检索结果-南通市图书馆

Sound Quality Prediction of Vehicle Interior Noise under Multiple Working Conditions Using back-propagation Neural Network Model

在线全文

学校读者我要写书评

暂无评论

Journal of Transportation Technologies 2015年第2期5卷 134-139页

作者： Zutong Duan Yansong Wang Yanfeng Xing College of Automotive Engineering Shanghai University of Engineering Science Shanghai China

This paper presents a back-propagation neural network model for sound quality prediction (BPNN-SQP) of multiple working conditions’ vehicle interior noise. According to the standards and regulations, four kinds of vehicle interior noises under operating conditions, including idle, constant speed, accelerating and braking, are acquired. The objective psychoacoustic parameters and subjective annoyance results are respectively used as the input and output of the BPNN-SQP model. With correlation analysis and significance test, some psychoacoustic parameters, such as loudness, A-weighted sound pressure level, roughness, articulation index and sharpness, are selected for modeling. The annoyance values of unknown noise samples estimated by the BPNN-SQP model are highly correlated with the subjective annoyances. Conclusion can be drawn that the proposed BPNN-SQP model has good generalization ability and can be applied in sound quality prediction of vehicle interior noise under multiple working conditions.

关键词： Multiple Working Conditions Neural Network back-propagation Sound Quality Prediction Annoyance

Stochastic speed prediction for connected vehicles using improved bayesian networks with back propagation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第7期65卷 1524-1536页

作者： WANG LiHua CUI YaHui ZHANG FengQi COSKUN Serdar LIU KaiLong LI GuangLei School of Mechanical and Precision Instrument Engineering Xi'an University of TechnologyXi'an 710048China Department of Mechanical Engineering Tarsus UniversityTarsusMersin 33400Turkey WMG University of WarwickCoventryCV47ALUK

Advanced vehicular control technologies rely on accurate speed prediction to make ecological and safe decisions. This paper proposes a novel stochastic speed prediction method for connected vehicles by incorporating a Bayesian network(BN) and a back propagation(BP) neural network. A BN model is first designed for predicting the stochastic vehicular speed in a priori. To improve the accuracy of the BN-based speed prediction, a BP-based predicted speed error compensation module is constructed by formulating a mapping between the predicted speed and its corresponding prediction error. In the end, a filtering algorithm is developed to smoothen the compensated stochastic vehicular speed. To validate the workings of the proposed approaches in experiments, two typical scenarios are considered: one predecessor vehicle in a double-vehicle scenario and two predecessor vehicles in a multi-vehicle scenario. Simulation results under the considered scenarios demonstrate that the proposed BN-BP fusion method outperforms the BN-based method with respect to the root mean square error, standardized residuals, and R-squared, and the online prediction time of proposed fusion prediction can satisfy a real-time application requirement. The main highlighted contributions of this article are threefold:(1) We put forward an improved BN method, which is combined with a BP neural network, to construct a stochastic vehicular speed prediction method under connected driving;(2) different from existing methods, a unique interconnected framework that consists of a stochastic vehicular speed prediction module, a compensation module, and a speed smoothing module is proposed;(3) extensive simulation studies based on a set of evaluation metrics are illustrated to reveal the advantages and merits of the proposed approaches.

关键词： connected vehicles stochastic vehicular speed prediction Bayesian network back-propagation

Optimization of Process Parameters for Cracking Prevention of UHSS in Hot Stamping Based on Hammersley Sequence Sampling and back propagation Neural Network-Genetic Algorithm Mixed Methods

在线全文

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2016年第2期23卷 31-39页

作者： menghan wang zongmin yue lie meng school of material science and engineering chongqing UniversityChongqing 400030China

In order to prevent cracking appeared in the work-piece during the hot stamping operation,this paper proposes a hybrid optimization method based on Hammersley sequence sampling( HSS),finite analysis,backpropagation( BP) neural network and genetic algorithm( GA). The mechanical properties of high strength boron steel are characterized on the basis of uniaxial tensile test at elevated temperatures. The samples of process parameters are chosen via the HSS that encourages the exploration throughout the design space and hence achieves better discovery of possible global optimum in the solution space. Meanwhile, numerical simulation is carried out to predict the forming quality for the optimized design. A BP neural network model is developed to obtain the mathematical relationship between optimization goal and design variables,and genetic algorithm is used to optimize the process parameters. Finally,the results of numerical simulation are compared with those of production experiment to demonstrate that the optimization strategy proposed in the paper is feasible.

关键词： hot stamping cracking Hammersley sequence sampling back-propagation genetic algorithm

Dynamic forecasting and optimal scheduling of by-product gases in integrated iron and steel works

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2019年第5期26卷 529-546页

作者： Qi Zhang Hui Li Jia-lin Ma Hua-yan Xu Bo-yang Yu Gang Wang Shan Jiang State Environmental Protection Key Laboratory of Eco-Industry Northeastern University Shenyang 110819 Liaoning China State Key Laboratory of Hybrid Process Industry Automation Systems and Equipment Technology Automation Research and Design Institute of Metallurgical Industry Beijing 100072 China Software College Northeastern University Shenyang 110169 Liaoning China Shougang Jingtang United Iron & Steel Co. Ltd. Tangshan 063200 Hebei China China United Engineering Company Hangzhou 310052 Zhejiang China

The by-product gases, which are generated in ironmaking, coking and steel making processes, can be used as fuel for the metallurgical processes and on-site power plants. However, if the supply and demand of by-product gases are imbalanced, gas flaring may occur, leading to energy wastage and environmental pollution. Therefore, optimal scheduling of by-product gases is important in iron and steel works. A BP_LSSVM model, which combines back-propagation (BP) neural network and least squares support vector machine (LSSVM), and an improved mixed integer linear programming model were proposed to forecast the surplus gases and allocate them optimally. To maximize energy utilization, the stability of gas holders and boilers was considered and a concise heuristic procedure was proposed to assign penalties for boilers and gas holders. Moreover, the optimal level of gas holder was studied to enhance the stability of the gas system. Compared to the manual operation, the optimal results showed that the electricity generated by the power plant increased by 2.93% in normal condition and by 22.2% in overhaul condition. The proposed model minimizes the total cost by optimizing the boiler load with less adjustment frequency and the stability of gas holders and can be used as a guidance in dynamic forecasting and optimal scheduling of by-product gases in integrated iron and steel works.

关键词： Iron and steel works back-propagation neural network Least squares support vector machine Mixed integer linear programming Dynamic forecasting Optimal scheduling

Retrieval of Water Vapor Profiles with Radio Occultation Measurements Using an Artificial Neural Network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2005年第5期22卷 759-764页

作者：王鑫吕达仁 Laboratory for Middle Atmosphere and Global Environment Observation Institute of Atmospheric Physics Chinese Academy of Sciences

A new method applying an artificial neural network （ANN） to retrieve water vapor profiles in the troposphere is presented. In this paper, a fully-connected, three-layer network based on the backpropagation algorithm is constructed. Month, latitude, altitude and bending angle are chosen as the input vectors and water vapor pressure as the output vector. There are 130 groups of occultation measurements from June to November 2002 in the dataset. Seventy pairs of bending angles and water vapor pressure profiles are used to train the ANN, and the sixty remaining pairs of profiles are applied to the validation of the retrieval. By comparing the retrieved profiles with the corresponding ones from the Information System and Data Center of the Challenging Mini-Satellite Payload for Geoscientific Research and Application （CHAMP-ISDC）, it can be concluded that the ANN is relatively convenient and accurate. Its results can be provided as the first guess for the iterative methods or the non-linear optimal estimation inverse method.

关键词： radio occultation water vapor artificial neural network back-propagation

A Multi-View Gait Recognition Method Using Deep Convolutional Neural Network and Channel Attention Mechanism

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2020年第10期125卷 345-363页

作者： Jiabin Wang Kai Peng College of Engineering Huaqiao UniversityQuanzhou362021China

In many existing multi-view gait recognition methods based on images or video sequences,gait sequences are usually used to superimpose and synthesize images and construct energy-like ***,information may be lost during the process of compositing image and capture EMG *** and the recognition accuracy may be introduced and affected respectively by some factors such as period *** better solve the problems,a multi-view gait recognition method using deep convolutional neural network and channel attention mechanism is ***,the sliding time window method is used to capture EMG ***,the back-propagation learning algorithm is used to train each layer of convolution,which improves the learning ability of the convolutional neural ***,the channel attention mechanism is integrated into the neural network,which will improve the ability of expressing gait *** a classifier is used to classify *** can be shown from experimental results on two public datasets,OULP and CASIA-B,the recognition rate of the proposed method can be achieved at 88.44%and 97.25%*** can be shown from the comparative experimental results,the proposed method has better recognition effect than several other newer convolutional neural network ***,the combination of convolutional neural network and channel attention mechanism is of great value for gait recognition.

关键词： EMG signal capture channel attention mechanism convolutional neural network multi-view gait recognition gait characteristics back-propagation

Activated sludge process based on artificial neural network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2002年第4期9卷 383-386页

作者： ZHANG Wen-yi(张文艺) CAI Jian-an(蔡建安) School of Chemical & Environmental Engineering Anhui University of Technology Maanshan 243002 China School of Chemical & Environmental Engineering Anhui University of Technology Maanshan 243002 China

Considering the difficulty of creating water quality model for activated sludge system, a typical BP artificial neural network model has been established to simulate the operation of a waste water treatment facilities. The comparison of prediction results with the on-spot measurements shows the model, the model is accurate and this model can also be used to realize intelligentized on-line control of the wastewater processing process.

关键词： artificial neural network back-propagation activated sludge system model

Prediction of daytime variations of HO_2 radical concentrations in the marine boundary layer using BP network

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2010年第12期53卷 2616-2621页

作者： WANG ZhuQing,CHEN YaShao,QI Bin & YANG Bing Key laboratory of Applied Surface and Colloid Chemistry,Ministry of Education School of Chemistry and Material Science,Shaanxi Normal University,Xi’an 710062,China Key laboratory of Applied Surface and Colloid Chemistry Ministry of Education School of Chemistry and Material Science Shaanxi Normal University Xi’an China

A back-propagation Neural Network (BPNN) was established to predict the daytime variations of HO 2 radical concentration observed in the field campaign RISFEX 2003 (RIShiri Fall Experiment 2003) conducted in September 2003 at Rishiri Island (45.07 N,141.12 E,and 35m asl) in the Sea of *** initial weight matrices and bias vectors for the network were optimized by a bee evolutionary genetic algorithm (BEGA).It was found that the input variables sensitive to HO 2 variation were photolysis frequency of O 3 to O(1 D) (J(O 1 D)),a composite parameter defined as the ratio of HC to NO x reactivity towards OH radicals (Φ),and the total aerosol surface area (A).The predicted results are closely correlated with the experimental data with the coefficient of determination (R2) close to *** addition,the means and ranges of the predicted HO 2 concentration agree with the observed data with the correlation coefficient (R),the index of agreement (IA) and the fractional bias (FB) in the range of 0.84-0.93,0.88-0.95 and 14%-7%,*** study demonstrates that BPNN is a potential tool to predict the daytime variations of HO 2 radical concentrations in the marine boundary layer (MBL).

关键词： back-propagation Neural Network HO 2 radical marine boundary layer

Application of BPANN in spinning deformation of thin-walled tubular parts with longitudinal inner ribs

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University of Technology 2004年第1期11卷 27-30页

作者：江树勇李萍薛克敏 School of Materials Science and Engineering Harbin Institute of Technology Harbin 150001China .School of Materials Science and Engineering Hefei University of Technology Anhui 230000China

back-propagation artificial neural network (BPANN) is used in ball backward spinning in order to form thin-walled tubular parts with longitudinal inner ribs. By selecting the process parameters which have a great influence on the height of inner ribs as well as fish scale on the surface of the spun part, a BPANN of 3-8-1 structure is established for predicting the height of inner rib and recognizing the fish scale defect. Experiments data have proved that the average relative error between the measured value and the predicted value of the height of inner rib is not more than 5%. It is evident that BPANN can not only predict the height of inner ribs of the spun part accurately, but recognize and prevent the occurrence of the quality defect of fish scale successfully, and combining BPANN with the ball backward spinning is essential to obtain the desired spun part.

关键词： artificial neural network back-propagation ball spinning power spinning