Efforts have been targeted at providing a comprehensive simulation of a centrifugal compressor undergoing surge. In the simulation process, an artificial neural network was utilized to produce an all-inclusive performance map encompassing those speeds not available in the provided curves. Two positive scenarios for the shaft speed, constant, and variable, were undertaken, and effects of load line on the dynamic response of the compressor have been studied. In order to achieve high-fidelity simulation in the variable speed case, an artificial neural network was utilized to produce an all-inclusive performance map encompassing those speeds not available in the provided curves. Moreover, effects of dynamic characteristics of throttle valve were also investigated. A novel controlling scheme, based on neuro-fuzzy control philosophy, was implemented to stabilize the compressor performance in the unstable region. Results indicate that if applied, this scheme could produce practical and satisfactory outcomes, possessing certain virtues compared to available techniques.

Application of Cogeneration systems based gas turbine for heat and power production is increasing. Because of finite natural energy resources and increasing energy demand the cost effective design of energy systems is essential. CGAM problem as a cogeneration system is considered here for analyzing. Two new approaches are considered, first in thermodynamic model of gas turbine and cogeneration system considering blade cooling of gas turbine and second using genetic algorithm for optimization. The problem has been optimized from thermodynamic and Thermoeconomic view point. Results show that Turbine Inlet Temperature (TIT) in thermodynamic optimum condition is higher than thermoeconomic one, while blade cooling technology must be better for optimum thermodynamic condition. Heat recovery of recuperator is lower in thermoeconomic case; also, stack temperature is higher relative to thermodynamic case. The sensitivity of the optimal solution to the decision variables is studied. It has been shown that while for both thermodynamic and thermoeconomic optimum condition, pressure ratio, blade cooling technology factor and pinch-point temperature difference (only for thermoeconomic case) has the lowest effect, turbomachinary efficiencies (epically compressor polytropic efficiency) have the major effect on performance of cycle. Finally; a new product known as Mercury 50 gas turbine is studied for a cogeneration system and it has been optimized thermoeconomicly. Results show good agreement with manufacturer data.

Gas turbine performances are directly related to site conditions. The use of gas turbines in combined gas-steam power plants, also applied to cogeneration, increases such dependence. In recent years, inlet air cooling systems have been introduced to control air temperature at compressor inlet, resulting in an increase in plant power and efficiency. In this paper, the dependence of outside conditions for a simple gas turbine and a combined cycle plant is studied, using absorption chiller as inlet air cooling system. We used, as case study, a simple plant equipped with one frame E gas turbine and a combined cycle with a two pressure level heat recovery steam generator (HRSG). It was found that inlet air cooling with absorption chiller has great positive influence on power and less on efficiency of the gas turbine plant. Two steam sources (External and Internal) have been considered for chiller. External source has large positive influence on power but keep the efficiency of the combined cycle unchanged, while internal source causes a reduction in steam turbine mass flow. Consequently power production and efficiency of the combined cycle decrease. This reduction is lower in mid temperature (25 to 35°C) but higher in high temperature (35 to 45°C). Inlet cooling would result in lowering turbine exhaust temperature, thus decreasing the efficiency of HRSG.

In this paper, the application of neural networks for simulation and optimization of the cogeneration systems has been presented. CGAM problem, a benchmark in cogeneration systems, is chosen as a case study. Thermodynamic model includes precise modeling of the whole plant. For simulation of the steady sate behavior, the static neural network is applied. Then using dynamic neural network, plant is optimized thermodynamically. Multi layer feed forward neural networks is chosen as static net and recurrent neural networks as dynamic net. The steady state behavior of CGAM problem is simulated by MFNN. Subsequently, it is optimized by dynamic net. Results of static net have excellence agreement with simulator data. Dynamic net shows that in thermodynamic optimization condition, σ and pinch point temperature difference have the lowest value, while CPR reaches a high value. Sensitivity study shows turbomachinery efficiencies have the highest effect on the performance of the system in optimum condition.