A Belief Rule-Based Performance Evaluation Model for Complex Systems Considering Sensors Disturbance

被引：10

作者：

Lian, Zheng ^{[1
]}

Zhou, Zhijie ^{[1
]}

Hu, Changhua ^{[1
]}

Ming, Zhichao ^{[1
]}

Wang, Jie ^{[1
]}

Zhao, Yu ^{[1
]}

机构：

[1] High Tech Inst Xian, Xian 710025, Peoples R China

来源：

IEEE TRANSACTIONS ON RELIABILITY | 2024年 / 73卷 / 02期

关键词：

Belief rule base; Newton-downhill method; performance evaluation; sensitivity analysis; sensor disturbance; EVIDENTIAL REASONING APPROACH; RISK-ASSESSMENT; CLASSIFIER; INFERENCE; NETWORK;

D O I：

10.1109/TR.2023.3311436

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Sensor disturbance has a significant impact on the performance state of complex systems in engineering. In this article, a new performance evaluation model for complex systems considering sensor disturbance is proposed. First, belief rule base (BRB) is used as a white-box model to establish a transparent performance evaluation model. To evaluate the influence of disturbance on the performance state, the sensor disturbance is described as an interval and added in the model input. The fluctuation range of the disturbed performance state is calculated. Then, to assist diminish the damage of disturbance on the performance state, the robustness of the sensor is analyzed for two types of tasks with different robustness requirements. In general tasks, the antidisturbance ability of sensors is analyzed based on the sensitivity analysis method. In specific tasks with strong robustness requirements, the disturbance tolerance interval (DTI) of the sensor to tolerate disturbances is calculated by the Newton-downhill method. A gyroscope performance evaluation case is used to verify the effectiveness of the proposed model.

引用

页码：1245 / 1257

页数：13

共 44 条

[1] Transparent Digital Twin for Output Control Using Belief Rule Base [J].