neural network based waveform processing

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 51, NO. 5, OCTOBER 2004 981 Neural-Network-Based Waveform Processing and Delayless Filtering in Power Electronics and AC Drives Jin Zhao and Bimal K. Bose , Life F ellow , IEEE Abstract—This pape r syst ema tica lly expl ore s the stat ic non- linea r mapp ing pro pert y of feed for ward neur al networks fo r var ious wav efo rm process ing and dela yles s filter ing that are applicable to power electronics and ac drives area. Neural-network-based processing of waves gives considerable simplification of hardware and/or software that are traditionally used for such appl icat ions. T wo gene ral cases hav e been inv esti gate d: The voltage or current waveforms which have constant frequency but var iabl e mag nitud es, and the othe r case is var iable -fr eque ncy variable-magnitude voltage or current waves. The former case is mainly important for power electronics that operate on a utility system and general-purpose constant-frequency converter power suppl ies, and the latt er is impo rtant for the adjus table -spe ed ac driv es area. In both cases, the perf ormance of neur al-ne t- wor k-ba sed wa vef orm process ing and dela yles s filter ing with offline training was found to be excellent. The results of this study are also applicable to other areas of electrical engineering. Index Terms—AC driv es, dela yles s filter ing, neur al network, power electronics, waveform processing. I. INTRODUCTION P OWER electronics and variable-frequency drive systems often deal with complex voltage and current waves that are rich in harmonics. These waveforms often require complex processing for control, monitoring, diagnostics, and protection of the system. Normally, analog/digital hardware, software, or a combin ation of both is required for processing these wa ve s. One of the important processing functions is predictive or delayless filt eri ng in ord er to ret rie ve the fun dament al (si ne wave ) component of the wave. For example, a diode or thyristor phase-controlled bridge converter, operating on a 60-Hz utility line, can generate square or six-stepped line current wave, and this waveform becomes multistepped (more than six steps) with multiple phase-shifted bridge converters on a three-phase line [1]. Sim- ilar waveforms are also generated, respectively, in the output voltage of a square-wave voltage-fed inverter with single bridge or phase-shifted multibridge configuration. The harmonic-rich line current and output voltage waves can again cause distor- tion in the line voltage and load current waves, respectively. Manuscript received January 12, 2004; revised June 22, 2004. Abstract pub- lished on the Internet July 15, 2004. J. Zhao was with the Department of Electrical Engineering, The University of Tennessee, Knoxville, TN 37996-2100 USA, on leave from the Department of Automatic Control Engineering, Huazhong University of Science and Tech- nology , Wuh an 430074, China (e-mail: zhao200061 [email protected].cn). B. K. Bose is with the Department of Electrical Engineering, The University of Tennessee, Knoxville, TN 37996-2100 USA (e-mail: [email protected]). Digital Object Identifier 10.1109/TIE.2004.834949 It is often necessary to retrieve the fundamental component of these waves in order to calculate, for example, the displacement power factor (DPF), fundamental frequenc y active (P) and reac- ti ve po wer (Q), and ene rgy mea sured by a kil owatthour met er . In photovoltaic and wind generation systems coupled to the grid, the distorted line voltage (due to converter harmonics) waves require delayless filtering in order to generate inverter sine ref- erence voltage waves for controlling the line DPF to unity [2], [3]. The distorted line voltage waves also create problems in the comparator (or zero-crossing detector) which is often es- sential for control of the converter (e.g., cosine-wave-crossing control of a phase-controlled converter). Generally, an active- or passive-type low-pass filter (LPF) with narrow bandwidth is used to filter out the harmonic components. However, an LPF causes phase lag and amplitude attenuation that vary with fundamental frequency. For a utility system, the fundamental frequency is essentially constant and, therefore, these phase and amplitude errors can be compensated without much difficulty [2]. However, for variable-frequency drive applications, the inverter usually operates in pulsewidth-modulation (PWM) mode with wide frequency variation generating machine voltage and current waves that are complex with harmonics. If a simple LPF with narrow bandwidth is used in these applications, the variable phase delay and amplitude attenuation for the fundamental may not be acce ptable , particularly at highe r funda menta l frequency. The phase error is particularly harmful in a vector-controlled drive where it creates the coupling problem and, thus, deteriorates the drive performance. In the past, complex digital adaptive filters, such a finite-impulse response (FIR), infi- nite-impulse respo nse (IIR), or a combination of both have been pro pos ed [3]–[5] to obt ain del ayl ess filt eri ng of the fundament al component. In this paper, we propose the neural network solution for waveform processing and delayless filtering problems. The artificial neural network (ANN), or neural network, a generic form of artificial intelligence (AI), is recently offering a new frontier in solving many control, estimation, and diagnostic problems in power electronics and motor drives. Between the two classes of ANN, i.e., the feedforward and feedback or recurrent types, the former provides static nonlinear input–output mapping or pattern recog nition prope rty with preci sion interp olation capa bility . With appropriate training, this property permits a feedforward ANN to recognize a waveshape and retrieve the desired component of the wave. Since the shape or pattern of the wave remains constant or goes through deterministic variation, simple offline training of the network has been used in the project. The advan- 0278-0046/04$20.00 © 2004 IEEE

neural network based waveform processing

Documents