Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine
Servo systems are important actuators of aeroengines. The repetitive, reciprocating motion of the servo system leads to significant changes in its time delay and gain characteristics, and degradation increases the uncertainty of these changes. These characteristic variations may have an adverse effe...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/12/1/64 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589454830731264 |
|---|---|
| author | Hongyi Chen Qiuhong Li Zhifeng Ye Shuwei Pang |
| author_facet | Hongyi Chen Qiuhong Li Zhifeng Ye Shuwei Pang |
| author_sort | Hongyi Chen |
| collection | DOAJ |
| description | Servo systems are important actuators of aeroengines. The repetitive, reciprocating motion of the servo system leads to significant changes in its time delay and gain characteristics, and degradation increases the uncertainty of these changes. These characteristic variations may have an adverse effect on the dynamic performance of the aeroengine. Therefore, a neural network-based parameter estimation and a multi-loop neural network-based predictive control (ML-NNPC) method for aeroengine inlet guide vane (IGV) servo systems (SVS) were proposed. In this study, the time delay estimation of the servo system was treated as a classification problem, and an SE (squeeze-and-excitation)-GRU (gated recurrent unit) network was proposed to estimate the time delay by using the selected dynamic data of the servo system. The estimated delay was embedded into an online sequential extreme learning machine, and a nonlinear model predictive controller was designed to obtain an optimal control sequence. The compensation control loop was designed to reduce the impact of the model and delay mismatch problems of the control system. The proposed method was applied to the IGV SVS control of a turboshaft engine. The simulation results demonstrate that the time delay is estimated accurately and compensated effectively. Compared to the existing PI and PI with Smith predictor methods, the ML-NNPC method achieves better control performance in the control of both the SVS and the engine rotor speed system. The stability and robustness of the ML-NNPC also show superiority. The results verify the effectiveness of the proposed time delay estimation method and the ML-NNPC method. |
| format | Article |
| id | doaj-art-1acc5ee8ae794fbd87073af002e577a9 |
| institution | Kabale University |
| issn | 2226-4310 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj-art-1acc5ee8ae794fbd87073af002e577a92025-01-24T13:15:42ZengMDPI AGAerospace2226-43102025-01-011216410.3390/aerospace12010064Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of AeroengineHongyi Chen0Qiuhong Li1Zhifeng Ye2Shuwei Pang3Jiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaServo systems are important actuators of aeroengines. The repetitive, reciprocating motion of the servo system leads to significant changes in its time delay and gain characteristics, and degradation increases the uncertainty of these changes. These characteristic variations may have an adverse effect on the dynamic performance of the aeroengine. Therefore, a neural network-based parameter estimation and a multi-loop neural network-based predictive control (ML-NNPC) method for aeroengine inlet guide vane (IGV) servo systems (SVS) were proposed. In this study, the time delay estimation of the servo system was treated as a classification problem, and an SE (squeeze-and-excitation)-GRU (gated recurrent unit) network was proposed to estimate the time delay by using the selected dynamic data of the servo system. The estimated delay was embedded into an online sequential extreme learning machine, and a nonlinear model predictive controller was designed to obtain an optimal control sequence. The compensation control loop was designed to reduce the impact of the model and delay mismatch problems of the control system. The proposed method was applied to the IGV SVS control of a turboshaft engine. The simulation results demonstrate that the time delay is estimated accurately and compensated effectively. Compared to the existing PI and PI with Smith predictor methods, the ML-NNPC method achieves better control performance in the control of both the SVS and the engine rotor speed system. The stability and robustness of the ML-NNPC also show superiority. The results verify the effectiveness of the proposed time delay estimation method and the ML-NNPC method.https://www.mdpi.com/2226-4310/12/1/64servo systemtime delay estimationparameter estimationdegradation compensation controlneural networknonlinear model predictive control |
| spellingShingle | Hongyi Chen Qiuhong Li Zhifeng Ye Shuwei Pang Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine Aerospace servo system time delay estimation parameter estimation degradation compensation control neural network nonlinear model predictive control |
| title | Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine |
| title_full | Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine |
| title_fullStr | Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine |
| title_full_unstemmed | Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine |
| title_short | Neural Network-Based Parameter Estimation and Compensation Control for Time-Delay Servo System of Aeroengine |
| title_sort | neural network based parameter estimation and compensation control for time delay servo system of aeroengine |
| topic | servo system time delay estimation parameter estimation degradation compensation control neural network nonlinear model predictive control |
| url | https://www.mdpi.com/2226-4310/12/1/64 |
| work_keys_str_mv | AT hongyichen neuralnetworkbasedparameterestimationandcompensationcontrolfortimedelayservosystemofaeroengine AT qiuhongli neuralnetworkbasedparameterestimationandcompensationcontrolfortimedelayservosystemofaeroengine AT zhifengye neuralnetworkbasedparameterestimationandcompensationcontrolfortimedelayservosystemofaeroengine AT shuweipang neuralnetworkbasedparameterestimationandcompensationcontrolfortimedelayservosystemofaeroengine |