Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Xiangkun Pang"'
Publikováno v:
E3S Web of Conferences, Vol 136, p 01012 (2019)
A multi-layer LSTM (Long short-term memory) model is proposed for condenser vacuum degree prediction of power plants. Firstly, Min-max normalization is used to pre-process the input data. Then, the model proposes the two-layer LSTM architecture to id
Externí odkaz:
https://doaj.org/article/1a957af5833b44f5a31f7cb5aff81b89
Publikováno v:
Entropy, Vol 19, Iss 12, p 663 (2017)
Transfer entropy (TE) is a model-free approach based on information theory to capture causality between variables, which has been used for the modeling and monitoring of, and fault diagnosis in, complex industrial processes. It is able to detect the
Externí odkaz:
https://doaj.org/article/5e75afc11ee94a02b31cf16f1395a767
Publikováno v:
Diamond and Related Materials. 136:109874
Publikováno v:
SSRN Electronic Journal.
Publikováno v:
International Journal of Electrical Power & Energy Systems. 108:19-30
Automatic generation control (AGC) is an important auxiliary service provided by power generation units, such that generated active powers closely follow the changes of desired active powers as required by power grids. This paper proposes a new metho
Publikováno v:
2021 33rd Chinese Control and Decision Conference (CCDC).
Publikováno v:
International Journal of Electrical Power & Energy Systems. 103:67-74
The paper proposes a method to analyze root causes of occurring alarms, for a special type of alarm variables in thermal power plants, where alarms are arisen from binary-valued root-cause variables. A Bayesian network with one child node and multipl
Publikováno v:
International Journal of Electrical Power & Energy Systems. 100:81-90
Primary frequency control (PFC) responses for thermal power generation units are concerned about whether changes of turbine rotating speeds lead to proper responses of generator active powers. A new method is proposed to estimate performance metrics
Publikováno v:
IOP Conference Series: Earth and Environmental Science. 512:012170
In this paper, the piecewise linear function regression method based on FNN (Forward neural network)-ReLU (Rectified linear units) is used to simulate the flow curve of steam turbine valve. In the big data scenario, this method couldaccelerate the fi
Publikováno v:
IOP Conference Series: Earth and Environmental Science. 526:012153
The Multivariate State Estimation Technique (MSET) is firstly implemented as the fault detection technique for monitoring parameters of the steam turbine valve. Second, healthy operation states are remained to form a preliminary dataset for the valve