Sparse Filtering Under Non-Random Bounded Exogenous Disturbances

2021 ◽  
Author(s):  
Mikhail Khlebnikov
Keyword(s):  
Sparse Filtering ◽  
Exogenous Disturbances

Construction of a deep sparse filtering network for rotating machinery fault diagnosis

2021 ◽  
pp. 095440702110148
Author(s):  
Chun Cheng ◽  
Wei Zou ◽  
Weiping Wang ◽  
Michael Pecht
Keyword(s):  
Fault Diagnosis ◽  
Back Propagation ◽  
Feature Learning ◽  
Back Propagation Neural Network ◽  
Rotating Machinery ◽  
Fine Tuning ◽  
Local Optimum ◽  
Back Propagation Algorithm ◽  
Intelligent Fault Diagnosis ◽  
Sparse Filtering

Deep neural networks (DNNs) have shown potential in intelligent fault diagnosis of rotating machinery. However, traditional DNNs such as the back-propagation neural network are highly sensitive to the initial weights and easily fall into the local optimum, which restricts the feature learning capability and diagnostic performance. To overcome the above problems, a deep sparse filtering network (DSFN) constructed by stacked sparse filtering is developed in this paper and applied to fault diagnosis. The developed DSFN is pre-trained by sparse filtering in an unsupervised way. The back-propagation algorithm is employed to optimize the DSFN after pre-training. Then, the DSFN-based intelligent fault diagnosis method is validated using two experiments. The results show that pre-training with sparse filtering and fine-tuning can help the DSFN search for the optimal network parameters, and the DSFN can learn discriminative features adaptively from rotating machinery datasets. Compared with classical methods, the developed diagnostic method can diagnose rotating machinery faults with higher accuracy using fewer training samples.

Output tracking and feedback stabilization for 6-DoF UAV using an enhanced active disturbance rejection control

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Aws Abdulsalam Najm ◽  
Ibraheem Kasim Ibraheem ◽  
Amjad J. Humaidi ◽  
Ahmad Taher Azar
Keyword(s):  
Disturbance Rejection ◽  
Feedback Stabilization ◽  
Active Disturbance Rejection Control ◽  
Parameter Uncertainties ◽  
Content Type ◽  
Active Disturbance Rejection ◽  
Disturbance Rejection Control ◽  
Exogenous Disturbances ◽  
System Uncertainties ◽  
Quadrotor System

PurposeThe hybrid control system of the nonlinear PID (NLPID) controller and improved active disturbance rejection control (IADRC) are proposed for stabilization purposes for a 6-degree freedom (DoF) quadrotor system with the existence of exogenous disturbances and system uncertainties.Design/methodology/approachIADRC units are designed for the altitude and attitude systems, while NLPID controllers are designed for the x−y position system on the quadrotor nonlinear model. The proposed controlling scheme is implemented using MATLAB/Simulink environment and is compared with the traditional PID controller and NLPID controller.FindingsDifferent tests have been done, such as step reference tracking, hovering mode, trajectory tracking, exogenous disturbances and system uncertainties. The simulation results showed the demonstrated performance and stability gained by using the proposed scheme as compared with the other two controllers, even when the system was exposed to different disturbances and uncertainties.Originality/valueThe study proposes an NLPID-IADRC scheme to stabilize the motion of the quadrotor system while tracking a specified trajectory in the presence of exogenous disturbances and parameter uncertainties. The proposed multi-objective Output Performance Index (OPI) was used to obtain the optimum integrated time of the absolute error for each subsystem, UAV quadrotor system energy consumption and for minimizing the chattering phenomenon by adding the integrated time absolute of the control signals.

Reset and prescribed performance approach to spacecraft attitude regulation

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Chengxi Zhang ◽  
Peng Dong ◽  
Henry Leung ◽  
Jin Wu ◽  
Kai Shen
Keyword(s):  
Attitude Control ◽  
Control Policy ◽  
Parameter Tuning ◽  
High Gain ◽  
Performance Tuning ◽  
Spacecraft Attitude ◽  
Spacecraft Attitude Control ◽  
Content Type ◽  
Exogenous Disturbances ◽  
Reset Control

Purpose This paper aims to investigate the attitude regulation for spacecraft in the presence of time-varying inertia uncertainty and exogenous disturbances. Design/methodology/approach The high gain approaches are typically used in existing researches for theoretical advantages, bringing better performance but sensitive to parameter selection, making the controller conservative. A reset-control policy is presented to achieve the spacecraft attitude control with easy control parameter tuning. Findings The reset-control policy guarantees satisfying control performance despite using performance tuning function and saturation function besides reducing the conservativeness of the controller, thus reducing the effort in tuning control parameters. Originality/value Notably, the adaptive function owns a reset mechanism, which is reset to a preset condition when the controlled variable crosses zero. The mathematical analysis also shows the system trajectory can converge to a set centered at the origin.

Disentangling the impacts of exogenous disturbances on forest stands to assess multi-centennial tree-ring reconstructions of avalanche activity in the upper Goms Valley (Canton of Valais, Switzerland)

2017 ◽  
Vol 42 ◽  
pp. 89-104 ◽  
Author(s):  
Adrien Favillier ◽  
Sébastien Guillet ◽  
Pauline Morel ◽  
Christophe Corona ◽  
Jérôme Lopez Saez ◽  
...  
Keyword(s):  
Tree Ring ◽  
Forest Stands ◽  
Exogenous Disturbances
Sign in / Sign up

Export Citation Format

Share Document