Pier Ruggero Spina

Artificial intelligence for the diagnostics of gas turbines-Part I: Neural network approach

In the paper, neural network (NN) models for gas turbine diagnostics are studied and developed. The analyses carried out are aimed at the selection of the most appropriate NN structure for gas turbine diagnostics, in terms of computational time of the NN training phase, accuracy, and robustness with respect to measurement uncertainty. In particular, feed-forward NNs with a single hidden layer trained by using a back-propagation learning algorithm are considered and tested. Moreover, multi-input/ multioutput NN architectures (i.e., NNs calculating all the system outputs) are compared to multi-input/single-output NNs, each of them calculating a single output of the system. The results obtained show that NNs are sufficiently robust with respect to measurement uncertainty, if a sufficient number of training patterns are used. Moreover, multi-input/ multioutput NNs trained with data corrupted with measurement errors seem to be the best compromise between the computational time required for NN training phase and the NN accuracy in performing gas turbine diagnostics.

Development and Validation of a Computational Code for Wet Compression Simulation of Gas Turbines

In this paper, a calculation code, developed in house by the authors, able to evaluate the performance of a gas turbine with all possible fogging strategies (high pressure fogging, overspray, and interstage injection) is presented and discussed. The code has a flexible structure and can be applied to evaluate the performance of every commercial gas turbine model. The aim of the calculation code is to overcome the limits of the most widespread commercial software, especially with regard to the two phase flow compression process simulation. The calculation code was validated on results available in the literature showing a good agreement with experimental and theoretical results.

Computational Fluid Dynamics Simulation of Fouling on Axial Compressor Stages

Three-dimensional numerical simulations of the effect of fouling on an axial compressor stage were carried out. As a case study, the NASA Stage 37 was considered for the numerical investigation, which was performed by means of a commercial computational fluid dynamic code. The numerical model was validated against the experimental data available from literature. Computed performance maps and main flow field features showed a good agreement with the experimental data. The model was considered representative of a realistic compressor stage. The model was then used to simulate the occurrence of fouling by imposing different combinations of added thickness and surface roughness levels. The effect of fouling on compressor performances was studied. Reductions in the flow coefficient and in the pressure coefficient were found to be of the same order of magnitude of the experimental results found in literature. The model developed seems to overcome some of the limitations of other models found in literature that tend to significantly underestimate the actual values of performance reduction. The numerical results were also used to analyze and debug the stage performance scaling procedure used in stage-stacking models in order to represent fouling in multistage compressors. The analysis highlighted that scaling can adequately represent the behavior of the fouled stage in the choked flow region, but it does not capture the reduction in the maximum of the pressure coefficient, which is instead revealed by the numerical simulations. Finally, blockage due to fouling was investigated both qualitatively and quantitatively.

Influence of Blade Deterioration on Compressor and Turbine Performance

Gas turbine operating state determination consists of the assessment of the modification due to deterioration and fault of performance and geometric data characterizing machine components. One of the main effects of deterioration and fault is the modification of compressor and turbine performance maps. Since detailed information about actual modification of component maps is usually unavailable, many authors simulate the effects of deterioration and fault by a simple scaling of the map itself. In this paper, stage-by-stage models of the compressor and the turbine are used in order to assess the actual modification of compressor and turbine performance maps due to blade deterioration. The compressor is modeled by using generalized performance curves of each stage matched by means of a stage-stacking procedure. Each turbine stage is instead modeled as two nozzles, a fixed one (stator) and a moving one (rotor). The results obtained by simulating some of the most common causes of blade deterioration (i.e., compressor fouling, compressor mechanical damage, turbine fouling, and turbine erosion), occurring in one or more stages simultaneously, are reported in this paper. Moreover, compressor and turbine maps obtained through the stage-by-stage procedure are compared with the ones obtained by means of map scaling. The results show that the values of the scaling factors depend on the corrected rotational speed and on the load. However, since the variation in the scaling factors in the operating region close to the design corrected rotational speed is small, the use of the scaling factor as health indices can be considered acceptable for gas turbine health state determination at full load. Moreover, also the use of scaled maps in order to represent compressor and turbine behavior in deteriorated conditions close to the design corrected rotational speed can be considered acceptable.

Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy Approach

In the paper neuro-fuzzy systems (NFSs) for gas turbine diagnostics are studied and developed. The same procedure used previously for the setup of neural network (NN) models (Bettocchi, R., Pinelli, M., Spina, P. R., and Venturini, M., 2007, ASME J. Eng. Gas Turbines Power, 129(3), pp. 711-719) was used. In particular, the same database of patterns was used for both training and testing the NFSs. This database was obtained by running a cycle program, calibrated on a 255 MW single-shaft gas turbine working in the ENEL combined cycle power plant of La Spezia (Italy). The database contains the variations of the Health Indices (which are the characteristic parameters that are indices of gas turbine health state, such as efficiencies and characteristic flow passage areas of compressor and turbine) and the corresponding variations of the measured quantities with respect to the values in new and clean conditions. The analyses carried out are aimed at the selection of the most appropriate NFS structure for gas turbine diagnostics, in terms of computational time of the NFS training phase, accuracy, and robustness towards measurement uncertainty during simulations. In particular, adaptive neuro-fuzzy inference system (ANFIS) architectures were considered and tested, and their performance was compared to that obtainable by using the NN models. An analysis was also performed in order to identify the most significant ANFIS inputs. The results obtained show that ANFISs are robust with respect to measurement uncertainty, and, in all the cases analyzed, the performance (in terms of accuracy during simulations and time spent for the training phase) proved to be better than that obtainable by multi-input/multioutput (MIMO) and multi-input/single-output (MISO) neural networks trained and tested on the same data.

A Feasibility Study of Existing Gas Turbines for Recuperated, Intercooled, and Reheat Cycle

In the present paper, a comprehensive and simple in application design methodology to obtain a gas turbine working on recuperated, intercooled, and reheat cycle utilizing existing gas turbines is presented. Applications of the proposed design steps have been implemented on the three existing gas turbines with wide ranging design complexities. The results of evaluated aerothermodynamic performance for these existing gas turbines with the proposed modifications are presented and compared in this paper. Sample calculations of the analysis procedures discussed, including stage-by-stage analysis of the compressor and turbine sections of the modified gas turbines, have been also included. All the three modified gas turbines were found to have higher performance, with cycle efficiency increase of 9% to 26%, in comparison to their original values.

Influence of Water Droplet Size and Temperature on Wet Compression

In the last years, among all different gas turbine inlet air cooling techniques, an increasing attention to fogging approach is dedicated. The various fogging strategies seem to be a good solution to improve gas turbine or combined cycle produced power with low initial investment cost and less installation downtime. In particular, overspray fogging and interstage injection involve two-phase flow consideration and water evaporation during compression process (also known as wet compression). According to the Author’s knowledge, the field of wet compression is not completely studied and understood. In the present paper, all the principal aspects of wet compression and in particular the influence of injected water droplet diameter and surface temperature, and their effect on gas turbine performance and on the behavior of the axial compressor (change in axial compressor performance map due to the water injection, redistribution of stage load, etc.) are analyzed by using a calculation code, named IN.FO.G.T.E. (IN terstage FO gging G as T urbine E valuation), developed and validated by the Authors.Copyright

Application of a Computational Code to Simulate Interstage Injection Effects on GE Frame 7EA Gas Turbine

This paper investigates effects of interstage water injection on the performance of a GE Frame 7EA gas turbine using aero-thermodynamic modeling. To accomplish this objective a computational code, written in Fortran 90 language and developed by DIEM – University of Bologna, has been used. The calculation procedure considers effects of evaporation of injected water within the compressor including droplets dynamics which are necessary in order to fully evaluate effects of wet compression on the gas turbine performance. The robustness of the computational code is demonstrated by evaluating stage-by-stage compressor performance and the overall gas turbine performance in presence of inlet evaporative fogging, overspray fogging and interstage water injection. The presented results show that water injection location influences compressor stage loading redistribution differently. The plausible explanations to the observed trends of various performance parameters are presented in the paper.Copyright

CFD Simulation of Water Injection in GT Inlet Duct Using Spray Experimentally Tuned Data: Nozzle Spray Simulation Model and Results for an Application to a Heavy-Duty Gas Turbine

This study describes an application of Computational Flow Dynamics (CFD) to the two-phase flow problem of water injection into a compressor inlet duct for fogging systems. The paper addresses issues related to the CFD setup and the developed spray simulation model. Water injection is simulated by fitting experimental data on sprays obtained from industrial nozzles. In particular, the initial droplets size distribution is defined in accordance with results of laboratory tests on impaction-pin type nozzles. By using a commercial CFD software, 3D numerical simulations have been carried out on a typical gas turbine inlet duct. The effects of the duct geometry, filter and silencer on the duct internal air flow-field were analyzed. Finally, the effect of water injection carried out by means of an array of nozzles in the inlet duct is investigated. The paper presents the CFD two-phase results obtained for the application case under study; the analysis of the compressor bellmouth conditions due to the evaporation phenomenon is included in the paper.Copyright

A Multistage Compressor Test Facility: Uncertainty Analysis and Preliminary Test Results

A multistage compressor test facility, fully instrumented with a dedicated data acquisition and processing system, has been developed to conduct experimental research work at the University of Ferrara. This paper provides a systematic description of the uncertainty analysis procedures required for compressor testing, including preliminary performance test results, in addition to a brief description of the test facility and its capabilities.