Application of Analytic Redundancy-based Fault Diagnosis of Sensors to Onboard Maintenance System

Analytic redundancy-based fault diagnosis technique （ARFDT） is applied to onboard maintenance system （OMS）. The principle of the proposed ARFDT scheme is to design a redundancy configuration using ARFDT to enhance the functions of redundancy management and built in test equipment （BITE） monitor. Redundancy configuration for dual-redundancy and analytic redundancy is proposed, in which, the fault diagnosis includes detection and isolation. In order to keep the balance between rapid diagnosis and binary hypothesis, a filter together with an elapsed time limit is designed for sequential probability ratio test （SPRT） in the process of isolation. Diagnosis results would be submitted to central maintenance computer （CMC） together with BITE information. Moreover, by adopting reconstruction, the designed method not only provides analytic redundancy to help redundancy management, but also compensates the output when both of the sensors of the same type are faulty. Our scheme is applied to an aircraft’s sensors in a simulation experiment, and the results show that the proposed filter SPRT （FSPRT） saves at least 50% of isolation time than Wald SPRT （WSPRT）. Also, effectiveness, practicability and rapidity of the proposed scheme can be successfully achieved in OMS.

ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NETWORKS

This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.

Analytical redundancy of variable cycle engine based on variable-weights neural network

In this paper, variable-weights neural network is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental variables are changing simultaneously, also accompanied with the whole engine’s degradation. In another word,variable-weights neural network is proposed to solve a multi-variable, strongly nonlinear, dynamic and time-varying problem. By making weights a function of input, variable-weights neural network’s nonlinear expressive capability is increased dramatically at the same time of decreasing the number of parameters. Results demonstrate that although variable-weights neural network and other algorithms excel in different analytical redundancy tasks, due to the fact that variableweights neural network’s calculation time is less than one fifth of other algorithms, the calculation efficiency of variable-weights neural network is five times more than other algorithms. Variableweights neural network not only provides critical variable-weights thought that could be applied in almost all machine learning methods, but also blazes a new way to apply deep learning methods to aeroengines.

硬支持向量回归机的快速在线近似解法及其在航空发动机解析余度中的应用(英文)

The hard support vector regression attracts little attention owing to the overfitting phenomenon. Recently, a fast offiine method has been proposed to approximately train the hard support vector regression with the generation performance comparable to the soft support vector regression. Based on this achievement, this article advances a fast online approximation called the hard sup- port vector regression （FOAHSVR for short）. By adopting the greedy stagewise and iterative strategies, it is capable of online estimating parameters of complicated systems. In order to verify the effectiveness of the FOAHSVR, an FOAHSVR-based analytical redundancy for aeroengines is developed. Experiments on the sensor failure and drift evidence the viability and feasibility of the analytical redundancy for aeroengines together with its base--FOAHSVR. In addition, the FOAHSVR is anticipated to find applications in other scientific-technical fields.