Xiaodong Yi
ABSTRACT
Through the optimized parameter prediction method, it can achieve a more accurate prediction of the rocket engine performance parameters; Initial values of the network parameters are randomly determined during the initialization of the BP neural network, making it easier to converge to the local minimum points when minimizing the error function by the gradient descent method, instead of the desired global minimum point; The particle swarm algorithm has better global search capability for nonlinear, multimodal problems, The insufficiency of BP neural network can be optimized; Liquid rocket engine nozzle throat is one of the worst working conditions, and the temperature change has a certain inertia and lag, therefore, based on the throat temperature data measured during the test run of a certain type of pose and orbital control engine, using particle swarm optimization BP neural network algorithm (PSO-BP) and BP neural network algorithm to establish the nonlinear time series model of engine throat temperature change; According to the comparison of the simulation results and the actual test data, the algorithm can achieve better throat temperature prediction effect and have better performance than BP neural network algorithm.
- Wang Lei. The PSO algorithm is optimized for the BP neural network [J], 2018, (34)Google Scholar
- BP Network and Particle Swarm Optimization Prediction of Total Energy[J],2016, No.179 (20)Google Scholar
- Zhang Hui. House price prediction based on PS [J], 2012, v.31;No.274(14)Google Scholar
- Yao Erguo, Yan Qifen, Nan Zhenqi, Xue Xiaohu. BP Neural Network Model Based on improved particle swarm algorithm [J], 2012, v.30;No.116(01)Google Scholar
- Ding Yan, Guan Yanming. Particle swarm algorithm optimization study [J], 2018, No.585(10)Google Scholar
- Xu Lan, Fang Zhi Geng, Liu Sifeng. Quality prediction models based on the particle swarm BP neural network [J], 2012, v.15;No.80(04)Google Scholar
- Zhang Shan, He Jiannong. Study of the optimization algorithms of BP neural networks [J], 2009, No.161(01)Google Scholar
- Yang Lifen, Cai Zhihua. Study on BP Neural Network Optimization Algorithm[J],2007, No.53 (05)Google Scholar
- Liu Jian, Wang Xin, Liu Jiang, Wen Mingyi. Application of Particle Swarm Optimization BP Neural Network in Elevator Group Control System[J],2009, v.25; No.122 (05)Google Scholar
- The Application of Back Propagation Neural Network Algorithm Based on Particle Swarm Optimization in Predicting Settlement of Buildings[J],2019, v.46; No.415 (13)Google Scholar
- Pang Mingyue. BP Neural Network Algorithm and Its Improvement[J],2014, v.10 (28)Google Scholar
- Wu Jianjun, Cheng Yuqiang, Cui Xing. Research status of liquid rocket engine health monitoring technology[J],2020, v.37; No.223 (01)Google Scholar
- Zhang Wei, Tian Gan, Xu Zhigao, and Yang Zhengwei. Analysis and diagnosis of liquid missile engine [B], headquartersGoogle Scholar
- Zhang Yulin. Health Monitoring Technology for Liquid Rocket Engines[B],1998,351Google Scholar
- Wang Zhijun, Chang Xinlong, Tian Gan, Zhang Xiaojun. Thrust chamber design for liquid rocket engines[B], National Defense Industry Press,2014Google Scholar
- Zhong Jinbao, Qi Jingshuai, Li Lei, etc. Simulation of hydraulic support column control circuit based on particle swarm algorithm [J]. Construction Machinery, 2023,54 (06)Google Scholar
- Feng Yan, Wu Yishan, Chen Lunjia and so on. Analysis of electric vehicle charging load prediction method for improving BP neural network based on particle swarm [J]. Electronics, 2023,52 (04)Google Scholar
- Li Haitao, Wang Borui. Application of BP neural network optimized based on particle swarm algorithm in seawater water quality evaluation [J]. Marine Science, 2020,44 (06)Google Scholar
Index Terms
- Rocket engine parameter prediction based on particle swarm optimized BP neural network
Recommendations
Mildew Prediction Model of Warehousing Tobacco Based on Particle Swarm Optimization and BP Neural Network
Intelligent Computing MethodologiesAbstractIn order to reduce the economic loss caused by mildew of warehousing tobacco, in this paper, particle swarm optimization algorithm is introduced into BP neural network mode. Particle swarm optimization is used to dynamically adjust the initial ...
Improved adaptive particle swarm for BP neural network optimization in hospital outpatient volume prediction
ESCC '21: The 2nd European Symposium on Computer and CommunicationsReal-time and accurate prediction of hospital outpatients is an important basis for the hospital to resolve the current contradiction between doctors and patients. However, the traditional hospital outpatients cannot accurately predict the data and ...
Prediction of Short-Term Traffic Flow Based on PSO-Optimized Chaotic BP Neural Network
CSA '13: Proceedings of the 2013 International Conference on Computer Sciences and ApplicationsIn order to improve the prediction accuracy of BP neural network model for chaotic time series, a new prediction method for chaotic time series of optimized BP neural network based on particle swarm optimization (PSO) was presented. The PSO was used to ...
Comments