Yijie Sun

Yijie Sun

Auto-generated profile, based on publicly available information

Yijie Sun

Rocket Force University of Engineering, Xian, Shaanxi, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2024 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
ZLZheng Lian
Zheng Lian
ZZZhijie Zhou
Zhijie Zhou
CHChanghua Hu
Changhua Hu
YCYou Cao
You Cao
STShuaiwen Tang
Shuaiwen Tang
YSYijie Sun
Yijie Sun
Fault diagnosis is crucial for mastering the operation status of complex equipment. However, due to the complexity of large-scale data-driven models, the process of fault diagnosis is difficult to comprehend and provide convincing results. In this paper, a transparent rule-based fault diagnosis method is proposed by introducing expert reliability, which covers three aspects: modeling, reasoning and optimization. Firstly, a transparent knowledge base is proposed using belief rule base and linguistic Z-number, namely LZ-BRB, in which the expert reliability is modeled. LZ-BRB characterizes the mapping relationship reflected by incompletely reliable knowledge between fault features and fault states. Secondly, a new evidential reasoning rule with the unreliable proposition (ER-UP) is developed to perform the reasoning of LZ-BRB and obtain the diagnosis result. The reliability of diagnosis results is acquired and measures the trustworthiness of the diagnosis result. Thirdly, to improve the diagnosis accuracy and maintain the transparent modeling process, expert reliability is considered in model optimization and a knowledge-data hybrid-driven gradient descent (KDGD) method is developed. Finally, a fault diagnosis case of the aerospace relay verifies the proposed method. The case results show that the diagnosis performance of the proposed method is competitive and maintains superb transparency. Note to Practitioners —Fault diagnosis holds paramount importance in the health management of industrial equipment. Nowadays, large-scale intelligent fault diagnosis methods have gained widespread application in the diagnosis of various mechanical and electronic equipment. Nevertheless, due to the complex structure and excessive parameters, it is hard for managers to make sense of the modeling, reasoning and optimization process of these models. Hence, there is an urgent need for a transparent fault diagnosis approach that can provide trustworthy diagnosis results. In this paper, based on BRB and linguistic Z-number, we present a transparent rule-based fault diagnosis method considering the knowledge reliability of human experts in engineering, including a transparent knowledge base, inference engine and model optimization. A fault diagnosis case of aerospace relay validates the effectiveness of the method and demonstrates the transparency of the fault diagnosis process. The proposed method can effectively model incompletely reliable expert knowledge and achieve transparent fault diagnosis, contributing to the health management of complex equipment.

18 December 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YSYijie Sun
Yijie Sun
ZZZhijie Zhou
Zhijie Zhou
ZFZhichao Feng
Zhichao Feng
CHChanghua Hu
Changhua Hu
XHXiaoxia Han
Xiaoxia Han
The determination of the optimal maintenance time can ensure the reliability of the system and reduce the maintenance cost. In this paper, to improve the performance of optimal maintenance timing (OMT) determination for complex electromechanical equipment (CEE), a new OMT model with quality factor is developed based on evidential reasoning, where the influence of historical maintenance and historical storage is addressed by introducing maintenance and storage impact factors into the fusion process of evidential reasoning (ER-MS). In ER-MS, maintenance and storage impact factors are accurately defined and then participate in the calculation of evidence reliability. The newly developed ER-MS method aims to handle three problems that exist in engineering practice for OMT determination method for CEE: difficulty in establishing an accurate mathematical model, the influence of historical maintenance and historical storage, and performance analysis of the established model. This paper also puts forward a quality factor definition method combines evidence weight and evidence reliability, where the quality factor turns out to be reasonable. Then, to quantitatively analyze the influence of historical maintenance and historical storage on the performance of CEE, sensitivity analysis of historical factors is carried out based on the transparency and traceability of the ER-MS method. The sensitivity factors obtained can provide an improvement basis for the use and storage of CEE. A case study for inertial navigation system (INS) is conducted to illustrated the effectiveness of the new OMT model.

22 December 2025 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
YSYijie Sun
Yijie Sun
ZFZhichao Feng
Zhichao Feng
ZZZhijie Zhou
Zhijie Zhou
Performance evaluation is one of the most important methods to guarantee the safe and reliable operation of complex systems. Currently, there are three main problems in the performance evaluation of complex systems: the evaluation model is difficult to establish; the correlation between indicators is difficult to measure; and expert knowledge is not effectively incorporated. To solve these problems, this article proposes a performance evaluation model considering indicator correlation on the basis of considering the cohesion ratio factor evidence reasoning rule (ERr-CRC). In the process of calculating indicator correlations, expert knowledge is first used to determine whether there is a correlation between two indicators, and then an outcome-oriented correlation calculation method is proposed, which transforms the problem of calculating the correlation between indicators into the problem of calculating the correlation between the confidence distributions of each outcome level. On this basis, the order of evidence fusion is determined according to the size of the correlation factor, and it is integrated into the process of assigning the basic probability quality of evidence in the form of a global discount factor for the final performance evaluation. To prove the effectiveness of the correlation factor, this article carries out a sensitivity analysis and a perturbation analysis. Finally, a case study of the ERr-CRC model is conducted using the rocket structure state-aware simulation platform.

31 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
PNPeng-Yun Ning
Peng-Yun Ning
ZZZhijie Zhou
Zhijie Zhou
JWJie Wang
Jie Wang
ZWZi-Wen Wang
Zi-Wen Wang
ZLZheng Lian
Zheng Lian
YSYi-Jie Sun
Yi-Jie Sun
Health assessment of complex systems is critical for Prognostics and Health Management (PHM), enhancing operational reliability and preventing catastrophic failures. However, in engineering systems, different testing intervals for subsystems complicate the evaluation of the system’s overall health state. Excluding data points with brief testing intervals could lead to a significant loss of critical information and compromise the accuracy of the health assessment. Towards this end, we develop a novel information fusion mechanism for non-equidistant data, introducing a federal evidential reasoning (FER) rule-based health assessment method. Firstly, we divide non-equidistant indicators into corresponding subsystems and define the calculation period and fusion period. On this basis, a corresponding non-equidistant information processing method is proposed. Secondly, to reduce the effect of non-equidistant data on the assessment results, the non-equidistant information discount coefficient is introduced to quantify the impact on indicator weight and reliability. Moreover, based on the calculation period and fusion period, the predicted health state and original health state can be obtained by the ER rule-based information fusion mechanism, respectively. Finally, a health assessment experiment of the Laser Inertial Measurement Unit (LIMU) is conducted. Comparative experiments demonstrate that the proposed FER rule-based model significantly outperforms the traditional ER rule-based model and other similar health assessment methods.

28 October 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YSYijie Sun
Yijie Sun
ZFZhichao Feng
Zhichao Feng
ZZZhijie Zhou
Zhijie Zhou
CHChanghua Hu
Changhua Hu
RYRuohan Yang
Ruohan Yang
Identifying the optimal maintenance timing (OMT) of complex industrial equipment (CIE) is a highly effective way to maintain its stable operation and reduce unreasonable maintenance costs. Currently, determination of OMT for CIE involves the following two main issues: an accurate mathematical model is hard to establish and difficulty in guaranteeing the validity of OMT determination. Hence, in this article, a new OMT model considering cohesion factor has been developed based on the evidential reasoning rule (ER-rule), where dynamic boundaries are set for model parameters to determine the optimal solution more accurate and faster in the optimization process (CERr-DB). In CERr-DB, cohesion factor is introduced to represent the fusion of weight and reliability of evidence in the original ER-rule method to make it more interpretable. What is more, CERr-DB adopts a new output feedback mechanism to provide a dynamic boundary solution space for the optimization process of parameters, which effectively improves the search accuracy and rate. In an effort to quantitatively assess the effect of cohesion factors and dynamic boundaries on the properties of CIE, a sensitivity analysis based on the transparency and traceability of the CERr-DB methodology has been performed. A case study of the electric servo mechanism is carried out to validate the effectiveness of the new OMT model.

13 November 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YSYijie Sun
Yijie Sun
ZZZhijie Zhou
Zhijie Zhou
ZFZhichao Feng
Zhichao Feng
CHChanghua Hu
Changhua Hu
ZLZheng Lian
Zheng Lian
Performance evaluation of complex electronic system (CES) is one of the core support means to ensure its safe and stable operation. Currently, the performance evaluation of CES mainly faces the following three problems: firstly, it is difficult to establish an accurate mathematical model for performance evaluation; secondly, historical data with off-cycle characteristics are not taken into account during the performance evaluation process; thirdly, present methodologies lack a performance analysis of evaluation model for off-cycle data. Therefore, this paper constructs a CES performance evaluation model considering off-cycle historical data by utilizing the evidential reasoning rule (ERr-OC). In ERr-OC, the off-cycle historical data are fused with current moment data by a bidirectional weighting method to generate the input data. What's more, a method for determining the weight of evidence from bidirectional weights has been proposed. To ensure the traceability of the evidence fusion process, sensitivity analysis of performance evaluation model has been conducted to demonstrate its validity. In the end, the inertial navigation system (INS) is applied as the experiment object to illustrate the effectiveness of the developed ERr-OC method.