检索结果-内蒙古大学图书馆

State of health estimation for lithium-ion batteries based on Savitzky Golay filter and evolving Elman neural network

引用

IONICS 2025年第2期31卷 1423-1436页

作者： Zheng, Di Wei, Rongjian Guo, Xifeng Ning, Yi Zhang, Ye Shenyang Jianzhu Univ Sch Elect & Control Engn Shenyang 110168 Liaoning Peoples R China

The battery's health status is fundamental to battery health management. Accurately estimating the health status of lithium-ion batteries is crucial for ensuring their safe, reliable, and long-term operation. In this paper, a novel method for estimating the health state of lithium-ion batteries, which is based on grey relational analysis (GRA), Savitzky Golay (SG) filter, and Elman neural network enhanced by sparrow search algorithm (SSA). Firstly, multiple representative health features (HFs) are extracted from the charge and discharge curves. In order to reduce computational complexity, the GRA method is employed for feature analysis and screening, resulting in reasonable, highly relevant, and explanatory HFs. Secondly, to improve the correlation by reducing unstable factors in HF curves, SG filter is utilized for noise reduction and data smoothing, effectively mitigating the influence of data noise and short-term fluctuations resulting from capacity regeneration. Thirdly, in order to accurately estimate the state of health (SOH) of lithium-ion batteries, a SOH estimation model based on SSA-Elman neural network is proposed. The neural network characteristics are optimized to effectively mitigate the issue of Elman network being prone to local optima. Finally, the proposed method's effectiveness is validated by comparing it with several other methods using NASA dataset. The results show that the RMSE and MAE of the model are controlled within 0.0045 and 0.0038 respectively, and the R2 is maintained above 99.79%, which significantly improves the accuracy and reliability of SOH estimation.

关键词： Lithium-ion battery State of health estimation Grey relational analysis Savitzky Golay filter sparrow search algorithm Elman network

来源：评论

学校读者我要写书评

暂无评论

Rapid non-destructive identification of blueberry origin based on near infrared spectroscopy combined with wavelength selection

引用

INFRARED PHYSICS & TECHNOLOGY 2025年 145卷

作者： Wang, Guannan Wang, Na Dong, Ying Liu, Jinming Gao, Peng Hou, Rui Heilongjiang Bayi Agr Univ Coll Informat & Elect Engn Daqing 163319 Heilongjiang Peoples R China Guangdong Prov Key Lab Intelligent Port Secur Insp Guangzhou 510700 Peoples R China Huangpu Customs Technol Ctr Sanyuan Rd 66 Dongguan 523000 Peoples R China

To realize the nondestructive identification of blueberry origin, near-infrared spectroscopy was used to obtain the original spectral data of blueberry. Given the problems of spectral bandwidth, severe overlap, and complicated information analysis in the collection of near-infrared spectral data, we integrated successive projection algorithm (SPA) and sparrow search algorithm (SSA) with partial least squares regression (PLS) and support vector machine (SVM), respectively, resulting in the construction of two wavelength selection (WS) models: SPAPLS and SSA-SVM for WS from blueberry spectral data, 30 and 148 wavelength variables were selected respectively. To further enhance the accuracy of blueberry origin identification, we incorporated SSA into both Optimal Latin hypercube idea and Osprey algorithm, creating a multi-strategy hybrid sparrow search algorithm (ZOSSA). This approach reduced the number of selected wavelengths from 148 to 36. Using wavelengths selected from three different techniques as input subsets, a blueberry origin recognition model is constructed by placing them separately into a support vector machine. The experimental results prove that the performance of the wavelength-optimized model is higher than that of the full spectra performance, and the wavelength variables screened by ZOSSA have the best effect. The wavelength variables identified by ZOSSA exhibit superior performance with an accuracy rate of 96.21%, precision rate of 95.12 %, recall rate of 94.78 %, and F1 score of 94.94 % on the test set;surpassing those obtained using SPA (89.39 %, 87.43 %, 88.72 %, and 88.08 %) as well as SSA (90.15 %, 87.90 %, 88.16 %, and 88.02 %). The method strikes a balance between selecting an appropriate number of wavelengths while maintaining high model performance levels;thus meeting requirements for fast, accurate, nondestructive origin identification not only for blueberries but also providing novel insights for identifying origins in other agricultural

关键词： Near-infrared spectroscopy Blueberry sparrow search algorithm Wavelength selection Origin identification Successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

COMPUTER-AIDED DISEASE CLASSIFICATION BASED ON KPLSKELM algorithm

引用

JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY 2025年第2期25卷

作者： Dou, Yifeng Liu, Jiantao Tianjin Med Univ Tianjin Baodi Hosp Baodi Hosp Tianjin 301800 Peoples R China

Objective: This study aims to explore the use of machine learning algorithms for predicting disease classification. Methods: An integrated algorithm (KPLSKELM) was proposed in this study. The algorithm employed kernel principal component analysis to transform the original data into a high-dimensional feature space, thereby enhancing its linear separability. It used the sparrow search algorithm (SSA) to optimize the weight matrix and parameters of the kernel extreme learning machine (KELM). The algorithm incorporated a Gaussian perturbation search mechanism to refine the population initialization strategy so as to mitigate the issues of poor convergence rate and susceptibility to local optima in the later SSA iterations. L & eacute;vy flight perturbations were introduced during the foraging search process of the sparrow population to guide the population in moving appropriate step sizes, thereby increasing the diversity of the spatial search. The proposed method was experimentally validated using a binary classification breast cancer dataset collected by Dr. William H. Wolberg from a Wisconsin hospital in the United States and a multiclass classification dataset of electrocardiographic recordings during childbirth. Multiple metrics were adopted to evaluate the classification performance. Results: The accuracy and F1_score of the KELM model remained relatively low across different percentages of the training set, although a recall of 1.0000 was consistently achieved. Both the SSA-improved KELM and the L & eacute;vy-improved SSA-optimized KELM algorithms exhibited better performance in terms of the comprehensive metric F1_score and improved with the increase in the percentage of the training set. The KPLSKELM model outperformed others in all metrics, with accuracy, precision, recall, and F1_score approaching or reaching the highest levels when using 90% of the training set. Conclusions: The proposed method demonstrated excellent performance in various disease predictio

关键词： Breast cancer disease kernel extreme learning machine kernel principal component analysis prediction sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Hosting Capacity Assessment of Distribution Networks Considering Source-Load Uncertainty

引用

ENERGIES 2025年第8期18卷 2134-2134页

作者： Chen, Chao Peng, Weifeng Xie, Cheng Dong, Shufeng Hua, Yibo State Grid Zhejiang Elect Power Co Ltd Elect Power Sci Res Inst Hangzhou 310014 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China

With the continuous expansion of distributed photovoltaic (PV) integration, the hosting capacity of distribution networks has become a critical issue in power system planning and operation. Under varying meteorological and load fluctuation conditions, traditional assessment methods often face adaptability and uncertainty handling challenges. To enhance the practical applicability and accuracy of hosting capacity evaluations, this paper proposes a PV hosting capacity assessment model that incorporates source-load uncertainty and constructs an alternative scenario optimization evaluation framework driven by target-oriented scenario generation. The model considers system constraints and employs the sparrow search algorithm (SSA) to optimize the maximum PV hosting capacity. On the source side, PV output scenarios with temporal characteristics are generated based on the mapping relationship between meteorological factors and PV power. On the load side, historical data are employed to extract fluctuation ranges and to introduce random perturbations to simulate load uncertainty. In addition, a PV power scenario generation method based on the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is proposed, integrating physical-data dual-driven strategies to enhance the physical consistency of generated data, while incorporating a target-driven weighted sampling mechanism to improve its learning ability for key features. Case studies verify that the proposed method demonstrates strong adaptability and accuracy under varying meteorological and load conditions.

关键词： hosting capacity assessment scenario generation sparrow search algorithm source-load uncertainty WGAN-GP

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional ship motion attitude combination prediction based on the SSA-BiGRU-Attention model

引用

MEASUREMENT 2025年 253卷

作者： Li, Panpan Wang, Qinfeng Chen, Ning Tu, Yongqiang Lin, Xiaochuan Chen, Yiming Jimei Univ Coll Marine Equipment & Mech Engn Xiamen 361021 Peoples R China

Ship motion attitude prediction is a key link in improving ship navigation safety and maritime operation efficiency. However, ship motion has non-stationary and nonlinear characteristics, and is affected by a variety of complex factors, resulting in low accuracy of existing prediction methods, which is difficult to meet actual needs. To address this problem, this paper proposes an integrated model (SSA-BiGRU-Attention) that combines the sparrow search algorithm (SSA), the Bidirectional Gated Recurrent Unit (BiGRU) and the improved Attention Mechanism. After comparing and analyzing multiple models, the BiGRU model is selected as the basis for constructing an integrated prediction model. In the SSA-BiGRU-Attention model, the BiGRU network captures the basic characteristics of ship motion time series. Then, an improved attention mechanism is used to analyze the interaction between different degrees of freedom and time series data, which can assign higher weights to important features while reducing the interference of less important features on the prediction results. In addition, the sparrow search algorithm is used to optimize the hyperparameters of the integrated model to improve the efficiency of model parameter settings. The experimental results present that the minimum Root Mean Square Errors (RMSEs) of the integrated model for predicting roll, pitch, and heave can reach 0.06411, 0.05434, and 0.01159, which are reduced by 32 %, 18 %, and 10 %, respectively, compared with the single model.

关键词： Bidirectional gated recurrent unit Improved attention mechanism sparrow search algorithm Ship motion attitude combination prediction

来源：评论

学校读者我要写书评

暂无评论

Investigation on the long short-term memory-based models for rural heating load prediction in Northeast China

引用

ENERGY 2025年 318卷

作者： Dong, Shengming Liu, Tong Hu, Xiaowei Zhang, Chen Hu, Pengli Zhuang, Wenhui Liu, Qiyou Tianjin Univ Commerce Tianjin 300134 Peoples R China Hebei Hangyan Refrigerat Equipment CO Ltd Shijiazhuang Peoples R China

Accurate and rapid prediction of rural heating load holds considerable significance for planning heating schemes and control strategies. However, the complex variation characteristics pose a significant challenge to it. Herein, based on the long-term monitoring of the indoor and outdoor parameters of 7 typical rural buildings in Northeast China, long short-term memory, convolutional neural network-long short-term memory, and sparrow search algorithm-convolutional neural network-long short-term memory models were comparatively and progressively investigated to explore their performances of the rural heating load prediction. The results indicate that input variables, including indoor and outdoor temperature, solar radiation intensity, carbon dioxide concentration and wind speed have endowed the models with optimal performances. Furthermore, it revealed that the adoption of convolutional neural network has reduced the standard deviation of the prediction relative errors by 29.53 %, indicating that spatial features of the rural heating data were crucial. Furthermore, by applying the sparrow search algorithm to the determination of the hyperparameters, root mean square error, mean absolute percentage error and standard deviation were further reduced by 17.46 %, 24.09 %, and 30.5 %, respectively. Therefore, the sparrow search algorithm-convolutional neural network-long short-term memory model was proven to be effective for rural heating load rapid prediction.

关键词： Rural heating load prediction Convolutional neural network Long short-term memory sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved Gaussian mixture model and Gaussian mixture regression for learning from demonstration based on Gaussian noise scattering

引用

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Feng, Chunhua Liu, Zhuang Li, Weidong Lu, Xin Jing, Yanguo Ma, Yongsheng Univ Shanghai Sci & Technol Sch Mech Engn Shanghai Peoples R China Leeds Trinity Univ Sch Comp Sci Leeds England Southern Univ Sci & Technol Dept Mech & Energy Engn Shenzhen Peoples R China

Learning from Demonstration (LfD) is an effectual approach for robots to acquire new skills by implementing intuitive learning through imitating human demonstration. As one of the mainstream learning models for LfD, Gaussian mixture modeling (GMM) and Gaussian mixture regression (GMR) exhibit the advantages of ease of use and robust learning capabilities. To further improve the learning and regression performance of GMM/GMR, in this paper, improved GMM/GMR based on a Gaussian noise scattering strategy is designed. The main contributions of this study include: 1) the Gaussian noise scattering strategy is developed to eliminate the requirement of creating multiple demonstrations and overcome the jitter and sharp-turning defects of the demonstration;2) based on a new evaluation criterion IBF and the sparrow search algorithm (SSA), GMM/GMR is optimized to achieve the balance of feature retention of the demonstration and the smoothness of the reproduced solution. Experimental results show that with the Gaussian noise scattering strategy, the geometric similarity of the reproduced solution and the demonstration increased for approximately 33.16 %, and the smoothness improved for 19.83 %. The challenges of underfitting and overfitting in GMM/GMR were effectively mitigated after incorporating the evaluation criterion IBF and leveraging SSA. This demonstrates the potential applicability of the improved GMM/GMR in practical industrial scenarios.

关键词： Learning from demonstration Gaussian Mixture Modeling Gaussian Mixture Regression sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Stress analysis and optimization of QFN solder joints under bending-torsion coupled conditions based on the SSA

引用

MICROELECTRONICS JOURNAL 2025年 159卷

作者： Wei, Jisheng Huang, Chunyue Gao, Chao Wang, Gui Guilin Univ Elect Technol Sch Mech & Elect Engn Guilin 541004 Peoples R China

A 3D finite element model of QFN (Quad Flat No-Lead Package) solder joints was established for stress-strain analysis under bending-torsion coupled loading. The accuracy of the finite element simulation was validated through bending-torsion coupled strain measurement experiments. The effects of pad length, pad width, solder joint standoff height, and PCB (Printed Circuit Board) thickness on bending-torsion coupled stress-strain behavior were analyzed using univariate and correlation analysis. To minimize stress, these parameters were optimized using the response surface-sparrow search algorithm (SSA). Results show a weakly positive correlation for pad length, strong negative correlations for pad width and standoff height, and a strong positive correlation for PCB thickness. The optimal parameters-pad length 0.66 mm, pad width 0.25 mm, solder joint standoff height 0.09 mm, and PCB thickness 1.2 mm-reduced maximum stress by 10.8 MPa. The research findings provide theoretical guidance for reducing the bending-torsion coupled stress of QFN solder joints.

关键词： QFN solder joints Bending-torsion coupling Structural parameters optimization Univariate analysis sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive fuzzy tracking control for vibration suppression of a cable-driven parallel hoisting robot

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2025年 226卷

作者： Li, Sipan Zhou, Bin Zi, Bin Zhu, Weidong Hefei Univ Technol Sch Mech Engn 193 Tunxi Rd Hefei 230009 Peoples R China Xidian Univ Sch Mechanoelect Engn Xian 710071 Peoples R China Xidian Univ State Key Lab Electromech Integrated Mfg High Perf Xian 710071 Peoples R China Univ Maryland Baltimore Cty Dept Mech Engn 1000 Hilltop Circle Baltimore MD 21250 USA

In practical engineering applications, most of the system parameters required for controlling cable-driven parallel hoisting robot (CDPHR) are unobtainable with precision. Additionally, when operating under various environmental conditions, the CDPHR is often disturbed by external unknown damping. These factors render the payload vibration suppression control during the motion of the CDPHR a challenging problem. Currently, there are few control methods that simultaneously consider both aforementioned factors, and the control effectiveness in practical applications is often unsatisfactory. To address the above issues, an adaptive fuzzy tracking control method is proposed in this paper, which comprises an adaptive controller and an improved fuzzy controller. In the design of the adaptive controller, by isolating unknown system parameters and elaborately designing parameter update law, the effectively estimation for changes in system parameters is achieved. This also helps the system in better adapting to external damping disturbances. Furthermore, an adaptive sine-following sparrow search algorithm (ASFSSA) is proposed to improve the fuzzy controller by optimizing its quantization and scale factors. The improved fuzzy controller is used to adjust the gain parameters of the adaptive controller online according to changes in the system state, thereby further enhancing the robustness of system and better suppressing external disturbances. The simulation and experimental results demonstrate that the higher positioning accuracy and faster payload vibration suppression can be achieved by the proposed control method compared to other existing control methods. Furthermore, the robustness and effectiveness are also experimentally validated.

关键词： Cable-driven parallel hoisting robots Rotational motion Vibration suppression Adaptive fuzzy tracking control sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Construction of teaching game evaluation model based on ISSA-BPNN

引用

ENTERTAINMENT COMPUTING 2025年 52卷

作者： Feng, Bibo Zhang, Lingli Yin, Jing Wang, Rong Chongqing Univ Technol Coll Comp Sci & Engn Chongqing 400054 Peoples R China Chongqing Univ Technol Sch Foreign Languages Chongqing 400054 Peoples R China

Teaching games are an effective teaching organization activity. In response to the evaluation and prediction problem of teaching games, a teaching game evaluation model based on improved sparrow search algorithm and back propagation neural network was studied and constructed. Firstly, a situational teaching game was designed and an evaluation index system was constructed. Then, a teaching game evaluation prediction model based on the improved method was established. Finally, the expert consultation method is adopted to collect opinions from experts in the field of education and construct an evaluation index system for teaching games. And based on the evaluation index system of teaching games, evaluate students' mathematical thinking ability before and after experiencing teaching games to verify the application effect of teaching games. The scenario based teaching game designed in this study has a certain effect on improving students' mathematical thinking ability. Students' mathematical thinking has significantly improved (P<0.05), and the teaching effect is the same for students of different genders (P>0.1). The improved sparrow search algorithm has a faster convergence rate than other algorithms, and tends to be stable when iteration is about 100 when solving the single peak benchmark function. When solving the multimodal benchmark test function, it tends to stabilize when iteration is around 20. The teaching game evaluation prediction price model based on the improved method shows a trend of first increasing and then decreasing with hidden units increasing. When the hidden unit is 16, the area index under model curve is the highest, around 0.962, and its prediction accuracy is relatively high. In summary, the model constructed in this study is applicating good in teaching game evaluation prediction, and can promote education industry developing.

关键词： sparrow search algorithm Back propagation neural network Teaching games Evaluating indicator

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：