Premium
Statistical identification of the dynamic behavior of a dual input heat exchanger network
Author(s) -
Wright J. D.,
Bacon D. W.
Publication year - 1974
Publication title -
the canadian journal of chemical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.404
H-Index - 67
eISSN - 1939-019X
pISSN - 0008-4034
DOI - 10.1002/cjce.5450520317
Subject(s) - dual (grammatical number) , computer science , noise (video) , superposition principle , identification (biology) , heat exchanger , transfer function , function (biology) , scale (ratio) , system identification , data mining , artificial intelligence , engineering , mathematics , art , physics , mechanical engineering , mathematical analysis , botany , literature , electrical engineering , quantum mechanics , evolutionary biology , image (mathematics) , biology , measure (data warehouse)
Statistical modelling procedures proposed by Box and Jenkins are used to develop models for the transfer function and noise behaviour of a dual input pilot scale heat exchanger network. Data were collected under operating conditions closely resembling full scale industrial operation first with uncorrelated inputs and then with correlated inputs. Two modelling strategies, a superposition approach and a transformed input approach, are employed to analyze the data. Computational advantages of the transformed input procedure for correlated input situations is demonstrated and the effectiveness of both strategies in detecting nonstationarity in the system noise is also illustrated.