Performance comparison of parameter estimation techniques for unidentifiable models

Graciano, José Eduardo Alves; Mendoza, D.F.; Roux, G.

doi:10.1016/j.compchemeng.2014.01.009

Cited by 15 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1B) without noise (e = 0). For both types of water content, the unique minimum of the least-squares function J was the value of the coefficients used to generate water content values (D ⁄ = 10-À10 m 2 s À1 and h ⁄ = 4 Â 10 À7 m s À1 ), indicating that the coefficients D and h are structurally identifiable [14,34].…”

Section: Resultsmentioning

confidence: 99%

Effect of the water content measurements on the estimation and identifiability of water diffusion and convection mass transfer coefficients

Mercier

Marcos

Moresoli

et al. 2015

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Effect of the water content measurements on the estimation and identifiability of water diffusion and convection mass transfer coefficients

Mercier

Marcos

Moresoli

et al. 2015

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

“…On the other hand, poor performance of the Least Squares estimator, and poor overall performance of the MPA method, should be expected in cases where measurements are corrupted with gross errors or are non‐independently distributed. In this case redescending or appropriate likelihood estimators should be used …”

Section: Discussionmentioning

confidence: 99%

Assessing the reliability of different real‐time optimization methodologies

et al. 2016

View full text Add to dashboard Cite

There is not a consensus about the benefits of implementing Real‐Time Optimization (RTO) technologies to increase the profit of process plants. A lack of experimental and theoretical works which evaluate the scope and limitations of different RTO approaches makes it more difficult to have a sensible opinion about this topic. Most works available in the open literature that study different RTO approaches use few (often one) operation conditions to draw general conclusions about the virtues of a particular methodology. In the present work, we compare the performance of the classical two‐step method with more recently proposed derivative‐based methods (modifier adaptation, Integrated System Optimization Parameter Estimation (ISOPE), and an algorithm based on the Sufficient Conditions of Feasibility and Optimality (SCFO)) under different measurement noise, model mismatch, and disturbance using a Monte Carlo methodology. The results show that the classical RTO method can be reasonably reliable if provided with a model flexible enough to mimic the local process topology, a parameter estimation method suitable for handling measurement noise characteristics, and a method to improve the sample information quality. Implementing a derivative‐based RTO method, in cases of evident model mismatch, should be considered only if the gap between the predicted and the real optimum is large enough and the level of measurement noise is low.

show abstract

“…The unique minimum of the error sum of squares function observed on the contour plot and supported by the inner product sensitivity matrix indicates that the coefficients D 0 and A of a concentration-dependent water diffusivity are (at least locally) structurally identifiable from measurements of the global water content [1,3,4]. Table 2 presents the confidence intervals of D 0 and A estimated from global water content values at 10 equally spaced sampling times according to the noise intensity (r).…”

Section: Structural Identifiability Of the Coefficientsmentioning

confidence: 98%

“…Experiments should be designed considering the structural and practical identifiability of the water diffusivity. Structural identifiability refers to the unicity of the least-squares objective function for the theoretical situation of perfect (noise-free) measurements of the output variable [1][2][3][4]. The input variables are structurally identifiable if the model mapping from the input variable space to the output variable space is injective [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Impact of the number and sampling time of water content measurements on the identifiability of a concentration-dependent water diffusivity

Mercier

Marcos

Moresoli

et al. 2016

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

Performance comparison of parameter estimation techniques for unidentifiable models

Cited by 15 publications

References 26 publications

Effect of the water content measurements on the estimation and identifiability of water diffusion and convection mass transfer coefficients

Effect of the water content measurements on the estimation and identifiability of water diffusion and convection mass transfer coefficients

Assessing the reliability of different real‐time optimization methodologies

Impact of the number and sampling time of water content measurements on the identifiability of a concentration-dependent water diffusivity

Contact Info

Product

Resources

About