Modeling of centrifugal compressor using RBF neural network based on cooperative clustering

Adaptive optimization strategy of air supply for automotive polymer electrolyte membrane fuel cell in life cycle

Effect of internal heat leakage on the performance of a high pressure ratio centrifugal compressor

The effect of tip clearance to the centrifugal compressor diffuser flow fields and stage overall performance are studied experimentally. The relative tip clearance (tip clearance divided by the impeller exit blade height) is increased by shimming the shroud side casing of a high-speed variable speed driven industrial centrifugal compressor. Four different relative tip clearances are studied: 0.027, 0.053, 0.082, and 0.106. The stage efficiency and pressure ratios are measured, as well as the diffuser flow fields. The diffuser flow fields are measured both at the diffuser inlet and outlet. The total pressure and flow angle are measured with a cobra probe, and the total pressure and temperature with three Kiel probes. Static pressures are measured adjacent to the probe measurements. As expected, increasing the tip clearance leads to lower stage efficiency and pressure ratios. The decrement in the efficiency due to the increasing of the tip clearance is higher with higher mass flows, and at lower rotational speeds. Increasing tip clearance increases the size of the secondary flow region present at the impeller outlet near the shroud.

The motivation to design a more efficient and compact aircraft engine leads to a continuous increase in overall pressure ratio and decrease in the stage number in compressors. Compared to the traditional multi-stage compressor, a single-stage ultra-high-pressure-ratio centrifugal compressor with a pressure ratio higher than 10.0 can significantly improve the engine’s power-to-weight ratio and fuel economy with a reduced structure complexity. Thus, it has great potential to be adopted in the compression system of advanced aero engines, such as turboshaft engines, in the future. However, the highly narrow Stable Flow Range (SFR) of ultra-high-pressure-ratio centrifugal compressors is a severe restriction for engineering applications. This research focuses on the aerodynamic performance of a ultra-high-pressure-ratio centrifugal compressor, and three-dimensional simulation is employed to investigate the effect of Self-Recirculating Casing Treatment (SRCT) on the performance and stability of the centrifugal compressor. Firstly, the parametric model of SRCT is established to investigate the effect of geometry parameters (rear slot distance and rear slot width) on the aerodynamic performance of the centrifugal compressor. It is concluded that SRCT improves the compressor’s SFR but deteriorates its efficiency. Also, a non-linear and non-monotone relationship exists between the SFR and rear slot distance or width. Then, the flow mechanism behind the effect of SRCT is explored in detail. By introducing the SRCT, an additional flow path is provided across the blade along the circumferential direction, and the behavior of the shock wave and tip leakage flow is significantly changed, resulting in the obviously different loading distribution along the streamwise direction. As a result, the mixing and flow separation loss are enhanced in the impeller flow passage to deteriorate the efficiency. On the other hand, the blockage effect caused by the mixing of slot recirculation and mainstream flow near the impeller inlet increases the axial velocity and reduces the incidence angle below the 90% spanwise section, which is considered to effectively stabilize the impeller flow field and enhance the stability.

Up to now, the design methods for centrifugal compressors have been based on results of physical experiments. The possibility of correct CFD calculation of centrifugal compressors gas-dynamic characteristics could fundamentally change the situation. Gas-dynamic projects will become more reliable, cheaper, and the performance of compressors will be improved. However, the problem has not been solved yet. The experience of various authors shows that CFD calculations in many cases do not align well with experimentally obtained data. The aim of this paper is to check whether the commercial CFD software is capable of simulating centrifugal compressor characteristics using a 16 MW pipeline two-stage compressor as an example. The calculated characteristics of pressure ratio, efficiency and head coefficient are compared with characteristics measured using the manufacturer test bench on air. The calculations are performed in two ways: in the first case the flow in the impeller-stator gaps is taken into consideration, and in the second one it is not. In the first case, we do not take into account friction losses of the outer surfaces of impeller shrouds and leakage through labyrinth seals. The interface “STAGE” averages the parameters of flow at the impeller outlet and vaneless diffuser inlet. The flow leaving the impeller is averaged in tangential direction. This way of calculation excludes the mixing process of high and low-energy flow zones at the exit of the impeller. The calculated characteristic configurations are similar to the experimental ones, but they are shifted to the area of higher flow rates, and the difference in pressure ratio is out of the limits acceptable for engineering and research. Calculations that take into consideration gap losses underestimate the maximum efficiency by up to 2.5%. The characteristics calculated without gap losses are closer to the experimental characteristics. However, it is hardly possible to use this circumstance as a recommendation for the simulation methodology. The problem needs further investigation.

A centrifugal compressor is an important rotating tool that is widely used in the natural gas transportation industry. In engineering practice, working conditions typically deviate from design conditions. For example, inlet pressure and temperature levels are fixed in design conditions, whereas these two parameters are unstable under actual working conditions. Moreover, the physical properties of actual gas are often different from those of designed gas. As a result, it is difficult for a design performance curve to accurately predict the actual performance of a compressor. Therefore, it is necessary to study compressor performance conversions based on similarity criteria. At present, three primary methods are used for the conversion of compressor performance, i.e., the complete similarity conversion method, the first similarity conversion method and the second similarity conversion method. The complete similarity method adheres to very strict requirements, and it is difficult to completely meet such requirements in practical engineering settings. The first similarity conversion method is based on an assumption of polytrophic processes, and it is suitable to apply to gases with different adiabatic index values. For this method, temperature conversion results are accurate, but pressure conversion results are less accurate. The second similarity conversion method is based on an assumption of isometric processes. In contrast to the first similarity conversion method, the pressure conversion results of this method are accurate, but the temperature conversion results are less accurate. This is attributed to different means of determining the pressure ratio according to similarity conversion methods. If calculations of pressure ratios could apply the advantages and overcome the disadvantages of the first and second similarity conversion methods, the accuracy of performance conversion methods could be effectively improved. Based on the above, a new similarity conversion method for centrifugal compressors based on the predictor-corrector method is proposed. According to the proposed method, the second similarity conversion method is first used to predict the pressure ratio, and the first similarity conversion method is subsequently used to correct the pressure ratio. Thus, the pressure ratio can be corrected to ensure that both pressure and temperature conversion results are accurate. Finally, the first and second similarity conversion methods and the proposed method are used to convert the performance curve of a compressor used in the natural gas transmission pipeline running from Sichuan to eastern China. Compared with the field test data, the conversion errors of these three methods are as follows: for the first similarity conversion method, the relative of the outlet pressure is about 6% and the error of the outlet temperature is about 4–7°C; for the second similarity conversion method, the relative of the outlet pressure is about 4% and the error of the outlet temperature is about 2°C; for the proposed method, the relative of the outlet pressure is about 2% and the error of the outlet temperature is about 2°C. The results show that the method proposed in this paper is significantly more accurate than the other two common methods. Therefore, the use of this new method for compressor performance conversion in actual engineering settings is recommended.

A new method of gas emission forecasting based on the optimized RBF network is presented. In this method, genetic algorithm (GA) is applied to optimize the position of data centers, widths, and weights of the RBF network, so forming a GA-RBF model. The principle and algorithms of neural network are introduced. The simulation results show that the improved RBF neural networks has high precision, with reliable accuracy, good convergence rate and fast network training speed. Compared with the traditional RBF and BP networks, the method is more efficient and feasible.

The switched reluctance motor drive (SRD) has obtained great attention as an AC stepless speed control system due to its large regulating scope, low cost and ruggedness. However, its strong nonlinearity and multivariable characteristic make it difficult to control. To solve the problem, this paper presents an approach of adaptive PWM speed control for switched reluctance motors (SRM) based on RBF neural network. This method builds up a speed controller based on RBF neural network which has powerful approximating ability and fast convergence property. The controller is trained off-line in advance, and then with the motor's operation, the on-line training of it makes its parameters vary with the environment in order to improve the control performance. In addition, another RBF network is constructed to offer gradient parameters, which is needed by the on-line training, via on-line identification. The results of experiments prove that the approach has lots of advantages in response speed, control accuracy and adaptability.

An encrypting algorithm based on RBF neural network is presented. The clear-text is regarded as RBF target vector. RBF network is trained with random input vector, and the trained results are regarded as the cryptograph. With the feature that the input vector of RBF neural network can be any random value, there are the infinite kinds of ways to build the input vector, so the cryptograph cannot be deciphered theoretically. The random seed used to generate the input vector is regarded as the secret-key. The receiver can get the clear-text from the cryptograph by reconstructing RBF neural network and its input vector with the secret-key. The simulation experiments prove the algorithm is feasible and effective.

Centrifugal compressor blade trimming can be used for the purpose of changing the performance characteristics of an impeller or allowing a single impeller design to be used for a range of operating conditions. There are a number of methods of impeller blade trimming that may be employed to change the impeller flowrate, the pressure ratio, or both; however, the limitations of blade trimming and the effect on the flow field are not well understood. In this study, CFD is used to model the effects of three different methods of blade trimming on a single centrifugal compressor design. Impeller performance characteristics and analysis of the flow field are presented for a series of trims for each of the three trimming methods. Each method of trimming was found to be limited at some point by choke. Shifting the original shroud profile both axially and radially in proportion to the desired flow coefficient allowed the pressure ratio and efficiency of the original impeller to be maintained while changing the flow coefficient. Trimming the blades along the meridional length in proportion to the desired new flow coefficient without regard to the original shroud profile produced similar results, but allowed the impeller to be trimmed further than was practical using the radial-axial shroud offset method. Trimming the blades axially so that the original shroud profile is maintained produced a change in pressure ratio while maintaining the original impeller flow coefficient.

Modelling of the non-reactive deposits impact on centrifugal compressor aerothermo dynamic performance

Currently existing regulatory documents assume that refrigeration compressors are tested as part of test rigs with heat-exchange equipment. Given the high energy intensity of centrifugal compressors, the drive power of which in cooling mode with a cold capacity of up to 8.0 MW can be 2.0 or more MW, the creation of test rigs for preliminary and acceptance tests at the manufacturer’s factory requires a large investment. An alternative to the considered refrigeration centrifugal compressors test method is a test on a test rig in which the agent is partially condensed. In this case, an evaporator and a full-sized condenser are not required. The mathematical model of the refrigeration centrifugal compressors developed by JSC VNIIKHOLODMASH, allows testing of the refrigeration centrifugal compressors in model conditions, when the entire compressor operation cycle at the test rig is carried out in the area of superheated steam. Since the refrigeration centrifugal compressors mathematical model is based on physical simulation of compression processes in model stages at different values of conditional Mach numbers, dimensionless characteristics of model stages can be used to calculate the characteristic of the created compressor when operating under new conditions. The implementation of the model test method provides reduction of testing time due to absence of phase changes of the agent, improves the accuracy of the obtained results, reduces of power consumption, simplifies the test rig, and reduces consumption of the agent for filling the rig and water for cooling the agent.

Turbocharging technique has played a critical role not only for improving automotive engine performance, but also for reducing fuel consumption and exhaust emissions both in Spark Ignition and Compression Ignition engines. In the research described in this paper, a 1D centrifugal compressor model has been developed for simulating turbocharger flow and performance. The model takes into account energy conservation and transfer which includes the losses determined from the compressor geometry. The losses including incident loss, friction loss, clearance loss, backward loss and volute loss were simulated by the thermodynamics model, rather than from the characteristic performance curves obtained experimentally. The proposed model was validated against experimental data and it showed simulating and experimental results are in very good agreement at three different rotational speeds, in particular near the surge line, though the deviation begins to increase as mass flow rate goes up. With current results, it has suggested the proposal is suitable for predicting the compressor performance curves such as outlet pressure, efficiency and losses for any centrifugal compressor. In addition, surge line obtained from the simulation result can be used to define stable operation range.

The paper presents the results of CFD-calculations of a centrifugal compressor stage with a high-pressure 3D impeller and a vaneless diffuser. The stage was designed by Prof. A. M. Simonov in the Problem Laboratory of Compressor LPI according to the following design parameters: flow rate coefficient 0.080, loading factor 0.74, and the relative Mach number 0.78. Two design grids were used: 2.4 and 4.4 million cells for the sector with one blade. The entire stage was calculated with a sparser grid. Special “Stage” interface conditions are used to interface the gas-dynamic parameters at the boundary regions. The SST turbulence model was used in the calculations. The results of efficiency characteristics and work coefficient comparison showed the following: in design flow rate all three variants of the calculation overstate the loading factor by 14.3%; the calculated characteristics of polytrophic work coefficient in the staging of 360 degrees are closest to the experimental characteristics, but the absolute value is greater than 12% at a flow rate coefficient of 0.085; the maximum calculated efficiency of a stage (the circle of 360 degrees) is almost equal to the measured maximum efficiency.

Compact aero-engines that use centrifugal compressors are in high demand due to their small size and cost-effectiveness. However, limited improvements in the aerodynamic performance of centrifugal impellers have led to a greater focus on improving the performance of diffusers. This paper introduces a novel vane conformal diffuser designed to match an impeller with a high pressure ratio. The diffuser utilizes a unique design method that creates transitions from a two-dimensional meridian to a three-dimensional configuration, to achieve a twisted design for the vane and hub. Eventually an integrated vane configuration is formed from the radial section to the bend and axial sections. The novel diffuser significantly reduces the radial size of the entire compressor compared with a conventional vaned diffuser. Different cross-section area distributions are studied to explore the reasonable static pressure recovery ability of the diffuser. To validate the new concept, the diffusers of two existing high-pressure centrifugal compressors are redesigned using the novel conformal diffuser configuration. The numerical results show that the aerodynamic performances of the two redesigned centrifugal compressors are improved in terms of both the total pressure ratio and the isentropic efficiency compared with their counterparts. These results demonstrate the effectiveness and applicability of the developed design method for the novel conformal diffuser.