Jingjing Cui
Jingjing Cui has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Yi Ren
School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China
3 shared publications - Binghui Xu
School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China
2 shared publications - Shengkui Zeng
School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China
2 shared publications - Bo Hu
Department of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, Hubei 430060, P.R. China
1 shared publication Cuiying Lin
College of Civil Aviation, Civil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication- Dezhen Yang
School of Reliability and Systems Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (10) , 6652-6662
An Intelligent Fault Diagnostic Method Based on 2D-gcForest and L${}_{\text{2,p}}$-PCA Under Different Data Distributions
Intelligent diagnosis based on deep learning can reveal the health status of running equipment and is attracting attention for an increasing number of industrial systems. However, two challenges, namely, the construction of deep models and the accommodation of different data distributions, restrict the effective application of such methods. To bridge these gaps, this article proposes an intelligent diagnostic method based on 2-D-gcForest and l 2,p -PCA. First, a 2-D sampling strategy is employed before a gcForest model to transform the raw 1-D sequence data into 2-D stacked data, thus reducing the amount of redundant information and the computational burden. Then, gcForest is used as a basic diagnostic model, which learns data features with simple hyperparameter settings by automatically extending layers. Simultaneously, l 2,p -PCA is incorporated to optimize the transformed features, improving the feature representation for different data sources. Finally, comparative experiments are reported to validate the effectiveness and superiority of the proposed method.
- 19 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (10) , 6652-6662
An Intelligent Fault Diagnostic Method Based on 2D-gcForest and L${}_{\text{2,p}}$-PCA Under Different Data Distributions
Intelligent diagnosis based on deep learning can reveal the health status of running equipment and is attracting attention for an increasing number of industrial systems. However, two challenges, namely, the construction of deep models and the accommodation of different data distributions, restrict the effective application of such methods. To bridge these gaps, this article proposes an intelligent diagnostic method based on 2-D-gcForest and l 2,p -PCA. First, a 2-D sampling strategy is employed before a gcForest model to transform the raw 1-D sequence data into 2-D stacked data, thus reducing the amount of redundant information and the computational burden. Then, gcForest is used as a basic diagnostic model, which learns data features with simple hyperparameter settings by automatically extending layers. Simultaneously, l 2,p -PCA is incorporated to optimize the transformed features, improving the feature representation for different data sources. Finally, comparative experiments are reported to validate the effectiveness and superiority of the proposed method.
- 31 March 2020
- Published by Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne in Eksploatacja i Niezawodność – Maintenance and Reliability
- Vol. 22 (1) , 42-51
Reliability analysis of a multi-eso based control strategy for level adjustment control system of quadruped robot under disturbances and failures
The complexity of control algorithms and their vulnerability to disturbances and failures are the main problems that restrict the operations of multi-legged mobile robots in more complex environments. In this paper, a multiple extended state observer (ESO) based control strategy is proposed to achieve stable tilt angle control for quadruped robots under the influence of disturbances and actuator failures. By treating the multiple legs as parallel control objects, more ESOs were added to improve the disturbance rejection ability of the linear active disturbance rejection control (LADRC). Correlation of interactive information about the legs is realized by the synthesis of multiple ESO information. Based on LADRC, this method has the advantages of easy parameter tuning, good robustness, and strong ability to cope with interference and fault conditions. A control system reliability evaluation method was proposed. The reliability and control performance of the multi-ESO based control system under leg stuck failure conditions were systematically analyzed. Simulation and experimental results for the level adjustment control system of a quadruped robot are provided to verify the disturbance rejection ability, feasibility and practicability of the proposed multi-ESO based control method
- 31 March 2020
- Published by Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne in Eksploatacja i Niezawodność – Maintenance and Reliability
- Vol. 22 (1) , 42-51
Reliability analysis of a multi-eso based control strategy for level adjustment control system of quadruped robot under disturbances and failures
The complexity of control algorithms and their vulnerability to disturbances and failures are the main problems that restrict the operations of multi-legged mobile robots in more complex environments. In this paper, a multiple extended state observer (ESO) based control strategy is proposed to achieve stable tilt angle control for quadruped robots under the influence of disturbances and actuator failures. By treating the multiple legs as parallel control objects, more ESOs were added to improve the disturbance rejection ability of the linear active disturbance rejection control (LADRC). Correlation of interactive information about the legs is realized by the synthesis of multiple ESO information. Based on LADRC, this method has the advantages of easy parameter tuning, good robustness, and strong ability to cope with interference and fault conditions. A control system reliability evaluation method was proposed. The reliability and control performance of the multi-ESO based control system under leg stuck failure conditions were systematically analyzed. Simulation and experimental results for the level adjustment control system of a quadruped robot are provided to verify the disturbance rejection ability, feasibility and practicability of the proposed multi-ESO based control method
- 13 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 24 (6) , 2616-2626
Mobile Robot ADRC With an Automatic Parameter Tuning Mechanism via Modified Pigeon-Inspired Optimization
This paper proposes an enhanced active disturbance rejection control (ADRC) method for the attitude deformation system of a self-developed mobile robot in conjunction with evolutionary game theory-based pigeon-inspired optimization (EGPIO). To achieve precise control of the object, EGPIO is employed as an automatic tuning mechanism for ADRC, and simultaneously improves the rapidity and robustness of the controller. In this novel algorithm, individuals in pigeon-inspired optimization (PIO) adjust their strategies dynamically as the evolutionary game proceeds so as to promote the adaptability of the original PIO. Thus, the optimal solutions calculated by EGPIO will be adopted as the main parameters of ADRC to control the mobile robot. The effectiveness of the novel controller is validated by a series of simulations, including cases with normal conditions and situations with disturbances. Experimental results indicate that the scheme we designed possesses better control performances and shows attractive advantages for efficiency and fault tolerance compared with conventional ADRC.
- 13 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 24 (6) , 2616-2626
Mobile Robot ADRC With an Automatic Parameter Tuning Mechanism via Modified Pigeon-Inspired Optimization
This paper proposes an enhanced active disturbance rejection control (ADRC) method for the attitude deformation system of a self-developed mobile robot in conjunction with evolutionary game theory-based pigeon-inspired optimization (EGPIO). To achieve precise control of the object, EGPIO is employed as an automatic tuning mechanism for ADRC, and simultaneously improves the rapidity and robustness of the controller. In this novel algorithm, individuals in pigeon-inspired optimization (PIO) adjust their strategies dynamically as the evolutionary game proceeds so as to promote the adaptability of the original PIO. Thus, the optimal solutions calculated by EGPIO will be adopted as the main parameters of ADRC to control the mobile robot. The effectiveness of the novel controller is validated by a series of simulations, including cases with normal conditions and situations with disturbances. Experimental results indicate that the scheme we designed possesses better control performances and shows attractive advantages for efficiency and fault tolerance compared with conventional ADRC.
- Open Access
- 14 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 29747-29756
On the Robustness and Reliability in the Pose Deformation System of Mobile Robots
A major vulnerability of mobile robots operating in more environments is their fragility in facing disturbances. A two-fold solution is proposed in this paper. First, a deformable structure was designed to reduce turbulence and to adapt to the uneven ground. Secondly, a novel control strategy is employed to avoid the limitations of the existing methods. In particular, among the existing solutions, the PID controller is known to be severely limited in handling disturbances and failures and the model-based designs all require detailed mathematical model, which may not be readily available, especially in the case of failures. To address these issues, a solution based on Active Disturbance Rejection Control (ADRC) is proposed in this paper, for its simplicity in design and tuning, and its robustness against parameter variations and even failures in the pose deformation system. The proposed solution is systematically validated in simulation and the results are promising. The performance of the system was maintained in the presence of disturbances and uncertain dynamics and the reliability of the robot is considerably improved when the unknown leg failures occurred.
- 14 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 29747-29756
Open AccessOn the Robustness and Reliability in the Pose Deformation System of Mobile Robots
A major vulnerability of mobile robots operating in more environments is their fragility in facing disturbances. A two-fold solution is proposed in this paper. First, a deformable structure was designed to reduce turbulence and to adapt to the uneven ground. Secondly, a novel control strategy is employed to avoid the limitations of the existing methods. In particular, among the existing solutions, the PID controller is known to be severely limited in handling disturbances and failures and the model-based designs all require detailed mathematical model, which may not be readily available, especially in the case of failures. To address these issues, a solution based on Active Disturbance Rejection Control (ADRC) is proposed in this paper, for its simplicity in design and tuning, and its robustness against parameter variations and even failures in the pose deformation system. The proposed solution is systematically validated in simulation and the results are promising. The performance of the system was maintained in the presence of disturbances and uncertain dynamics and the reliability of the robot is considerably improved when the unknown leg failures occurred.
- Open Access
- 12 November 2017
- Published by Wiley in BioMed Research International
- Vol. 2017, 1-10
Enhancement of Angiogenesis by Ultrasound-Targeted Microbubble Destruction Combined with Nuclear Localization Signaling Peptides in Canine Myocardial Infarction
Objective. This study aimed to develop a gene delivery system using ultrasound-targeted microbubbles destruction (UTMD) combined with nuclear localization signal (NLS) and investigate its efficacy and safety for therapeutic angiogenesis in canine myocardial infarction (MI) model. Methods. Fifty MI dogs were randomly divided into 5 groups and transfected with Ang-1 gene plasmid: (i) group A: only injection of microbubbles and Ang-1 plasmid; (ii) group B: only UTMD mediated gene transfection; (iii) group C: UTMD combined with classical NLS mediated gene transfection; (iv) group D: UTMD combined with mutational NLS mediated transfection; and (v) group E: UTMD combined with classical NLS in the presence of a nucleus transport blocker. The mRNA and protein expression of Ang-1 gene, microvessel density (MVD) cardiac troponin I (cTnI), and cardiac function were determined after transfection. Results. The expression of mRNA and protein of Ang-1 gene in group C was significantly higher than that of the other groups (all P < 0.01). The MVD of group C was 10.2-fold of group A and 8.1-fold of group E (P < 0.01). The cardiac function in group C was significant improvement without cTnI rising. Conclusions. The gene delivery system composed of UTMD and NLS is efficient and safe.
- 12 November 2017
- Published by Wiley in BioMed Research International
- Vol. 2017, 1-10
Open AccessEnhancement of Angiogenesis by Ultrasound-Targeted Microbubble Destruction Combined with Nuclear Localization Signaling Peptides in Canine Myocardial Infarction
Objective. This study aimed to develop a gene delivery system using ultrasound-targeted microbubbles destruction (UTMD) combined with nuclear localization signal (NLS) and investigate its efficacy and safety for therapeutic angiogenesis in canine myocardial infarction (MI) model. Methods. Fifty MI dogs were randomly divided into 5 groups and transfected with Ang-1 gene plasmid: (i) group A: only injection of microbubbles and Ang-1 plasmid; (ii) group B: only UTMD mediated gene transfection; (iii) group C: UTMD combined with classical NLS mediated gene transfection; (iv) group D: UTMD combined with mutational NLS mediated transfection; and (v) group E: UTMD combined with classical NLS in the presence of a nucleus transport blocker. The mRNA and protein expression of Ang-1 gene, microvessel density (MVD) cardiac troponin I (cTnI), and cardiac function were determined after transfection. Results. The expression of mRNA and protein of Ang-1 gene in group C was significantly higher than that of the other groups (all P < 0.01). The MVD of group C was 10.2-fold of group A and 8.1-fold of group E (P < 0.01). The cardiac function in group C was significant improvement without cTnI rising. Conclusions. The gene delivery system composed of UTMD and NLS is efficient and safe.