ZLZheng Lian

Zheng Lian

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zheng Lian has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Belief Rule-Based Fault Diagnosis Method Incorporating Two-Stage Feature Selection

    by Kun Wang, Zhijie Zhou, Tao Wang, Zhichao Ming, Zheng Lian, Kejun Wang

  • Open Access

    An Interpretable Belief Rule-Based Fault Diagnosis Method for Complex Equipment Considering Linguistic Fuzzy Information

    by Kun Wang, Tao Wang, Zhijie Zhou, Zhichao Ming, Zheng Lian, Kejun Wang

    To address the challenges of linguistic fuzziness, cognitive variability across fault modes, and the risk of model distortion during optimization, this paper proposes an interpretable belief rule-based fault diagnosis method for complex equipment considering linguistic fuzzy information. First, to address the difficulty experts face in providing precise probability values, an interval grey number table is constructed. By converting linguistic fuzzy information into interval grey representations, the approach quantifies the uncertainty inherent in expert judgments while fully preserving the boundary information of the underlying knowledge. Second, recognizing that expert familiarity varies across different fault modes, a certainty degree fusion method is introduced. This method utilizes fusion weights to mitigate the interference of low-confidence evidence during rule generation. Finally, an interpretable parameter optimization method featuring dynamic knowledge anchoring is designed to constrain model parameters within the reasonable bounds defined by expert knowledge. Validation on an electromechanical actuator demonstrates that the proposed method not only achieves superior diagnostic performance but also ensures model usability and interpretability in practical engineering applications.

  • An Evidential Reasoning Rule-Based Performance Evaluation Method for Complex Electronic System Under Off-Cycle Data

    by Yijie Sun, Zhijie Zhou, Zhichao Feng, Changhua Hu, 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.


  • A Linguistic Z-Number Rule-Based Modeling Framework Considering Knowledge Reliability Based on Evidential Reasoning Rule

    by Zheng Lian, Zhijie Zhou, Changhua Hu, Pengyun Ning, Zhichao Ming, Xiaoqin Liu

    Expert knowledge holds a pivotal role in artificial intelligence models. Constrained by the subjectivity and ignorance of human cognition, it is imperfectly reliable. Modeling and decision-making driven by such knowledge may generate large risks. To this end, it is necessary to investigate a mechanism for handling such imperfectly reliable knowledge. In this paper, the reliability of knowledge is described as expert reliability. A novel rule-based modeling framework with expert reliability is proposed correspondingly, including the following four parts: modeling, reasoning, optimization and robustness analysis. The main works are: (1) Based on the transparent knowledge representation of belief rule base (BRB), a linguistic Z-number BRB (LZ-BRB) is proposed, where the linguistic Z-number quantitatively represents expert reliability. (2) An improved evidential reasoning (ER) rule is developed to obtain the inference result of the LZ-BRB model. (3) A data-driven parameter optimization model is designed to reduce modeling errors caused by imperfectly reliable knowledge. (4) The robustness analysis of expert reliability is performed to further analyze its influence on the inference result. Finally, a fiber optic gyro (FOG) health evaluation case verifies the proposed method.


  • Large-Scale linguistic Z-Number Belief Rule Base Methodology for Multidimensional and Unreliable Knowledge Representation and Learning

    by Zheng Lian, Zhichao Feng, Zhijie Zhou, Changhua Hu, Shuaiwen Tang, Jie Wang

    With excellent interpretability, the fuzzy rule-based method stands as a formidable instrument for knowledge representation and learning. Nowadays, the knowledge representation problem with multidimensional input information is widespread, leading to a large rule base and making it difficult to embed expert knowledge. In addition, human knowledge is not entirely reliable, causing inaccurate reasoning results. In this article, a novel large-scale linguistic Z-number belief rule base (LSLZ-BRB) method is proposed for the above multidimensional and unreliable knowledge representation and learning. Specifically, a multidimensional knowledge mapping representation method under the probabilistic framework is proposed to generate an LSLZ-BRB. It allows experts to embed knowledge via conditional probability and prior probability. To reduce the modeling error caused by uncertainty of knowledge, an online interactive learning mechanism of uncertain knowledge is developed. This mechanism ensures that LSLZ-BRB has high real-time performance and improves the accuracy of knowledge representation. A performance evaluation case for the laser inertial measurement unit (LIMU) and experiments on some public datasets illustrate the implementation process of the proposed method and further verify its effectiveness.


  • Health Assessment of Complex Systems Based on the Evidential Reasoning Rule With Nonequidistant Data

    by Peng-Yun Ning, Zhi-Jie Zhou, Jie Wang, Zi-Wen Wang, Zheng Lian, 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.


  • Transparent Fault Diagnosis for Complex Equipment Considering Expert Reliability Based on Belief Rule Base and Linguistic Z-Number

    by Zheng Lian, Zhijie Zhou, Changhua Hu, You Cao, Shuaiwen Tang, 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.


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

    by Zheng Lian, Zhijie Zhou, Changhua Hu, Zhichao Ming, Jie Wang, Yu Zhao

    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.


  • Open Access

    Fault Diagnosis for Complex Equipment Based on Belief Rule Base with Adaptive Nonlinear Membership Function

    by Zheng Lian, Zhijie Zhou, Xin Zhang, Zhichao Feng, Xiaoxia Han, Changhua Hu

    Fault diagnosis of complex equipment has become a hot field in recent years. Due to excellent uncertainty processing capability and small sample problem modeling capability, belief rule base (BRB) has been widely used in the fault diagnosis. However, previous BRB models almost did not consider the diverse distributions of observation data which may reduce diagnostic accuracy. In this paper, a new fault diagnosis model based on BRB is proposed. Considering that the previous triangular membership function cannot address the diverse distribution of observation data, a new nonlinear membership function is proposed to transform the input information. Then, since the model parameters initially determined by experts are inaccurate, a new parameter optimization model with the parameters of the nonlinear membership function is proposed and driven by the gradient descent method to prevent the expert knowledge from being destroyed. A fault diagnosis case of laser gyro is used to verify the validity of the proposed model. In the case study, the diagnosis accuracy of the new BRB-based fault diagnosis model reached 95.56%, which shows better fault diagnosis performance than other methods.