The calibration of force offset for rocket engine based on deep belief network

Zhang, Jun; Yu, Tian; Ren, Zongjin; Chang, Qingbing; Jia, Zhenyuan

doi:10.1177/0020294018776442

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, the Merlin-1D+ model has reached 232 weight-to-weight ratio in the dive test, and can work under 111% thrust. The Falcon 9 launch vehicle equipped with this model is also called the Falcon 9 full-thrust version [13].…”

Section: Merlin-1 Series Enginesmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of the development of reusable launch vehicle technology

Wu,

Zhang

2023

ACE

View full text Add to dashboard Cite

Nowadays, with the development of the space technology and the maturity of traditional launch vehicle technology, there are sufficient foundations for the research of higher-level space vehicles. As space vehicles gradually enter the commercial market, the demand for better cost control and higher carry capacity has been put forward. The recovery and reuse of space vehicles, especially launch vehicle, often means higher resource utilization and effective cost control, which has unprecedented advantages in business mode. Many countries and organizations have shown concern about the reusable vehicles. In order to facilitate the further research of reusable rocket technology, this article summaries the research and developments of reusable vehicles over the years and sorts out the overall scheme and key technologies of it. In particular, in view of the successful case of Falcon 9, this article analyses the commercialization experience of SpaceX reusable rockets and its business model. This article may offer a reference for the reusable rocket technology development.

show abstract

Section: Merlin-1 Series Enginesmentioning

confidence: 99%

“…Figure1. The 100th Merlin-1D engine[13]. In particular, the Falcon 9 launch vehicle stage I employs nine engine configurations evenly distributed in Octaweb, with multiple low-thrust engines in parallel.…”

mentioning

confidence: 99%

Analysis of the development of reusable launch vehicle technology

Wu,

Zhang

2023

ACE

View full text Add to dashboard Cite

show abstract

“…So, extracting useful fault features directly from raw data is a key advantage. Hence, deep belief network (DBN), convolutional neural network (CNN), and long short-term memory network (LSMN) are commonly implemented to diagnose faults related to mechanical applications [21,22]. The DBN was implemented by Xu et al [23] to diagnose the air path fault of turbofan engines with higher classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Combination of Optimized Variational Mode Decomposition and Deep Transfer Learning: A Better Fault Diagnosis Approach for Diesel Engines

et al. 2022

View full text Add to dashboard Cite

Extracting features manually and employing preeminent knowledge is overly utilized in methods to conduct fault diagnosis. A diagnosis approach utilizing intelligent methods of the optimized variational mode decomposition and deep transfer learning is proposed in this manuscript to deal with fault diagnosis. Firstly, the variational mode decomposition is optimized by K values of the dispersion entropy to realize an adaptive decomposition and reduce the noise of the signal. Secondly, an image with two dimensions is generated by a vibration signal with one dimension utilizing a short-time Fourier transform, after conducting noise reduction. Then, the ResNet18 network model is used to pre-train the model. Finally, the model transfer method is used to detect faults of a diesel engine. The results show that the proposed method outperforms the deep learning methods available in the literature. Besides, better noise reduction ability and higher diagnostic accuracy are attained.

show abstract

“…Xing et al (2010) used the calibration matrix to improve accuracy of static calibration in laboratory threedimensional force/moment measurement of hybrid rocket thrust force. Zhang et al (2018) proposed a novel force offset non-linear calibration method based on the Deep Belief Network and adopted the Levenberg Marquartdt method to train data sets, to decrease non-linear mapping convergence errors. However, most non-linear calibration methods do not consider the change of loading positions, which omit the impact of change of loading positions on measurement accuracy of test system.…”

Section: Introductionmentioning

confidence: 99%

Research on a non-linear calibration method for dynamometer

Chang

Zhang

Ren

2020

View full text Add to dashboard Cite

Purpose The purpose of this paper is to solve the problem that the relationship between loading forces, which were applied at different positions on a plane, and output values of load-sharing dynamometer is non-linear. Design/methodology/approach First, the analytical model of ISPM (isodynamic surface proportional mapping method) method, which is used to calibrate dynamometer, was established. Then, a series of axial force calibration tests were performed on a load-sharing dynamometer at different loading positions. Finally, according to output values, calibration forces at different loading positions were calculated by ISPM method, and corresponding distribution histogram of calibration force error was generated. Findings The largest error between calculated force and standard force is 2.92 per cent, and the probability of calculated force error within 1 per cent is 91.03 per cent, which verify that the ISPM method is reliable for non-linear calibration of dynamometers. Originality/value The proposed ISPM method can achieve non-linear calibration between measured force and output signal of load-sharing dynamometer at different positions. In addition, ISPM method can also solve some complex non-linear problems, such as prediction of plane cutting force under the influence of multiple parameters, the force measurement of multi-degree-of-freedom platform and so on.

show abstract

The calibration of force offset for rocket engine based on deep belief network

Cited by 4 publications

References 14 publications

Analysis of the development of reusable launch vehicle technology

Analysis of the development of reusable launch vehicle technology

Combination of Optimized Variational Mode Decomposition and Deep Transfer Learning: A Better Fault Diagnosis Approach for Diesel Engines

Research on a non-linear calibration method for dynamometer

Contact Info

Product

Resources

About