Search

This paper reports on an investigation into the relationship between stiffness and applied force of an advanced biological composite structure using four techniques: experimental observation; finit...

Feedforward backpropagation artificial neural networks (ANNs) have been increasingly employed in many engineering practices concerning materials modeling. Despite their extensive applications, how to achieve successfully trained ANNs is not thoroughly explained in the literature, nor are there lucid discussions to delineate influential parameters obtained from analyses. Long bones are composite materials possessing nonhomogeneous and anisotropic properties, and their mechanical responses exhibit dependency on numerous variables. Material complexity hinders researchers from arriving at a consensus in implementing an optimal constitutive model or encourages them to adopt a simple constitutive model including many simplifying assumptions. However, such exceptional features and engineering challenges make long bones materials worth investigating, enriching our comprehension of complex engineering structures using novel techniques where traditional methods may present limitations. This paper reports on the prediction of loading, displacement, load and displacement simultaneously, and strains using feedforward backpropagation ANNs trained with experimental recordings. The technique was used to find optimum network structures (architectures) that encompass the best prediction ability. To enhance predictions, the influence of several elements such as a network training algorithm, injecting noise to datasets prior to training, the level of injected noise which directly affects model fitting and regularization, and data normalization prior to training were investigated and discussed. Essential parameters influencing decision making in identifying well-trained and well-generalized ANNs were elaborated. A considerable emphasis in this study was placed on examining the generalization ability of the already trained and tested ANNs, thus guaranteeing unbiased models that avoided overfitting. Gaining favorable outcomes in this study required three years of performing experiments and data collection before establishing the networks. The subsequent training, testing, and determination of the generalization of more than 60,000 ANNs are promising and will assist researchers in comprehending mechanical responses of complicated engineering structures that exhibit peculiar nonlinear properties.

Artificial intelligence (AI) and machine learning (ML) are fascinating interdisciplinary scientific domains where machines are provided with an approximation of human intelligence. The conjecture is that machines are able to learn from existing examples, and employ this accumulated knowledge to fulfil challenging tasks such as regression analysis, pattern classification, and prediction. The horse biomechanical models have been identified as an alternative tool to investigate the effects of mechanical loading and induced deformations on the tissues and structures in humans. Many reported investigations into bone fatigue, subchondral bone damage in the joints of both humans and animals, and identification of vital parameters responsible for retaining integrity of anatomical regions during normal activities in all species are heavily reliant on equine biomechanical research. Horse racing is a lucrative industry and injury prevention in expensive thoroughbreds has encouraged the implementation of various measurement techniques, which results in massive data generation. ML substantially accelerates analysis and interpretation of data and provides considerable advantages over traditional statistical tools historically adopted in biomechanical research. This paper provides the reader with: a brief introduction to AI, taxonomy and several types of ML algorithms, working principle of a feedforward artificial neural network (ANN), and, a detailed review of the applications of AI, ML, and ANN in equine biomechanical research (i.e. locomotory system function, gait analysis, joint and bone mechanics, and hoof function). Reviewing literature on the use of these data-driven tools is essential since their wider application has the potential to: improve clinical assessments enabling real-time simulations, avoid and/or minimize injuries, and encourage early detection of such injuries in the first place.

Mobility solutions offered by living creatures have inspired engineers to capture their locomotion patterns and then develop novel animal-like robots that use legs for locomotion. Exploring relationships among mechanical responses and kinematic parameters is essential for both inventing these robots and enhancing computational techniques. Establishment of accurate physical models to quantify mechanical responses of biological systems is challenging because the corresponding variables are multidimensional, dynamic and highly nonlinear. This encourages the advent of data-driven models in mechanical sciences. This paper delves into the use of feedforward and time-series (dynamic) artificial neural networks (ANN) to analyse experimental data recorded from a racing horse exercised up to 60 km/h to then relate hoof mechanical strain to kinematic parameters recorded experimentally. An inertial measurement unit that was comprised of a sensor and data acquisition system package was designed and mounted on the horse's hoof to measure linear accelerations and angular rates of motion. In addition, an instrumented Aluminium horseshoe that was designed and manufactured and contained: 1) inertial sensors including three orthogonal accelerometers and three orthogonal rate gyroscopes; and, 2) a strain gauge located at the middle of the shoe. The horse was warmed up in a steady gallop at around 35 km/h for 1 km then turned around and galloped at increasing speed to 68 km/h back to the finishing line. Nine kinematic parameters, measured during horse exercise, formed the ANNs input variables: hoof linear accelerations along three orthogonal directions (ax,ay,az), hoof angular rates of motion along three orthogonal directions (Gx, Gy, Gz), shoe linear accelerations along three orthogonal directions (axs, ays, azs), and time. Feedforward and time-series ANNs trained using 1,000,000 experimental instances offered excellent reliability for the prediction of mechanical strain from kinematic measurements, i.e. R ≥ 0.97.

Long bones are composite materials possessing nonhomogeneous and anisotropic properties. They repair themselves (self-repairing) and adapt to changing mechanical demands by altering their shape and mechanical properties (self-adapting). Such exceptional features make long bones intriguing materials to comprehend properly. This also expands our knowledge of engineering materials and motivates researchers to employ novel techniques where conventional approaches may present limitations. This paper delves into the use of artificial neural network (ANN) expert systems to predict load-displacement curves of a long bone. Thirteen hydrated third metacarpal (MC3) bones from thoroughbred horses aged from twelve hours to three years were loaded in compression in an MTS machine. Strain readings from one three-gauge rosette and three distinct single-element gauges at different locations on the MC3 midshaft, displacement, load, load exposure time, horse age and bone side (left or right limb) were recorded for each bone. This information shaped ANNs input variables. Two in-series feedforward back-propagation ANNs were employed where the experimental recordings except for load were fed into the first ANN to predict load. Then, the predicted load along with the rest of experimental recordings were fed into the second ANN to predict displacement. Cyclic load-displacement and stiffness predicted by ANNs were plotted versus experimental counterparts. ANNs regression analyses showed R > 0.95 for training and testing datasets. To confirm their accuracy, ANNs were used to predict responses of specific bone samples that were not used in ANNs training. The ANNs trained using 17,718 experimental data points from twelve bones predicted the load (R = 0.997, RMSE = 2.44 kN), displacement (R = 0.948, RMSE = 0.321 mm), and stiffness (R = 0.982, RMSE = 1.197 kN/mm) of the thirteenth bone. The encouraging outcomes exhibit the exceptional ability of artificial neural networks in capturing the mechanical characteristics of complex structures.

The hierarchical nature of bone makes it a difficult material to fully comprehend. The equine third metacarpal (MC3) bone experiences nonuniform surface strains, which are a measure of displacement induced by loads. This paper investigates the use of an artificial neural network expert system to quantify MC3 bone loading. Previous studies focused on determining the response of bone using load, bone geometry, mechanical properties, and constraints as input parameters. This is referred to as a forward problem and is generally solved using numerical techniques such as finite element analysis (FEA). Conversely, an inverse problem has to be solved to quantify load from the measurements of strain and displacement. Commercially available FEA packages, without manipulating their underlying algebraic formulae, are incapable of completing a solution to the inverse problem. In this study, an artificial neural network (ANN) was employed to quantify the load required to produce the MC3 displacement and surface strains determined experimentally. Nine hydrated MC3 bones from thoroughbred horses were loaded in compression in an MTS machine. Ex-vivo experiments measured strain readings from one three-gauge rosette and three distinct single-element gauges at different locations on the MC3 midshaft, associated displacement, and load exposure time. Horse age and bone side (left or right limb) were also recorded for each MC3 bone. This information was used to construct input variables for the ANN model. The ability of this expert system to predict the MC3 loading was investigated. The ANN prediction offered excellent reliability for the prediction of load in the MC3 bones investigated, i.e. R2 ≥ 0.98.

This paper, in line with the previous study [23] , is concerned with the finite element implementation of nanoplates. However, in this contribution free vibration responses of multicrystalline nanoplates by considering surface effects are presented. Nanomaterials and nanostructures have been receiving widespread attentions during last decades. This fact is due largely to surprising, peculiar, and impressive mechanical; electrical; and physical behaviors of nanostructures. Currently, nanostructures such as nanoplates are being utilized in the designing and manufacturing Nanoelectromechanical systems (NEMS) and Microelectromechanical systems (MEMS). Furthermore, silicon, thanks to its exceptional mechanical, physical, and electrical properties is extensively employed in the NEMS and MEMS. The mechanical properties and responses of nanoplates are intensely size-dependent, and in contrast to plates with macro dimensions, static and free vibration responses of nanoplates strongly depend on the size of nanoplates. In this study, a rectangular multicrystalline plate with nanothickness; arbitrary geometry, and boundary conditions is analyzed. Each crystal of the nanoplate is assumed to be anisotropic, and a prominent point that must be taken into consideration is the interface region, which exists between every two crystals. The free vibration responses of nanoplate such as natural frequency are considered, and the influence of size, surface effects, interface region, and various boundary conditions over natural frequency of the nanoplate is considered. Due to the fact that geometry of the multicrystalline nanoplate is not straightforward to be dealt with the governing equations, the finite element method is employed to obtain the results of free vibration response. Moreover, we succeed to employ ANSYS software in order to attain the free vibration responses of multicrystalline nanoplates. In addition, the present finite element method results, the code of which is generated in MATLAB, are compared with those obtained from ANSYS software, and the correlation of the results is quite remarkable.

Nanostructures have been receiving extensive attention during the last two decades, due to their peculiar mechanical and other physical properties as compared with other macrostructures and macrosystems. The mechanical properties of nanostructures are intensely size-dependent. Furthermore, in the absence of external forces, nanostructures have a great tendency to deform due to their surface effects. Moreover, since the atoms on the surface have different equilibrium configuration from that of in the bulk, the elastic stiffness of the surface can be different from that of the bulk. In this study an ultra-thin plate of nanoscale thickness with an arbitrary geometry and boundary conditions is analyzed. A rectangular plate with nanoscale thickness is presented. In order to generalize the study, a multicrystalline plate with varying crystal properties has been assumed. Furthermore, the mechanical properties of the plate are dependent on the orientation. In fact the multicrystalline nanoplate is an anisotropic plate. The shapes and orientations of each crystal have been chosen haphazardly. However, the entire shape of the plate is a rectangle of microdimension with nanothickness. Due to the fact that silicon is much more applicable than any other material in Nanoelectromechanical systems (NEMS), it is assumed that the plate is made of silicon. The plate is subjected to a static load and the deformation as well as the corresponding strain is demonstrated. Due to the fact that the governing equation of the plate and its solution is not too straightforward to be solved easily, the finite element method is implemented so as to obtain the corresponding results. The results which have been achieved by the method of finite element and by employing the ANSYS software are illustrated and compared. Accordance of the results is quite remarkable.