Speed Tracking of Indirect Field Oriented Control Induction Motor using Neural Network

Transcription

1 Avalable onlne at Proceda Technology 8C (13) The 4th Internatonal Conference on Electrcal Engneerng and Inforatcs (ICEEI 13) Speed Trackng of Indrect Feld Orented Control Inducton Motor usng Neural Network Azuwen Ada Bohar a, *, Wahyu Mulyo Utoo a, Zanal Ala Haron a, Nooradzane Muhd. Zn a, Sy Y S a, Roslna Mat Arff a a Faculty of Electrcal and Electronc Engneerng, Unverst Tun Hussen Onn Malaysa, 860 Part Raja, Batu Pahat, Johor, Malaysa Abstract Developent of a neural network (NN) based ndrect feld orented control (IFOC) of nducton otor (IM) drve s presented n ths paper. The neural network ndrect feld orented control (NNIFOC) s desgned to generate sgnal of quadrature current, hence the otor speed wll follow the reference speed value. The sulaton odel usng Matlab/Sulnk was developed to valdate the effectveness of the proposed controller. The sulaton results show that the proposed NNIFOC schees of IM drve s ore effectve and found to be a proper replaceent of the proportonal ntegral dervatve (PID) controller. 13 The Authors. Publshed by Elsever B.V. Selecton and peer-revew under responsblty of the Faculty of Inforaton Scence and Technology, Unverst Kebangsaan Malaysa. Keywords: Inducton Motor; Indrect Feld Orented Control; Neural Network Controller. 1. Introducton A three phase IM s desgned to operate fro a three phase source of alternatng voltage and t s a one of asynchronous AC otor. The advantages of the IM ncludes hgh relablty, relatvely sple, has rugged structure, * Correspondng author. Tel.: ; fax: E-al address: he110247@sswa.uth.edu.y The Authors. Publshed by Elsever B.V. Selecton and peer-revew under responsblty of the Faculty of Inforaton Scence and Technology, Unverst Kebangsaan Malaysa.

2 Azuwen Ada Bohar et.al. / Proceda Technology 8C (13) low cost, robustness and hgh effcences. These advantages ake the IM advance n all aspects lke speed change, speed reversal, startng and brakng. The overall syste perforance depends on the IM dynac operaton. Due to the swft developent n croprocessor and power electronc, the advanced control ethods have IM possble for hgh perforance applcatons. A lot of researcher has been attracted to the feld of electrc drves by IM control over te [1-14]. IM wth varable speed ac drves and eployed the feld orented control ethod expands n recent years to acheve better perforances set by DC drves. In order to provde good steady-state perforance n fast dynac response, decouplng between the torque and flux s hghly recoends. Hgh dynac perforance n IM can be acheved by eans of feld-orented control where t provdes a sutable atheatcal descrpton of three phase IM. The translaton of coordnate fro the fxed references stator frae to the frae of rotatng synchronous s pled by the vector control [1]. In early 1970s, the decouplng technque akes the possblty of separated control for torque and flux n the coplex dynac for IM [2]. By applyng the control technques such as adaptve control [3] a good perforance can be acheve wth paraeter senstve property. A great attenton has been ade by NN due to ts natural parallels n the feld of power electronc, thus allow and pert the hgh speed processng. The NN have capablty for tolerance, to ss data, to fault, and to carry out n nose envronent [4]. To dentfy and control nonlnear dynac systes and nonlnear paraeter estaton, the use of NN has been proposed [5][6]. An estaton of the stator flux and traned to ap the nonlnear behavor of a rotor flux s perfored on the proposed NN [7]. Hgh perforance control has been the objectves of [8], whch presents robust neural controller and aganst varaton of paraeter. Wthout knowng the exact atheatcal odel of the syste, the desred appng between the nput and outputs sgnals of the syste can be learned by the NN. The NN are excellent estators n non-lnear syste because t does not use the atheatcal odel of the syste [9]. Ths paper wll present a NN based IFOC of IM drve. The perforance of three phase IM drve syste wth NN controlled appled n ths paper. The theoretcal prncple, nuercal sulaton procedures and the results of these ethods are dscussed and copared wth conventonal PID controller. 2. Dynac Modelng of IM The IM odel has been presented n a varous reference fraes. Ths akes t easer to adjust the odel accordngly and to fx the reference frae to a partcular otor quantty. Norally, a rotary type of nducton s used wth a rotatng rotor and statonary stator. In order to derve the IM dynac odel of three phase coordnate nto two phases drect and quadrature coordnate s requred. The nuerc odel n statonary reference frae s gven [10]. Vds Rs Ls p 0 L p 0 ds V qs 0 Rs Lsp 0 Lp qs V dr L p r L Rr Lr p r Lr dr Vqr r L L p r Lr Rr Lr p qr (1) The reference frae of fxed d-q stator n IM odel s descrbed as follow, Vs Rs d s ( s ) dt Vr 0 Rr d r ( r ) j dt r r L L s s s L L r s r r

3 1 Azuwen Ada Bohar et.al. / Proceda Technology 8C (13) Whereas the echancal equaton s gven as below: ds ( Vds Rsds ) dt qs ( Vqs Rsqs ) dt s 1 qs tan ( ) ds The electroagnetc torque of the achne can be presented as follow: 3 p Te ( ) 4 dsqs qsds 3. IFOC Syste Descrpton The IFOC conssts of controllng the stator currents represented by a vector. Ths control s based on projectons whch transfor three phase te and speed dependent syste nto two co-ordnate te nvarant syste. Ths technque akes IM control schee slar to a DC otor control schee. In ths IFOC technque, nput and torque reference constant s requred whch algned wth the d-q axs by usng ths ethod. The control prose good qualty of IM for both dynac and steady-state operaton. 4. Neural Network Generally a NN controller was developng based on features of the huan brans to handle coplex proble and any task n one te. Bascally the huan brans syste has ablty to process the nput nforaton and the output data sultaneously and generate response nstantaneously n handle ult job. By ths reason any researcher beleve that developent of the NN control systes sutable for the nonlnear syste. Developent of the structure and learnng algorth of the NN s explaned as follows [11] Proposed NN speed controller Ths paper proposed a NN control ethod of IFOC based on hysteress to reduce the overshoot and torque rpple. The NN control s added to the speed controller to produce the torque reference. The block dagra of the proposed NNIFOC of IM drve s shown n Fg. 1. ω* NN ω Ψ* (2/3Pb)*(Lr/L)*(1/Ψ*) 1/L Iq Id d-q αbc HYSTERISIS CURRENT CONTROL (1/Tr)(1/Ids) d-q αbc ω sl IM Pb Fg. 1. The proposed NNIFOC dagra

4 Azuwen Ada Bohar et.al. / Proceda Technology 8C (13) Structure of NNIFOC Generally, nput and output neuron nuber of the NN control syste wll be based on the nput sgnal and output sgnal nubers. In order to develop the NNIFOC a ultlayer percepton wth certan structure was proposed as shown n Fg. 2. Fg. 2. Structure of NNIFOC The controller conssts of nput layer, hdden layer and output layer. Based on nuber of the neuron n the layers, the NNIFOC s defned as a network structure. The frst neuron of the output layer s used as a torque reference sgnal (a 2 1= f ). The connectons weght paraeter between j th and th neuron at th layer s gven by w j, whle bas paraeter of ths layer at th neuron s gven by b. Transfer functon of the network at th neuron n th layer s defned by: 1 S 1 j j j1 n w a b The output functon of neuron at th layer s gven by: a f ( n ) Where f s actvaton functon of the neuron. In ths desgn the actvaton functon of the output layer s unty and for the hdden layer s a tangent hyperbolc functon gven by: f 2 ( ) 1 n 2 1 e n Updatng of the connecton weght and bas paraeters are gven by: Fk ( ) w ( k 1) w ( k) w j j j Fk ( ) b ( k 1) b ( k) b where k s saplng te, α s learnng rate, and F perforance ndex functon of the network.

5 142 Azuwen Ada Bohar et.al. / Proceda Technology 8C (13) Sulaton Results A sulaton was constructed for the entre syste n Fg 1 wth the pleentaton of NN based IFOC schee for the three-phase IM usng Borland C++, and then ebedded as S-functon n Matlab/Sulnk software. In ths paper, the pattern of the reference speed that used to verfy the effectveness of the proposed controller s shown n Fg 3 the paraeters for the otor are 2V, 50Hz, Poles=4, Rs=0.3Ω, Rr=0.25Ω, Ls=0.0415H, Lr=0.0412H, L=0.03H, J=0.1kg-2. 1 REFERENCE SPEED Fg. 3. Pattern of the reference speed The output response of the syste based on the speed reference patern s shown n Fg. 4. and Fg Fg. 4. Acceleraton rap response of NN and PID speed controller Fg.5. Deceleraton rap response of NN and PID speed controller

6 Azuwen Ada Bohar et.al. / Proceda Technology 8C (13) Referrng to the Fg 4, the acceleraton rap of the syste by usng both controllers n between te 0 to 2 seconds, shows that NN speed controller follow the shape of speed reference pattern and have a response proved fro the conventonal PID controller. Whle, n Fg 5 between te 2 to 3 seconds, the speed contnue at 130 rad/s. Then, NN speed controller follow the shape of deceleraton rap at the te of 3 to 5 seconds. The results for the both fgure shows the great reduce n rpple of the transent respose and proved the perforance at the sae te rather than PID controller. 6. Concluson The NN based IFOC of IM drve syste has been presented n ths paper. The purpose of ths paper s to nvestgate the perforance of NN copared to the PID controller. The coparatve results show that NN based IFOC schees of IM drve s ore effectve and, hence, found to be a sutable replaceent of the conventonal PID controller. It s concluded that IFOC by usng NN are useful and able to prove the perforance. The result shows that the perforance of the syste s proved by reducng the rpple. Acknowledgeent The author would lke to grattude Unversty Tun Hussen Onn Malaysa for any valuable supports durng conductng ths research and n preparng ths anuscrpt. References [1] Goyat, S. and Ahuja, R. K., Speed Control of IM usng Vector or Feld Orented Control, Internatonl Journal of Advances n Engneerng and Technology. 12. [2] Blaschke, F., The prncple of feld orentaton as appled to the new transvector closed-loop control syste for rotatng-fled achnes, Seens Vol.34.p [3] Von Zuben, F.J., Netto, M.L.A., B, E., Szajner, J., "Adaptve vector control of a three-phase IM usng NNs," NNs, IEEE World Congress on Coputatonal Intellgence., 1994 IEEE Internatonal Conference on, Vol 6.p [4] Ba-Razzouk, A., Chert, A., Olver, G.,1997."A NNs based feld orented control schee for IMs," Industry Applcatons Conference, Thrty-Second IAS Annual Meetng, IAS '97., Conference Record of the 1997 IEEE, vol.2, no., pp [5] Wshart, M.T., Harley, R.G.,. "Identfcaton and control of nducton achnes usng artfcal NNs," Industry Applcatons, IEEE Transactons on, 1995;31(3): [6] Narendra, K.S., Parthasarathy, K., "Identfcaton and control of dynacal systes usng NNs," NNs, IEEE Transactons on, (1).p [7] Ba-Razzouk, A., Chert, A., Olver, G., Scard, P., "Feld orented control of IMs usng NNs decouplers," Industral Electroncs, Control, and Instruentaton, 1995., Proceedngs of the 1995 IEEE IECON 21st Internatonal Conference on, 1995.Vol. 2.p [8] Mloud, A., Draou, A., 01. "Neural controller desgn for speed control of an ndrect feld orented nducton achne drve," Industral Electroncs Socety, IECON '01. The 27th Annual Conference of the IEEE. 01. p [9] Svasubraana, A., Applcaton of neural network structure n voltage vector selecton of drect torque control nducton otor Internatonal Journal of Appled Engneerng Research, 09. 4(6),p.903. [10] Kuar, Rajesh, Gupta, R.A., Bhangale, S.V., Gothwal, Hanshu; 07. "Artfcal NN based drect Torque Control of IM drves," Inforaton and Councaton Technology n Electrcal Scences (ICTES 07), ICTES. IET-UK Internatonal Conference on, 07. p [11] Yat A.H.M., and Utoo W.M.,. On-Lne Optal Control of Varable Speed Copressor Motor Drve Usng Neural Control Model. PECon Proceedngs Conference, 04. p