2021/03/29 by Inan Timur, Timur, Inan, Baba Ahmet Fevzi +1
Computer Science · Engineering · #Data Mining and Machine Learning Applications #Energy Load and Power Forecasting #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Fault Diagnosis Techniques #Machine Learning (cs.LG) #Magnetic Bearings and Levitation Dynamics #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.00538
openalex publication_date 2021/03/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Estimation of the wind speed plays an important role in many issues such as\nroute determination of ships, efficient use of wind roses, and correct planning\nof agricultural activities. In this study, wind velocity estimation is\ncalculated using artificial neural networks (ANN) and adaptive artificial\nneural fuzzy inference system (ANFIS) methods. The data required for estimation\nwas obtained from the float named E1M3A, which is a float inside the POSEIDON\nfloat system. The proposed ANN is a Nonlinear Auto Regressive with External\nInput (NARX) type of artificial neural network with 3 layers, 50 neurons, 6\ninputs and 1 output. The ANFIS system introduced is a fuzzy inference system\nwith 6 inputs, 1 output, and 3 membership functions (MF) per input. The\nproposed systems were trained to make wind speed estimates after 3 hours and\nthe data obtained were obtained and the successes of the systems were revealed\nby comparing the obtained values with real measurements. Mean Squarred Error\n(MSE) and the regression between the predictions and expected values (R) were\nused to evaluate the success of the estimation values obtained from the\nsystems. According to estimation results, ANN achieved 2.19 MSE and 0.897 R\nvalues in training, 2.88 MSE and 0.866 R values in validation, and 2.93 MSE and\n0.857 R values in testing. ANFIS method has obtained 0.31634 MSE and 0.99 R\nvalues\n