检索结果-内蒙古大学图书馆

A Two-Stage Bayesian data-driven method to Improve Model Prediction

WATER RESOURCES RESEARCH 2021年第12期57卷 e2021WR030436-e2021WR030436页

作者： Sun, Xiaozhuo Zeng, Xiankui Wu, Jichun Wang, Dong Nanjing Univ Sch Earth Sci & Engn Key Lab Surficial Geochem Minist Educ Nanjing Peoples R China

Because of the earth system complexity, groundwater/hydrology models are always built with structural errors, which may lead to systematic errors in model predictions. Bayesian data-driven methods (DDMs) provide a feasible way to correct systematic model errors statistically. Generally, the physical and statistical model parameters, namely physical parameters and hyperparameters, are assumed to be independent and jointly calibrated. However, this assumption may be unreasonable and lead to over-adjusted parameter estimation and biased model prediction. This study proposes a two-stage DDM to calibrate physical parameters and hyperparameters separately, which does not make the independence assumption. Three case studies, including a groundwater solute transport analytical model, a three-dimensional groundwater flow model, and a real-world snowmelt runoff model, were used to evaluate the predictive performance of this two-stage DDM. Based on the three case studies, we found that the independence assumption of physical parameters and hyperparameters could lead to the over-fitting of parameter estimation and deviations in model predictions. Two-stage DDM can constrain the systematic error model calibration;that is, physical parameters are first calibrated in the entire hyperparameter prior probability space, and then hyperparameters are calibrated in the posterior probability space of physical parameters obtained previously. As a result, compared with traditional joint calibration-based DDM, two-stage DDM can alleviate parameter over-fitting and improve model predictive performance.

关键词： systematic error data-driven method gaussian process regression Bayesian inference model prediction

来源：评论

学校读者我要写书评

暂无评论

Thermal Runaway Diagnosis of Lithium-Ion Cells Using data-driven method

引用

APPLIED SCIENCES-BASEL 2024年第19期14卷 9107页

作者： Choi, Youngrok Park, Pangun Chungnam Natl Univ Dept Radio & Informat Commun Engn Daejeon 34134 South Korea

Fault diagnosis is crucial to guarantee safe operation and extend the operating time while preventing the thermal runaway of the lithium-ion battery. This study presents a data-driven thermal runaway diagnosis framework where Bayesian optimization techniques are applied to optimize the hyperparameter of various machine learning techniques. We use different machine learning models such as support vector machine, naive Bayes, decision tree ensemble, and multi-layer perceptron to estimate a high likelihood of causes of thermal runaway by using the experimental measurements of open-source battery failure data. We analyze different evaluation metrics, including the prediction accuracy, confusion metrics, and receiver operating characteristic curves of different models. An experimental evaluation shows that the classification accuracy of the decision tree ensemble outperforms that of other models. Furthermore, the decision tree ensemble provides robust prediction accuracy even with the strictly limited dataset.

关键词： lithium-ion battery thermal runaway data-driven method decision tree ensemble

来源：评论

学校读者我要写书评

暂无评论

Development of flow rate and equipment simulation model for commercial building HVAC&R system by data-driven method

引用

JOURNAL OF BUILDING ENGINEERING 2021年 44卷

作者： Kim, Hyemi Sumiyoshi, Daisuke Choi, Youngjin Kyushu Univ Grad Sch Human Environm Studies Fukuoka Japan Kyushu Univ Fac Human Environm Studies Fukuoka Japan Kyonggi Univ Dept Architectural Engn Suwon South Korea

This study proposes a new computational model in which HVAC&R (Heating, Ventilation, Air Conditioning, and Refrigeration) systems are automatically simulated using only data. Unlike the existing simulation method, it is possible to understand the power and performance of the device at each time by predicting the parameters based on the physics equation with the machine learning model and substituting the values back into the physics equation. We developed a flow model that predicts the load to be handled by each device and equipment models that calculate the device's performance. The model's performance was excellent, and the highest accuracy was obtained by sequentially inputting the input variables ranked using the Spearman correlation coefficient for both the flow rate and each equipment model. In the case of pumps, all five pumps satisfied CV(RMSE) of 30% in Cases 07 to 09, to which the Spearman correlation coefficient was applied. The CV(RMSE), due to the outlet temperature of the turbo chiller, heat exchanger, and heat storage tank, satisfies +/- 30%. This method overcomes the limitation of not reflecting the physical characteristics of devices in data-based modeling (black-box) of HVAC&R systems. Also, this reflects the current system status from data, and it could solve the limitations of the existing simulation method (white-box) that relied on design documents. As a result, it is possible to obtain reliable calculation results by reducing the modeler's subjective intervention. Because it is modeled on device units, it can also be used for fault detection and optimal operation control calculations inside the system.

关键词： data-driven method Gray-box method Automation simulation model Equipment performance model HVAC&R system simulation

来源：评论

学校读者我要写书评

暂无评论

The moving vibration source perception using bionic lateral line system and data-driven method

引用

OCEAN ENGINEERING 2022年 247卷 110463-110463页

作者： Wang, Mengmeng Jin, Bei Liu, Guijie Li, Zhixiong Ocean Univ China Dept Mech & Elect Engn Qingdao 266100 Peoples R China Ocean Univ China Key Lab Ocean Engn Shandong Prov Qingdao 266100 Peoples R China Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea

In recent years, the application scope of artificial lateral line sensor (ALLS) systems is mainly limited to the perception of water flow environment and dipole source. In order to expand the application scope, an ALLS based on a pressure sensor array is proposed in this work to recognize the shape and size parameters of moving vibration sources. First of all, the pressure sensor array is appropriately installed in the underwater vehicle with the help of sensor topology optimization. Then, a numerical simulation model of the ALLS is established and its validation is verified by experimental tests. Subsequently, the information of the moving vibration sources with different parameters is collected by the simulations and experiments to generate training data sets. Lastly, two typical data-driven methods (i.e., the random forest algorithm and support vector machine) are trained to identify the shape and size parameters of the moving vibration sources. The analysis results demonstrate that the developed ALLS is effective in vibration source perception, which enhances the function of underwater vehicles.

关键词： Autonomous underwater vehicle Bionic lateral lines Moving vibration source data-driven method

来源：评论

学校读者我要写书评

暂无评论

A data-driven method for optimal control of ship motions for safe crew transfer to offshore wind turbines

引用

APPLIED OCEAN RESEARCH 2019年 90卷 1页

作者： Farzanegan, Behzad Esmailian, Ehsan Menhaj, Mohammad Bagher Amirkabir Univ Technol Dept Elect Engn Tehran Iran Amirkabir Univ Technol Dept Maritime Engn Tehran Iran

Due to uncertainties and random behavior of sea loads, presenting an accurate hydrodynamic analysis for motion control of offshore ships is a big challenge. This paper aims to propose a novel method for motion control of a crew transfer vessel (CTV) in order to ensure safe crew transfer to an offshore wind turbine (OWT). For this purpose, we propose a novel neural network observer-based optimal control (NOPC) scheme to tackle unlcnown dynamics and disturbances, nonlinear effects, and non-symmetric control input saturation constraints. Accordingly, the neural network (NN) structure addresses the Hamilton-Jacobi-Bellman (HJB) equation and forms an optimal control signal remaining in the saturation bounds. The Lyapunov theory guarantees the Ultimately Uniformly Boundedness (UUB) of all signals of the closed-loop system. The high performance of the presented method is demonstrated in regular waves with high frequency in comparison with the previous studies. It is worth mentioning that there are not any limitations to implement the adopted strategy for other offshore applications.

关键词： data-driven method Optimal control system Motion control Neural networks Safe offshore operations Unknown dynamics

来源：评论

学校读者我要写书评

暂无评论

Prediction of remaining fatigue life of metal specimens using data-driven method based on acoustic emission signal

引用

APPLIED ACOUSTICS 2023年第1期211卷

作者： Li, Jialin Cao, Xuan Chen, Renxiang Zhao, Chengying Li, Yuxiong Huang, Xianzhen Chongqing Jiaotong Univ Chongqing Engn Lab Transportat Engn Applicat Robot Chongqing 400074 Peoples R China Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China

Aiming at the difficulty of predicting the remaining fatigue life of mechanical parts, a similar fatigue life prediction method based on acoustic emission signals is proposed considering the failure of vibration signals. Moreover, this paper innovatively introduces the temperature signal as a degradation feature to assist the acoustic emission signal feature for fatigue life prediction. The proposed fatigue life prediction method involves multiple processes such as feature extraction, feature smoothing, feature selection, feature compression and health index construction. A variational autoencoder structure combined with a long short-term memory neural network is used to achieve feature compression and retain feature trend. A tensile fatigue test bench was developed to collect the degradation signal from health to fatigue fracture to validate the proposed method. The validation results show that the proposed method can accurately predict the remaining fatigue life. In addition, the role of various data processing methods and the applicability of the proposed method in different working conditions are also discussed.

关键词： Fatigue life prediction Acoustic emission signal data-driven method Feature compression Temperature signal

来源：评论

学校读者我要写书评

暂无评论

Probabilistic solution of non-linear random ship roll motion by data-driven method

引用

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION 2024年 139卷

作者： Feng, Changshui Nie, Xinhui Hangzhou Dianzi Univ Sch Mech Engn Hangzhou 310018 Peoples R China

In this paper, a data-driven method is employed to investigate the probability density function (PDF) of nonlinear stochastic ship roll motion. The mathematical model of ship roll motion comprises a linear term with cubic damping and a nonlinear restoring moment represented as an odd-degree polynomial up to the fifth order. The data-driven method integrates maximum entropy, the pseudo-inverse algorithm, and a backpropagation (BP) neural network to obtain the PDF. The process begins with simulating data for the nonlinear stochastic system, followed by dimensional analysis to identify dimensionless parameter clusters. Optimization algorithms are then employed to solve for the coefficients, leading to the development of a BP neural network model trained to predict the PDF across various system characteristics and excitation intensities. The method's effectiveness is validated with Monte Carlo simulations, demonstrating high accuracy and reduced sensitivity to parameter variations.

关键词： Probability density function data-driven method Nonlinear systems BP neural network ship roll motion

来源：评论

学校读者我要写书评

暂无评论

A data-driven inspection method for identifying container bookings with concealed hazardous materials

引用

ENGINEERING OPTIMIZATION 2024年第9期56卷 1361-1381页

作者： Shen, Xiuyu Chen, Jingxu Zhu, Siying Yu, Xinlian Southeast Univ Sch Transportat Nanjing Peoples R China Singapore Univ Social Sci Sch Business Singapore Singapore

Hazardous materials (a.k.a. hazmats) are transported by containers with special equipment in transportation engineering but must be declared prior to shipment. Some shippers deliberately conceal hazmat information in their container bookings to gain a higher profit, which has potentially serious consequences. To reduce such risk, the inspection office selects a part of the containers for hazmat concealment inspection, but the efficiency is low. In this study, a data-driven inspection method is proposed for identifying container bookings with concealed hazmats by exploring the relationship between inspection results and items in the container booking information profile filled by shippers. A tailored cost-sensitive loss function is designed to address the class imbalance issue. The application of the proposed method is validated by case studies based on the hazmat inspection database from Ningbo Ocean Shipping Company. The findings provide instructive implications on the identification of subsequent container bookings that are of high interest for inspection.

关键词： Transportation engineering hazardous materials transport container booking concealment inspection data-driven method

来源：评论

学校读者我要写书评

暂无评论

A data-driven design method of distributed dynamic vibration absorber for broadband vibration suppression of thin-walled structures

引用

THIN-WALLED STRUCTURES 2023年第PartB期182卷

作者： Wu, Shaoqing Li, Hangxing Southeast Univ Dept Engn Mech Nanjing 211189 Jiangsu Peoples R China Southeast Univ Jiangsu Key Lab Engn Mech Nanjing 211189 Jiangsu Peoples R China

It is generally impractical to design Dynamic Vibration Absorbers (DVAs) according to each vibration mode for the vibration suppression of complex flexible structures due to the dense vibration modes. DVAs design according to the Excitation-Dependent Representative Basis (EDRB) derived in Li et al. (2021) allows one DVA to suppress the vibration response dominated by multiple closely-space modes, which broadens the application of the DVAs in vibration control. A data-driven method is developed based on EDRB to design the distributed DVAs for the broadband vibration suppression of thin-walled structures. Via the singular value decomposition on structural response data, both structural vibration modes and the EDRB can be obtained for well separated modes and closely-space modes, respectively. These derived structural vibration modes and EDRB will be regarded as the targeted "modes"and suppressed by the further designed distributed DVAs with one DVA per targeted "mode". The vibration suppression of a simply-supported plate subjected to a concentrated dynamic force is firstly investigated to verify the effectiveness of the proposed method. Then, the distributed DVAs design for the vibration suppression of a complex fairing structure subjected to distributed dynamic force is conducted to show the applicability of the proposed method on complex engineering structures. Results show that the proposed data-driven method has a similar vibration suppression effect to the method in Li et al. (2021), and a better performance than the traditional method proposed by Zhu et al. (2018).

关键词： data-driven method Excitation-Dependent Representative Basis Singular value decomposition Distributed DVAs design Broad band vibration suppression

来源：评论

学校读者我要写书评

暂无评论

Investment Model and its Multi-year Rolling Deduction Based on a data-driven method for Distribution Network

Investment Model and its Multi-year Rolling Deduction Based ...

引用

IEEE Asia Power and Energy Engineering Conference (APEEC)

作者： Wenliang Liu Yanxin Chai Yue Xiang Junyong Liu Xiaodong Shen State Grid Xiamen Electric Power Supply Company Xiamen China Department of Electrical Engineering Sichuan University Chengdu China

ISBN: (数字)9781728167824

ISBN: (纸本)9781728167831

With the access of large-scale clean energy, in the face of a lot of reconstruction strategies, the problems of complexity and poor convergence exist in the traditional investment planning optimization model which includes optimal power flow (OPF) and network safety constraint (NSC). Thus, an optimal investment decision model of distribution network (DN) is proposed based on the correlation constraint between reconstruction strategies and reliability which is obtained by a data-driven method, as well as the iteration calculation of reliability index. Based on the correlation, the multi-year investment model is established respectively aiming at maximizing the index and minimizing the total investment cost to obtain the optimal investment plans. Finally, an example is given to verify the rapidity, feasibility and effectiveness of the investment model.

关键词： multi-year investment model for distribution network data-driven method reconstruction strategy reliability Power grids Investments data driven reliability index DEDUCTION

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：