Enhanced network learning model with intelligent operator for the motion reliability evaluation of flexible mechanism

Abstract The evaluation of flexible mechanism involving multi-body dynamics with high nonlinearity and transients urgently requires an efficient evaluation method to enhance its reliability and safety. In this work, an enhanced network learning method (ENLM) is proposed to improve the modeling precision and simulation efficiency in flexible mechanism reliability evaluation, by introducing generalized regression neural network (GRNN) and multi-population genetic algorithm (MPGA) into extremum response surface method (ERSM). In the ENLM modeling, the ERSM is adopted to reasonably handle transients (time-varying) problem in motion reliability analysis by considering one extreme value in whole response process; the GRNN is applied to address high-nonlinearity in surrogate modeling; the MPGA is utilized to find the optimal model parameters in ENLM modeling. In respect of the developed ENLM, the motion reliability of two-link flexible robot manipulator (TFRM) was evaluated, with regard to the related input random parameters to material density, elastic modulus, section sizes, and deformations of components. In term of this study, it is illustrated that (i) the comprehensive reliability of flexible robot manipulator is 0.951 when the allowable deformation is 1.8×10−2 m; (ii) the maximum deformations of member-1 and member-2 obey normal distributions with the means of 1.45×10−2 m and 1.69×10−2 m as well as the standard variances of 6.77×10−4 m and 4.08×10−4 m, respectively. The comparison of methods demonstrates that the ENLM improves the modeling precision by 3.29% and reduces the simulation efficiency by 1.19 s under 10 000 simulations, and the strengths of the ENLM with high modeling precision and high simulation efficiency become more obvious with the increase of simulations. The efforts of this study provide a learning-based reliability analysis way (i.e., ENLM) for the motion reliability design optimization of flexible mechanism and enrich mechanical reliability theory.

[1]  Guang-Chen Bai,et al.  Dynamic surrogate modeling approach for probabilistic creep-fatigue life evaluation of turbine disks , 2019 .

[2]  Tatyana V. Zavrazhina.  Dynamics of Robot Manipulator with Elastically Flexible Links and Drive Mechanisms , 2005 .

[3]  Anthony Green,et al.  Dynamics and Trajectory Tracking Control of a Two-Link Robot Manipulator , 2004 .

[4]  Cheng-Wei Fei,et al.  Whole-process design and experimental validation of landing gear lower drag stay with global/local linked driven optimization strategy , 2020 .

[5]  J. Knani.  Dynamic modelling of flexible robotic mechanisms and adaptive robust control of trajectory computer simulation––Part I , 2002 .

[6]  Ying Xiong,et al.  A double weighted stochastic response surface method for reliability analysis , 2012 .

[7]  Cheng-Wei Fei,et al.  Decomposed-Coordinated Framework With Enhanced Extremum Kriging for Multicomponent Dynamic Probabilistic Failure Analyses , 2019, IEEE Access.

[8]  S. Kemal Ider,et al.  Trajectory tracking control of robots with flexible links , 2002 .

[9]  Cheng-Wei Fei,et al.  Moving extremum surrogate modeling strategy for dynamic reliability estimation of turbine blisk with multi-physics fields , 2020 .

[10]  Kwok-Wing Chau,et al.  A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources , 2019, IEEE Access.

[11]  Xu Han,et al.  A response-surface-based structural reliability analysis method by using non-probability convex model , 2014 .

[12]  Umile Gianfranco Spizzirri,et al.  Combining Carbon Nanotubes and Chitosan for the Vectorization of Methotrexate to Lung Cancer Cells , 2019, Materials.

[13]  Yanbin Han,et al.  Dynamic Reliability Analysis of Flexible Mechanism Based on Support Vector Machine , 2014 .

[14]  Jinkun Liu,et al.  Adaptive neural network vibration control of a flexible aircraft wing system with input signal quantization , 2020 .

[15]  Lu-Kai Song,et al.  Dynamic neural network method-based improved PSO and BR algorithms for transient probabilistic analysis of flexible mechanism , 2017, Adv. Eng. Informatics.

[16]  Liang Gao,et al.  Real-time estimation error-guided active learning Kriging method for time-dependent reliability analysis , 2020 .

[17]  Cheng Lu,et al.  Improved Kriging with extremum response surface method for structural dynamic reliability and sensitivity analyses , 2018 .

[18]  Rui Calçada,et al.  Computational framework for multiaxial fatigue life prediction of compressor discs considering notch effects , 2018, Engineering Fracture Mechanics.

[19]  Xiangyang Wang,et al.  Aerodynamic shape optimization using a novel optimizer based on machine learning techniques , 2019, Aerospace Science and Technology.

[20]  Cheng-Wei Fei,et al.  Fuzzy Multi-SVR Learning Model for Reliability-Based Design Optimization of Turbine Blades , 2019, Materials.

[21]  Huan Li,et al.  Multilevel nested reliability-based design optimization with hybrid intelligent regression for operating assembly relationship , 2020 .

[22]  Melin Şahin,et al.  Enhancement of quality of modal test results of an unmanned aerial vehicle wing by implementing a multi-objective genetic algorithm optimization , 2017 .

[23]  A. R. Firoozjaee,et al.  Numerical solution of bed load transport equations using discrete least squares meshless (DLSM) method , 2020 .

[24]  李洪双,et al.  SUPPORT VECTOR MACHINE FOR STRUCTURAL RELIABILITY ANALYSIS , 2006 .

[25]  John W. Fowler,et al.  A multi-population genetic algorithm to solve multi-objective scheduling problems for parallel machines , 2003, Comput. Oper. Res..

[26]  Tian Chao,et al.  Extremum Response Surface Method for Casing Radial Deformation Probabilistic Analysis , 2013, J. Aerosp. Inf. Syst..

[27]  Chao Wang,et al.  A multi-objective multi-population ant colony optimization for economic emission dispatch considering power system security , 2017 .

[28]  Kevin Burrage,et al.  Estimates of the coverage of parameter space by Latin Hypercube and Orthogonal Array-based sampling , 2017 .

[29]  Marija Samardžić,et al.  UAV aerodynamic design involving genetic algorithm and artificial neural network for wing preliminary computation , 2019, Aerospace Science and Technology.

[30]  Zheng Liu,et al.  PSO-BP Neural Network-Based Strain Prediction of Wind Turbine Blades , 2019, Materials.

[31]  Hua Peng,et al.  Underwater acoustic source localization using generalized regression neural network. , 2018, The Journal of the Acoustical Society of America.

[32]  Wei Wang,et al.  An improved radial basis function network for structural reliability analysis , 2011 .

[33]  Xufeng Yang,et al.  Active learning method combining Kriging model and multimodal‐optimization‐based importance sampling for the estimation of small failure probability , 2020, International Journal for Numerical Methods in Engineering.

[34]  Xiuli Shen,et al.  Surrogate-based optimization with improved support vector regression for non-circular vent hole on aero-engine turbine disk , 2020 .

[35]  Rongqiao Wang,et al.  Reliability assessment for system-level turbine disc structure using LRPIM-based surrogate model considering multi-failure modes correlation , 2019 .

[36]  Linlin Hou,et al.  Anti-disturbance attitude control of flexible spacecraft with quantized states , 2020 .

[37]  Xianmin Zhang,et al.  A level set method for reliability-based topology optimization of compliant mechanisms , 2008 .

[38]  Guang-chen Bai,et al.  Extremum response surface method of reliability analysis on two-link flexible robot manipulator , 2012 .

[39]  Ing-Rong Horng,et al.  Robust observer-based frequency-shaping optimal vibration control of uncertain flexible linkage mechanisms , 2001 .

[40]  K. Nose-Filho,et al.  Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network , 2011, IEEE Transactions on Power Delivery.

[41]  Huajiang Ouyang,et al.  Pole assignment for control of flexible link mechanisms , 2013 .

[42]  Henri P. Gavin,et al.  High-order limit state functions in the response surface method for structural reliability analysis , 2008 .

[43]  Steven J. Hoff,et al.  Development and Comparison of Backpropagation and Generalized Regression Neural Network Models to Predict Diurnal and Seasonal Gas and PM10 Concentrations and Emissions from Swine Buildings , 2008 .

[44]  Yongshou Liu,et al.  A system reliability analysis method combining active learning Kriging model with adaptive size of candidate points , 2019, Structural and Multidisciplinary Optimization.

[45]  Cheng-Wei Fei,et al.  Transient probabilistic design of flexible multibody system using a dynamic fuzzy neural network method with distributed collaborative strategy , 2018, Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering.

[46]  Yun-Wen Feng,et al.  Improved Decomposed-Coordinated Kriging Modeling Strategy for Dynamic Probabilistic Analysis of Multicomponent Structures , 2020, IEEE Transactions on Reliability.