An even-load-distribution design for composite bolted joints using a novel circuit model and artificial neural networks

Due to the brittle feature of carbon fiber reinforced plastic laminates, mechanical multi-joint within these composite components shows uneven load distribution for each bolt, which weaken the strength advantage of composite laminates. In order to reduce this defect and achieve the goal of even load distribution in mechanical joints, we propose a machine learning-based framework as an optimization method. Since that the friction effect has been proven to be a significant factor in determining bolt load distribution, our framework aims at providing optimal parameters including bolt-hole clearances and tightening torques for a minimum unevenness of bolt load. A novel circuit model is established to generate data samples for the training of artificial networks at a relatively low computational cost. A database for all the possible inputs in the design space is built through the machine learning model. The optimal dataset of clearances and torques provided by the database is validated by both the finite element method, circuit model, and an experimental measurement based on the linear superposition principle, which shows the effectiveness of this general framework for the optimization problem. Then, our machine learning model is further compared and worked in collaboration with commonly used optimization algorithms, which shows a potential of greatly increasing computational efficiency for the inverse design problem.

[1]  Libin Zhao,et al.  A modified stiffness method considering effects of hole tensile deformation on bolt load distribution in multi-bolt composite joints , 2019, Composites Part B: Engineering.

[2]  S. Du,et al.  An improved model for predicting stiffness of single-lap composites bolted joints using Matlab/Simulink , 2019, Mechanics of Advanced Materials and Structures.

[3]  Libin Zhao,et al.  An interpretation of the load distributions in highly torqued single-lap composite bolted joints with bolt-hole clearances , 2018 .

[4]  Chiho Kim,et al.  Machine learning in materials informatics: recent applications and prospects , 2017, npj Computational Materials.

[5]  L. Lessard,et al.  Improving load sharing in hybrid bonded/bolted composite joints using an interference-fit bolt , 2016 .

[6]  M. A. McCarthy,et al.  Three-dimensional finite element analysis of single-bolt, single-lap composite bolted joints: Part II––effects of bolt-hole clearance , 2005 .

[7]  S. Sampathkumar,et al.  Prediction of impact damage tolerance of drop impacted WGFRP composite by artificial neural network using acoustic emission parameters , 2014 .

[8]  Grace X. Gu,et al.  Machine learning for composite materials , 2019, MRS Communications.

[9]  H. Schürmann,et al.  FAILURE ANALYSIS OF FRP LAMINATES BY MEANS OF PHYSICALLY BASED PHENOMENOLOGICAL MODELS , 1998 .

[10]  Markus J. Buehler,et al.  Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment , 2018 .

[11]  Takashi Ishikawa,et al.  Bearing strength and failure behavior of bolted composite joints (part I: Experimental investigation) , 2005 .

[12]  Anh Tran,et al.  An active learning high-throughput microstructure calibration framework for solving inverse structure-process problems in materials informatics , 2020, ArXiv.

[13]  P. Camanho,et al.  A design methodology for mechanically fastened joints in laminated composite materials , 2006 .

[14]  Wei-keng Liao,et al.  Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets , 2018 .

[15]  Yuxing Yang,et al.  An enhanced spring-mass model for stiffness prediction in single-lap composite joints with considering assembly gap and gap shimming , 2018 .

[16]  Grace X. Gu,et al.  Generative Deep Neural Networks for Inverse Materials Design Using Backpropagation and Active Learning , 2020, Advanced science.

[17]  M. A. McCarthy,et al.  Experiences with Modeling Friction in Composite Bolted Joints , 2005 .

[18]  M. Marques,et al.  Recent advances and applications of machine learning in solid-state materials science , 2019, npj Computational Materials.

[19]  H. Wargnier,et al.  An analytical model for the prediction of load distribution in multi-bolt composite joints including hole-location errors , 2014 .

[20]  Alok Choudhary,et al.  A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials , 2016 .

[21]  M. A. McCarthy,et al.  A simple method for determining the effects of bolt-hole clearance on load distribution in single-column multi-bolt composite joints , 2006 .

[22]  Alok Choudhary,et al.  A predictive machine learning approach for microstructure optimization and materials design , 2015, Scientific Reports.

[23]  Benjamin Luce,et al.  Accelerated design and characterization of non-uniform cellular materials via a machine-learning based framework , 2020, npj Computational Materials.

[24]  Reza Vaziri,et al.  Theory-guided machine learning for damage characterization of composites , 2020 .

[25]  Srinivasa D. Thoppul,et al.  Mechanics of mechanically fastened joints in polymer–matrix composite structures – A review , 2009 .

[26]  Conor T. McCarthy,et al.  An analytical model for the prediction of load distribution in highly torqued multi-bolt composite joints , 2011 .

[27]  B. Grabowski,et al.  A machine learning approach to model solute grain boundary segregation , 2018, npj Computational Materials.

[28]  Saqib Mehmood,et al.  A modified failure envelope method for failure prediction of multi-bolt composite joints , 2013 .

[29]  Trevor M. Young,et al.  Bonded repair of composite aircraft structures: A review of scientific challenges and opportunities , 2013 .

[30]  Lorenzo Iannucci,et al.  Physically-based failure models and criteria for laminated fibre-reinforced composites with emphasis on fibre kinking: Part I: Development , 2006 .

[31]  Takashi Ishikawa,et al.  Bearing strength and failure behavior of bolted composite joints (part II: modeling and simulation) , 2005 .