This paper proposes an evaluation index of wind turbine generator operating health based on the relationships with SCADA (Supervisory Control and Data Acquisition) data. First, the relationship among the data from a wind turbine SCADA system is thoroughly analyzed. Then, a time based sliding window model is used to process the SCADA data by the bin method, and a running state model of the wind turbine is established by data fitting. Taking the normal operation state model of the wind turbine as the standard reference and based on the Euclidean distance between the state model curve and the standard model curve, the health index of the wind turbine operation state is proposed. Finally, using SCADA data from two 2 MW direct-drive wind turbines as examples for analysis and discussion, the results show that: (1) health indicators have good stability and sensitivity to wind turbine operating conditions; (2) the width of the data window in the sliding window model must cover all operating conditions of the wind turbine to ensure that the health index depicts the operating state of the wind turbine; (3) the data window width, window increment, and data fitting modeling all affect the health indicators, and thus, the selection of the sliding window model parameters and the data relationship modeling methods should consider the accuracy and real-time performance of the health indicators; and (4) the data acquisition cycle does not affect the health indicators. Once the basic characteristics of the data relations are known, direct data fitting modeling is more efficient than bin preprocessing modeling.
Condition monitoring and overheating warnings of the main bearing of large-scale wind turbines (WT) plays an important role in enhancing their dependability and reducing operating and maintenance (O&M) costs. The temperature parameter of the main bearing is the key indicator to characterize the normal or abnormal operating condition. Therefore, forecasting the trend of temperature change is critical for overheating warnings. To achieve forecasting with high accuracy, this paper proposes a novel model for the WT main bearing, named stacked long-short-term memory with multi-layer perceptron (SLSTM-MLP) by utilizing supervisory control and data acquisition (SCADA) data. The model is mainly composed of multiple LSTM cells and a multi-layer perceptron regression layer. By combining condition parameters into a characteristic matrix, SLSTM can mine nonlinear, non-stationary dynamic feature relationships between temperature and its related variables. To evaluate the performance of the SLSTM-MLP model, experimental analysis was carried out from three aspects: different sample capacity sizes, different sampling time segments, and different sampling frequencies. Furthermore, the model’s capability of online fault detection was also carried out by simulation. The results of comparative studies and online fault simulation tests show that the proposed SLSTM-MLP has better performance for temperature forecasting of the main bearing of large-scale WTs.
As clean and low-carbon energy, wind energy has attracted the attention of many countries. The main bearing in the transmission system of large-scale wind turbines (WTs) is the most important part. The research on the condition monitoring of the main bearing has received more attention from many scholars and the wind industry, and it has become a hot research topic. The existing research on the condition monitoring of the main bearing has the following drawbacks: (1) the existing research assigns the same weight to each condition parameter variable, and the model extracts features indiscriminately; (2) different historical time points of the condition parameter variable are given the same weight, and the influence degree of different historical time points on the current value is not considered; and (3) the existing literature does not consider the operating characteristics of WTs. Different operating conditions have different control strategies, which also determine which condition parameters are artificially controlled. Therefore, to solve the problems above, this paper proposes a novel method for condition monitoring of WT main bearings by applying the dual attention mechanism and Bi-LSTM, named Dual Attention-Based Bi-LSTM (DA-Bi-LSTM). Specifically, two attention calculation modules are designed to extract the important features of different input parameters and the important features of input parameter time series, respectively. Then, the two extracted features are fused, and the Bi-LSTM building block is utilized to perform pre-and post-feature extraction of the fused information. Finally, the extracted features are applied to reconstruct the input data. Extensive experiments verify the performance of the proposed method. Compared with the Bi-LSMT model without adding an attention module, the proposed model achieves 19.78%, 2.17%, and 18.92% improvement in MAE, MAPE, and RMSE, respectively. Compared with the Bi-LSTM model which only considers a single attention mechanism, the proposed model achieves the largest improvement in MAE and RMSE by 28.84% and 30.37%. Furthermore, the proposed model has better stability and better interpretability of the monitoring process.
In this paper, two second-order methods are proposed for reliability analysis. First, general random variables are transformed to standard normal random variables. Then, the limit-state function is additively decomposed into one-dimensional functions, which are then expanded at the mean-value point to second-order terms. The approximated limit-state function becomes the sum of independent variables following noncentral chi-square distributions or normal distributions. The first method computes the probability of failure by the saddle-point approximation. If a saddle-point does not exist, the second method is then used. The second method approximates the limit-state function by a quadratic function with independent variables following normal distributions with the same variances. This treatment leads to a quadratic function that follows a noncentral chi-square distribution. These methods generally produce more accurate reliability approximations than the first-order reliability method (FORM) with 2n + 1 function evaluations, where n is the dimension of the problem. The effectiveness of the proposed methods is demonstrated with three examples, and the proposed methods are compared with the first- and second-order reliability methods (SROMs).
Variable pitch technology is an indispensable key technology of large-scale wind turbines. The reliable pitch mechanism is the basic guarantee for achieving variable pitch. At present, the main problem with the design and maintenance of the variable pitch mechanism is that the pitch load is not clearly known. This paper focuses on obtaining pitch load characteristics through extracting SCADA (Supervisory Control and Data Acquisition) data. Here, the pitch load refers to the resistance moment to be overcome when the wind turbine blade is rotated on its own axis. From the data collected by the SCADA system, although the edgewise moment and the flapwise moment cannot be obtained, the pitch torque (load) can be extracted indirectly. This provides data support for the research. Specifically, the pitch moment is obtained by indirect calculation of the pitch motor current. Then, the effects of the wind speed, rotor speed, hub angle and pitch angle on the pitch load are theoretically analyzed. To obtain more reliable results, data preprocessing algorithms are presented to consider the data filtering range, the elimination of abnormal values and data dispersity. Subsequently, the influence mechanisms of wind speed, rotor speed, hub angle and pitch angle on the pitch load are investigated in detail based on the SCADA data.
Based on the rain-flow counting method, a new random numerical simulation method for evaluating dynamic response characteristics of a launch and recovery system is presented in this study. It takes a random irregular wave as an input, and the random distribution characteristics of the dynamic responses of the launch and recovery system of a seafloor drill is analyzed by using the rain-flow counting method. The nonlinear coupling mechanisms among the movements of the ship, the umbilical cable, and the seafloor drill caused by random irregular wave are investigated. A dynamic model that considers the influence of the seawater resistance on the launch and recovery system of seafloor drill is established. Then, significant wave heights are used to produce excitation of the random irregular wave, and the corresponding dynamic random responses of the launch and recovery system are calculated and analyzed. At the same time, the movement of the seafloor drill and the tension of the umbilical cable are calculated and analyzed for the cases of seafloor drill at different water depths. This method provides a new tool for evaluating the dynamic response characteristics of launch and recovery system of other seafloor equipment under random irregular wave.