Research on Vibration Law and Fault Prediction of Conventional Island Steam Turbine Shafting Based on Data Mining

Turbine shafting works in harsh environment, and vibration problems occur frequently, which seriously affects the safety and reliability of the unit. Traditional vibration analysis methods rely on empirical formulas and simple statistics, and it is difficult to fully reveal the complex mechanism behind vibration. The rapid development of data mining technology provides new ideas and methods for this field. In the analysis of vibration law, filtering technology is used to remove high-frequency noise, data is processed by linear normalization, and features are extracted by time domain and frequency domain analysis. K-means clustering algorithm is used to identify different vibration modes, and Apriori algorithm is used to mine the association rules between vibration features. In the aspect of fault prediction model construction, support vector machine (SVM) is selected as the basic model, and training and optimization are carried out based on the extracted feature vectors to predict potential faults. The experimental results show that different vibration modes are successfully identified by K-means clustering algorithm, and the mining results of Apriori association rules reveal the key relationship between steam turbine operating conditions and vibration characteristics. The SVM fault prediction model has excellent prediction performance in different fault categories, and the overall accuracy, recall and F1 score all remain at a high level, especially in the prediction of temperature anomalies. The results of this study not only reveal the vibration characteristics of steam turbine shafting under different operating conditions, but also effectively predict the faults of steam turbine shafting through data mining technology, which provides strong support for the operation and maintenance management of power plants, helps to find and deal with potential faults in time, reduces downtime and maintenance costs, and improves the operating efficiency and reliability of steam turbines.