Comparative Analysis of Real-Time Fault Detection Methods Based on Certain Artificial Intelligent Algorithms for a Hydrogen–Oxygen Rocket Engine

Abstract

The real-time fault detection and diagnosis algorithm of a liquid rocket engine is the basis of online reconfiguration of guidance and the control system of a launch vehicle, which is directly related to the success or failure of space mission. Based on previous related works, this paper carries out comparative experimental studies of relevant intelligent algorithm models for real-time fault detection engineering application requirements of a liquid hydrogen–oxygen rocket engine. Firstly, the working state and detection parameters’ selection of a hydrogen–oxygen engine are analyzed, and the proposed three real-time intelligent fault detection algorithm model design methods are elaborated again. Fault detection calculation and analysis are carried out through normal test data and fault test data. The comparative analysis results of real-time intelligent fault detection algorithm models is presented from three dimensions: detection time, fault detection, and stability and consistency. Finally, based on a correlation analysis, a comprehensive intelligent fault diagnosis model design framework is given to further solve the requirements of real-time fault detection and diagnosis engineering development of a liquid rocket engine, a complex piece of equipment.

A new complex system fault detection method based on belief rule base for unreliable interval values

“…Suppose the input information of indicator 1 is four and the indicator interval it belongs to is [3,6], then according to the rules corresponding to the values 3 and 6 of the upper and lower bounds, the ER analysis algorithm is used to fuse them, and a new rule is generated using the fusion result. Meanwhile, if the input information of indicator 2 is five and the indicator interval it belongs to is [4,6]; then according to the rules corresponding to 4 and 6, the fusion is performed, and a new rule is also generated; then the ER rule algorithm is used to fuse these new rules, and the final utility result of the model is derived. The ER rule algorithm is then used to fuse these new rules to produce the final utility result of the model.…”

“…Fault detection is an important part of keeping complex systems such as milling machines and inertial navigation systems (INSs) working properly. In the event of a failure of such a complex system, it may cause major property losses and 4 Contributed equally to this work. * Author to whom any correspondence should be addressed.…”

“…Methods based on artificial intelligence, such as one mentioned in the article [3] by Hussain et al The main contribution of this work is to present a novel algorithm that can carry out fault detection in a photovoltaic system, to a high degree of accuracy, requiring only two inputs. Huang et al [4] proposed a comprehensive intelligent fault diagnosis model design framework to further address the requirements of real-time fault detection and diagnosis for liquid rocket engines, which is a complex system. Methods based on the analytical model, such as Jiao et al [5] proposed a novel approach for quality-related fault detection in industrial processes using dynamic least squares.…”