改进SO优化KELM的液体火箭发动机故障检测  被引量:4

Improved SO and Optimized KELM for Liquid Rocket Engine Fault Detection

在线阅读下载全文

作  者:王闻浩 许亮[1,2] Wang Wenhao;Xu Liang(Tianjin University of Technology,School of Electrical Engineering and Automation,Tianjin 300384,China;Tianjin Key Laboratory for Control Theory&Applications in Complicated Systems,Tianjin 300384,China)

机构地区:[1]天津理工大学电气工程与自动化学院,天津300384 [2]天津市复杂系统控制理论与应用重点实验室,天津300384

出  处:《航天控制》2023年第4期84-90,共7页Aerospace Control

基  金:国家自然科学基金(61975151);航天六院北京航天动力研究所(20ZXJCWX2000032001)。

摘  要:提出了一种ISO-KELM的液体火箭发动机故障检测模型。首先引入Tent混沌映射、动态策略和柯西变异3种方法对原算法进行改进。然后,采用改进后的蛇优化算法(ISO)对核极限学习机(KELM)惩罚因子和核函数参数进行寻优,构建了ISO-KELM液体火箭发动机故障检测模型。最后选取包含5种典型故障模式的某液体火箭发动机历史试车数据进行仿真。结果表明,ISO-KELM模型的故障检测准确率为95.2%,高于SO-KELM故障检测模型和传统BP神经网络故障检测模型,可有效检测火箭发动机的故障状态。同时也表明了ISO相比于SO,收敛速度更快,寻优精度更高。A fault detection model of liquid rocket engine based on ISO-KELM is proposed.Firstly,tent chaotic map,dynamic strategy and Cauchy mutation are introduced to improve the original algorithm.Then,the improved snake optimization(ISO)is used to optimize the penalty factor and the kernel function parameter of Kernel Extreme Learning Machine(KELM),and the ISO-KELM fault detection model of liquid rockhet engine is established.Finally,the historical test data of a liquid rocket engine including five typical fault modes are selected for simulation.The results show that the fault detection accuracy of the ISOKELM model is reached by 95.2%,which is higher than that of the SO-KELM fault detection model and the traditional BP neural network fault detection model,and which can effectively detect the fault state of the rocket engine.At the same time,it also shows that ISO has faster convergence speed and higher optimization accuracy than SO.

关 键 词:液体火箭发动机 故障检测 蛇优化算法 核极限学习机 混沌映射 

分 类 号:V434.3[航空宇航科学与技术—航空宇航推进理论与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象