检索结果-内蒙古大学图书馆

Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process

引用

EXPERT SYSTEMS WITH APPLICATIONS 2012年第3期39卷 2397-2407页

作者： Mukherjee, Indrajit Routroy, Srikanta Indian Inst Technol Shailesh J Mehta Sch Management Bombay 400076 Maharashtra India Birla Inst Technol & Sci Dept Mech Engn Pilani 333031 Rajasthan India

Monitoring and control of multiple process quality characteristics (responses) in grinding plays a critical role in precision parts manufacturing industries. Precise and accurate mathematical modelling of multiple response process behaviour holds the key for a better quality product with minimum variability in the process. Artificial neural network (ANN)-based nonlinear grinding process model using backpropagation weight adjustment algorithm (BPNN) is used extensively by researchers and practitioners. However, suitability and systematic approach to implement Levenberg-Marquardt (L-M) and Boyden, Fletcher, Gold-farb and Shanno (BFGS) update Quasi-Newton (Q-N) algorithm for modelling and control of grinding process is seldom explored. This paper provides L-M and BEGS algorithm-based BPNN models for grinding process, and verified their effectiveness by using a real life industrial situation. Based on the real life data, the performance of L-M and BFGS update Q-N are compared with an adaptive learning (A-L) and gradient descent algorithm-based BPNN model. The results clearly indicate that L-M and BEGS-based networks converge faster and can predict the nonlinear behaviour of multiple response grinding process with same level of accuracy as A-L based network. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Back propagation neural network gradient descent algorithm Levenberg-Marquardt algorithm Multiple response Quasi-Newton algorithm

来源：评论

学校读者我要写书评

暂无评论

A High-Order Neutrosophic-Neuro-gradient descent algorithm-Based Expert System for Time Series Forecasting

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2019年第7期21卷 2245-2257页

作者： Singh, Pritpal Huang, Yo-Ping Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan Natl Taipei Univ Dept Comp Sci & Informat Engn New Taipei 23741 Taiwan

This article proposed a novel hybrid time series forecasting model using neutrosophic set (NS) theory, artificial neural network (ANN) and gradient descent algorithm. This study deals with three main problems of time series dataset, viz., representation of time series dataset using NS, three degrees of memberships of NS together, and generation of the forecasting results. To resolve these three domain specific problems, this study advocated the application of neutrosophic-neuro-gradient approach. NS theory was utilized to represent the uncertainty associated with time series dataset and was referred to as neutrosophic time series (NTS). In NTS, various decision rules were created in the form of IF-THEN rules, which were termed as neutrosophic entropy decision rules (NEDRs). An ANN-based architecture took NEDRs as input to evolve the forecasting results. To improve the performance of ANN and to obtain optimal forecasting results, this study additionally utilized the gradient descent algorithm to minimize the differences between the calculated and target output values during the simulation. The proposed model was verified and validated with three different datasets, including TAIFEX index, university enrollment dataset of Alabama and Taiwan Stock Exchange Corporation (TSEC) weighted index. Experimental results showed that the proposed model outperformed existing benchmark models with average forecasting error rates of 1.02%, 0.74% and 1.27% for the TAIFEX, university enrollment and TSEC, respectively.

关键词： Neutrosophic set Artificial neural network gradient descent algorithm Entropy Time series forecasting

来源：评论

学校读者我要写书评

暂无评论

PMSM Drive System Efficiency Optimization Using a Modified gradient descent algorithm With Discretized Search Space

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2020年第3期6卷 1104-1114页

作者： Lai, Chunyan Feng, Guodong Tian, Jiangbo Li, Ze Zuo, Ying Balamurali, Aiswarya Kar, Narayan C. Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou 510006 Peoples R China Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada

This article investigates efficiency optimization in a permanent magnet synchronous machine (PMSM) drive system, including the motor and the power converter. At first, the motor drive efficiency model based on the input and output power is proposed. In this model, the input power is calculated from the dc-link voltage and current measurements, and the output power is modeled and computed from the dq-axis voltages and currents considering temperature rise, magnetic saturation, cross-coupling effect, and inverter nonlinearity. The proposed efficiency model includes both the inverter and motor losses without the need of loss models, so it simplifies the efficiency calculation significantly. Based on this efficiency model, a novel gradient descent algorithm-based approach with a discrete search space and proper constraints is proposed to optimize the PMSM drive system efficiency, ensure a fast searching speed, and reduce the influence from measurement uncertainties. Compared with the existing approaches, the proposed approach is computationally efficient, does not require loss models, and is noninvasive as no signal injection is involved. The proposed approach is evaluated on a laboratory PMSM drive system with extensive experimental tests.

关键词： Inverters Iron Optimization Computational modeling Torque Copper Mathematical model DC-link power measurement efficiency optimization gradient descent algorithm permanent magnet synchronous machine (PMSM) drives

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of gradient descent algorithm using scaling methods for improving the prediction process based on Artificial Neural Network

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第6期83卷 15677-15691页

作者： Seeli, D. Jeni Jeba Thanammal, K. K. Scott Christian Coll Autonomous Dept Comp Sci Nagercoil India ST Hindu Coll Dept Comp Sci Nagercoil India

The health development is one of the most important challenges in the world today. All human beings are affected by many diseases due to various circumstances like pollution, climate change, living habits, etc. Therefore, the improvement of predicting diseases is a very essential process in medical management. Prediction refers to the results of an algorithm after it has been trained on a dataset. It is a mathematical process that seeks to predict future outcomes by analyzing methods. Classification methods of machine learning can be used to find accurate prediction of disease by the symptoms. This paper reviews the gradient descent algorithm such as Logistic Regression and Artificial Neural Network. These models are highly applicable and deliver reliable prediction accuracy with the help of a dataset. The survey indicates that the most popular classification techniques are Artificial Neural Network and Logistic Regression. The major purpose of this study is to investigate the performance of various scaling methods, including ensemble normalization and standardization methods, for improving disease prediction. The study also presents a performance comparison of classification algorithms, with and without applying the feature scaling of the data preprocessing techniques. In the proposed system, two algorithms, Artificial Neural Network and Logistic Regression, were used for the classification. Firstly, the accuracy of Artificial Neural Network and Logistic Regression without scaling method was calculated. The results show that Artificial Neural Network produces the highest accuracy of 86.13% in predicting heart disease. Next, various scaling methods were applied with Artificial Neural Network and Logistic Regression algorithms to improve the accuracy of the prediction process. The experimental results show that the accuracy of Artificial Neural Network using Ensemble Normalization and Standardization is 98.81%, which is greater than the other accuracies. Finally, a s

关键词： Artificial Neural Network Logistic Regression gradient descent algorithm Scaling Methods Statistical Test Ensemble Normalization and Standardization

来源：评论

学校读者我要写书评

暂无评论

gradient descent algorithm to optimize the offshore scale squeeze treatment

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第PartB期208卷 109469-109469页

作者： Azari, Vahid Vazquez, Oscar Mackay, Eric Sorbie, Ken Jordan, Myles Heriot Watt Univ Edinburgh Midlothian Scotland ChampionX Loughborough Leics England

Scale deposition is one of the serious oilfield chemical issues which may lead to a range of downhole and production problems, including the reduction of well productivity index. Scale Inhibitor (SI) squeeze treatments are one of the most common techniques which are applied to prevent downhole scaling in production wells. A treatment typically consists of four stages, (i) a preflush, to condition the rock surface;(ii) a main treatment, where a batch of high concentration inhibitor is bullheaded into the formation;(iii) an overflush, to displace the scale inhibitor slug deeper into the near-well formation, and (iv) a shut-in stage to allow further inhibitor retention before putting the well back on production. During this backflow period, scale inhibitor is released from the rock surface into the produced water, and the scale deposition is prevented if the inhibitor concentration is above some specified Minimum Inhibitor Concentration (MIC). Due to logistic constraints in offshore wells, it is often required that the scale protection afforded by a squeeze treatment should last for some fixed design lifetime until the next treatment becomes available. For example, in the North Sea sector, well operations are often based on an annual treatment design. This paper presents a methodology to optimize the squeeze treatment design for a fixed target lifetime and this is applied for two offshore well squeeze treatments. This approach allows us to account for the operational constraints in the squeeze optimization process to treat a fixed volume of produced water, while minimizing the inhibitor neat volume and the total pumping time. A sensitivity study was performed on the inhibitor concentration, where the results showed that deploying a smaller inhibitor slug but with higher concentration is more effective than a larger slug with lower concentration, assuming a fixed volume of inhibitor and injected water. Therefore, it is recommended that the inhibitor is deployed at the m

关键词： Oilfield scale Squeeze treatment Iso-lifetime designs Treatment optimization gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

An approximate gradient descent algorithm for Spiking Neural Network 35

An approximate gradient descent algorithm for Spiking Neural...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Chen, Wenjie Li, Chuandong Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China

ISBN: (纸本)9798350334722

Spiking Neural Network (SNN) is the third generation of neural networks, which transmits information through the impulse train, but the discrete impulse train has the property of non-differentiable, so it is difficult to apply the gradient descent algorithm to the spiking neural network. In this paper, the approximate derivative of the impulse activity is introduced to simulate the impulse activity, and then the spiking neural network based on the gradient descent algorithm is realized. On this basis, the influence of different approximate derivatives on the training accuracy of the spiking neural network is explored, and the iterative formula of LIF (Leaky Integrate and Fired) neurons is optimized and simplified. The results show that when the approximate derivative is introduced, our neural network has lower consumption, better performance, and the accuracy of the moment function model neural network is higher. We take the MNIST data set as the input of the spiking neural network, convert it into the impulse sequence information by the frequency coding method based on the impulse counting, and transmit it through the simplified LIF neuron model. On the basis of the error back propagation rules, the synaptic weight and error deviation of the neural network are constantly updated. The results show that the proposed algorithm is of higher accuracy and faster speed.

关键词： Spiking Neural Network (SNN) MNIST gradient descent algorithm Approximate derivative LIF

来源：评论

学校读者我要写书评

暂无评论

Modified gradient descent algorithm Based Maximum Torque Per Ampere Control of PMSMs 24

Modified Gradient Descent Algorithm Based Maximum Torque Per...

引用

24th International Conference on Electrical Machines and Systems (ICEMS)

作者： Kim, Do-Hyeon Kim, Sang-Hoon Kangwon Natl Univ Elect & Med Convergent Eng Chunchon South Korea Kangwon Natl Univ Elect & Elect Eng Chunchon South Korea

ISBN: (纸本)9788986510218

In this paper, a modified gradient descent algorithm based MTPA (Maximum Torque Per Ampere) control scheme to improve the driving efficiency of a permanent magnet synchronous motor is proposed. The modified gradient descent algorithm tracks the optimal current angle for MTPA control by using a newly defined gradient based on a change rate of copper losses. Since a magnitude of stator current is only required to track the optimal current angle for MTPA control, the proposed method is not dependent on motor parameters such as stator inductances and permanent magnet flux linkage. By using the proposed method, it is possible to track the optimal current angle that minimizes the copper losses for all load conditions in a short time, even with the motor parameters error or an offset in measured rotor position. The validity of the proposed method is verified by simulations using Matlab/Simulink for 210kW and 1.5kW IPMSMs (Interior Permanent Magnet Synchronous Motors) and experiments with a 1.5kW IPMSM.

关键词： permanent magnet synchronous motor drives Maximum torque per ampere control optimization method gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Implementation of hybrid neuro-fuzzy controller based on radial basis function network with gradient descent algorithm for non-linear system

Implementation of hybrid neuro-fuzzy controller based on rad...

引用

IEEE Power, Communication and Information Technology Conference (PCITC)

作者： Soni, Ravi Kumar Nigam, M. J. Mitra, R. IIT Roorkee Elect & Commun Engn Dept Roorkee Uttar Pradesh India

ISBN: (纸本)9781479974559

The main focus of this paper is on stabilization of non-linear system using proposed Hybrid Neuro-fuzzy Logic Controller based on Radial Basis Function Network (HNFRBFN). A control unit matrix has been introduced according to the non-linearity and uncertainty of the plant. The parameters used to obtain the individual control action in this matrix are optimized by gradient descent algorithm. IF part of the fuzzy rules is approximated using Radial Basis Function (RBF) Network & THEN part of fuzzy rules are synthesized by the control action matrix which incorporates Error-correction algorithm. This error correction algorithm forms the basis of HNFRBFN. The simulation results obtained show that the suggested controller gives promising improvement and better performance.

关键词： Radial basis membership function Neural network Fuzzy logic controller gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

A Robust Quaternion based Kalman Filter Using a gradient descent algorithm for Orientation Measurement

A Robust Quaternion based Kalman Filter Using a Gradient Des...

引用

IEEE International Instrumentation and Measurement Technology Conference (I2MTC) - Discovering New Horizons in Instrumentation and Measurement

作者： Woehle, Lukas Gebhard, Marion Westphalian Univ Appl Sci Elect Engn & Appl Sci Gelsenkirchen Germany

ISBN: (纸本)9781538622223

This paper presents a robust quaternion based filter approach to estimate orientation from Magnetic Angular Rate Gravity (MARG)-sensors. These sensors consist of tri-axis accelerometer and gyroscope as well as a tri-axis magnetometer which allow a complete measurement of orientation relative to the direction of gravity and magnetic field of the earth. The proposed filter uses a gradient descent algorithm (GDA) to compute an orientation from magnetometer and accelerometer data. This calculated orientation is directly used as an input in a Kalman filter framework (KFF) which predicts the orientation estimation from gyroscope data. The embedding of the gradient descent algorithm into the Kalman filter allows the computation of a weighted orientation represented as quaternion. Furthermore, the designed filter can overcome short time magnetic disturbance by switching between MARG and IMU equations inside the gradient descent filter stage (GDFS) and therefore enables a more robust orientation estimation without the need for additional algorithms. Tests show the proposed filter to be superior to a commercially available sensor fusion algorithm related to orientation estimation at slow angular rates. Moreover, the proposed filter is able to maintain good orientation estimation under short term magnetic disturbance.

关键词： sensor fusion orientation estimation magnetic disturbances gradient descent algorithm Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Facility Layout in Horizontal Cylindrical Space Based on Adaptive gradient descent algorithm 40

Facility Layout in Horizontal Cylindrical Space Based on Ada...

引用

40th Chinese Control Conference (CCC)

作者： Yuan, Peng Miao, Yiran Huang, Deqing Hao, Junkai Qin, Na Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China Nucl Power Inst China Sci & Technol Reactor Syst Design Technol Lab Chengdu 610041 Peoples R China

ISBN: (纸本)9789881563804

FLP(Facility layout problem) is a common problem in engineering field. The past research tend to focus on the twodimensional space and a small amount of three-dimensional box space as well as vertical cylinder space. The FLP in horizontal cylinder space is less researched. Lots of FLP of box space and vertical cylinder space can transform to FLP of two-dimensional space easily, however, the FLP of horizontal cylinder space need design special calculation method of overlap constraint and boundary constraint. This paper designed the calculation method of overlap constraint and boundary constraint, used adaptive gradient descent algorithm with heuristic strategy to optimize the facility layout in horizontal cylinder space. On this basis, added symmetry constraint, absolute height constraint and relative distance constraint to close to the real engineering demand. The experiment results confirm the feasible of proposed scheme.

关键词： facility layout problem horizontal cylinder space gradient descent algorithm

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：