Abstract:In this paper, compressor aerodynamic performance has been predicted based on throughflow theory, combined with a surrogate model, which is a combination of the Genetic Algorithm (GA) and generalized Radial Basis function (RBF) neural network. And the predicting results have been compared with those from the traditional models and spanwise mixing model, which still widely be used to predict the aerodynamic performance. We first predicted the deviation angle and total-pressure loss coefficient (TPLC) by the sur… Show more
“…The GA has been proven to solve both linear and non-linear problems by exploring all regions of the state space and exponentially exploiting the potential regions through crossover, mutation, and selection operations adopted to individuals in the population. 22 In this article, the GA is adapted to optimize the initial values of weights and biases of BPNN to have a better prediction capability. The layout of the GA-BPNN procedure is shown in Figure 6.Figure 6.Layout of the genetic algorithm-back propagation neural network procedure.…”
While the consistent advance in computational power has enabled the Computational Fluid Dynamics (CFD) an effective tool for compressor performance characterization, the need for quick performance estimates at initial design phase of compressor still requires the use of low order models. Thus, the throughflow method remains the backbone of compressors design process. The accuracy of the throughflow calculation mainly depends on the adopted empirical correlations. However, the traditional empirical models are just accurate for the conventionally loaded compressor at normal working conditions. In this article, the mechanism of blade profile loss generation and the formation mode of existing empirical correlation are studied, and the reason why the traditional diffusion factor based empirical models are not applicable for modern high-loading compressors or conventional-loading blades at negative incidence is also discussed. Then, the Genetic Algorithm assisted Back Propagation Neural Network (GA-BPNN) is used to train the surrogate model for the design and off-design loss prediction along the blade span of the compressor. Based on the test data of four transonic compressor stages, a database containing 72 sets of blade element geometry and about 1400 sets of blade element performance data is established. Considering the different mechanisms of rotor and stator losses at different working conditions, the entire database and surrogate model are divided into four components according to the rotor and stator at positive incidence and negative incidence. Comparing the prediction results of the surrogate model with the traditional empirical correlations and experimental data, the results show that the GA-BPNN is an alternative solution for developing the empirical model.
“…The GA has been proven to solve both linear and non-linear problems by exploring all regions of the state space and exponentially exploiting the potential regions through crossover, mutation, and selection operations adopted to individuals in the population. 22 In this article, the GA is adapted to optimize the initial values of weights and biases of BPNN to have a better prediction capability. The layout of the GA-BPNN procedure is shown in Figure 6.Figure 6.Layout of the genetic algorithm-back propagation neural network procedure.…”
While the consistent advance in computational power has enabled the Computational Fluid Dynamics (CFD) an effective tool for compressor performance characterization, the need for quick performance estimates at initial design phase of compressor still requires the use of low order models. Thus, the throughflow method remains the backbone of compressors design process. The accuracy of the throughflow calculation mainly depends on the adopted empirical correlations. However, the traditional empirical models are just accurate for the conventionally loaded compressor at normal working conditions. In this article, the mechanism of blade profile loss generation and the formation mode of existing empirical correlation are studied, and the reason why the traditional diffusion factor based empirical models are not applicable for modern high-loading compressors or conventional-loading blades at negative incidence is also discussed. Then, the Genetic Algorithm assisted Back Propagation Neural Network (GA-BPNN) is used to train the surrogate model for the design and off-design loss prediction along the blade span of the compressor. Based on the test data of four transonic compressor stages, a database containing 72 sets of blade element geometry and about 1400 sets of blade element performance data is established. Considering the different mechanisms of rotor and stator losses at different working conditions, the entire database and surrogate model are divided into four components according to the rotor and stator at positive incidence and negative incidence. Comparing the prediction results of the surrogate model with the traditional empirical correlations and experimental data, the results show that the GA-BPNN is an alternative solution for developing the empirical model.
“…This network is applied to estimate non-linear functions and set up mappings between the input and output parameters. Standard RBF forward-propagation is as follows (Tang and Liu, 2021):…”
Section: Ga-km-radial Basis Functionmentioning
confidence: 99%
“…3, n is the training samples number, i.e., the hidden nodes number, and w i is the coefficients of weights. G(x, O i ) is presented as follows (Tang and Liu, 2021):…”
A compressor is one of the key components of a gas turbine engine and its performance and characteristics significantly affect the overall performance of the engine. Axial flow compressors are one of the most conventional types of compressors and are widely used in turbine engines for large-scale power generation. Intelligent techniques are useful for numerical simulation, characterization of axial compressors, and predicting their performance. The present work reviews studies applying different intelligent methods for performance forecasting and modeling different aerodynamic aspects of axial compressors. Corresponding to the outcomes of the considered research works, it can be expressed that by using these methods, axial compressors can be characterized properly with acceptable exactness. In addition, these techniques are useful for performance prediction of the compressors. The accuracy and performance of these methods is impacted by several elements, specifically the employed method and applied input variables. Finally, some suggestions are made for future studies in the field.
“…The global exploratory method has a long history of development, and it has played an important role in the field of compressor aerodynamic design as an effective optimization design method [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. In centrifugal compressors, due to the complex flow field, the global exploratory method is wildly used because it is difficult to directly carry out aerodynamic design.…”
Section: Introductionmentioning
confidence: 99%
“…Sometimes, global exploration has been used on throughflow method to optimize the compressor [ 16 ]. In some cases, global exploratory method is also used to assist the design process of a compressor, such as optimizing the hyper parameters of the other algorithms [ 18 , 19 ]. In general, compared to local optimization, global exploration usually requires more CFD calls to achieve its powerful exploration capacity.…”
The endwall effect has a great impact on the aerodynamic performance of compressor blades. Based on three conventional near-endwall blade modeling methods of bowed blade, endbend blade and leading-edge strake blade (LESB), two combined optimization design methods of highly loaded blades have been developed considering the endwall effect in the current study, i.e., the bowed blade combined with the LESB (bowed LESB blade) and the endbend blade combined with the LESB (endbend LESB blade). Optimization designs were conducted for a compressor cascade with low solidity by using the two combined modeling methods and the three conventional modeling methods, and the optimization results were compared and analyzed in detail. The results showed that the five optimization modelling methods could all improve the performance for the original cascade, and the optimized cascade with the bowed LESB modeling method has the best aerodynamic performance. The total pressure loss of the optimal bowed LESB cascade was only 40.3% of that in the original cascade while reducing the solidity of the original cascade from 1.53 to 1.25 and keeping the static pressure rise and diffusion factor at the same level as the original one. Among the optimal cascades, the radial migration height of the low-energy fluid and the corresponding vortex have great effects on the aerodynamic performance, and the optimal bowed LESB cascade is superior to the other optimal cascades in this aspect.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
