Predicting the Parameters of Vortex Bladeless Wind Turbine Using Deep Learning Method of Long Short-Term Memory

Abstract

From conventional turbines to cutting-edge bladeless turbines, energy harvesting from wind has been well explored by researchers for more than a century. The vortex bladeless wind turbine (VBT) is considered an advanced design that alternatively harvests energy from oscillation. This research investigates enhancing the output electrical power of VBT through simulation of the fluid–solid interactions (FSI), leading to a comprehensive dataset for predicting procedure and optimal design. Hence, the long short-term memory (LSTM) method, due to its time-series prediction accuracy, is proposed to model the power of VBT from the collected data. To find the relationship between the parameters and the variables used in this research, a correlation matrix is further presented. According to the value of 0.3 for the root mean square error (RMSE), a comparative analysis between the simulation results and their predictions indicates that the LSTM method is suitable for modeling. Furthermore, the LSTM method has significantly reduced the computation time so that the prediction time of desired values has been reduced from an average of two and a half hours to two minutes. In addition, one of the most important achievements of this study is to suggest a mathematical relation of output power, which helps to extend it in different sizes of VBT with a high range of parameter variations.

Investigating the predictive contribution of attitude towards life and belief system on self-resilience and psychological toughness of cancer patients about the mediating role of emotion regulation

“…Therefore, emotion regulation can be effective on psychological toughness. By Increasing the data points the machine learning methods can be used, e.g., [33][34][35][36][37][38][39][40][41][42][43][44]. Therefore, the study on the perception to life and belief system on self-resilience and psychological toughness of cancer patients about the mediating role of emotion regulation can be better investigated.…”

Data-Driven Methods of Machine Learning in modeling the Smart Grids

“…Similar to other fields of science and technology where advanced ML methods are dominant, e.g., [50][51][52][53][54][55], the SG will also benefit from the novel methods in the years to come. Novel training and evolutionary optimization algorithms for ML, e.g., [56][57][58][59] can indeed improve the quality of the models in SG as had been the case in numerous other applications, e.g., energy and environmental sciences [60][61][62]. Based on the presented survey, the following applications of ML in SG have been seen a) out of several ML algorithms, RF and isolation forest algorithms give the best result for cyber security in SG,b) for prediction in SG, the autoregressive integrated moving average model gives the best results, c) sparse mean confusion metrics help for a robust modeling approach and clustering analysis is effectively helpful for understanding the neighborhood type, such as residential, mixed, or business, d) the blockchain model and bidirectional LSTM algorithm are useful for acquiring a sustainable electric power supply.…”

Comparative Analysis of Machine Learning and Numerical Modeling for Combined Heat Transfer in Polymethylmethacrylate

“…For storing the data, the “cell states” are used to store the long-term data in hidden layers. As presented in Equations (16) and (17), f and i represent the forget and input gates to control the input of each cell [ 33 ]. …”

“…Moreover, Equation (18) presents the relation to understand the input’s current state, where the c index shows each parameter’s current state. Equation (19) uses both the forget and input gates to obtain the current cell state [ 33 ]. …”