Partager

Évaluation et quantification des capacités prédictives d’un modèle de compresseur semi-empirique soumis à des scénarios de modulation et d’extrapolation. 

Evaluation and quantification of semi-empirical compressor model predictive capabilities under modulation and extrapolation scenarios.

Numéro : 1318

Auteurs : GABEL K. S., BRADSHAW C. R.

Résumé

Testing and evaluation of select semi-empirical compressor models is carried out to quantify performance in modulation and extrapolation scenarios. Three representative models from literature are benchmarked against an artificial neural network (ANN) model and the industry standard AHRI model. A methodology for quantifying model performance, compared against experimental data, in extrapolation and modulation scenarios is presented. Predictions from the five models are compared against high-fidelity performance data taken from either a hot-gas bypass load stand or a compressor calorimeter. Scroll, screw, reciprocating, and spool compressor technologies were collected with R410A, R1234ze(E), R134a, and R32 refrigerants. In total, 327 experimental data points were used for model testing. The Mean Absolute Percentage Error (MAPE) is calculated for the mass flow rate and power of each compressor providing a means to quantify the model’s ability to predict experimental data under modulation and extrapolation scenarios. The semi-empirical models yield MAPE’s less than 5% for mass flow rate and power in modulation scenarios while performing at or below 8% MAPE in envelope extrapolation scenarios. The semi-empirical models capture superheat extrapolation to below 6% MAPE for mass flow rate and power with the exception of one model, the Popovic and Shapiro model performing at 18% MAPE in power prediction for Spool compressor working with R1234ze(E). The semi-empirical models show a maximum extrapolation MAPE of 7.3%, given the model captures the compressor technology. The empirical formulations do not predict modulation behavior and showed varying performance at the extrapolation scenarios, with the ANN performing the best. Future work based on the presented results include the development of a new model, based on a semi-empirical formulation that can capture multiple compressor technologies while exhibiting good modulation and extrapolation capabilities.

Documents disponibles

Format PDF

Pages : 11 p.

Disponible

Gratuit

Télécharger

Détails

  • Titre original : Evaluation and quantification of semi-empirical compressor model predictive capabilities under modulation and extrapolation scenarios.
  • Identifiant de la fiche : 30030309
  • Langues : Anglais
  • Sujet : Technologie
  • Source : 2022 Purdue Conferences. 26th International Compressor Engineering Conference at Purdue.
  • Date d'édition : 15/07/2022

Liens


Voir d'autres communications du même compte rendu (83)
Voir le compte rendu de la conférence

Indexation