Legal forms

Intelligent ultra fast charger for Ni-Cd batteries

Intelligent ultra fast charger for Ni-Cd batteries
of 5
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
  IEEE PEDS 2005 GA-trained GRNN for Intelligent Ultra Fast Charger for Ni-C atteries Panom Petchjatupom, Noppadol Khaehintung, PhinyoWicheanchote Khamron Sunat and Wiwat Kiranon Faculty of Engineering, Mahanakom University of Technology Test Engineer Department Bangkok, Thailand. Sanmina-SCISystems co. ltd.  Thailand Email: {Panom,Noppadol, Khamron,Wiwat } Abstract- This paper presents an intelligent genetic algorithm successfully applied to Ni-Cd batteries [6]. With less  GA) technique for training of a neural network controller to computational burden, it has beenfound that its data selectionachieve a compactnetworkand to decrease battery charging performance is greater than some techniques, for example time. An ultra fast charging device for Nickel-Cadmium  Ni-Cd ANFIS. Moreover, the computational afford reduction of batteries is designed through the generalized regression neural GRNN has beenimproved by further in [7]. Nonetheless, the network  GRNN) and implemented with the data selection of construction GRNN still was  ot thoroughly MATLAB SIMULINK fortesting and operating on real system. considered. The input-output data for training neural networks were collected from GA. The suitable data were selected to establish Genetic algorithms are probabilistic search techniques that GRNN comprising only 13 processing elements. Each node of emulate the mechanics of evolution [8]. They are capable of RBFs is an extendable support functionthat overcomes the globally exploringa solutionspace, pursuing potentially drawback in the existing compact support radial basis functions fruitful paths while also examining additional random points to  CSRBF). Experiments with real time implementation clearly reduce the likelihood of settling for a local optimum. The show that the proposed technique notonlyrequires less neuralapplied GA-trained RBF network for maximum power point processing units but also yields less MSE than RBF technique. tracking in photovoltaic applications was presented in [9]. Keywords-component; genetic algorithm; fast charging; the This paper proposes an efficient approach for battery fast- generalized regression neuralnetwork; radial basis functions; chargingusing GA-trained GRNN controller. Its main advantages over other algorithms are the simple topological I. INTRODUCTION structure, precision in nonlinear dynamics approximation, and fast learning capability. The remainder of the paper is In present the secondary or rechargeable batterles have organized as follows. Following this a system configuration of been massivelyused in variety of electrical appliances with th prpoe fs hrigmtoisadeednScinI. wide range of size and capacity. These batteries can be the proposed fast-charging method is addressed in Section II rechrge afer ingexhustd b pasingcurentthrugh The GA-trained GRNN controller forthe fast-charging method recharged after being exhausted by passing current through is reviewed in Section III In Section IV, the development of them in the opposite direction tothat of discharge current [1]. fast-charging is discussed and experimental results with The widely used secondary batteries are Nickel Cadmium  Ni- emphasis on performance of the proposed GRNN controller are Cd ,Nickel Metal Hydride  Ni-MH) andLithium Ion  Li-Ion , given. Finally, conclusion is drawn in Section V. In principal, charging of a battery may be a straightforward task. In practical, however, it could involvecomplicated control algorithm, especially when high power demand needs II. PROPOSED SYSTEM to be supported by highperformance while cost effective battery charger. A. UltraFastChargingMethod When charging at high rate, temperature inside thebattery Recently, fast-charging algorithms have beenproposed in could change very rapidly, as shown by typicalprofiles of many places. Their common purpose iS to speed up thebatterybattery voltage and temperature during a charging period in recharging time. In [2], forinstance, the fast-charging Fig. 1. lt s and tosgicatly decring efic in alorth bae upo th reato beweX otg n Fig. 1. This can lead to significantly decreasing efficiency of temperased upo tatiro e tw t voltage ant the charging process, and, hence, the degradation or even teprtr of tebteyhsenpretd. Moepacia serious damage of the battery. Therefore, this effect must be work in [3] employs a non-linear controller to cope with the sevalusat eoforeap atioro. Tfast-cha i procss. problem. Some intelligent control techniques, such as Neuro- s p Fuzzy [4] and Adaptive Neuro-Fuzzy Inference System The maximum rate of charging currentfor Ni-Cd batteries  ANFIS) [5] have also been applied for fast-battery chargers. is 8C [5], where C is capacity in Amp-Hour unit of the battery. These algorithms, though very sophisticated and adaptable to In general, the battery will be charged at different rates with the environment, require relatively high performance processor different durations, accordingly to internal pressure and and may not be appropriate for certain applications where cost temperature o the battery. When the battery reaches its full iS a prime concern. charge level, the temperature gradient will increase An utra astcharingtechiqueusig th Geeralzed significantly, and the charging rate should be slowed down in RegressionNeural Network  GRNN) has been introduced and ore oaodteoecag tt Teeoe h atr 0-7803-9296-5/05/ 20.00 © 2005 IEEE 1 194  Slope =Temperature gradient / Time X 6D Figure 1. Typical profiles of battery temperatureand voltage during fast- charging process. Figure 2. Input-output relationship of a GRNN-based battery charger temperature  T) and temperaturegradient  dTldt) can be used in the determination of the rate of charging current  C, . As an example, 561 points data set representing the input-output relationship during a battery fast-charging process using GRNN algorithm is shown in Fig. 2. B. Circuit Configuration The circuit configuration of the proposed battery charger is shown in Fig. 3. It comprises of a voltage control current source circuit and battery temperature and voltage detector circuits. The charging current command is sent via the digital to analog converter of xPC Targets Computer [12], and thevoltage is applied to the current source circuit viathe non- Figure 3. Circuit configurationof the proposed ultra fast charger. inverting input of op-amp  1/4 LM324). During charging, the battery temperature, T, is measured by a temperature sensor LM335 and is fed to a digital computer via analog to digital converter  xPC Targetscomputer). The temperature gradient, iRBFtljx1jj dTldt, is, then, computed using a unit delay. Both temperature C - II lII and temperature gradient are us as theparameters for C, x) n  1 evaluating the rate of charging current. The battery voltage is ER.BF Ix,x.jj also sent to digital computer in order to checkwhether the charging process should be terminated. where x E Rn is input vector of dimension n, RBF .) is radial III. GA-GRNN FoR FAST-CHARGING basisfunction,   denotes the Euclidean norm, Y arethe weights or parameters of network, xi e Rn are known asthe A. The GRNN centers of RBF .), and n is the number of centers. Since the Let us consider Fig. 2. From our observation, when 3D network size directly depends on the number of training data surface of the T, dTldt and C, was plotted, it should be [13],  t therefore, must be carefully selected in order to get a approximated by a smooth surface or the data regression compact network, and, at the same time, it can represent the method. Accordingly, the generalized regression neural net- surface appropriately. work  GRNN comprising of threelayers is selected to perform this task. The first-layer comprises of input nodes. The second- B. The selection process of training data layer comprises of neurons each of which is represented by a Since GRNN behaves like a functional approximation or a basisfunction. The output ofnetwork according to the input x; non-linear regression, its characteristic highly depends on the ya, depends on the weighted combination of thefunctional characteristic of training data. Once the training model is distance between the input data and thecenter of the basis completed, in order to evaluate the goodness the selected datafunction in the hidden layer. the charging current C, can be set, the Mean-Square Error  MSE) of the validation set must be computedby evaluated. MSE is defined by 1195  Ansioglnput   lnl L;nOuti   eural N~t rk CRgte_Sl  hg PClUII UpUI   l ~~V Temp to TanpS Cff   TSi -n C PCL S12PG dTldt Figure 4. The GRNN controller implementation block diagram. stringlI I   500   100 1  l F4 MSEE  C,d n C C, n 2  2) string   521   13   21 -.---- W where C,{n denotes the desiredoutput of thevalidation set, string   I I   201 ....... C n denotes the actual output of GRNN model, and N is the Figure 5. Exampleof string for selectedinput-output datapoint for GRNN number of datapoints taken for model validation. is shown in Fig. 6. It is clearly seen that after 320 generations C. The GA-trained GRNNfor Data Selection the GA gives the best result of fitness value, 4.37x 10-3. In GA, the set of variables for a given problem is encoded Inthe experiment, we appliedthe proposed data selection into a string  population which is analogous to a chromosome criteria tothe charger of aPanasonic Ni-Cd battery [14]. Table in nature. Each string contains a number of alleles, and each H shows a set of data having 6 out of 561. Itis a data set thatfeature of the system located at a specific position in the string the GA-trained GRNN with 13 processing units yields a very is called gene. Each string, therefore,contains possible solution low MSE as shown in Table III. If the whole data set was used, to the problem. The GA performs with a set of binary-coded the number of processing units of the trained GRNN will be 2x strings of set parameter,representing thesuitable data for 561+1=1,123 units. GA-trained GRNN of this size has a battery fast-charging thatwill be trainedfor the GRNN These comparableperformance butpossessesahigher cost than GA data may be the optimum solution to the problem. The trained GRNN of thesmaller size. searching of selected input-output data point i start from a randomly generated set of population. The center of RBF xi can B. Neural Network setup be decoded as The simulations were conducted to evaluatethe xi = input-output data point  pop 3 performance of GRNN controllerfor fast-charging using xj=mput outputdatapoultWop MATLAB/Neural Network Toolbox. A Simulink model ofwhere pop is the population. The fitness  * of each GRNN for real time control of battery charger as shown in Fig. chromosome is evaluated as1 was implemented. The training data set taken from Table II is chromosome is evaluated asr applied to set up the GA-trained GRNN networks. After f = MSE  4 training process, the surface of output  Ct and input battery temperature T with associatedbattery temperature gradient Theoptimum solution can be obtained by minimizing the  dTldt was obtained, shown in Fig. 2. fitness function. The lower fitness value string at each searching step will be chosen to be the parent of the next C. Charging Results generation, while the higher fitness one will be rejected. In In order to determine the characteristic ofnormal charging creatingthe new offspring,theselected parentstrings undergo this battery, the Ni-Cd battery was tested intensively at charg- reproduction process, such as crossover and mutation as ing current rate at 4C and 8C at the environment temperature of described in [8]. The process continues updating newer and30 OC. Inthese experiments, we investigate the controller fitter chromosome, until a predefinedstopping condition is performance by comparing MSE of GA-trained GRNN with satisfied. MSE of ANFIS [5]. Itis noticed that the GA-trained GRNN In our work, the number of alleles is determined from the network yields not only alower number of processing units butinput-outputdata points as same as that used in [11]. It is a data also a lower MSE than ANFIS [5] controller and GRNN [7] set that the trained GRNN as shown in Fig. 5.  see Table III . Fig. 7 depicts the results of battery temperature and voltage during charging with constant current  C It indicates that charging processshould be stopped with in 1,400 IV. EXPERIMENTAL RESULTS seconds, becauseovercharge can be detected by positive dTldt and negative dV/dt at this point.Fig. 8 shows the result of A. Data Selection Results constant current charging at 8C. It indicates that charging This experiment aims to evaluate our training procedure. process should be stopped within 415 seconds. Although the The population size used in each trial is 20. Each system is results from Fig. 7 and Fig. 8 indicatethat charging at 8C is randomly assigned between 1 and 561 represented the order of faster than charging 4C, the former yields a hightemperature the input-output data points taken from [ 11]. Table I shows the gradient which may cause batteries deterioration.Fig. 9 depicts parameters used in the GA process. The result of GA selected 1196  TABLE 1. GENETIc PARAMErER USED 2 r i I ~ 50 Crossover 0.8   45 FMutation 0.1 T7 .. .... i-----  40   I   35 TABLE II. INPuT ouTPUT DATA FOR Ni Cd BAT rERY CHARGER  30 No. Inpu Output 2 __ ~~ ~~~T T/dt Ct _ _i 4 0.2 8 20   .9 8   I - - --   -15 ___3 38 0.9 8   10 440 0.58   43 0.4 2 Tempaatie  I I I -I----- ---5 6 5 0  L 5 0 a 0100150200 250 300350 400 45i TABLE III Totne  sen COMPARISONBETWEEN ANFIS RBF AND GRNN BATTERY CHARGER Figure 8. The battery voltage and temperature in a Ni Cd battery ANFIS [5 GRNN 71 GA-trained GRNN  1 2VI600mH at a 8C charging rate. Number of Layers 6 33 Number of Nodes 27 1 3 1350 MSE 0.1321 0.0905 0.0046 4.5  4 40   40 Best: 0. 0043719 Mexi: 0.54306 10-   3   ---   ~ S 0~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.5  Voltage   25 ..........~~~~~0. 10 0 1 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2 00 ---400 --5-0 600-700---   -------------   2.0 > ..........-------Tim  iec   Fiure . Th ate...oltae .c ren.andtempratue.ina.NiCd.btte. --------__________________ I........I.....of RBF cotolr o 5t br 100200300400500600 700000900 loot----   controller dCureaeh hrigcretwe epratur 2.0 30 increases. Fr~~~~~~~~~~~~~~~~~~~~~~~~~om hes reslts by--detecting-- the--- oItive--- dI   Voltage- ~ ~~~ 40 and negative dV/dt the Ni Cd battery was reached the ull~~~~--- Tera   ............I-------------------40-- shourt ie wi h oubtt oery v limtae, retad temperature. i iC atr construcion of highly compatrle GorN oshrgfat-harin 200 400 6 400 00 1000 12 8014900 newr ee esta AFSadRF.Frhror tera  eneration ~ sythem reslso valu enation ftepopsdcitireral wasimplementedo Figreg.uTe6 atryoltgresandftmratireingfreealtNi-Cl atesn oulnfirmedtel reslts.rtdi his.woul lea stoarlow costsstemt  l.2VI600H t 4 chargingratetrim lem entationei the future. gcfen hnteprtr 2 050 inrese. ro thsereuls bydeectngth ps1197dId  REFERENCES [7] P. Petchjatuporn, P. Wicheanchote, N.Khaehintung,K. Sunat, W. Kiranonand S. Chiewchanwattana,  Intelligent ultra fast charger ofNi- [1] D.Linden, HandbookofBatteries, McGraw Hill Inc.,1995. Cd batteries , Proc of ISCAS05 Conf., pp. 5162-5165, 2005. [2] M. Gonzalez, F. .J. Ferrero, J. C. Anton and M. A. Perez, [8] D. E. Goldberg, Genetic Algorithm on Search Optimization and  Considerations to improve thepractical design of universal and full- Machine Learning, Reading, MA Addision-Wesley,1989 effective NiCd/NiMH battery fast-chargers,   Proc. of 14th APEC  99 [9] L. Zhang, B. Yunfeiand A. Al-Amoudi,  GA-RBF neural network Conf., Vol   l pp. 167-173.,1999. []L hn B ufiad lAod ARFnua ewr based maximum power point tracking for grid-connected photovoltaic [3] J. C.Viera, M. Gonzalez,C.Blanco, and J. C. Alvarez,  Application systems, Proc ofInt. PEDS Conf, pp. 18 -23,2002. range of fast-charging in NiCd batteries, Proc. of 24th INTELEC Conf, [10] J. Binfet and B. M. Wilamowski,  Microprocessorimplementation of pp. 259-264, 2002. fuzzysystems and neural networks, Proc. of IJCNN  01 Conf:,Vol. 1 [4] Z. Ullah,B. Burford, and S. Dillip,  Fast intelligent battery charging: pp.234-239 2001. neural-fuzzy approach, IEEE Aerospace and Electronic Systems Maga [11] zine, Vol. 1 pp. 26 34., June, 1996, [5] A. Khosla, S. Kumar, andK.K.Aggarwal,  Fuzzy controllerforrapid [12] nickel-cadmium batteries charger through adaptive neuro-fuzzy [13] S. Chen, C. F. N. Covan, and P. M. Grant,  Orthogonal least squareinference system  ANFIS) architecture, Proc. Of NAFIPS 2003Conf, learning algorithm forradial basis function networks, IEEE Trans. pp. 540 544, 2003. Neural Networks, Vol.2, No 2 March, 1991,pp.302-309. [6]P. Petchjatupom, P. Wicheanchote, N.Khaehintung, K. Sunat, P. [14] Panasonic, Nickel Cadmium Handbook, August, 1998, p.51. Sookavatanaand W. Kiranon,  Data Selection if a Compact GRNN for Ni-Cd Batteries fast charging ,Proc. of TENCON 2004 Conf, pp. 213- 216,2004. 1198
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks