A health condition assessment and prediction method of Francis turbine units using heterogeneous signal fusion and graph-driven health benchmark model.
Fengyuan ZhangJie LiuYuxin LiYujie LiuMing-Feng GeXingxing JiangPublished in: Eng. Appl. Artif. Intell. (2023)
Keyphrases
- prediction model
- mathematical model
- cost function
- probabilistic model
- prior knowledge
- statistical model
- predictive model
- input data
- energy function
- hybrid model
- objective function
- tree structure
- analytical model
- linear regression model
- theoretical analysis
- graph model
- regression analysis
- linear model
- prediction error
- evaluation method
- bp neural network
- optimization method
- linear regression
- similarity measure
- clustering method
- topological information
- autoregressive
- em algorithm
- modeling method
- fusion model
- pairwise
- forecasting model
- wavelet analysis
- support vector machine
- markov random field
- model selection
- parameter estimation
- frequency domain
- bipartite graph