was established, and a multiple regression model and a random forest (RF) model were established for comparative analysis. The analysis reveals that the powder feeding rate exerts the most significant impact on the dilution rate, laser power is the key determinant of the area of the heat-affected zone, and the overlap rate predominantly affects surface flatness of the coating. The evaluation of parameter importance indicates that, under the conditions of this experiment, the overlap rate in the predictive model has a minimal contribution to the area of the heat-affected zone, and the laser power has a minimal contribution to the surface flatness of the coating. The WOA-RF model demonstrates superior performance in predicting morphological features across all evaluated metrics, outperforming both the RF model and the multiple regression mo

关键词： Laser cladding Morphology prediction Random Forest algorithm whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Flight Safety Risk Prediction for Civil Aircraft Approach and Landing

引用

JOURNAL OF AEROSPACE INFORMATION SYSTEMS 2025年第3期22卷 220-230页

作者： Wang, Xiangzhang Mou, Ruifang Southwest Jiaotong Univ Sch Transportat & Logist Chengdu 610031 Sichuan Peoples R China

The approach and landing phase is the critical juncture in flight operations, where flight-state risks must be meticulously identified and mitigated to avert significant safety incidents. This paper proposes a risk prediction model that enhances the Light Gradient Boosting Machine (LightGBM) using the whale optimization algorithm (WOA). First, a six-degree-of-freedom model is used to establish a system of differential equations to describe the aircraft's flight states. In conjunction with longitudinal and lateral motion risk analyses, parameters prone to typical flight accidents are selected as risk prediction indicators, focusing on abnormal flight states. Subsequently, the LightGBM algorithm is employed to construct a flight safety risk prediction model using WOA to optimize hyperparameters within the LightGBM framework, enhancing the predictive accuracy of the model. Finally, a data set is created using actual flight data from a particular airline, aggregating flight-state parameter data from 910 flights for model training and testing. The proposed model's performance is compared with similar machine-learning methods, including LightGBM, XGBoost, and Random Forest. The results demonstrate that the WOA-LightGBM model achieves 95.6% accuracy in predicting flight safety risks during the approach and landing phase, demonstrating a significant advantage in predictive precision over other methods.

关键词： Hyperparameter optimization flight safety flight status risk prediction Light Gradient Boosting Machine whale optimization algorithm Quick Access Recorder Gradient Boosting Decision Tree integrated transportation

来源：评论

学校读者我要写书评

暂无评论

MSGCN-xLSTM: Efficient Wind Power Forecasting Approach Combining Multiscale Graph Convolutional Network and Extended LSTM

引用

IEEE SENSORS JOURNAL 2025年第10期25卷 17568-17584页

作者： He, Xinyi Ni, Wei Zhang, Zhenxiang Luo, Haixia Wan, Lanjun Hunan Univ Technol Sch Comp Sci Zhuzhou 412007 Peoples R China Hunan Univ Technol Sch Railway Transportat Zhuzhou 412007 Peoples R China

Wind power generation is an important approach to achieving clean energy and is associated with notable randomness and uncertainty. Wind power data exhibit strong periodicity and historical dependence, which are influenced by wind speed, temperature, and other environmental factors. Existing methods struggle to simultaneously capture complex time-space dependence and dynamic changes in wind power data, resulting in limited forecasting accuracy and generalization ability. To address these challenges in wind power forecasting (WPF), a method that can comprehensively account for the characteristics of spatiotemporal interaction and the long- and short-term dependencies in the data is urgently needed. Therefore, an efficient WPF method combining a multiscale graph convolutional network (MSGCN) and an extended long short-term memory (xLSTM) is proposed, referred to as the MSGCN-xLSTM. First, an MSGCN is designed to extract the spatial characteristics of each node, obtaining feature information across multiple timescales through multiscale graph convolution (MSGC) operations, where the characteristics of nodes and their neighbors are weighted and fused. Second, the global feature enhancement mechanism is employed to adjust the characteristics extracted over different timescales, capturing long-distance global dependencies. Third, the improved xLSTM is applied to model wind power time series characterized by strong periodicity and multivariate dependence, enhancing the capturing of long- and short-term dependencies. Finally, an enhanced global exploration-whale optimization algorithm (EGE-WOA) is used to adaptively optimize the hyperparameters of the model, thereby improving its adaptability to complex wind power data. Furthermore, extensive experiments conducted on historical datasets from real wind farms demonstrate that the proposed method effectively captures the complex interactions and dynamic changes in spatiotemporal characteristics of wind power data. The proposed

关键词： Long short term memory Wind power generation Forecasting Accuracy Predictive models Adaptation models Spatiotemporal phenomena Data models Feature extraction Wind farms Extended long short-term memory (xLSTM) multiscale graph convolutional network (MSGCN) temporal and spatial characteristics whale optimization algorithm wind power forecasting (WPF)

来源：评论

学校读者我要写书评

暂无评论

Intelligent prediction of compressive strength of self-compacting concrete incorporating silica fume using hybrid IWOA-GPR model

引用

MATERIALS TODAY COMMUNICATIONS 2025年 45卷

作者： Yu, Yang Wang, Guangyin Huseien, Ghasan Fahim Zou, Zhen Ding, Zhenghao Zhang, Chunwei Shenyang Univ Technol Multidisciplinary Ctr Infrastruct Engn Sch Architecture & Civil Engn Shenyang 110870 Liaoning Peoples R China Natl Univ Singapore Sch Design & Environm Dept Built Environm Singapore 117566 Singapore Kyoto Univ Dept Civil & Earth Resources Engn Kyoto Japan

Self-compacting concrete (SCC) has been widely used due to its ability to fill complex molds without the need for mechanical vibration. However, the compressive strength of SCC is influenced by various factors, and traditional prediction methods often fail to provide accurate models. Gaussian process regression (GPR) demonstrates high accuracy when dealing with complex, high-dimensional data;however, the performance of the model is highly dependent on the selection of hyperparameters. To address these issues, this study proposes an improved whale optimization algorithm (IWOA) to optimize the hyperparameters of the GPR prediction model. Cement, water-tobinder ratio, silica fume (nano silica or/and micro silica), coarse aggregate, fine aggregate, superplasticizer, and viscosity-modifying agent are selected as inputs, with the 28-day compressive strength of SCC as the output. A nonlinear convergence factor is employed to enhance the global search capability, thereby improving the prediction accuracy and stability of the model. Finally, experimental data is used to compare the proposed method with various other prediction models, validating the superiority of the proposed approach. The results indicate that the IWOA-GPR model achieved a root mean squared error (RMSE) of 4.80 on the training set and 6.52 on the testing set, with a mean absolute error (MAE) of 3.05 and 4.67, respectively. The coefficient of determination (R2) on the testing set was 0.95, indicating excellent predictive performance. Compared to other models (BPNN, SVM, EDT, RF), the IWOA-GPR model demonstrated significant improvements in RMSE and MAE, with reductions of up to 25.77 % on the training set and 20.90 % on the testing set. Sensitivity analysis identified the water-to-binder ratio as the most critical factor (SHAP value = 8.2), followed by fine aggregate and cement content. These results validate the IWOA-GPR model as a robust tool for SCC strength prediction and mix optimization.

关键词： Self-compacting concrete Compressive strength whale optimization algorithm Gaussian process regression Sensitivity analysis

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：