资源类型

期刊论文 428

会议视频 4

年份

2023 69

2022 73

2021 44

2020 44

2019 29

2018 22

2017 27

2016 11

2015 16

2014 11

2013 4

2012 5

2011 4

2010 6

2009 8

2008 9

2007 8

2006 4

2005 5

2004 3

展开 ︾

关键词

机器学习 27

深度学习 15

人工智能 12

参数估计 3

代理模型 2

优化 2

工艺参数 2

强化学习 2

材料设计 2

结构健康监测 2

计算机视觉 2

高层建筑 2

1)幂模型 1

2D—3D配准 1

2R-1C模型；嵌入式系统；参数估计；非迭代方法；二次型 1

3D打印 1

6G 1

ARM 1

BP神经网络 1

展开 ︾

检索范围：

排序： 展示方式：

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

《机械工程前沿（英文）》 2022年 第17卷 第2期 doi: 10.1007/s11465-022-0673-7

摘要： Convolutional neural network (CNN) has achieved remarkable applications in fault diagnosis. However, the tuning aiming at obtaining the well-trained CNN model is mainly manual search. Tuning requires considerable experiences on the knowledge on CNN training and fault diagnosis, and is always time consuming and labor intensive, making the automatic hyper parameter optimization (HPO) of CNN models essential. To solve this problem, this paper proposes a novel automatic CNN (ACNN) for fault diagnosis, which can automatically tune its three key hyper parameters, namely, learning rate, batch size, and L2-regulation. First, a new deep reinforcement learning (DRL) is developed, and it constructs an agent aiming at controlling these three hyper parameters along with the training of CNN models online. Second, a new structure of DRL is designed by combining deep deterministic policy gradient and long short-term memory, which takes the training loss of CNN models as its input and can output the adjustment on these three hyper parameters. Third, a new training method for ACNN is designed to enhance its stability. Two famous bearing datasets are selected to evaluate the performance of ACNN. It is compared with four commonly used HPO methods, namely, random search, Bayesian optimization, tree Parzen estimator, and sequential model-based algorithm configuration. ACNN is also compared with other published machine learning (ML) and deep learning (DL) methods. The results show that ACNN outperforms these HPO and ML/DL methods, validating its potential in fault diagnosis.

关键词： deep reinforcement learning     hyper parameter optimization     convolutional neural network     fault diagnosis    

HTML PDF 收藏

Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD, Wen-Jing GU

《结构与土木工程前沿（英文）》 2021年 第15卷 第2期   页码 490-505 doi: 10.1007/s11709-020-0669-5

摘要： This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( ), precision, recall, , and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models’ performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.

关键词： seismic soil liquefaction     Bayesian belief network     cone penetration test     parameter learning     structural learning    

HTML PDF 收藏

在非对称大规模MIMO系统中基于集成—迁移学习的信道参数预测 Research Article

何遵文1,李悦1,张焱1,张万成1,张恺恩1,郭柳1,王海明2

《信息与电子工程前沿（英文）》 2023年 第24卷 第2期   页码 275-288 doi: 10.1631/FITEE.2200169

摘要： 近年来，多智能体深度强化学习（multi-agent deep 为降低第六代移动网络中的数据处理负担和硬件成本，非对称大规模多入多出（multiple-input multiple-output，MIMO）系统被提出。然而，在非对称大规模MIMO系统中，上行和下行无线信道之间的互易性是无效的。因此，需要基站和用户设备都发送导频来预测双向信道，这会消耗更多传输和计算资源。本文提出一种基于集成迁移学习的非对称大规模MIMO系统的信道参数预测方法，可以预测多个下行信道参数，包括路径损耗、多径数、时延扩展和角度扩展。选择上行信道参数和环境特征来预测下行参数。此外，提出一种基于SHAP（SHapley Additive exPlanations）值和最小描述长度标准的两步特征选择算法，以降低由弱相关或不相关特征引起的计算复杂度和对模型准确性的负面影响。引入实例迁移方法，以支持预测模型应对在新的传播条件下难以在短时间内收集足够训练数据的问题。仿真结果表明，该方法比反向传播神经网络和3GPP TR 38.901信道模型更准确。当波束宽度或通信扇区发生变化时，所提出的基于实例迁移的方法在预测下行参数方面优于没有迁移学习的方法。

关键词： 非对称大规模MIMO系统；信道模型；集成学习；实例迁移；参数预测    

HTML PDF 收藏

Processing parameter optimization of fiber laser beam welding using an ensemble of metamodels and MOABC

《机械工程前沿（英文）》 2022年 第17卷 第4期 doi: 10.1007/s11465-022-0703-5

摘要： In fiber laser beam welding (LBW), the selection of optimal processing parameters is challenging and plays a key role in improving the bead geometry and welding quality. This study proposes a multi-objective optimization framework by combining an ensemble of metamodels (EMs) with the multi-objective artificial bee colony algorithm (MOABC) to identify the optimal welding parameters. An inverse proportional weighting method that considers the leave-one-out prediction error is presented to construct EM, which incorporates the competitive strengths of three metamodels. EM constructs the correlation between processing parameters (laser power, welding speed, and distance defocus) and bead geometries (bead width, depth of penetration, neck width, and neck depth) with average errors of 10.95%, 7.04%, 7.63%, and 8.62%, respectively. On the basis of EM, MOABC is employed to approximate the Pareto front, and verification experiments show that the relative errors are less than 14.67%. Furthermore, the main effect and the interaction effect of processing parameters on bead geometries are studied. Results demonstrate that the proposed EM-MOABC is effective in guiding actual fiber LBW applications.

关键词： laser beam welding     parameter optimization     metamodel     multi-objective    

HTML PDF 收藏

Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach

Pijush Samui, Jagan J

《结构与土木工程前沿（英文）》 2013年 第7卷 第2期   页码 133-136 doi: 10.1007/s11709-013-0202-1

摘要： This article examines the capability of Gaussian process regression (GPR) for prediction of effective stress parameter ( ) of unsaturated soil. GPR method proceeds by parameterising a covariance function, and then infers the parameters given the data set. Input variables of GPR are net confining pressure ( ), saturated volumetric water content ( ), residual water content ( ), bubbling pressure ( ), suction ( ) and fitting parameter ( ). A comparative study has been carried out between the developed GPR and Artificial Neural Network (ANN) models. A sensitivity analysis has been done to determine the effect of each input parameter on . The developed GPR gives the variance of predicted . The results show that the developed GPR is reliable model for prediction of of unsaturated soil.

关键词： unsaturated soil     effective stress parameter     Gaussian process regression (GPR)     artificial neural network (ANN)     variance    

HTML PDF 收藏

1000 MW ultra-supercritical turbine steam parameter optimization

FENG Weizhong

《能源前沿（英文）》 2008年 第2卷 第2期   页码 187-193 doi: 10.1007/s11708-008-0030-5

摘要： The 2 × 1000 MW ultra-supercritical steam turbine of Shanghai Waigaoqiao Phase III project, which uses grid frequency regulation and overload control through an overload valve, is manufactured by Shanghai Turbine Company using Siemens technology. Through optimization, the steam pressure is regarded as the criterion between constant pressure and sliding pressure operation. At high circulating water temperature, the turbine overload valve is kept closed when the unit load is lower than 1000 MW while at other circulating water temperatures the turbine can run in sliding pressure operation when the unit load is higher than 1000 MW and the pressure is lower than 27 MPa This increases the unit operation efficiency. The 3D bending technology in the critical piping helps to reduce the project investment and minimize the reheat system pressure drop which improves the unit operation efficiency and safety. By choosing lower circulating water design temperature and by setting the individual Boiler Feedwater Turbine condenser to reduce the exhaust steam flow and the heat load to the main condenser, the unit average back pressure and the terminal temperature difference are minimized. Therefore, the unit heat efficiency is increased.
HTML PDF 收藏

Structural parameter design method for a fast-steering mirror based on a closed-loop bandwidth

Guozhen CHEN, Pinkuan LIU, Han DING

《机械工程前沿（英文）》 2020年 第15卷 第1期   页码 55-65 doi: 10.1007/s11465-019-0545-y

摘要： When a fast-steering mirror (FSM) system is designed, satisfying the performance requirements before fabrication and assembly is vital. This study proposes a structural parameter design approach for an FSM system based on the quantitative analysis of the required closed-loop bandwidth. First, the open-loop transfer function of the FSM system is derived. In accordance with the transfer function, the notch filter and proportional-integral (PI) feedback controller are designed as a closed-loop controller. The gains of the PI controller are determined by maximizing the closed-loop bandwidth while ensuring the robustness of the system. Then, the two unknown variables of rotational radius and stiffness in the open-loop transfer function are optimized, considering the bandwidth as a constraint condition. Finally, the structural parameters of the stage are determined on the basis of the optimized results of rotational radius and stiffness. Simulations are conducted to verify the theoretical analysis. A prototype of the FSM system is fabricated, and corresponding experimental tests are conducted. Experimental results indicate that the bandwidth of the proposed FSM system is 117.6 Hz, which satisfies the minimum bandwidth requirement of 100 Hz.

关键词： fast-steering mirror     structural parameter     PI controller     bandwidth     notch filter    

HTML PDF 收藏

Energy efficient cutting parameter optimization

Xingzheng CHEN, Congbo LI, Ying TANG, Li LI, Hongcheng LI

《机械工程前沿（英文）》 2021年 第16卷 第2期   页码 221-248 doi: 10.1007/s11465-020-0627-x

摘要： Mechanical manufacturing industry consumes substantial energy with low energy efficiency. Increasing pressures from energy price and environmental directive force mechanical manufacturing industries to implement energy efficient technologies for reducing energy consumption and improving energy efficiency of their machining processes. In a practical machining process, cutting parameters are vital variables set by manufacturers in accordance with machining requirements of workpiece and machining condition. Proper selection of cutting parameters with energy consideration can effectively reduce energy consumption and improve energy efficiency of the machining process. Over the past 10 years, many researchers have been engaged in energy efficient cutting parameter optimization, and a large amount of literature have been published. This paper conducts a comprehensive literature review of current studies on energy efficient cutting parameter optimization to fully understand the recent advances in this research area. The energy consumption characteristics of machining process are analyzed by decomposing total energy consumption into electrical energy consumption of machine tool and embodied energy of cutting tool and cutting fluid. Current studies on energy efficient cutting parameter optimization by using experimental design method and energy models are reviewed in a comprehensive manner. Combined with the current status, future research directions of energy efficient cutting parameter optimization are presented.

关键词： energy efficiency     cutting parameter     optimization     machining process    

HTML PDF 收藏

Hierarchical parameter estimation of DFIG and drive train system in a wind turbine generator

Xueping PAN, Ping JU, Feng WU, Yuqing JIN

《机械工程前沿（英文）》 2017年 第12卷 第3期   页码 367-376 doi: 10.1007/s11465-017-0429-y

摘要：

A new hierarchical parameter estimation method for doubly fed induction generator (DFIG) and drive train system in a wind turbine generator (WTG) is proposed in this paper. Firstly, the parameters of the DFIG and the drive train are estimated locally under different types of disturbances. Secondly, a coordination estimation method is further applied to identify the parameters of the DFIG and the drive train simultaneously with the purpose of attaining the global optimal estimation results. The main benefit of the proposed scheme is the improved estimation accuracy. Estimation results confirm the applicability of the proposed estimation technique.

关键词： wind turbine generator     DFIG     drive train system     hierarchical parameter estimation method     trajectory sensitivity technique    

HTML PDF 收藏

Variational mode decomposition based modal parameter identification in civil engineering

Mingjie ZHANG, Fuyou XU

《结构与土木工程前沿（英文）》 2019年 第13卷 第5期   页码 1082-1094 doi: 10.1007/s11709-019-0537-3

摘要： An out-put only modal parameter identification method based on variational mode decomposition (VMD) is developed for civil structure identifications. The recently developed VMD technique is utilized to decompose the free decay response (FDR) of a structure into to modal responses. A novel procedure is developed to calculate the instantaneous modal frequencies and instantaneous modal damping ratios. The proposed identification method can straightforwardly extract the mode shape vectors using the modal responses extracted from the FDRs at all available sensors on the structure. A series of numerical and experimental case studies are conducted to demonstrate the efficiency and highlight the superiority of the proposed method in modal parameter identification using both free vibration and ambient vibration data. The results of the present method are compared with those of the empirical mode decomposition-based method, and the superiorities of the present method are verified. The proposed method is proved to be efficient and accurate in modal parameter identification for both linear and nonlinear civil structures, including structures with closely spaced modes, sudden modal parameter variation, and amplitude-dependent modal parameters, etc.

关键词： modal parameter identification     variational mode decomposition     civil structure     nonlinear system     closely spaced modes    

HTML PDF 收藏

Shallow foundation response variability due to soil and model parameter uncertainty

Prishati RAYCHOWDHURY,Sumit JINDAL

《结构与土木工程前沿（英文）》 2014年 第8卷 第3期   页码 237-251 doi: 10.1007/s11709-014-0242-1

摘要： Geotechnical uncertainties may play crucial role in response prediction of a structure with substantial soil-foundation-structure-interaction (SFSI) effects. Since the behavior of a soil-foundation system may significantly alter the response of the structure supported by it, and consequently several design decisions, it is extremely important to identify and characterize the relevant parameters. Moreover, the modeling approach and the parameters required for the modeling are also critically important for the response prediction. The present work intends to investigate the effect of soil and model parameter uncertainty on the response of shallow foundation-structure systems resting on dry dense sand. The SFSI is modeled using a beam-on-nonlinear-winkler-foundation (BNWF) concept, where soil beneath the foundation is assumed to be an assembly of discrete, nonlinear elements composed of springs, dashpots and gap elements. The sensitivity of both soil and model input parameters on shallow foundation responses are investigated using first-order second-moment (FOSM) analysis and Monte Carlo simulation through Latin hypercube sampling technique. It has been observed that the degree of accuracy in predicting the responses of the shallow foundation is highly sensitive soil parameters, such as friction angle, Poisson’s ratio and shear modulus, rather than model parameters, such as stiffness intensity ratio and spring spacing; indicating the importance of proper characterization of soil parameters for reliable soil-foundation response analysis.

关键词： shallow foun dation     sensitivity analysis     centrifuge data     first-order-second-moment (FOSM) method     parameter uncertainty    

HTML PDF 收藏

Parameter studies on impact in a lap joint

Amir M. RAHMANI,Elizabeth K. ERVIN

《机械工程前沿（英文）》 2015年 第10卷 第1期   页码 64-77 doi: 10.1007/s11465-014-0322-x

摘要：

To represent a loose lap joint, a beam impacting four springs with gaps is modeled. Modal analysis with base excitation is solved, and time histories of contact points are closely monitored. Using the impulse during steady state response, six influential parameters are studied: damping ratio, contact stiffness, intermediate contact position, gap, excitation amplitude and beam height. For all parameters, the system response is highly controlled by modes with two contacting springs. Each parameter’s effect on system response is presented including unstable regions, unique trend behaviours result. Recommendations for structural designers are also noted.

关键词： impact mechanics     contact     joint behaviour     modal analysis     parameter study    

HTML PDF 收藏

Performance design of a cryogenic air separation unit for variable working conditions using the lumped parameter

Jinghua XU, Tiantian WANG, Qianyong CHEN, Shuyou ZHANG, Jianrong TAN

《机械工程前沿（英文）》 2020年 第15卷 第1期   页码 24-42 doi: 10.1007/s11465-019-0558-6

摘要： Large-scale cryogenic air separation units (ASUs), which are widely used in global petrochemical and semiconductor industries, are being developed with high operating elasticity under variable working conditions. Different from discrete processes in traditional machinery manufacturing, the ASU process is continuous and involves the compression, adsorption, cooling, condensation, liquefaction, evaporation, and distillation of multiple streams. This feature indicates that thousands of technical parameters in adsorption, heat transfer, and distillation processes are correlated and merged into a large-scale complex system. A lumped parameter model (LPM) of ASU is proposed by lumping the main factors together and simplifying the secondary ones to achieve accurate and fast performance design. On the basis of material and energy conservation laws, the piecewise-lumped parameters are extracted under variable working conditions by using LPM. Takagi–Sugeno (T–S) fuzzy interval detection is recursively utilized to determine whether the critical point is detected or not by using different thresholds. Compared with the traditional method, LPM is particularly suitable for “rough first then precise” modeling by expanding the feasible domain using fuzzy intervals. With LPM, the performance of the air compressor, molecular sieve adsorber, turbo expander, main plate-fin heat exchangers, and packing column of a 100000 Nm O /h large-scale ASU is enhanced to adapt to variable working conditions. The designed value of net power consumption per unit of oxygen production (kW/(Nm O )) is reduced by 6.45%.

关键词： performance design     air separation unit (ASU)     lumped parameter model (LPM)     variable working conditions     T–S fuzzy interval detection    

HTML PDF 收藏

Stress-strain relationship with soil structural parameter of collapse loess

SHAO Shengjun, YU Qinggao, LONG Jiyong

《结构与土木工程前沿（英文）》 2008年 第2卷 第3期   页码 293-293 doi: 10.1007/s11709-008-0100-0

HTML PDF 收藏

Predictor-corrector algorithm for solving quasi-separated-flow and transient distributed-parameter model

Ping ZHANG, Guoliang DING

《能源前沿（英文）》 2010年 第4卷 第4期   页码 535-541 doi: 10.1007/s11708-010-0113-y

摘要： The successive sub?stitution (SS) method is a suitable approach to solving the transient distributed-parameter model for heat exchangers. However, this method must be enhanced because its convergence heavily depends on the iterative initial pressure. When the iterative initial pressure is improperly assigned, the calculated flow rates become negative values, causing the state parameters to exhibit negative values as well. Therefore, a predictor-corrector algorithm (PCA) is proposed to improve the convergence of the SS method. A predictor is developed to determine an appropriate iterative initial pressure. Total fluid mass is adopted as the convergence criterion of pressure iteration instead of outlet flow rate as is done in the SS method. Convergence analysis and case study of the PCA and SS method are conducted, which show that the PCA has better convergence than the SS method under the same working conditions.

关键词： algorithm     convergence     heat exchanger     modeling     transient    

HTML PDF 收藏

标题 作者 时间 类型 操作

A new automatic convolutional neural network based on deep reinforcement learning for fault diagnosis

期刊论文

Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD, Wen-Jing GU

期刊论文

在非对称大规模MIMO系统中基于集成—迁移学习的信道参数预测

何遵文1,李悦1,张焱1,张万成1,张恺恩1,郭柳1,王海明2

期刊论文

Processing parameter optimization of fiber laser beam welding using an ensemble of metamodels and MOABC

期刊论文

Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach

Pijush Samui, Jagan J

期刊论文

1000 MW ultra-supercritical turbine steam parameter optimization

FENG Weizhong

期刊论文

Structural parameter design method for a fast-steering mirror based on a closed-loop bandwidth

Guozhen CHEN, Pinkuan LIU, Han DING

期刊论文

Energy efficient cutting parameter optimization

Xingzheng CHEN, Congbo LI, Ying TANG, Li LI, Hongcheng LI

期刊论文

Hierarchical parameter estimation of DFIG and drive train system in a wind turbine generator

Xueping PAN, Ping JU, Feng WU, Yuqing JIN

期刊论文

Variational mode decomposition based modal parameter identification in civil engineering

Mingjie ZHANG, Fuyou XU

期刊论文

Shallow foundation response variability due to soil and model parameter uncertainty

Prishati RAYCHOWDHURY,Sumit JINDAL

期刊论文

Parameter studies on impact in a lap joint

Amir M. RAHMANI,Elizabeth K. ERVIN

期刊论文

Performance design of a cryogenic air separation unit for variable working conditions using the lumped parameter

Jinghua XU, Tiantian WANG, Qianyong CHEN, Shuyou ZHANG, Jianrong TAN

期刊论文

Stress-strain relationship with soil structural parameter of collapse loess

SHAO Shengjun, YU Qinggao, LONG Jiyong

期刊论文

Predictor-corrector algorithm for solving quasi-separated-flow and transient distributed-parameter model

Ping ZHANG, Guoliang DING

期刊论文