Showing papers in "IEEE Transactions on Industrial Electronics in 2007"

Multilevel Voltage-Source-Converter Topologies for Industrial Medium-Voltage Drives

Abstract: This paper presents a technology review of voltage-source-converter topologies for industrial medium-voltage drives. In this highly active area, different converter topologies and circuits have found their application in the market. This paper covers the high-power voltage-source inverter and the most used multilevel-inverter topologies, including the neutral-point-clamped, cascaded H-bridge, and flying-capacitor converters. This paper presents the operating principle of each topology and a review of the most relevant modulation methods, focused mainly on those used by industry. In addition, the latest advances and future trends of the technology are discussed. It is concluded that the topology and modulation-method selection are closely related to each particular application, leaving a space on the market for all the different solutions, depending on their unique features and limitations like power or voltage level, dynamic performance, reliability, costs, and other technical specifications.

Predictive Current Control of a Voltage Source Inverter

Abstract: This paper presents a predictive current control method and its application to a voltage source inverter. The method uses a discrete-time model of the system to predict the future value of the load current for all possible voltage vectors generated by the inverter. The voltage vector which minimizes a quality function is selected. The quality function used in this work evaluates the current error at the next sampling time. The performance of the proposed predictive control method is compared with hysteresis and pulsewidth modulation control. The results show that the predictive method controls very effectively the load current and performs very well compared with the classical solutions

Decentralized Control for Parallel Operation of Distributed Generation Inverters Using Resistive Output Impedance

Abstract: In this paper, a novel wireless load-sharing controller for islanding parallel inverters in an ac-distributed system is proposed This paper explores the resistive output impedance of the parallel-connected inverters in an island microgrid The control loops are devised and analyzed, taking into account the special nature of a low-voltage microgrid, in which the line impedance is mainly resistive and the distance between the inverters makes the control intercommunication between them difficult In contrast with the conventional droop-control method, the proposed controller uses resistive output impedance, and as a result, a different control law is obtained The controller is implemented by using a digital signal processor board, which only uses local measurements of the unit, thus increasing the modularity, reliability, and flexibility of the distributed system Experimental results are provided from two 6-kVA inverters connected in parallel, showing the features of the proposed wireless control

Input-Admittance Calculation and Shaping for Controlled Voltage-Source Converters

Abstract: A controlled power electronic converter can cause local instabilities when interacting with other dynamic subsystems in a power system. Oscillations at a certain frequency cannot, however, build up if the converter differential input admittance has a positive conductance (real part) at that frequency, since power is then dissipated. In this paper, input-admittance expressions for a voltage-source converter are derived. It is seen how the admittance can be shaped in order to get a positive real part in the desired frequency regions by adjusting the controller parameters.

FPGA Design Methodology for Industrial Control Systems—A Review

Abstract: This paper reviews the state of the art of field- programmable gate array (FPGA) design methodologies with a focus on industrial control system applications. This paper starts with an overview of FPGA technology development, followed by a presentation of design methodologies, development tools and relevant CAD environments, including the use of portable hardware description languages and system level programming/design tools. They enable a holistic functional approach with the major advantage of setting up a unique modeling and evaluation environment for complete industrial electronics systems. Three main design rules are then presented. These are algorithm refinement, modularity, and systematic search for the best compromise between the control performance and the architectural constraints. An overview of contributions and limits of FPGAs is also given, followed by a short survey of FPGA-based intelligent controllers for modern industrial systems. Finally, two complete and timely case studies are presented to illustrate the benefits of an FPGA implementation when using the proposed system modeling and design methodology. These consist of the direct torque control for induction motor drives and the control of a diesel-driven synchronous stand-alone generator with the help of fuzzy logic.

Flexible Active Power Control of Distributed Power Generation Systems During Grid Faults

Abstract: The increasing penetration of distributed power generation into the power system leads to a continuous evolution of grid interconnection requirements. In particular, active power control will play an important role both during grid faults (low-voltage ride-through capability and controlled current injection) and in normal conditions (reserve function and frequency regulation). The aim of this paper is to propose a flexible active power control based on a fast current controller and a reconfigurable reference current selector. Several strategies to select the current reference are studied and compared using experimental results that are obtained during an unsymmetrical voltage fault. The results of the analysis allow selection of the best reference current in every condition. The proposed methods facilitate multiple choices for fault ride through by simply changing the reference selection criteria.

Topology Study of Photovoltaic Interface for Maximum Power Point Tracking

Abstract: This paper looks at the performance of photovoltaic modules in nonideal conditions and proposes topologies to minimize the degradation of performance caused by these conditions. It is found that the peak power point of a module is significantly decreased due to only the slightest shading of the module, and that this effect is propagated through other nonshaded modules connected in series with the shaded one. Based on this result, two topologies for parallel module connections have been outlined. In addition, dc/dc converter technologies, which are necessary to the design, are compared by way of their dynamic models, frequency characteristics, and component cost. Out of this comparison, a recommendation has been made

Predictive Control of a Three-Phase Neutral-Point-Clamped Inverter

Abstract: A new predictive strategy for current control of a three-phase neutral-point-clamped inverter is presented. The algorithm is based on a model of the system. From that model, the behavior of the system is predicted for each possible switching state of the inverter. The state that minimizes a given quality function is selected to be applied during the next sampling interval. Several compositions of are proposed, including terms dedicated to achieve reference tracking, balance in the dc link, and reduction of the switching frequency. In comparison to an established control method, the strategy presents a remarkable performance. The proposed method achieves comparable reference tracking with lower switching frequency per semiconductor and similar transient behavior. The main advantage of the method is that it does not require any kind of linear controller or modulation technique, achieving a different approach to control a power converter.

Ultracapacitor-Based Auxiliary Energy System for an Electric Vehicle: Implementation and Evaluation

Abstract: In the search for better efficiency, an auxiliary energy system (AES) for electric vehicles (EVs) was designed, implemented, and tested. The system, which is composed of an ultracapacitor bank and a buck-boost converter, was installed in an EV, which is powered by a lead-acid battery pack and a 54-kW brushless dc motor. Two control strategies where developed: one based on heuristics and the other based on an optimization model using neural networks. These strategies were translated to algorithms and implemented in a digital signal processor, and their performance was evaluated in urban driving. The results were incorporated to an economic evaluation of the system, which shows that the reduction in costs would only justify the inclusion of this type of system in a lead-acid battery-powered vehicle if the battery life is extended by 50% or more, which is unlikely. The same results were extrapolated to a case in which the lead-acid batteries are replaced by a fuel cell. In this case, the costs of different power support systems were evaluated, such as ultracapacitors and high-specific-power lithium-based batteries. The results showed a significant cost reduction when AES configurations are included in contrast to a system powered by fuel cells only. Also, the cost reduction was higher when using ultracapacitors for this purpose.

Neural Network Applications in Power Electronics and Motor Drives—An Introduction and Perspective

Abstract: Artificial intelligence (AI) techniques, particularly the neural networks, are recently having significant impact on power electronics and motor drives. Neural networks have created a new and advancing frontier in power electronics, which is already a complex and multidisciplinary technology that is going through dynamic evolution in the recent years. This paper gives a comprehensive introduction and perspective of neural network applications in the intelligent control and estimation for power electronics and motor drives area. The principal topologies of neural networks that are currently most relevant for applications in power electronics have been reviewed including the detailed description of their properties. Both feedforward and feedback or recurrent architectures have been covered in the description. The application examples that are discussed in this paper include nonlinear function generation, delayless filtering and waveform processing, feedback signal processing of vector drive, space vector PWM of two-level and multilevel inverters, adaptive flux vector estimation, and some of their combination for vector-controlled ac drive. Additional selected applications in the literature are included in the references. From the current trend of the technology, it appears that neural networks will find widespread applications in power electronics and motor drives in future

A Three-Phase Inductive Power Transfer System for Roadway-Powered Vehicles

Abstract: The development of a new three-phase bipolar inductive power transfer system that provides power across the entire width of a roadway surface for automatic guided vehicles and people mover systems is described. A prototype system was constructed to verify the feasibility of the design for a number of moving loads (toy cars). Here, 40 A/phase is supplied at 38.4 kHz to a 13-m-long test track. Flat pickups are used on the underside of each vehicle to couple power from the track to the vehicle. Finite element modeling software was used to design the geometrical position of the track cables and to predict the power output. This design resulted in a considerably wider power delivery zone than possible using a single-phase track layout and has been experimentally verified. Mutual coupling effects between the various track phases require additional compensation to be added to ensure balanced three-phase currents.

Networked Predictive Control of Systems With Random Network Delays in Both Forward and Feedback Channels

Abstract: The design problem of networked control systems (NCS) with constant and random network delay in the forward and feedback channels, respectively, is considered in this paper. A novel networked predictive control (NPC) scheme is proposed to overcome the effects of network delay and data dropout. Stability criteria of closed-loop NPC systems are presented. The necessary and sufficient conditions for the stability of closed-loop NCS with constant time delay are given. Furthermore, it is shown that a closed-loop NPC system with bounded random network delay is stable if its corresponding switched system is stable. Both simulation study and practical experiments show the effectiveness of the control scheme

State-of-Charge Determination From EMF Voltage Estimation: Using Impedance, Terminal Voltage, and Current for Lead-Acid and Lithium-Ion Batteries

Abstract: State-of-charge (SOC) determination is an increasingly important issue in battery technology. In addition to the immediate display of the remaining battery capacity to the user, precise knowledge of SOC exerts additional control over the charging/discharging process, which can be employed to increase battery life. This reduces the risk of overvoltage and gassing, which degrade the chemical composition of the electrolyte and plates. The proposed model in this paper determines the SOC by incorporating the changes occurring due to terminal voltage, current load, and internal resistance, which mitigate the disadvantages of using impedance only. Electromotive force (EMF) voltage is predicted while the battery is under load conditions; from the estimated EMF voltage, the SOC is then determined. The method divides the battery voltage curve into two regions: 1) the linear region for full to partial SOC and 2) the hyperbolic region from partial to low SOC. Algorithms are developed to correspond to the different characteristic changes occurring within each region. In the hyperbolic region, the rate of change in impedance and terminal voltage is greater than that in the linear region. The magnitude of current discharge causes varying rates of change to the terminal voltage and impedance. Experimental tests and results are presented to validate the new models.

Modeling of Three-Phase Dynamic Systems Using Complex Transfer Functions and Transfer Matrices

Abstract: A compilation of methods for modeling and analysis of three-phase dynamic systems-such as AC machines, resistance-inductance-capacitance components, and power electronic converters including their control algorithms-using complex transfer functions and transfer matrices is presented. Restrictions of the two modeling methods and relations between them are given. Various frequency-domain results, including closed-loop stability theory, are presented. The theory is illustrated by several examples showing areas of application.

Distributed Intelligent Energy Management System for a Single-Phase High-Frequency AC Microgrid

Abstract: In this paper, a single-phase high-frequency AC (HFAC) microgrid is shown as a novel solution towards integrating renewable energy sources in a distributed generation system. Better utilization of the Microgrid is achieved by solving power flow and power quality issues using p-q theory-based active filtering called universal active power line conditioner and unified power quality conditioner, respectively. A distributed intelligent energy management system (DIEMS) is implemented to optimize operating costs. As the optimization greatly depends on the power generation and the power output from renewable sources strongly depends on the weather, the forecast of power generation is required for DIEMS. A Fuzzy ARTMAP neural network is used to predict hourly day-type outputs based on which generation can be forecasted. Depending on the forecast, an optimization scheme is developed utilizing linear programming along with heuristics. The results obtained show the successful implementation of HFAC Microgrid with adequate power flow and power quality control, as well as the optimization of operation cost by the DIEMS with Fuzzy ARTMAP-based day-type forecasting. The improvement in the battery life is also achieved due to optimization of storage charge states using the proposed DIEMS

Features, Design Tools, and Application Domains of FPGAs

Abstract: In the past two decades, advances in programmable device technologies, in both the hardware and software arenas, have been extraordinary. The original application of rapid prototyping has been complemented with a large number of new applications that take advantage of the excellent characteristics of the latest devices. High speed, very large number of components, large number of supported protocols, and the addition of ready- to-use intellectual property cores make programmable devices the preferred choice of implementation and even deployment in mass production quantities. This paper surveys the advanced features, design tools, and application domains for field-programmable gate arrays (FPGAs). The main characteristics and structure of modern FPGAs are first described to show their versatility and abundance of available design resources. Software resources are also discussed, as they are the main enablers for the efficient exploitation of the design capabilities of these devices. Current application domains are described, such as configurable computing, dynamically reconfigurable systems, rapid system prototyping, communication processors and interfaces, and signal processing. This paper also presents the authors' prospective view of how FPGAs will evolve to enter new application domains in the future.

High-Efficiency DC-DC Converter With High Voltage Gain and Reduced Switch Stress

Abstract: In this paper, a high-efficiency dc-dc converter with high voltage gain and reduced switch stress is proposed. Generally speaking, the utilization of a coupled inductor is useful for raising the step-up ratio of the conventional boost converter. However, the switch surge voltage may be caused by the leakage inductor so that it will result in the requirement of high-voltage-rated devices. In the proposed topology, a three-winding coupled inductor is used for providing a high voltage gain without extreme switch duty-cycle and enhancing the utility rate of magnetic core. Moreover, the energy in the leakage inductor is released directly to the output terminal for avoiding the phenomenon of circulating current and the production of switch surge voltage. In addition, the delay time formed with the cross of primary and secondary currents of the coupled inductor is manipulated to alleviate the reverse-recovery current of the output diode. It can achieve the aim of high-efficiency power conversion. Furthermore, the closed-loop control methodology is utilized in the proposed scheme to overcome the voltage drift problem of the power source under the variation of loads. Some experimental results via an example of a proton exchange membrane fuel cell power source with 250-W nominal rating are given to demonstrate the effectiveness of the proposed power conversion strategy

Vibration Suppression in a Two-Mass Drive System Using PI Speed Controller and Additional Feedbacks—Comparative Study

Abstract: In this paper, an analysis of control structures for the electrical drive system with elastic joint is carried out. The synthesis of the control structure with proportional-integral controller supported by different additional feedbacks is presented. The classical pole-placement method is applied. Analytical equations, which allow for calculating the control structure parameters, are given. The limitation of the design due to the number of degrees of freedom of the considered drive systems is shown. In order to damp the torsional vibration effectively, the application of the feedback from one selected state variable is necessary. In the literature, a large number of possible feedbacks have been reported. However, in this paper, it is shown that all systems with one additional feedback can be divided into three different groups, according to their dynamical characteristics. In addition, the system with two additional feedbacks is investigated. The comparison between considered structures is carried out. The simulation results are confirmed experimentally in the laboratory setup

Control Strategy of Fuel Cell and Supercapacitors Association for a Distributed Generation System

Abstract: This paper proposes an innovative control strategy for a voltage-regulated dc hybrid power source employing polymer electrolyte membrane fuel cell as the main energy source and supercapacitors as the auxiliary power source for a distributed generation system. This strategy is based on a standard dc link voltage regulation, which is simpler than standard state machines used for hybrid source control, and free of chattering problems. Its originality lies in using only the storage device for supplying the energy required to achieve the dc link voltage regulation. Therefore, the main source of the hybrid system is considered as a standard load, working only in regenerative braking, to keep the storage device charged. The general structure of the studied system, the control principle of the hybrid source, the realization of the experimental bench, and the experimental validation are all presented.

Modeling of Force Sensing and Validation of Disturbance Observer for Force Control

Abstract: Controlling robots in contact with the environment is an important problem in industry applications. Generally, a force sensor is used for sensing the external force. It is well known that information of a force sensor has much noise. Furthermore, unstable state is also caused by the narrow bandwidth of force information by a force sensor. This paper shows that stable contact with the environment is difficult when a force sensor is used because of its soft mechanical structure and narrow bandwidth of force sensing. In order to solve the instability of force control, the disturbance observer is implemented instead of the force sensor. The disturbance observer can observe the external force without force sensors. When the disturbance observer is implemented in a robot, a force control system does not include a soft mechanism between a robot and the environment. Since a robot can detect the environmental information directly, a wide bandwidth of force sensing is attained. In this way, this paper solves the problems of force control by considering the force sensing method without changing the control architecture, and the ability of force control is improved. Experimental results show viability of the proposed method

Regulation of Photovoltaic Voltage

Abstract: In photovoltaic power systems, both photovoltaic modules and switching-mode converters present nonlinear and time-variant characteristics, which result in a difficult control problem. This paper presents an in-depth analysis and modeling to discover the inherent features of a photovoltaic power system. The method of successive linearization simplifies the nonlinear problem back to the linear case. This paper also presents the use of Youla parameterization to design a stable control system for regulating the photovoltaic voltage. The experimental and simulation results demonstrate the effectiveness of the presented analysis, design, and implementation.

A High-Resolution Frequency Estimation Method for Three-Phase Induction Machine Fault Detection

Abstract: Fault detection in alternating-current electrical machines that is based on frequency analysis of stator current has been the interest of many researchers. Several frequency estimation techniques have been developed and are used to help the induction machine fault detection and diagnosis. This paper presents a technique to improve the fault detection technique by using the classical multiple signal classification (MUSIC) method. This method is a powerful tool that extracts meaningful frequencies from the signal, and it has been widely used in different areas, which include electrical machines. In the proposed application, the fault sensitive frequencies have to be found in the stator current signature. They are numerous in a given frequency range, and they are affected by the signal-to-noise ratio. Then, the MUSIC method takes a long computation time to find many frequencies by increasing the dimension of the autocorrelation matrix. To solve this problem, an algorithm that is based on zooming in a specific frequency range is proposed with MUSIC in order to improve the performances of frequency extraction. Moreover, the method is integrated as a part of MUSIC to estimate the frequency signal dimension order based on classification of autocorrelation matrix eigenvalues. The proposed algorithm has been applied to detect a rotor broken bar fault in a three-phase squirrel-cage induction machine under different loads and in steady-state condition.

A Low-Cost Real-Time Hardware-in-the-Loop Testing Approach of Power Electronics Controls

Abstract: Hardware-in-the-loop (HIL) testing is increasingly recognized as an effective approach in the design of power electronics controls. A high-performance real-time simulation environment is necessary to obtain high-fidelity results in HIL simulations. This paper presents the detailed implementation of a very-low-cost multisolver hard real-time simulation environment, namely the real-time extension of the virtual test bed (VTB-RT). VTB-RT is implemented completely from open-source software and off-the-shelf hardware. Using VTB-RT, this paper proposes an efficient real-time HIL testing approach for control designs in power electronics applications. VTB-RT enables the natural coupling between the simulation environment and the hardware under test and, thus, makes virtual power exchange in HIL simulation possible. For validation purposes, the proposed real-time HIL testing approach is applied in two well-known power electronics application examples, namely a boost converter and an H-bridge inverter with their respective control systems, representing a very-low-cost and a relatively advanced hardware setup, respectively. The consistency of the experimental results with the theoretical results proves the applicability of VTB-RT and the proposed testing approach. Finally, the most recent research progresses in VTB-RT are summarized

Hybrid Multilevel Converters: Unified Analysis and Design Considerations

Abstract: The concept of hybrid multilevel converters has been generalized for different arrangements of direct-current voltage levels, modulation strategies, topologies of series-connected cells, and/or semiconductor technologies to optimize the power processing of the overall system. Therefore, a given number of levels can be synthesized by several multilevel configurations, significantly increasing flexibility and complexity in the design of hybrid multilevel converters. However, a generalized design methodology to define the main parameters of these topologies for distinct design criteria has not yet been presented. To overcome this lack, this paper presents a comparative analysis among various hybrid multilevel topologies, and it proposes some design considerations for distinct applications. Consequently, this paper constitutes a useful basis for defining an adequate hybrid arrangement for any application

Predictive Control Strategy for DC/AC Converters Based on Direct Power Control

Abstract: This paper proposes predictive direct power control (P-DPC), a new control approach where the well-known direct power control is combined with predictive selection of a voltage-vectors' sequence, obtaining both high transient dynamics and a constant-switching frequency. The developed P-DPC version is based on an optimal application of three voltage vectors in a symmetrical way, which is the so-called symmetrical 3 + 3 vectors' sequence. The simulation and experimental results of the P-DPC are compared to standard voltage-oriented control (VOC) strategies in a grid-connected three-phase voltage-source inverter under 400-V 15-kVA operation conditions. The P-DPC improves the transient response and keeps the steady-state harmonic spectrum at the same level as the VOC strategies. Due to its high transient capability and its constant-switching behavior, the P-DPC could become an interesting alternative to standard VOC techniques for grid-connected converters

Speed-Sensorless Estimation for Induction Motors Using Extended Kalman Filters

Abstract: In this paper, extended-Kalman-filter-based estimation algorithms that could be used in combination with the speed-sensorless field-oriented control and direct-torque control of induction motors (IMs) are developed and implemented experimentally. The algorithms are designed aiming minimum estimation error in both transient and steady state over a wide velocity range, including very low and persistent zero-speed operation. A major challenge at very low and zero speed is the lost coupling effect from the rotor to the stator, which makes the information on rotor variables unobservable on the stator side. As a solution to this problem, in this paper, the load torque and the rotor angular velocity are simultaneously estimated, with the velocity taken into consideration via the equation of motion and not as a constant parameter, which is commonly the case in most past studies. The estimation of load torque, on the other hand, is performed as a constant parameter to account for Coulomb and viscous friction at steady state to improve the estimation performance at very low and zero speed. The estimation algorithms developed based on the rotor and stator fluxes are experimentally tested under challenging variations and reversals of the velocity and load torque (step-type and varying linearly with velocity) over a wide velocity range and at zero speed. In all the scenarios, the current estimation error has remained within a very narrow error band, also yielding acceptable velocity estimation errors, which motivate the use of the developed estimation method in sensorless control of IMs over a wide velocity range and persistent zero-speed operation

Design and Implementation of a Robust Current-Control Scheme for a PMSM Vector Drive With a Simple Adaptive Disturbance Observer

Abstract: This paper introduces a robust current-control scheme for a permanent-magnet synchronous motor (PMSM) with a simple adaptive disturbance observer. The robust controller is realized by including an adaptive element in the reference-voltage-generation stage using the feedforward control. Due to the time-varying nature and the high-bandwidth property of the uncertainties in a practical PMSM drive system, the adaptive element is simply chosen as the estimated uncertainty function, which adaptively varies with different operating conditions. Subsequently, the frequency modes of the uncertainty function are embedded in the control effort, and a robust current-control performance is yielded. Furthermore, the inclusion of the estimated uncertainty function provides an efficient solution for torque-ripple minimization in PMSM drives. This is because the frequency modes of the disturbances to be eliminated, i.e., the flux harmonics, are included in the stable closed-loop system. To provide a high-bandwidth estimate of the uncertainty function, a simple adaptation law is derived using the nominal current dynamics and the steepest descent method. To guarantee the system's convergence and to properly tune the proposed observer, a stability analysis based on a discrete-time Lyapunov function has been used. Comparative evaluation experiments are presented to demonstrate the effectiveness of the proposed control scheme under different operating conditions.

Repetitive-Based Controller for a UPS Inverter to Compensate Unbalance and Harmonic Distortion

Abstract: This paper discusses a repetitive-based controller for an uninterruptible power supply (UPS) inverter. It is shown that a bank of resonant filters, used as a refinement term for harmonic compensation in earlier works, is equivalent to a repetitive scheme with a particular structure. The latter is implemented using a simple feedback array with a delay line, thus making the implementation relatively easy. More precisely, the repetitive scheme takes a negative feedback structure plus a feedforward path whenever the odd harmonics are considered for compensation only. The repetitive scheme, equivalent to the bank of resonant filters, acts as a refinement term to reject the harmonic distortion caused by the unbalanced and distorted load current, and thus, allowing the UPS inverter to deliver an almost pure sinusoidal balanced voltage. Experimental results in a 1.5 KVA three-phase inverter are included to show the performance of the proposed controller

Comparison of 2.3-kV Medium-Voltage Multilevel Converters for Industrial Medium-Voltage Drives

Abstract: This paper compares the expense of power semiconductors and passive components of a (2.3 kV, 2.4 MVA) two-level, three-level neutral-point-clamped, three-level flying-capacitor, four-level flying-capacitor, and five-level series-connected H-bridge voltage source converter on the basis of the state-of-the-art 6.5-, 3.3-, 2.5-, and 1.7-kV insulated gate bipolar transistors for industrial medium-voltage drives. The power semiconductor losses, the loss distribution, the installed switch power, the design of flying capacitors, and the components of an sine filter for retrofit applications are considered.

Online Stator and Rotor Resistance Estimation Scheme Using Artificial Neural Networks for Vector Controlled Speed Sensorless Induction Motor Drive

Abstract: This paper presents a new method of online estimation for the stator and rotor resistances of the induction motor for speed sensorless indirect vector controlled drives, using artificial neural networks. The error between the rotor flux linkages based on a neural network model and a voltage model is back propagated to adjust the weights of the neural network model for the rotor resistance estimation. For the stator resistance estimation, the error between the measured stator current and the estimated stator current using neural network is back propagated to adjust the weights of the neural network. The rotor speed is synthesized from the induction motor state equations. The performance of the stator and rotor resistance estimators and torque and flux responses of the drive, together with these estimators, are investigated with the help of simulations for variations in the stator and rotor resistances from their nominal values. Both resistances are estimated experimentally, using the proposed neural network in a vector controlled induction motor drive. Data on tracking performances of these estimators are presented. With this speed sensorless approach, the rotor resistance estimation was made insensitive to the stator resistance variations both in simulation and experiment. The accuracy of the estimated speed achieved experimentally, without the speed sensor clearly demonstrates the reliable and high-performance operation of the drive