Electro-Hydraulic Servomechanism (EHS) serves as critical actuators in aerospace equipment, and maintaining its health status is vital for ensuring the safe and stable operation of aerospace systems. However, existing health assessment models face two major challenges: first, the vast amount of historical text data generated during EHS operation is difficult to utilize effectively; second, there is a lack of efficient methods for integrating historical text data with test data. To address these issues, a health status assessment model is proposed based on natural language processing evidence inference rules. First, a historical text information extraction strategy is designed based on Bidirectional Encoder Representations from Transformers (BERT). Subsequently, by analyzing the operational mechanisms of EHS, a health assessment indicator system is constructed, and methods for calculating maintenance levels and operational time influence factors are proposed. On this basis, an Evidential Reasoning rule with Multisource Information Fusion health status assessment model (ER-MIF) is developed. To mitigate the impact of expert knowledge uncertainty, a health assessment model parameter optimization model is established to determine optimal parameters and enhance assessment accuracy. Finally, the effectiveness of the proposed model was validated through an evaluation case study and comparative analysis of a specific electro-hydraulic servo mechanism.
- Article type
- Year
Open Access
Full Length Article
Issue
It is vital to establish an interpretable fault diagnosis model for critical equipment. Belief Rule Base (BRB) is an interpretable expert system gradually applied in fault diagnosis. However, the expert knowledge cannot be utilized to establish the initial BRB accurately if there are multiple referential grades in different fault features. In addition, the interpretability of BRB-based fault diagnosis is destroyed in the optimization process, which reflects in two aspects: deviation from the initial expert judgment and over-optimization of parameters. To solve these problems, a new interpretable fault diagnosis model based on BRB and probability table, called the BRB-P, is proposed in this paper. Compared with the traditional BRB, the BRB-P constructed by the probability table is more accurate. Then, the interpretability constraints, i.e., the credibility of expert knowledge, the penalty factor and the rule-activation factor, are inserted into the projection covariance matrix adaption evolution strategy to maintain the interpretability of BRB-P. A case study of the aerospace relay is conducted to verify the effectiveness of the proposed method.
京公网安备11010802044758号