Aug 2026· International Conference on Circuit, Power and Computing Technologies· pp. 1430-1435· 0 citations· 8 references
Abstract
In this work, an advanced PFC converter was designed and AI-based predictive maintenance (PM) module was suggested to be included in complex PMSM drives.In this paper, an advanced PFC converter was designed and the AI based predictive maintenance (PM) module was proposed to be added in a complex PMSM drives system. The power quality of the PFC stage is good and reduces the generation of harmonic distortion caused by PWM based soft switching and effectively controls the power factor close to unity by using the capacitor bank controls, and noise suppression. The converter, motor drive, communication and data processing is controlled by a microcontroller. The use of a multi-sensor approach, which uses a three-axis accelerometer for vibration monitoring, a current sensor for electrical fault detection and a temperature sensor for thermal condition assessment, is used in the predictive maintenance system. These are then inputted into machine-learning algorithms, that detect unabnormal vibration, temperature and current fluctuations, which happen at the occurrence of faults such as bearing wear, rotor misalignment, inverter switching problems, thermal stress and so on. The integrated solution provides greater efficiency and reliability of the PMSM drives, increased equipment life and maintenance effectiveness, reduced unexpected downtime and operating costs.
In the present work, an artificial intelligence (AI)-based direct current to alternating current converter is developed for fast power conversion with reduced harmonic distortion in three-phase power systems. The system that comprises a DC-link source, inverter switching network, pulse width modulation (PWM) control method, output filter and AI-based adaptive controller minimise voltage fluctuation and improves quality waveforms. An adaptive switching signal for inverter generation based on the error in voltage, rate of change of error and variations in power along with DC-link voltage is processed as a part of the control strategy. Mathematical modelling is established using inverter pole-voltage equations, neutral-point voltage compensation, Clarke and Park transformations, sinusoidal reference generation, the modulation index ratio to duty ratio for filter dynamics, and root mean square (RMS) estimation, along with total harmonic distortion (THD). The performance metric is a weighted sum of voltage tracking error, current variation and harmonic distortion, which aims to provide a stable low-distortion operation for the converter. Results of the simulation demonstrate accuracy in converter response, including input DC voltage, switching pulse patterns, unfiltered output voltage, filtered three-phase AC voltage and THD. The emulated DC-AC converter can be used for renewable energy systems, grid-connected inverter applications, electric vehicle power interfaces and various configuration units that require stable voltage output and reduced distortion.
S. Venkatakiran, N. B, V. S. Reddy et al.· 2026 6th International Confe...· 0 citations
Pulse Width Modulation (PWM) is a popular control method used in embedded and power electronics systems to control voltage, speed, and power in applications like motor drives, converters, lighting systems, and Internet of Things (IoT) devices. The traditional PWM controllers tend to be implemented by fixed or rule-based control schemes and usually have one operating parameter which restricts their flexibility and operation in dynamically changing environmental and load conditions. Adaptive PWM strategies have received more and more attention with increasing demand of intelligent and flexible control systems built on embedded platforms. In this regard, the concept of machine learning (ML) can be effectively utilized as a data-driven solution to the problem, whereby it learns the connection between various system parameters and the duty cycle that is needed. In this paper, a multi-parameter closed-loop adaptive PWM control approach based on machine learning is proposed, in which temperature, speed, and load would be collectively counted in predicting the duty cycle. A comparative analysis of lightweight machine learning models is conducted to determine the most appropriate one to be used in embedded implementation regarding the accuracy of prediction and calculation efficiency. Moreover, a feedback loop is used to help build a more stable system and counterbalance prediction errors and external disturbances. The framework proposed is more adaptable, robust and more accurate in control and has low computational complexity, which makes it suitable to resource-constrained embedded and IoT-based control applications.
Abhinav Chalil, Vivek Ashok Nair, R. Megalingam· International Conference on...· 0 citations
This study examines four MPPT strategies for a solar pumping application subjected to rapid and simultaneous fluctuations in irradiance and temperature. These variations influence the torque and rotational speed of the Permanent Magnet DC (PMDC) motor. The conventional Incremental Conductance (IC) and Perturb and Observe (P&O) algorithms, which use reference-voltage generation, are compared with Takagi-Sugeno (FL-TS) and Mamdani (FL-Mamdani) fuzzy controllers. The conversion chain includes a photovoltaic array, a boost converter, and a PMDC motor that drives a centrifugal pump. All controllers and system components were modelled and simulated using MAT-LAB/Simulink. The results show that the fuzzy controllers provide improved robustness and faster tracking. Fuzzy MPPT structures typically use the gradient of the power-voltage characteristic,
E
= d
P
/d
V
, and its variation as input variables. The proposed formulation instead employs the gradient of the power-current characteristic,
E
= d
P
/d
I
, and its variation, thereby improving stability and dynamic response. Response times of 85.69 ms and 61.07 ms are obtained with FL-Mam and FL-TS, respectively, compared with 320.06 ms for IC and 276.63 ms for P&O. The boost converter also achieves an efficiency of approximately 97%.
Mohammed Boutaybi, Y. Khlifi, A. Hali· EPJ Web of Conferences· 0 citations
The increasing demand for electric drives in the context of electrification requires the development of advanced, efficient control systems. Modern electric drives require high dynamic response and robustness to varying operating conditions. In this paper, the authors propose a Model Predictive Current Control with Preliminary Voltage Vector Selection (PVVS-MPCC). In this novel concept, the squared difference between the reference and measured current values is used, along with an analytical method to determine optimal scaling factors. The proposed solution was evaluated and compared with Continuous Control Set MPCC (CCS-MPCC), deadbeat duty-cycle MPCC (DB-MPCC), and a preliminary voltage vector selection based on low-pass filtering. Experimental results demonstrate that the developed control scheme achieves lower current ripple and higher robustness against drive-parameter variations while maintaining high dynamic performance, compared to reference methods.
Hubert Lisinski, T. Tarczewski· Electronics· 0 citations
This paper describes an advanced algorithm for current control in a modular multilevel power converter based on deadbeat model predictive control, which is further enhanced by applying an artificial neural network.
Milovan Majstorović, B. Brkovic, L. Ristic et al.· IEEE Open Access Journal of...· 0 citations
The traditional photovoltaic (PV) systems have several limitations, such as low voltage gain and inefficient power extraction, this study proposes a single-phase grid-connected PV system to increase solar power conversion and grid integration efficiency. A DC–DC NX cascaded converter is used by the system to boost the PV output voltage, and a Radial Basis Function Neural Network (RBFNN)-based MPPT (Maximum Power Point Tracking) is used to maximise the PV panel’s power output. PWM signals are generated by a DSPIC30F4011 controller to regulate the inverter and converter stages. Furthermore, a DQ control theory-based Proportional Integral (PI) controller controls the inverter output and keeps it in sync with the utility grid. The proposed system achieves a converter efficiency of 93% and an MPPT tracking efficiency of 95%, according to the simulation results.
J. Antony Robinson, S. Anna Planteena, S. V. Nithya Shree et al.· International Conference on...· 0 citations
