Simulation of Compressor Transient Behavior Through Recurrent Neural Network Models

[+] Author and Article Information
M. Venturini

 ENDIF—University of Ferrara, Via Saragat, 1, 44100 Ferrara, Italy

J. Turbomach 128(3), 444-454 (Feb 01, 2005) (11 pages) doi:10.1115/1.2183315 History: Received October 01, 2004; Revised February 01, 2005

In the paper, self-adapting models capable of reproducing time-dependent data with high computational speed are investigated. The considered models are recurrent feed-forward neural networks (RNNs) with one feedback loop in a recursive computational structure, trained by using a back-propagation learning algorithm. The data used for both training and testing the RNNs have been generated by means of a nonlinear physics-based model for compressor dynamic simulation, which was calibrated on a multistage axial-centrifugal small size compressor. The first step of the analysis is the selection of the compressor maneuver to be used for optimizing RNN training. The subsequent step consists in evaluating the most appropriate RNN structure (optimal number of neurons in the hidden layer and number of outputs) and RNN proper delay time. Then, the robustness of the model response towards measurement uncertainty is ascertained, by comparing the performance of RNNs trained on data uncorrupted or corrupted with measurement errors with respect to the simulation of data corrupted with measurement errors. Finally, the best RNN model is tested on field data taken on the axial-centrifugal compressor on which the physics-based model was calibrated, by comparing physics-based model and RNN predictions against measured data. The comparison between RNN predictions and measured data shows that the agreement can be considered acceptable for inlet pressure, outlet pressure and outlet temperature, while errors are significant for inlet mass flow rate.

Copyright © 2006 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Scheme of a recurrent neural network (RNN) model

Grahic Jump Location
Figure 2

Implementation of the physics-based model for compressor dynamic simulation through the Simulink tool

Grahic Jump Location
Figure 3

Compressor rotational speed versus time for transients TRi (simulated data) used for RNN training ((a) and (b)) and testing ((c) and (d))

Grahic Jump Location
Figure 4

Scheme of the recurrent neural network models adopted in the paper

Grahic Jump Location
Figure 5

Influence of the choice of the compressor maneuver used for training (one-time delayed RNNs, delay time=0.5s, nHLN=15)

Grahic Jump Location
Figure 6

Influence of the number of neurons in the hidden layer (one-time delayed RNNs with total delay time=0.5s)

Grahic Jump Location
Figure 7

Influence of the number of outputs for testing transients TR8 and TR11 (one-time delayed RNNs; total delay time=0.5s; nHLN=15)

Grahic Jump Location
Figure 8

Influence of the delay time (nHLN=15)

Grahic Jump Location
Figure 9

Influence of the delay time with respect to the number of neurons in the hidden layer normalized with the number of inputs

Grahic Jump Location
Figure 10

Influence of the delay time (0.1, 0.5, 1.0s) for one-time delayed RNNs in the presence of measurement uncertainty

Grahic Jump Location
Figure 11

Rotational speed profile versus time for the two test cases (measured data)

Grahic Jump Location
Figure 12

Comparison between predictions (calculated through both the physics-based model and through the RNN) and measured values

Grahic Jump Location
Figure 13

Comparison of measured values and predictions (obtained through the physics-based model and the RNN) for TC1 curve

Grahic Jump Location
Figure 14

Comparison of measured values and predictions (obtained through the physics-based model and the RNN) for TC2 curve



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In