Search

In critical applications of electrical machines, ensuring validity and safety is paramount to prevent system failures with potentially hazardous consequences. The integration of machine learning (ML) technologies plays a crucial role in monitoring system performance and averting failures. Among various motor types, permanent magnet synchronous motors (PMSMs) are widely favored for their versatile speed range, enhanced power density, and ease of control, finding applications in both industrial settings and electric vehicles. This study focuses on the detection and classification of the percentage of broken magnets in PMSMs using a pre-trained AlexNet convolutional neural network (CNN) model. The dataset was generated by combining finite element methods (FEMs) and short-time Fourier transform (STFT) applied to stator phase currents, which exhibited significant variations due to diverse broken magnet structures. Leveraging transfer learning, the pre-trained AlexNet model underwent adjustments, including the elimination and rearrangement of the final three layers and the introduction of new layers tailored for electrical machine applications. The resulting pre-trained CNN model achieved a remarkable performance, boasting a 99.94% training accuracy and 0.0004% training loss in the simulation dataset, utilizing a PMSM with 4% magnet damage for experimental validation. The model's effectiveness was further affirmed by an impressive 99.95% area under the receiver operating characteristic (ROC) curve in the experimental dataset. These results underscore the efficacy and robustness of the proposed pre-trained CNN method in detecting and classifying the percentage of broken magnets, even with a limited dataset. [ABSTRACT FROM AUTHOR]

The income inequality-economy link has been argued by researchers a long time. But the impact of income inequality on environmental pollution is a new investigation topic for developing countries. Turkey is well known as an emerging economy which has a high level of income inequality and CO2 emissions. Therefore, this paper concentrates on the income inequality-CO2 emissions link in Turkish economy by applying a nonlinear analysis. This paper integrates economic growth and financial development to the CO2 emissions specification over the period of 1987–2019. We employ the nonlinear autoregressive distributed lag approach to explore the long-run nonlinear linkages between the series. Our findings reveal an asymmetric cointegration among variables. Positive and negative income inequality shocks positively affect CO2 emissions implying that positive and negative shocks of income inequality enhance CO2 emissions in the long run. Negative economic growth shocks decrease CO2 emissions, while positive shocks to financial development increase CO2 emissions in the long run. We provide important policy suggestions that might be useful to the policymakers to decrease CO2 emissions in Turkey. [ABSTRACT FROM AUTHOR]

The integrity of electric motors in work and passenger vehicles can best be maintained by frequently monitoring their condition. In this paper, a signal processing-based motor fault-diagnosis scheme in detail is presented. The practicability and reliability of the proposed algorithm are tested on rotor asymmetry detection at zero speed, i.e., at startup and idle modes in the case of a vehicle. Regular rotor asymmetry tests are done when the motor is running at a certain speed under load with stationary current signal assumption. It is quite challenging to obtain these regular test conditions for long-enough periods of time during daily vehicle operations. In addition, automobile vibrations cause nonuniform air-gap motor operation that directly affects the inductances of electric motors and results in a noisy current spectrum. Therefore, it is challenging to apply conventional rotor fault-detection methods while examining the condition of electric motors as part of the hybrid electric vehicle (HEV) powertrain. The proposed method overcomes the aforementioned problems by simply testing the rotor asymmetry at zero speed. This test can be achieved at startup or repeated during idle modes, where the speed of the vehicle is zero. The proposed method can be implemented at no cost using the readily available electric motor inverter sensor and microprocessing unit. Induction motor fault signatures are experimentally tested online by employing the drive-embedded master processor [TMS320F2812 digital signal processor (DSP)] to prove the effectiveness of the proposed method. Index Terms--Digital signal processor (DSP)-based fault detection, hybrid electric vehicle (HEV), induction motor, motor fault diagnosis.

With the increase in prosperity level and industrialization, energy need continues to overgrow in many countries. To meet the rapidly increasing energy needs, countries attach great importance to using limited natural resources rationally, diversifying their energy production using novel technologies, improving the efficiency of existing technologies, and implementing policies and strategies toward alternative energy sources. In particular, individual energy prosumers (someone that both produces and consumes energy) head toward smart home energy management systems (SHEMS) that include renewable energy sources in their homes. By integrating PV solar panels into houses, there is a need to optimize home energy production/consumption scenarios by consumer behavior. In this study, an intelligent residential energy management architecture and algorithm to manage residential energy production/consumption are proposed. The algorithm controls the energy flow in the home according to real-time potential solar power estimation, demanded energy estimation, electricity consumption price, and battery state-of-charge (SoC). The fuzzy logic algorithm has been developed to determine the estimated comfort and cost-effectiveness ratios in the near future. The simulated annealing algorithm, a meta-heuristic algorithm, is performed to obtain the best operating point decision of the battery using the comfort and cost-effectiveness ratios. Energy flow direction and battery SoC are optimized using simulated annealing based on the comfort and cost-effectiveness ratio (comparison of alternatives with respect to multiple criteria of different levels of importance for energy usage). The focus is to generate maximum profit from energy sales for monthly profit to be achieved. Prototyped hardware and software are implemented and tested in real-time. The test results show that the 20% reduces energy consumption, and a monthly gain of $89.2 is obtained from energy sales using the proposed method. Therefore, the test results reveal the effectiveness of the proposed architecture and algorithm. [ABSTRACT FROM AUTHOR]

Power electronic systems are rapidly evolving; thus, effective prototyping methods are required to test control algorithms and assess system performance prior to hardware implementation. This research suggests a Model-In-The-Loop (MIL), Software-In-The-Loop (SIL), and Processor-In-The-Loop (PIL) methodologies-based complete prototyping strategy for flyback converters using the TI F28069M Launchpad kit. These techniques can be combined to evaluate control strategies accurately and quickly, speeding up design cycles and enhancing system reliability. The proposed prototyping platform is presented in this work, along with a thorough explanation of each prototyping stage and its associated advantages. The effectiveness of the suggested approach for 50W rated power flyback converter in terms of quick algorithm development, system simulation, real-time control implementation and controller design accuracy is analyzed and shown by experimental results. The results show that the performance of the designed controller for the flyback converter is almost the same as in MIL and SIL implementation in terms of the overshoot and settling time in the reference voltage tracking. On the other hand, in the PIL implementation, the overshoot performance of the controller deviates by 1.18% more than in SIL and MIL implementation. These also confirm that the flyback control system's performance is reliable and effective during all phases of development. [ABSTRACT FROM AUTHOR]