Combining ICA and SVR in Times Series Predication

Wensheng Dai,Jui-Yu Wu,Chi-Jie Lu 인하대학교 정석물류통상연구원 2009 인하대학교 정석물류통상연구원 학술대회 Vol.2009 No.10

In this paper, a time series prediction approach by combing independent component analysis (ICA) and support vector regression (SVR)is proposed ICA is a novel statistical signal processing technique that was originally proposed to find the latent source signals from observed mixture signal without knowing any prior knowledge of the mixing mechanism. SVR is and artificial intelligence forecasting technique and has been widely applied in time series prediction problems. The proposed approach First uers ICA to the forecasting variables for generating the independent components(ICs). After identifying and removing the ICs containing the noise, the rest of the ICs are then used to reconstruct the forecasting variables which contain less noise. The SVR then uses the denoised forecasting variables to build the forecausting model. in order to evaluaate the performance of the proposed approach the TAIEX(Taiwan Stock Exchange Capitalization weighted Steock index) closing cash index is usde as the illusrtative example. Experimental results show that the proposed model outperforms the SVR model with mon ?filtered forecasting variables and random walk model

Application research of consumer credit Score model based on SVM and DEA

Wensheng Dai,Chi-Jie Lu 인하대학교 정석물류통상연구원 2009 인하대학교 정석물류통상연구원 학술대회 Vol.2009 No.10

Clustering and Classification are the most popular techniques in credit scoring. Most of the hybrid models are lack of revision abilities. To overcome this limitation, a two stages credit scoring model using SVM and DEA is proposed in this paper. Firstly constructing a SVM model and classifying all customs to two groups which are efficient and inefficient group, the performing DEA for those lower efficiency customers and proposing the way to improve their efficiency. This study also performs an empirical research based on the credit card database of a bank. The results show that the SVM has great ability to predict the efficiency and combined model can provide an indeed improvement for bank to improve the efficiency of non-efficient customer.

The economic and management use of rhododendron petals in potas-sium-ion nano batteries anode via efficient computer simulation

Dai, Wensheng,Zand, Yousef,Agdas, Alireza Sadighi,Selmi, Abdellatif,Roco-Videla, Angel,Wakil, Karzan,Issakhov, Alibek Techno-Press 2021 Advances in nano research Vol.10 No.6

Nano batteries are manufactured batteries which use nanoscale technology, small particles measuring less than 100 nanometers or 10-7 meters. In addition, because of plentiful potassium supplies and less cost, potassium-ion batteries (PIBs) are taken as possible substitutes for lithium-ion batteries for massive energy storing systems. Our modern lifestyle could be totally different without rechargeable batteries. Regarding their economic and management usage, these batteries are applied in electric and hybrid vehicles, devices, and renewable power generation systems. Accordingly, regarding the huge K ion radius, it is a difficult process for identifying relevant materials with excellent cycling stability and capacity. At present, the production of suitable anode materials with high specific capacities, long cycle life and low costs for PIBs remains a major challenge. Also, the continuing improvement in defining future electors, the manufacture of PIBs has been complicated by multiple challenges, namely low reversible performance, insufficient cycling stability and poor energy density, all of which have created important doubts for the effective implications of PIBs. Nano-particles have shown various advantages for enhanced energy and power density, cyclability and safety when it comes to designing and producing electrode materials via efficient computer simulation. In combination with large volume expansion, slow reaction kinetics, and low electrical conductivity the main cause for the degradation of SnO₂ reaction reversibility and power decay observed are not as obvious as those of Lithium-ion batteries (LIBs) as anodes of sodium-ion batteries (SIBs), and potassium-ion batteries (KIBs).

Separation and Characterization of Waste Cotton/polyester Blend Fabric with Hydrothermal Method

Wensheng Hou,Chen Ling,Sheng Shi,Zhifeng Yan,Meiling Zhang,Bonan Zhang,Jinming Dai 한국섬유공학회 2018 Fibers and polymers Vol.19 No.4

In the study, a good separation efficiency of waste cotton/polyester blended fabrics (WBFs) was achieved, with dilute hydrochloric acid as the catalyst under hydrothermal conditions. The morphology and structure of the hydrothermal products including solid and liquid products were characterized by scanning electron microscopy, Fourier transform Infrared spectroscopy, X-ray diffraction, and high-performance liquid chromatography techniques and compared to the untreated polyester and cotton. The results show that the cotton fiber decomposed completely while polyester still retained its fiber characteristics after 3 h of reaction time at 150 oC and 1.5 wt% dilute hydrochloric acid. The hydrolysis of cellulose resulted in a recovery of 96.24 % of the polyester without significant change in its properties; 48.21 % of cellulose powder can be further used as the raw material of microcrystalline cellulose (MCC) and 15.57 % of glucose.

Comparison of semi-active and passive tuned mass damper systems for vibration control of a wind turbine

Eric R. Lalonde,Kaoshan Dai,Girma Bitsuamlak,Wensheng Lu,Zhi Zhao 한국풍공학회 2020 Wind and Structures, An International Journal (WAS Vol.30 No.6

Robust semi-active vibration control of wind turbines using tuned mass dampers (TMDs) is a promising technique. This study investigates a 1.5 megawatt wind turbine controlled by eight different types of tuned mass damper systems of equal mass: a passive TMD, a semi-active varying-spring TMD, a semi-active varying-damper TMD, a semi-active varying-damper-and-spring TMD, as well as these four damper systems paired with an additional smaller passive TMD near the mid-point of the tower. The mechanism and controllers for each of these TMD systems are explained, such as employing magnetorheological dampers for the varying-damper TMD cases. The turbine is modelled as a lumped-mass 3D finite element model. The uncontrolled and controlled turbines are subjected to loading and operational cases including service wind loads on operational turbines, seismic loading with service wind on operational turbines, and high-intensity storm wind loads on parked turbines. The displacement and acceleration responses of the tower at the first and second mode shape maxima were used as the performance indicators. Ultimately, it was found that while all the semi-active TMD systems outperformed the passive systems, it was the semi-active varying-damper-and-spring system that was found to be the most effective overall – capable of controlling vibrations about as effectively with only half the mass as a passive TMD. It was also shown that by reducing the mass of the TMD and adding a second smaller TMD below, the vibrations near the mid-point could be greatly reduced at the cost of slightly increased vibrations at the tower top.

Wind turbine testing methods and application of hybrid testing: A review

Eric R. Lalonde,Kaoshan Dai,Wensheng Lu,Girma Bitsuamlak 한국풍공학회 2019 Wind and Structures, An International Journal (WAS Vol.29 No.3

This paper presents an overview of wind turbine research techniques including the recent application of hybrid testing. Wind turbines are complex structures as they are large, slender, and dynamic with many different operational states, which limits applicable research techniques. Traditionally, numerical simulation is widely used to study turbines while experimental tests are rarer and often face cost and equipment restrictions. Hybrid testing is a relatively new simulation method that combines numerical and experimental techniques to accurately capture unknown or complex behaviour by modelling portions of the structure experimentally while numerically simulating the remainder. This can allow for increased detail, scope, and feasibility in wind turbine tests. Hybrid testing appears to be an effective tool for future wind turbine research, and the few studies that have applied it have shown promising results. This paper presents a literature review of experimental and numerical wind turbine testing, hybrid testing in structural engineering, and hybrid testing of wind turbines. Finally, several applications of hybrid testing for future wind turbine studies are proposed including multi-hazard loading, damped turbines, and turbine failure.