Microgrids are localized electric grids that can operate independent of the main grid and help strengthen grid resiliency by working alongside backup generators to maintain electricity supply in the event of a large-scale grid disturbance. This research proposes a single-source capacitated facility location coverage problem (SS-CFLCP) to optimize the location, assignment and number of renewable distributed generators (DGs) within a utility-based microgrid during a large-scale grid disturbance, where the microgrid is operating independent of the main grid. Traditional analytical techniques for DG placement within microgrids tend to focus on minimizing power losses, minimizing electric energy losses, improving voltage profile and maximizing cost savings. To deter from these traditional techniques, the proposed SS-CFLCP combines the facility location and location coverage problems, with an aim to minimize the following: total investment costs, total operation and maintenance cost, the distance traveled for electricity distribution, the power outage levels (unmet electricity demand) experienced due to a large-scale grid disturbance, and the levels of excess renewable penetration, which can cause reverse power flow issues that damage the main grid, within a network. Additionally, the proposed SS-CFLCP is modeled with a budgetary constraint for installing the DGs, making it a more practical and applicable model for a utility company. A case study using solar/photovoltaic-based DGs is used to show the effectiveness of the proposed model.
Sensors attached to an asset acquiring vibration patterns during both operational and failure states have been used to diagnose fault conditions and to predict future failures of the components being monitored. In this research, we investigate Long Short-Term Memory (LSTM) networks, a type of Recurrent Neural Network (RNN), for failure diagnosis and remaining useful life (RUL) prognosis of such deteriorating components. LSTM networks' long-term dependency capability, which allows LSTM's to recall information for long term sequence lengths, can also be used to predict the probability of failure within a specified time frame. In this paper, we develop and apply a stylized LSTM model to a motor degradation dataset for the purposes of diagnosing failure and predicting the probability of failure within a specified time frame, as well as predicting RUL. We developed the dataset by acquiring automated sensor measurements from an induction motor attached to a destructive test platform. The performance of the LSTM model on the developed dataset is compared to that of the Random Forest (RF) algorithm as RF is reputably known for classification and regression. The results demonstrate that the LSTM provides quality predictions of motor failure, failure probability and RUL on the developed dataset. When compared to the RF approach, the LSTM performs comparably well in failure classification and outperforms the RF in RUL prediction.INDEX TERMS predictive maintenance, deep learning, long short-term memory, condition monitoring, rotor bar failure, industrial internet of things, prognostic health management, RUL prediction
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.