In this paper, a practical machine learning based fault diagnosis method is proposed for induction motors using experimental data. Various single- and multi- electrical and/or mechanical faults are applied to two identical induction motors in lab experiments. Stator currents and vibration signals of the motors are measured simultaneously during experiments and are used in developing the fault diagnosis method. Two signal processing techniques, Matching Pursuit (MP) and Discrete Wavelet Transform (DWT), are chosen for feature extraction. Three classification algorithms, support vector machine (SVM), K-nearest neighbors (KNN), and Ensemble, with 17 different classifiers offered in MATLAB Classification Learner toolbox are used in the study to evaluate the performance and suitability of different classifiers for induction motor fault diagnosis. It is found that five classifiers (Fine Gaussian SVM, Fine KNN, Weighted KNN, Bagged trees, and Subspace KNN) can provide near 100% classification accuracy for all faults applied to each motor, but the remaining 12 classifiers do not perform well. A novel curve fitting technique is developed to calculate features for the motors that stator currents or vibration signals under certain loadings are not tested for a particular fault. The proposed fault diagnosis method can accurately detect single- or multi- electrical and mechanical faults in induction motors.

This paper investigates the issues of day-ahead and real-time cooperative energy management for multienergy systems formed by many energy bodies. To address these issues, we propose an event-triggered-based distributed algorithm with some desirable features, namely, distributed execution, asynchronous communication, and independent calculation. First, the energy body, seen as both energy supplier and customer, is introduced for system model development. On this basis, energy bodies cooperate with each other to achieve the objective of maximizing the day-ahead social welfare and smoothing out the real-time loads variations as well as renewable resource fluctuations with the consideration of different timescale characteristics between electricity and heat power. To this end, the day-ahead and real-time energy management models are established and formulated as a class of distributed coupled optimization problem by felicitously converting some system coordinates. Such problems can be effectively solved by implementing the proposed algorithm. With the effort, each energy body can determine its owing optimal operations through only local communication and computation, resulting in enhanced system reliability, scalability, and privacy. Meanwhile, the designed communication strategy is event-triggered, which can dramatically reduce the communication among energy bodies. Simulations are provided to illustrate the effectiveness of the proposed models and algorithm.

With more renewable energy based distributed generation (DG) units connected to utility power grids, deterioration of power quality at the point of common coupling (PCC) becomes a major concern. There are two types of harmonics associated with DG units, and together they may cause excessive harmonic distortion at the PCC. The first type of harmonics is generated by power electronic devices in DG units such as photovoltaic systems, which contains high-frequency harmonic components at multiples of the carrier frequency of the DG interfacing inverter. Such harmonics are first reviewed in this paper, and the potential operational effect at the system level due to LCL or LC filters installed at the inverter output to mitigate such harmonics are discussed. The second type of harmonics is generated by other nonlinear local, PCC, and utility loads in the system, which are common type of harmonics at multiples of the power grid frequency, 50/60 Hz. Harmonic mitigation for such harmonics achieved through advanced control of the DG interfacing inverter operated as a power quality conditioner are reviewed and summarized. This systematic review can facilitate better understanding of harmonics associated with renewable energy based DG units and provide guidelines on advanced control schemes to realize ancillary harmonic compensation service through DG interfacing inverters.

Condition monitoring and fault diagnosis of induction motors serve as essential techniques toward the reliable operation of critical industrial processes. The finite element method (FEM) offers a great insight into fundamental principle and physical operation of the machine. It can model complex magnetic circuit topology, discrete windings layouts, and nonlinear magnetic material properties of the machine. It determines the machine parameters (such as the magnetic field distribution, flux density, electromagnetic torques, and stator current) and can model localized magnetic saturation due to faults to a high degree of accuracy. Used as fault detection algorithms, the FEM can address the issues such as the lack of comprehensive fault databases through field measurements, and the difficulty in distinguishing fault severity. It can reduce the number of destructive tests required in the field/labs, simulate any faulty states of the machine. Although FEM has been widely used in induction motors' design and analysis, its application in fault diagnosis is limited despite the promising potential. In this article, a literature review is conducted on induction motor fault diagnosis techniques using FEM. The state-of-the-art techniques reported in the literature are categorized into three streams: first, FEM-based fault diagnosis approach, second, FEM and signal processing-based approach, and third, FEM, machine learning, and other advanced techniques-based approach. The advantages of fault diagnosis techniques using the FEM are demonstrated and the future research direction is recommended.

Load forecasting is a critical aspect for power systems planning, operation and control. In this paper, as part of research efforts of an ambitious project at Memorial University of Newfoundland in St. John’s, Canada, to achieve more energy efficient and environmental friendly “Sustainable Campus”, we present a day-ahead load forecasting approach for the energy management system of the project. The hourly load consumption dataset from January 1, 2016 to March 31, 2020 is used in the paper, which was collected from two power meters on campus. Using the load consumption dataset along with the collected meteorological dataset, a total of 19 regression model-based day-ahead load forecasting algorithms for Memorial University of Newfoundland’s campus load are developed and evaluated in this paper. These 19 models belong to five families of regression models in MATLAB Regression Toolbox: Linear Regression, Regression Trees, Support Vector Machines (SVM), Gaussian Process Regression (GPR), and Ensemble of Trees. It is found that the family of GPR models shows the best load forecasting performance because they are nonparametric kernel-based probabilistic models. Two GPR models, Rational Quadratic GPR and Exponential GPR, are recommended as the best models for load forecasting through this study.

As a new emerging approach, Virtual Synchronous Generator (VSG) control for interfacing inverters in renewable distributed generation (DG)-based microgrids has attracted significant research interest. However, VSG control cannot ensure proportional reactive power sharing among DG units when unequal transmission line impedances are involved, although active power sharing remains proportional among DGs. In this paper, an adaptive virtual impedance-based VSG control approach for grid-connected and islanded microgrids is proposed to alleviate impedance difference at the inverter output and improve proportional reactive power sharing among DGs. The virtual impedance consists of an adaptive virtual resistance and a fixed virtual inductance, where the virtual resistance is designed adaptively based on operation points of the microgrid. In this paper, the proposed adaptive virtual impedance control is implemented on a modified VSG control, known as Fuzzy secondary controller (FSC)-based VSG control, offering excellent voltage and frequency regulation at the PCC. Its performance is demonstrated through case and sensitivity studies using MATLAB/Simulink simulation; and further validated by comparing with an existing method.