Maximum Power Point Tracking During Partial Shading Effect in PV System Using Machine Learning Regression Controller

Padmavathi N.,Chilambuchelvan A.,Shanker N. R. 대한전기학회 2021 Journal of Electrical Engineering & Technology Vol.16 No.2

Maximum Power Point Tracking (MPPT) algorithm performs for maximizing the effi ciency of solar Photo Voltaic (PV) system. The solar photovoltaic system effi ciency reduces due to partial shading and ambient atmospheric condition, which varies with geographic locations. Traditional MPPT systems solve the above problem through diff erent soft computing algorithms such as Perturb and observe (P&O), Flower pollination algorithm (FPA) and Particle swarm optimization (PSO). In P&O, FPA and PSO algorithms, duty cycle of boost converter varies to attain MPPT. The soft computing algorithms in MPPT perform less during the partial shading eff ect or rapid insolation, fl uctuation condition of solar energy. The performance of MPPT with traditional algorithms is reduced due to slow convergence speed and oscillations in tracking by computing algorithms. In this paper, Regression controller based MPPT achieve maximum peak voltage during partial shading eff ect is developed. The regression controller predicts the duty cycle for boost converter based on stored dataset of PV system output voltage and load, during partial shading eff ect or rapid isolation for that particular geographic location. The regression based duty cycle prediction controller is programmed in MATLAB R2018a Simulink. Furthermore, Regression controller is implemented in PV system test bed. The simulation and hardware results of Regression controller based MPPT perform more of about 20%, 16.96% and 15% in effi ciency respectively than PSO, FPA and P&O algorithms during partial shading condition in PV.

Development of Machine Learning Based Microclimatic HVAC System Controller for Nano Painted Rooms Using Human Skin Temperature

Lavanya R.,Murukesh C.,Shanker N. R. 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.3

In this paper, a microclimatic data based occupancy regression controller (ORC) is proposed for heating, ventilation, and air conditioning (HVAC) systems and is termed microclimatic HVAC (M-HVAC). Microclimatic data consist of various measurements such as PIR, CO2, humidity, wall, floor and roof temperatures, as well as human skin temperature for the prediction of the optimal thermal setpoint temperature in an M-HVAC system. Microclimatic conditions have a major role in building energy consumption and indoor thermal comfort. Human skin temperature, wall, floor and roof temperatures in the room are obtained through a thermal camera. ORC controller performance is evaluated on the SiO2 nanocoated room walls for high energy savings. Up until now, researchers have focused on the optimization of thermal setpoint temperature (SPT) using indoor air temperature and room occupant count data, but have never addressed the microclimatic conditions. ORC predicts the optimal SPT after including the microclimate data. M-HVAC systems implement the ORC using a Raspberry Pi board connected with sensors and a thermal camera. ORC leads to thermal comfort in a room and reduces energy consumption. ORC improves prediction accuracy through regression analysis and reduces the energy cost of about 23.9% when compared to the traditional method. ORC provides high thermal comfort of about 97% with higher energy savings than the traditional method of temperature setpoint.

Induction Motor Torque Prediction Using Dual Function Radar Received Polarised Signals and Machine Learning Algorithm

Chinthamani B.,Kavitha S.,Bhuvaneswari N. S.,Shanker N. R. 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.5

Induction motor is used for different applications in industries such as grinding, milling, mining and automation. Induction motor performance degrades over time due to continuous operation, over load, transient unbalanced supply voltage and current. Hence, induction motor performance and efficiency are evaluated through measurement of motor torque. The torque measurement using various sensors such as acoustic, mems-vibration, strain gauge, in line sensors, never provides the inaccurate results due to contact type sensors and improper mounting of sensor on the motor. Moreover, existing methods never provides inaccurate torque measurement for different types of motor duty cycle such as continuous duty, intermittent periodic duties, short-time duty and continuous operation with intermittent load. In this paper, novel non-contact method measures torque with Dual-function ultra-wide band (UWB) (DFR) Radar sensor. DFR acquires polarized signal reflected from air gap of motor magnetic flux. Moreover, air gap magnetic flux radiation through motor ventilator is directly proportional to motor torque. In this paper, motor torque is measured through air gap magnetic flux radiation and DFR sensor. The electromagnetic waves from DFR is reflected by the air gap magnetic flux emitted from motor and the reflected waves are polarized. The reflected DFR sensor signal from air gap magnetic flux has high polarity charge and resonance. From received polarized signal, Instantaneous Frequency (IF) is obtained through Multi-Synchro Squeezing Transform (MSST) algorithm. The motor torque is measured with IF and Gaussian regression algorithm. Torque spikes in Induction motor is analyzed during frequent change in heavy, low load, and induced transient Torque prediction through MSST IF frequency and Gaussian Regression is compared with Torque predicted through different transform such as Discrete Wavelet Transform (DWT), Stationary Wavelet Transform (SWT), Dyadic Wavelet Transform (DyWT). The MSST based torque measurement provides 96% of accuracy, when compared with traditional strain gauge torque measuring instrument. Initial review.

Running State Monitoring of Induction Motor Windings Using Near Infra-red Sensor Residual Signal and Q Factor Analysis

Gani M. Ismail,Jothi Swaroopan N. M.,Shanker N. R. 대한전기학회 2022 Journal of Electrical Engineering & Technology Vol.17 No.3

In Electric motors, identifi cation of insulation and winding faults in stator and rotor during running state is a challenging task. Winding and insulation fault is identifi ed through burning smell of coil, evaluating the effi ciency of motor, or dismantling of motor. Motor running with winding and insulation faults lead to coil-to-coil and phase-to-phase short circuit fault. Winding insulation and winding coil fault in motor leads to unbalanced and diff erential fl ux radiation. Monitoring the winding and insulation during running state of motor is a challenging task. In this paper, monitoring of stator and rotor winding is proposed through NIR sensor during running state of motor. Near Infra-Red (NIR) sensor is fi xed in air gaps of motor. NIR refl ect rays from winding fl ux through air gaps are analysed for faults in stator and rotor winding and insulation. NRI refl ected signals process with spectral band separation and NIR refl ected residual (NRR) signals are obtained. NRR signal process with Tunable Q Wavelet Transform (TQWT) for monitoring and detecting, the insulation and winding fault of motor. Motor allowed to operate at diff erent induced faults such as no load, loaded, stator, rotor insulation fault and stator, rotor-winding fault and NRR signal obtained. Q-factor base Energy band of NRR signals are analysed for winding and insulation faults through sub band energy variations. The low and high frequency component of faulty NRR signal detect with TQWT more accurately. The performance of NIR sensor-based winding and insulation fault diagnosis is compared with conventional transducers such as current signatures and radar signals. The NIR sensor based NRR signals classifi es insulation and winding fault accurately of about 92% compared to current signal signatures.