Estimating monotonic functions and their bounds

AIChE Journal

Volumn 46, Issue 12, 2000, Pages 2426-2434

  Kay, Herbert ^a   Ungar, Lyle H ^a  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; COMPUTATIONAL METHODS; CONSTRAINT THEORY; FAILURE ANALYSIS; NEURAL NETWORKS; PARAMETER ESTIMATION; REGRESSION ANALYSIS;

BACKPROPAGATION NEURAL NETWORKS; MONOTONIC FUNCTION; MONOTONIC SEMIQUANTITATIVE SYSTEM IDENTIFICATION METHOD;

SYSTEMS ENGINEERING;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CHEMICAL REACTION; FLOW KINETICS; MATHEMATICAL ANALYSIS; NOISE;

EID: 0034517586     PISSN: 00011541     EISSN: None     Source Type: Journal    
DOI: 10.1002/aic.690461211     Document Type: Article

References (29)

1. Qualitative and quantitative simulations: Bridging the gap
2. Improved infeasible path optimization for sequential modular simulators: II. The optimization algorithm
3. Improved infeasible path optimization for sequential modular simulators: I. The interface
4. Qualitative system identification: Deriving structure from behavior
5. Approximation by superpositions of sigmoidal functions
6. Hybrid neutral network models for environmental process control
7. Prediction intervals for neural networks via nonlinear regression
8. Model-based monitoring of dynamic systems
9. Obtaining quantitative predictions from monotone relationships
10. Encoding a prior information in feedforward networks
11. SQSIM: A simulator for imprecise ODE models
12. Numerical behavior envelopes for qualitative models
13. Deriving monotonic function envelopes from observations
14. Semi-quantitative system identification
15. Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
16. Using incomplete quantitative knowledge in qualitative reasoning
17. Qualitative simulation
18. Using radial basis functions to approximate a function and its error bounds
19. A hybrid neural network - First principles approach to process modeling
20. Monitoring piecewise continuous behaviors by refining trackers and their models
21. Gas-turbine condition monitoring using qualitative model-based diagnosis
22. Dynamic process monitoring and fault diagnosis with qualitative models