Performance Prediction of the Centrifugal Compressor Based on a Limited Number of Sample Data

Abstract

Centrifugal compressor is widely used in various engineering domains, and predicting the performance of a centrifugal compressor is an essential task for its conceptual design, optimization, and system simulation. For years, researchers seek to implement this mission through various kinds of methods, including interpolation, curve fitting, neural network, and other statistics-based algorithms. However, these methods usually need a large amount of data, and obtaining data may cost considerable computing or experimental resources. This paper focuses on constructing the performance maps of pressure ratio and isentropic efficiency using a limited number of sample data while maintaining accuracy. Firstly, sample data are generated from simulation using Vista CCD. Then, corrected flow rate and corrected rotational speed are used as independent variables, and the regression expressions with physical meaning of pressure ratio and isentropic efficiency are derived and simplified through thermodynamic analysis and loss analysis of centrifugal compressor, resulting in two loss-analysis-based models. Meanwhile, kriging models based on a second-order polynomial and neural network models are built. Results show that, when predicting inside data boundary, the loss-analysis-based model and the kriging model produce higher accuracy prediction even in a small data set, and the predicting result is stable, while the neural network model provides better results only in a more extensive data set with more speed lines. For the prediction outside the data boundary, the loss-analysis-based model can provide relatively accurate results. Besides, it takes less time to train and utilize a loss-analysis-based model than other models.

Nghiên cứu xây dựng công cụ học máy dự báo nhiệt độ đầu ra cấp 1 và cấp 2 của máy nén khí cao áp

“…Hongsheng Jiang cùng cộng sự [7] tiến hành xây dựng mô hình tỷ lệ áp suất và hiệu suất đẳng entropy của máy nén bằng cách sử dụng một số lượng mẫu dữ liệu hạn chế trong khi vẫn đảm bảo được độ chính xác cao. Đầu tiên, dữ liệu mẫu được tạo ra bằng phương pháp mô phỏng Vista CCD.…”

Turbomachinery Design: Checking Artificial Neural Networks Suitability for Design Automation

“…In recent years, ANNs have been applied to a lot of industrial problems, from functional prediction and system modelling (where physical processes are not well understood or are highly complex) to pattern recognition engines and robust classifiers, with the ability to generalise while making decisions about different kind of input data (Meireles et al, 2003). In the literature, the first applications of ANNs in the turbomachinery industry concern the simulations of design and off-design conditions of gas turbines operability (Lazzaretto and Toffolo, 2001), the prediction of axial compressors performance map (Yu et al, 2007), and the centrifugal compressors performance (Jiang et al, 2019). This approach, however, gives an estimation of the performance of the single components without taking into account the effects of the variations of internal design parameters on performance.…”

Automatic Detection of Linear Thermal Bridges from Infrared Thermal Images Using Neural Network

“…This study applied a backpropagation neural network, which is appropriate for processing small amounts of data to train the ANN [31]. Among the training parameters, the number of hidden layers has a significant influence on prediction results [32]. This study set the number of hidden layers to one by considering the number of input and output layers.…”