Predicting mechanical behaviors of rubber materials with artificial neural networks

Yuan, Zengrui; Niu, Mu‐Qing; Ma, Hongtu; Gao, Tao; Shi, Mei; Zhang, Yewei; Chen, Liqun

doi:10.1016/j.ijmecsci.2023.108265

Cited by 25 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T fram1 is obtained from the deflection calculation method of cantilever beam under uniform loading, T fram1 = Ewt 3 12l1 θ 3 , as well as T fram2 = Ewt 3 12l2 θ 4 . T p1 and T p2 are the pressure torques generated by the inflation pressure p, T p1 = 1 2 pwl 2 1 , T p2 = 1 2 pwl 2 2 ; E is the Young's modulus of the actuator material (Dragon-Skin 30), E = 15.75+2.15HA 100−HA (MPa) [33], HA is the Shore hardness of silicone elastomer, HA = 30; w is the arc length in the middle of the actuator's corrugated fold, w = π ( l1 2 + r…”

Section: Bending Angle Modelingmentioning

confidence: 99%

Corrugated V-fold soft actuator with large deformation and high force density

Xu,

Liu,

Zhang

et al. 2023

Smart Mater. Struct.

View full text Add to dashboard Cite

Soft pneumatic actuators with a corrugated structure have the advantage of low inflation pressure and a large actuation range and have great potential for use in grippers. However, they are generally difficult to have both large deformation and high force density performance. Inspired by the hydraulic joints of spider legs, this paper designs a multi-cavity soft-pneumatic actuator with a corrugated V-fold structure, which realizes bending through the deformation of the air cavity structure instead of the traditional way of squeezing the air cavities against each other, and has significantly large curvature high force density compared with actuators such as PneuNets. At an inflation pressure of 40 kPa, the proposed soft actuator achieves a bending angle of 306° with a curvature of 0.114 rad mm−1, while at an inflation pressure of 45 kPa, the actuator achieves an actuation force of 5.15 N with a force density of 0.0101 mN (mm3.kPa)−1. The modeling approach based on continuum mechanics modeling of soft materials combined with finite element analysis (FEA) (or experiment) is proposed to achieve accurate modeling of the bending angle and actuation force of actuators with complex corrugated structures. In addition, the proposed actuator has made initial explorations into the application of soft grippers and has achieved fairly good gripping results compared to other types of grippers.

show abstract

Section: Bending Angle Modelingmentioning

confidence: 99%

Corrugated V-fold soft actuator with large deformation and high force density

Xu,

Liu,

Zhang

et al. 2023

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…However, ANN relies excessively on large sample sizes and requires sufficient training data to maintain the stability of the model ( Kholi et al, 2023 ). To improve the ANN model, Yuan et al (2023) proposed a self-adjusting particle swarm optimization (APSO) algorithm to optimize the weights, thresholds, and number of neurons of the ANN.…”

Section: Machine Learningmentioning

confidence: 99%

Machine learning applications for multi-source data of edible crops: A review of current trends and future prospects

Zhang,

Wang

2023

Food Chemistry: X

View full text Add to dashboard Cite

“…The observed residual errors in the hybrid numerical-experimental identification process hence were fully consistent with the level of uncertainty normally entailed by FEMU-based characterization. Optically measured (d) Remarkably, HS-JAYA solved variants 1 and 2 of the identification problem including, respectively, 324 and 110 unknown material/structural parameters, a significantly larger number of unknowns than those usually reported in the literature for elastomers and rubberlike materials [66][67][68][69][70][71][72] (from two to six unknown material parameters or neural networks depending on three input characteristics), visco-hyperelastic materials [73][74][75] (from six to nine unknown material parameters including tangent modulus and softening index, Prony constants and relaxation times), biological tissues [76][77][78][79][80][81] (from five to sixteen unknowns accounting also for visco-elastic effects and stochastic variation of material properties), non-homogeneous hyperelastic structures [37,63,[82][83][84] (from four to sixteen unknown material parameters for the global model, or two unknown material parameters for each local inverse problem at the element level) or anisotropic hyperelastic materials modeled with much more complicated constitutive equations [27,34,[84][85][86] (from three to seventeen unknown material parameters). A very recent study by Borzeszkowski et al [38] considered identification problems of nonlinear shells subject to various loading conditions (i.e., uniaxial tension, pure bending, sheet inflation and abdominal wall pressurization).…”

Section: Solution Of the Inverse Problem: Fe Analysis And Metaheurist...mentioning

confidence: 99%

Mechanical Characterization of Soft Membranes with One-Shot Projection Moiré and Metaheuristic Optimization

et al. 2023

View full text Add to dashboard Cite

Mechanical characterization of soft materials is a complicated inverse problem that includes nonlinear constitutive behavior and large deformations. A further complication is introduced by the structural inhomogeneity of tested specimens (for example, caused by thickness variations). Optical methods are very useful in mechanical characterization of soft matter, as they provide accurate full-field information on displacements, strains and stresses regardless of the magnitude and/or gradients of those quantities. In view of this, the present study describes a novel hybrid framework for mechanical characterization of soft membranes, combining (i) inflation tests and preliminary in-plane equi-biaxial tests, (ii) a one-shot projection moiré optical setup with two symmetric projectors that project cross-gratings onto the inflated membrane, (iii) a mathematical model to extract 3D displacement information from moiré measurements, and (iv) metaheuristic optimization hybridizing harmony search and JAYA algorithms. The use of cross-gratings allows us to determine the surface curvature and precisely reconstruct the shape of the deformed object. Enriching metaheuristic optimization with gradient information and elitist strategies significantly reduces the computational cost of the identification process. The feasibility of the proposed approach wassuccessfully tested on a 100 mm diameter natural rubber membrane that had some degree of anisotropy in mechanical response because of its inhomogeneous thickness distribution. Remarkably, up to 324 hyperelastic constants and thickness parameters can be precisely identified by the proposed framework, reducing computational effort from 15% to 70% with respect to other inverse methods.

show abstract

Predicting mechanical behaviors of rubber materials with artificial neural networks

Cited by 25 publications

References 65 publications

Corrugated V-fold soft actuator with large deformation and high force density

Corrugated V-fold soft actuator with large deformation and high force density

Machine learning applications for multi-source data of edible crops: A review of current trends and future prospects

Mechanical Characterization of Soft Membranes with One-Shot Projection Moiré and Metaheuristic Optimization

Contact Info

Product

Resources

About