Analytical Redundancy for Variable Cycle Engine Based on Variable-Weights-Biases Neural Network
Aerospace
Abstract and Figures
Due to the complex nature of a variable cycle engine (VCE), which has numerous control variables and working modes across a broad flight envelope, coupled with the whole engine’s degradation, the analytical redundancy method based on component-level models may not provide an accurate estimation of the sensors. Variable-weights-biases neural network (VWB Net) is proposed to construct VCE’s analytical redundancy. Unlike conventional networks whose weights and biases are fixed, VWB Net’s variable-weights and variable-biases are functions of input which greatly increase its nonlinear mapping capability by integrating input information. Variable-biases can also be used to eliminate the error between actual sensor output and estimated value quickly at the terminal node. Compared with the BP network and Dense net, VWB Net has fewer parameters, faster calculation speed, and higher accuracy. Digital simulation results of VCE parameter estimation demonstrate that VWB Net’s average relative errors are under 0.27% with calculation and parameter efficiency at least 166 times higher than that of Dense net. Hardware in the loop simulation further verifies VWB Net’s estimation accuracy and real-time calculation.
Figures - available from: Aerospace
This content is subject to copyright.
ResearchGate has not been able to resolve any citations for this publication.
The variable cycle engine switches working modes by way of changing variable-geometry components to achieve the dual advantages of high unit thrust and low specific fuel consumption. Due to the lack of a large amount of rig test data and the complex modeling of rotating components, the incomplete characteristics of the variable-geometry rotating components lead to the non-convergence of the component-level model of the variable cycle engine, which makes it difficult to design the follow-up control system. Aiming at this problem, a characteristics modeling method of variable-geometry rotating components for variable cycle engine based on reference characteristic curves is proposed in this paper. This method establishes a neural network estimation model for the offset coefficients of key component operating points based on the characteristic law of the maturely designed variable-geometry rotating component. Combining the neural network model and the reference characteristic curves of the variable-geometry component to be designed, the offset positions of the operating points for positive and negative guide vane angles are determined. Instead of directly connecting operating points to generate characteristic lines, this paper solves the Bezier curve optimization problem based on sequential quadratic programming (SQP) to smoothly fit characteristic lines. Thereby, component characteristics that conform to the actual variable-geometry characteristics can be quickly established in the absence of rig test data. The simulations show that the characteristics of the variable-geometry rotating components established by the proposed method have satisfactory accuracy and reliability, which further improves the operation stability of the component-level model of the variable cycle engine.
The aero-engine system is complex, and the working environment is harsh. As the fundamental component of the aero-engine control system, the sensor must monitor its health status. Traditional sensor fault detection algorithms often have many parameters, complex architecture, and low detection accuracy. Aiming at this problem, a convolutional neural network (CNN) whose basic unit is an inception block composed of convolution kernels of different sizes in parallel is proposed. The network fully extracts redundant analytical information between sensors through different size convolution kernels and uses it for aero-engine sensor fault detection. On the sensor failure dataset generated by the Monte Carlo simulation method, the detection accuracy of Inception-CNN is 95.41%, which improves the prediction accuracy by 17.27% and 12.69% compared with the best-performing non-neural network algorithm and simple BP neural networks tested in the paper, respectively. In addition, the method simplifies the traditional fault detection unit composed of multiple fusion algorithms into one detection algorithm, which reduces the complexity of the algorithm. Finally, the effectiveness and feasibility of the method are verified in two aspects of the typical sensor fault detection effect and fault detection and isolation process.
The variable cycle engine selects the appropriate working mode through mode switch to meet the requirements of low specific fuel consumption and high unit thrust. When the variable cycle engine switches between different modes, it should ensure the smooth transition of working modes and obtain the expected performance at the same time. Consequently, a general control schedule design method for mode switch is investigated in this paper. The feasible switching domains of single-bypass working mode and double-bypass working modes are obtained based on multifurcating tree traversal, and the switching point in the feasible switching domain is determined by solving the collaboration-game optimization problem based on sequential quadratic programming (SQP). Finally, the schedule of control variables is designed to realize smooth and fast switching between different working modes of variable cycle engine. The simulations show that based on the general control schedule of mode switch proposed in this paper, smooth transition of thrust and rotor speed can be achieved under the premise of safe engine operation, with small fluctuations and a short switching time, which is about 2.5 s.
The safety and reliability of the measuring elements of an aero-engine are important preconditions of the stable operation of the engine control system. The number of control parameters of a variable cycle engine increases by 20%–40% compared to traditional engines. Therefore, it is important to conduct study on the analytical redundancy, design fault diagnosis and isolation of the sensors, as well as the signal reconstruction system, so as to increase the ratability and fault-tolerant capability of the variable cycle engine control system. The analytical redundancy method relies on the accuracy of the mathematical model of the engine. During the service cycle of the engine, it is inevitable that the engine performance will deteriorate, resulting in a mismatch with the model. In this paper, the adaptive model of the variable cycle engine is built with a Kalman filter. Based on this, the strategy of analytical redundancy logic is built and the dynamic adaptive calculation of the threshold is introduced. Simulation results reflect that this method can effectively increase the reliability of sensor fault diagnosis and the accuracy of the analytical redundancy when there is performance degradation of the variable cycle engine.
In this paper, Proper net is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental variables change simultaneously, also accompanied with the whole engine’s degradation. In another word, Proper net is proposed to solve a multivariable, strongly nonlinear, dynamic, and time-varying problem. In order to make the topological structure of Proper net physically explainable, Proper net’s topological structure is designed according to physical relationship between variables, by which means analytical redundancy based on Proper net achieves higher accuracy with less calculation time. Experiments were compared with performance of analytical redundancy based on Proper net, seven convolutional neural network topological structures, and five shallow learning methods. Results demonstrate that under condition of average relative error less than 1.5%, Proper net is the most accurate and the least time-consuming one, which proves not only the effectiveness of Proper net but also the feasibility of topological structures’ design method based on physical relationship.
Air transport plays an inevitable role in the transportation sector. In the modern world, the aviation contribution is very immense to establish worldwide developments. However, the emission released by the aviation industry is massively high. Due to the sudden increase in the air traffic the contribution of global CO2 and CO have increased in recent years. Hence the aviation sector seeks the replacement for fossil fuels. In this study, the micro gas turbine engine has been experimentally studied for different engine speeds and throttle position. The gas turbine was allowed to run in the different test fuels such as, Jet-A, A20 (20% microalgae 80% Jet-A) and A30 (30% microalgae 70% Jet-A) and the predicted results were compared. In addition to the typical experimental calibrations, machine learning has been applied to examine the differences in the both performance and emission characteristics of the biofuel blends with approximately 51 different fuel combinations using LSTM networks. Based on the predicted results, introduction of the biofuel affects the production of the static thrust. On the contrary, the emissions of the CO and CO2 were very low compared to Jet-A. With regard to the nitrogen of the oxides, no massive reduction has been witnessed despite running at different fuel conditions. Besides, the marginal decrease in the NOx was observed above 75000 rpm.
Airbreathing aero-engines are regarded as excellent propulsion devices from ground takeoff to hypersonic flight, and require control systems to ensure their efficient and safe operation. Therefore, the present paper aims to provide a summary report of recent research progress on airbreathing aero-engine control to help researchers working on this topic. First, five control problems of airbreathing aero-engines are classified: uncertainty problem, multi-objective and multivariable control, fault-tolerant control, distributed control system, and airframe/propulsion integrated control system. Subsequently, the research progress of aircraft gas turbine engine modelling, linear control, nonlinear control, and intelligent control is reviewed, and the advantages and disadvantages of various advanced control algorithms in aircraft gas turbine engines is discussed. Third, several typical hypersonic flight tests are investigated, and the modelling and control issues of dual-mode scramjet are examined. Fourth, modelling, mode transition control and thrust pinch control for turbine-based combined cycle engines are introduced. Followed, significant hypersonic airframe/propulsion integrated system control is analysed. Finally, the study provides specific control research topics that require attention on airbreathing aero-engines.
Intelligent data-driven fault diagnosis based on conventional machine learning techniques has been extensively studied in recent years. However, these methods often assumed that the data used for training and testing are drawn from the identical distribution, which is impractical in real application. Such idealized hypothesis may confine these promising data-driven techniques to well-designed experimental environments rather than actually putting them into real-world applications. In practice, the distribution discrepancies between source domain and target domain will degrade the diagnostic performance. To this end, this work introduces a transfer learning based extreme learning machine to align the distribution discrepancies of the data collected from a turbofan engine, which is rarely studied in the fault diagnosis for aero-engine. The proposed method is capable of learning the transferable cross domain features while preserving the properties and structures of source domain as much as possible. Meanwhile, the marginal distribution and conditional distribution discrepancies are matched. Through these transfer data representations, a relatively high diagnostic accuracy is guaranteed. Finally, extensive experiments have been performed on gas path fault diagnosis of turbofan engine, including hybrid transfer cases and complete transfer cases, to verify the effectiveness and feasibility of the proposed method.
This paper investigates the authenticity of the biofuels as an alternative to Jet A fuel. Owing to the fact of reduced CO2 emission quality, biofuels can be used in the field of aviation to substantially reduce the CO2 emission and improve the performance. In this analysis, microalgae Spirulina biofuel was added with Jet-A fuel at different proportions such as 20%, 40%, 60%, 80% and 100%. The proportions used are B20% (20% biofuel with 80% jet-A fuel), B40% (40% biofuel with 60% Jet-A fuel), B60% (60% biofuel with 40% Jet-A fuel), B80% (80% biofuel with 20% Jet-A fuel) and B100% biofuel. All the test results were compared with the neat jet A fuel. The experiments were conducted at different engine speeds. A small experimental jet engine was used to conduct all the experimental tests. Engine performance characteristics and emission characteristics were found for different fuel blends. It is concluded that the biofuel at a lower proportion level with the Jet–A fuel comparatively produced a good result. In terms of thrust and engine speed, the lower level of addition of biofuel is fruitful. The emission level of CO, CO2, and NOx was reduced owing to the presence of excess oxygen content in the blends. However, when the addition percentage was increased, the results produced by them were not positive because of its low energy.