Artificial neural network-based DTC of an induction machine with experimental implementation on FPGA

This paper presents Artificial Neural Networks (ANN) and Adaptive Neural-Fuzzy Inference System (ANFIS) for reduction of torque and flux ripples in transient and steady state response of Direct Torque Control (DTC) for Induction Motor drive. The Flux and Electromagnetic torque can be controlled by using efficient Direct Torque Control (DTC) scheme This proposed technique is to improve the torque, speed and flux response with the Artificial Neural Network (ANN) and then with the Adaptive Neuro-Fuzzy Inference (ANFIS). This paper shows implementation of DTC system using ANN and ANFIS on three phase induction motor to optimize the flux and to improve the performance of fast stator flux response in transient state. To improve the performance of DTC with the modern technique using ANN and ANFIS approach is implemented and performance of ANN DTC compared with CDTC and ANN DTC with ANFIS is done, conclusion is about the ANN approach shows the better performance than CDTC and ANFIS shows superior performance than ANN. The performance has been tested by using MATLAB/SIMULINK and NEURAL NETWORK toolbox.

In this paper, a design method of direct torque control (DTC) of an induction machine, which is based on fuzzy logic control (FLC), is proposed. The FLC which is introduced to improve the DTC uses a reduced number of fuzzy inference rules that facilitates the reduction of the FLC computation time. The improvement is performed by reducing the torque and stator flux ripples in the induction machine drive. Then, a hardware description that is based on the VHDL hardware description language of the proposed design is presented and discussed. The techniques of the parallel architecture, direct computation, and modular architecture are adopted for the design of the controller. Simulation and experimental results of the DTFC are compared with those of the conventional DTC. The comparison results illustrate the reduction in the torque and stator flux ripples of the DTFC. The validity of the proposed method is confirmed by the simulation and experimental results.

The objective of this paper is to design and study of duty ratio modulated modified Direct Torque Control drive, especially for Permanent Magnet Synchronous Motor (PMSM). Conventional Direct Torque Control (DTC) is typically associated with torque ripple and stator flux ripple. Duty ratio modulated direct torque control (DDTC) reduces torque ripple and stator flux ripple. For high performance applications the conventional DDTC is again modified to obtain comparatively less torque and flux ripple. In this paper the DDTC is associated with MTPA approach to obtain duty ratio calculation more effectively.

The direct torque control (DTC) system, which is based on induction machine drive is a developed and simple control method. It allows high dynamic performance with very simple hysteresis control scheme; However, its disadvantages are high current, torque, and flux ripple. In this paper, DTC of induction machine drive has been improved by using the applications of artificial intelligence (AI) approaches to reduce the current, torque, and flux ripples and also get better performance of the machines. At the conclusion of this study, the outcomes of traditional DTC and artificial intelligent methods are compared. By the program MATLAB/SIMULINK, the modeling and simulation results of the DTC system for induction machine (IM) have been proposed.

This paper proposes a novel direct torque control (DTC) scheme to reduce the torque and stator flux ripples for permanent-magnet synchronous motor (PMSM) drives using a relatively low sampling frequency. Unlike the conventional DTC in which the voltage vectors are determined by hysteresis controllers, the proposed DTC uses nonlinear saturation comparators and a duty ratio modulation scheme for switch selection and switching duration determination. Compared to the conventional DTC, the proposed DTC scheme significantly reduces the steady-state torque and flux ripples of PMSMs while preserving most of the intrinsic properties of the conventional DTC, e.g. fast dynamic, robust to disturbances, no coordinate transformation, etc. The effectiveness of the proposed DTC scheme is verified by simulation and experimental results on a 200W PMSM drive system.

In this chapter, we will compare the performance of a multilevel direct torque control (DTC) control for the double-star induction machine (DSIM) based on artificial neural network (ANN). The application of DTC control brings a very interesting solution to the problems of robustness and dynamics. However, this control has some disadvantages such as variable switching frequency, size, and complexity of the switching tables and the strong ripple torque. A solution to this problem is to increase the output voltage level of the inverter and associate the DTC control with modern control techniques such as artificial neural networks. Theoretical elements and simulation results are presented and discussed. As results, the flux and torque ripple of the five-level DTC-ANN control significantly reduces compared to the flux and torque ripple of the three-level DTC-ANN control. By viewing the simulation results using MATLAB/Simulink for both controls, the results obtained showed a very satisfactory behavior of this machine.

Among all the control methods developed for Induction Motor (IM) drivers, the hysteresis controller based Direct Torque Control (DTC) method has an important place. This control method does not require other rotor and stator parameters except the stator resistance and does not require position or velocity sensors. However, there are some disadvantages of the DTC method, such as high torque, flux and current ripples. In this study, in order to reduce the high torque ripples occurring in an induction motor that is controlled by the hysteresis controller based conventional DTC method, a simple and effective Sugeno type Neuro-Fuzzy Torque Controller (NFTC) is proposed. This proposed controller is used instead of hysteresis controller. An experimental setup consisting of 1.1 kW induction motor, current and voltage measurement, DS1103 control card and two-level voltage source inverter was installed. To evaluate the performance of the proposed controller structure, various experimental studies were performed. Results obtained from the proposed NFTC based structure and conventional hysteresis controller based DTC structures are given comparatively. By the obtained experimental results, it was confirmed that the proposed NFTC-based controller structure considerably reduced flux and torque ripples in the motor.

Introduction. Currently, the direct torque control is very popular in industry and is of great interest to scientists in the variable speed drive of asynchronous machines. This technique provides decoupling between torque control and flux without the need to use pulse width modulation or coordinate transformation. Nevertheless, this command presents two major importunities: the switching frequency is highly variable on the one hand, and on the other hand, the amplitude of the torque and stator flux ripples remain poorly controlled throughout the considered operating speed range. The novelty of this article proposes improvements in performance of direct torque control of asynchronous machines by development of a fuzzy direct torque control algorithm. This latter makes it possible to provide solutions to the major problems of this control technique, namely: torque ripples, flux ripples, and failure to control switching frequency. Purpose. The emergence of this method has given rise to various works whose objective is to show its performance, or to provide solutions to its limitations. Indeed, this work consists in validation of a fuzzy direct torque control architecture implemented on the ML402 development kit (based on the Xilinx Virtex-4 type field programmable gate array circuit), through hardware description language (VHDL) and Xilinx generator system. The obtained results showed the robustness of the control and sensorless in front of load and parameters variation of induction motor control. The research directions of the model were determined for the subsequent implementation of results with simulation samples.

The direct torque control (DTC) technique for a three-phase induction and synchronous motor is receiving increasing attention due to the important advantages as the elimination of the current controllers and the low dependence on motor parameters when compared with other motor control techniques. However high torque and stator linkage magnetic flux ripples and stator voltage and, stator current harmonic contents result when using a two-level inverter with hysteresis controller. This paper presents simulation results of a three-phase permanent magnet synchronous motor (PMSM) fed from a three-level voltage-controlled inverter showing low air-gap flux and torque ripples and reduced stator current and stator voltage harmonic distortion. As far as the authors know this is the first paper showing the benefits of the use of a three-level voltage-controlled inverter in DTC scheme to control the torque and speed of PMSM with the proposed algorithm.

This paper presents the implementation of a high performance direct torque control (DTC) of induction machines drive. DTC has two major problems, namely, high torque ripple and variable switching frequency. In order to solve these problems, this paper proposed a pair of torque and flux controllers to replace the hysteresis-based controllers. The design of these controllers is fully discussed and a set of numerical values of the parameters for the proposed controllers is given. The simulation of the proposed controllers applied to the DTC drive is presented. The simulation results are then verified by experimental results. The hardware implementation is mainly constructed by using DSP TMS320C31 and Altera FPGA devices. The results prove that a significant torque and stator flux ripples reduction is achieved. Likewise, the switching frequency is fixed at 10.4 kHz and a more sinusoidal phase current is obtained.

• A new water pumping system configuration is proposed, based on the DFIG. • The Fuzzy INC MPPT technique is used to extract the maximum power available from the PV array, while the TSR-based MPPT optimizes the available wind energy; • Advanced FDTC control to enhance the dynamic performances by minimizing the stator flux and torque ripple of the SCIM. • Proposing an energy management algorithm employing the self-powering feature of the DFIG to charge the batteries. This paper introduces a promising structure incorporating renewable energies to meet the water needs of a small-scale manufacturing system. The innovative design provides a continuous water supply. The proposed configuration is an effective and eco-friendly solution for the water pumping application. This novel structure includes a Variable Wind Energy Conversion System (VWECS) based on a Doubly Fed Induction Generator (DFIG), a Photovoltaic (PV) system, and batteries serve as a storage unit. Furthermore, the Squirrel Cage Induction Motor (SCIM) is used to drive the centrifugal pump in the water pumping system. Moreover, an Energy Management System (EMS) is proposed to ensure the seamless synergy among all the components of the new structure. The particularity of this latter includes the unique feature of self-powering of the DFIG. The stator power is employed in the DC bus to fulfill the energy requirement in the deficiency mode. This allows the batteries to recharge even in the case of a deficiency. Additionally, the proposed algorithm supervises the batteries to avoid deep discharges and excessive overcharges. On the other hand, Advanced non-linear techniques such as Fuzzy Twelve Direct Torque Control (F12DTC) and Fuzzy Twelve Direct Power Control (F12DPC) are applied to the back-to-back inverter instead of the conventional methods, Direct Torque Control (DTC) and Direct Power Control (DPC) to enhance the dynamic performances of the two-level back-to-back converter in terms of the ripples and Total Harmonic Distortion (THD) shortcomings of the controlled variables (torque, flux, active and reactive powers) by the combination of the Fuzzy Logic controller (FLC), and the twelve sector methodology for accurate voltage selection. In addition, the DTC exhibits significant ripples of the stator torque and the flux magnitudes in the water pumping system. Therefore, the Fuzzy Direct Torque Control (FDTC) is used to drive the SCIM. The powerful tool FLC is employed to replace the hysteresis controllers and handle uncertainties of the controlled variables. The simulation findings by MATLAB/Simulink demonstrate the effectiveness and robustness of the EMS in decision-making and utilize the self-powering feature to recharge the batteries. In addition, successfully supervises the batteries in the optimal range of 20 % and 90 %. Thus, extending the life span and reducing the depth of charge of the batteries. Finally, the simulation results validate the higher performance of the proposed advanced techniques in mitigating the drawbacks of the conventional methods. The F12DTC technique reduces rotor flux and torque ripples by 68 % and 67 %, respectively. The F12DPC ensures efficient power control, minimizing active and reactive power ripples to over 50 % with a minimum total harmonic distortion of 1.69 % for the grid side converter currents, which conforms to the IEEE 519 standards.

Conventional direct torque control (DTC) achieves faster dynamic response compared to field-oriented control in permanent magnet synchronous motor drives (PMSM). However, it usually features large torque and stator flux ripple which deteriorates the steady performance of PSM drive. Various duty- based DTC schemes have been proposed to reduce torque ripple at the expense of increased complexity and parameter dependent. According to the perspective of flux vectors and load angle, a simple yet efficient method is proposed to calculate the duty ratio of active vector. The proposed scheme is able to reduce torque ripple significantly and is insensitive to variations in PMSM parameters, while the inherent merits of the conventional DTC, e.g., fast transient performance and simple control structure, are maintained. Simulations results are provided to confirm the valid of the proposed method.

In this work, the direct torque control (DTC) is applied to the five-phase permanent magnet synchronous motor (FP-PMSM). The DTC method based on classical space vector pulse width modulation (SVPWM) is a common solution used to overcome traditional problems; such as stator flux ripple, electromagnetic torque ripple and gives more total harmonic distortion (THD) of the stator current. The actual paper is based on improving the performance of DTC-SVPWM by using the feedforward neural networks (FNNs) instead of the proportional-integral (PI) regulators and hysteresis comparators (HCs) of the conventional SVPWM strategy. This algorithm can solve the traditional PI regulators and HCs problems which are represented in responses dynamic and reduce the torque ripple, flux ripple, and the THD of stator current of FP-PMSM drives. The proposed strategy was tested in different tests with simulation using Matlab software.

A fuzzy direct torque control (DTC) algorithm to permanent magnet synchronous motor (PMSM) with a novel space vector modulation (SVM) defuzzification is proposed. The defuzzification unit outputs a vector contains two voltage vectors as well as the duty of each vector instead of a single vector. And more voltage vectors can be obtained. A simulation model is built up, basic DTC and conventional fuzzy DTC and proposed fuzzy DTC are carried out respectively. Torque ripple, flux ripple and current distortion are compared and analyzed. The proposed fuzzy controller makes the torque and flux ripples lower and current smoother compared with basic DTC and conventional fuzzy DTC.

SummaryThe switched reluctance motor (SRM) is a prominent electrical machine drive with low cost and good performance in different drive applications. This machine's main drawbacks are torque ripple and flux ripple. However, the existing SRM‐operated direct torque control (DTC) Voltage vectors (VVs) give high torque ripples due to improper sector division and minimum selection of VVs switching states. On the other hand, a two‐level hysteresis torque band can result in torque ripples. Therefore, this paper proposed DTC using 16 partitions, active small and large VVs, and a multilevel hysteresis torque band (MHTB) strategy to mitigate the torque ripple further. More active VVs (i.e., 16) are employed in the modified sector‐based switching tables, suppressing the torque ripples. The proposed strategy is verified and validated using MATLAB/Simulink. The detailed result discusses the response of torque, flux, and speed of SRM. The DTC‐operated SRM drive experimental results prove the effective minimization of torque ripples in the proposed DTC compared to the existing DTC.