Fault Trend Prediction And Assessment For Hydropower Unit

Songjianghe cascade is northeast area" seven five " during the hydropower construc-tion projects, located in southeastern Jilin province a mountainous area, in recent years,Songjianghe cascade turbine increasingly large-scale, complex, automation, because thefault led to the unexpected shutdown will result in serious losses. Fault prediction tech-nology can effectively avoid accident occurrence and development, to provide advancedpredictive maintenance to provide scientific methods. Therefore, this paper to Songjianghecascade hydropower station as the background, the turbine shaft fault trend predictionmethod and unit operation state evaluation methods are studied, results of fault diagnosisand expert decision support system research and development is an important part of thescientific and reasonable evaluation unit, health status, realize the unit condition mainte-nance and predictive maintenance lay a solid foundation.This paper expounds the turbine generator shaft structure, and the fault characteristicundertook thorough analysis. Research Based on time series autoregressive model analysisof shafting fault prediction method, the frame vibration and bearing temperature is pre-dicted and the results were analyzed according to the shafting status data structures, basedon BP neural network unit shafting fault prediction method. In order to overcome the BPnerve network training slow convergence speed, easy to fall into local minimum point,LM algorithm is applied to replace the traditional gradient method, so as to improve BPneural network prediction model of efficiency and accuracy. BP neural network predictionmodel and autoregressive prediction models were compared and analyzed, the resultsshow the improved BP neural network model to predict the effect better than the auto-regressive model.In shafting status prediction research foundation, the unit state evaluation method re-search and system development. Based on the analytic hierarchy process of shafting statusevaluation model, fuzzy mathematics and traditional AHP combination, ensure the con-sistency of the judgment matrix; to ensure the scientific evaluation is proposed based onthe information entropy, the shafting condition assessment methods, and the results ofevaluation and Fuzzy AHP to get the evaluation results fusion, synthetic form shaftingstatus assessment results, effectively improve the rationality of evaluation.