Joint Parameter Research Articles

Effects of geometric parameters of screw type blind rivet joints on large blind head formation and pre-load

Effects of geometric parameters of screw type blind rivet joints on large blind head formation and pre-load

ENHANCING WELDING QUALITY THROUGH PREDICTIVE MODELLING — INSIGHTS FROM MACHINE LEARNING TECHNIQUES

In this work, the application of various machine learning (ML) algorithms for predicting tensile strength based on welding parameters in AA2014-T6 aluminium alloy joints is studied. Six ML models namely linear regression, AdaBoost regression, random forest regression, support vector regression (SVR), multi-layer perceptron regression and gaussian process regression (GPR) are considered. The comprehensive analysis revealed that SVR exhibited superior generalization capabilities on unseen data, achieving an R² of 0.89 and a low RMSE of 15.64. In contrast, GPR, despite its high training accuracy, showed significant overfitting. This work highlights the potential of ML in optimizing welding parameters and highlights the importance of model selection and tuning to prevent overfitting and ensure reliable predictions.

Association between acromion morphological parameters and rotator cuff tears in Somali population—a three-dimensional computed tomographic study

BackgroundPrevious research has established connections between the acromion index (AI), critical shoulder angle (CSA), acromiohumeral distance (AHD), and lateral acromion angle (LAA) with the incidence of rotator cuff tears (RCTs). Despite numerous international studies exploring the variability of shoulder joint morphology and parameters, research incorporating these parameters has yet to be conducted in Somalia. This study aims to analyze and describe the radiological parameters of acromion morphology in the Somali populations. Furthermore, to investigate the relationship of these parameters with rotator cuff tears within the Somali population.MethodsThe data and physical examination of 188 patients who had a CT scan of the shoulder from 2018 to 2023 were retrospective analyses, including 107 patients (49 females, 58 males) with RCT and 81 patients (20 females, 61 males) with non-RCT. Using Three-dimensional computed tomography (3D-CT), parameters such as the AI, CSA, AHD, and LAA were compared between the RCT and non-RCT groups. Two independent assessors measured Each parameter from anterior views of the scapula. The inter- and intra-observer reliability was evaluated using the intraclass correlation coefficient (ICC). Additionally, the relationship between these parameters and the presence of rotator cuff tears was explored, and the predictive value of each parameter was assessed through receiver operating characteristic (ROC) analysis.ResultsThe results showed excellent intra- and inter-observer reliability, with all ICC values above 0.75. Among these, the CSA exhibited the greatest measurement stability, with an intra-observer ICC of 0.929 and an inter-observer ICC of 0.911. Significant positive correlations were identified between the AI, CSA, and the presence of RCTs, with CSA exhibiting the strongest correlation (r = 0.629; P < 0.001). Additionally, significant negative correlations were found between the presence of RCTs and both AHD (–0.247) and LAA (–0.338; P < 0.001 for both). The ROC analysis revealed that the CSA is the most effective parameter for identifying the presence of RCT (area under the ROC curve. 0.857).ConclusionThe outcome of this study shows that AI, CSA, AHD, and LAA are independent factors associated with rotator cuff tears in the East African, particularly the Somali population. Specifically, larger AI, CSA, and smaller AHD and LAA are correlated with an increased likelihood of RCTs in this population. In patients with shoulder disease suspected of RCTs, using a 3D-CT scan to measure the CSA may be helpful, as it is the best predictor measurement.Clinical trial numberNot Applicable.

The effects of joint process parameters of two-step manufacturing processes on the mechanical performance of biocomposites using Taguchi and multiple regression techniques

This study evaluates the influence of joint parameters of extrusion (extrusion profile temperature) and injection molding (barrel profile temperature and mold temperature) manufacturing processes on the mechanical performance of biocomposite materials via the Taguchi and multiple regression techniques. Statistical analysis of variance (ANOVA) was performed to determine the most influential controllable factors for the individual responses. The results of the study revealed that the mechanical properties of the biocomposites are affected by the joint parameters of the two-step manufacturing techniques. This study will help in the process design of biocomposites with improved mechanical performance.

A hybrid prognostic framework: Stochastic degradation process with adaptive trajectory learning to transfer historical health knowledge

Remaining useful life (RUL) prediction is crucial to supporting intelligent maintenance and health management of safety–critical products. Although advanced data-driven approaches such as deep neural networks are effective in processing high-dimensional non-linear health features, their application to field RUL prediction confronts with two challenges: (a) adaptivity of the lifetime parameter learning process is often restricted, and (b) prediction of multi-source uncertainties is almost analytically intractable. This paper addresses such challenges by devising a tractable, global adaptive model-data-interaction prognostic framework, where a non-linear stochastic degradation model governed by self-adaptive trajectory pattern is constructed to transfer historical health knowledge. In particular, a joint parameter learning framework is established under the structure of a multi-branch Bayesian network, such that to simultaneously learn: (a) degradation model parameters, and (b) network hyper-parameters. Additionally, the key control parameters of the degradation process are updated adaptively leveraging multi-dimensional sequential Bayesian learning. An efficient interpolation algorithm is further proposed to alleviate computation burden of RUL distributions. Case studies conducted on both turbofan engines degradation data and field train bearing vibration data demonstrate the superior model performance compared to existing methodologies.

Enhancing the reliability of CSP solder joints under thermal cycling conditions through particle swarm optimization of an improved BP neural network

The packaging of chip-scale (CSP) devices plays a pivotal role in enhancing the reliability of CSP under thermal cycling conditions, largely due to the intricate structure and the recurrent alterations in the actual operating environment. The objective of this study is to enhance the reliability of solder joints by optimising the structural parameters of CSP packaging in order to reduce the strain values at the solder joints. In order to enhance the design efficiency and accuracy of the computational model, the Anand model is adopted in order to define the solder joint parameters, and finite element simulations are conducted using Ansys software. This paper puts forward a novel intelligent algorithm that fuses response surface methodology with a neural network-particle swarm optimization algorithm, thereby enhancing the precision of the system. The method is capable of identifying the combination with the minimum strain value using limited data, thereby addressing the issue of insufficient generalisation ability in conventional methods. The implementation of this method into the model resulted in a minimum strain value of 4.071 × 10−3, representing a 37.6 % reduction compared to the original CSP structure. Furthermore, the optimized lifespan is approximately 3.24 times longer than that observed prior to optimization. The approach presented in this paper has the potential to significantly enhance design efficiency and increase the lifespan of components. It offers a novel perspective for optimising the structural parameters of CSP packaging.

AI-Powered Geotechnics: Enhancing Rock Mass Classification for Safer Engineering Practices

AbstractRock mass classification is fundamental for evaluating rock mass quality, essential for stability analysis and geotechnical design. Traditional classification methods are limited by joint observation technology, which typically gathers joint information from one-dimensional or two-dimensional perspectives, failing to comprehensively capture three-dimensional joint occurrences. This often necessitates empirical formulas for joint distribution, resulting in less precise joint parameter calculations. This paper reviews 44 seminal articles on rock engineering classification in construction and subterranean projects, tracing the evolution from foundational methods like Rock Quality Designation, Rock Mass Rating, Q-system, Basic Quality, and Hydropower Classification to contemporary techniques. It highlights the transformative impact of data science, particularly artificial intelligence, on rock engineering. The analysis reveals 73 distinct algorithms used 162 times in literature, with Support Vector Machines Support, Vector Regression, K-means clustering, K-Nearest Neighbors, Artificial Neural Networks and Random Forest being the most successful. This paper examines each method's advantage and limitations, discussing the challenges of algorithm deployment in the scientific community. The findings underscore the integration of machine learning and meta-heuristic optimization methods in rock engineering classification, offering valuable insights for future research and applications.

Effect of maxillary molars distalization using clear aligners and fixed orthodontic appliances on the positional and dimensional temporomandibular joint parameters: a three-dimensional comparative study

ObjectiveThe use of clear aligners (CAs) for orthodontic treatment has substantially increased in recent decades. However, limited empirical evidence exists regarding their potential effects on the temporomandibular joint (TMJ). The aim of this study was to assess the effect of maxillary molar distalization on the positional and dimensional TMJ parameters between CAs and conventional fixed orthodontic appliances (FAs) in skeletal class II malocclusion.MethodsThis is a retrospective cohort study examined 70 adult patients with skeletal class II malocclusion with similar baseline characteristics based on American Board of Orthodontics (ABO) discrepancy index scores. The patients were treated by maxillary distalization movement by CAs or FAs, of which there were two equal groups of 35 patients were included in each group. CBCTs on TMJs were performed before and after treatment through Anatomage Invivo Dental 6.0. The measured parameters included inclination, position, condyle and articular fossa dimensions, and the volumetric joint spaces.ResultsIn both groups, linear measurements of the maxillary molar position revealed significant improvement after treatment (P < 0.001). Regarding TMJ parameters, intra-group comparisons revealed significant changes in FA group in the anterioposterior condylar inclination and condylar position across the three planes. Additionally, the pretreatment-centric condylar position in the glenoid fossa was 45.7% and 40% in the CA and FA groups, respectively. After treatment, these percentages changed to 51.4% and 31.4%, respectively. In inter-group comparisons, significant changes were noted in the mediolateral condylar position, which was more inward in the FA group than the CA group.ConclusionThe FA group had more significant dimensional and positional changes in the mandibular condyle than the CA group; nevertheless, the changes are considered clinically negligible.

Comparative study of machine learning method and response surface methodology in BGA solder joint parameter optimization

Comparative study of machine learning method and response surface methodology in BGA solder joint parameter optimization

Hessian-based mixed-precision quantization with transition aware training for neural networks.

Model quantization is widely used to realize the promise of ubiquitous embedded deep network inference. While mixed-precision quantization has shown promising performance, existing approaches often rely on time-consuming search process to determine the optimal bit configuration. To address this, we introduce Hessian-based Mixed-Precision Quantization Aware Training(HMQAT) to decrease the search overhead of bit configuration. By using the sensitivity metric of joint average Hessian trace and parameter size, HMQAT effectively guides the search process. We solve the optimization problem about bit configuration automatically using a Pareto frontier method. The lowest search overhead can be achieved through our scheme. Additionally, our approach incorporates quantization transition aware fine-tuning of scale factor. This strategy consistently ensures optimal inference performance along the accuracy-size Pareto frontier across multiple models. We extensively evaluated our method on ImageNet and CIFAR10. In particular, we show that compared to the baseline, HMQAT achieves a 10.34× reduction in model size while retaining 99.81% of the Top-1 accuracy on ResNet18 for ImageNet. Moreover, HMQAT surpassed the state-of-the-art mixed-precision quantization methods in compressing neural networks with reduced search cost and achieving a satisfying trade-off between size and accuracy. This study paves the way of deploying neural networks on lightweight devices.

Strength characteristics analysis and unified model establishment of bonded, riveted, and adhesive-rivet hybrid CFRP joints

Carbon fiber-reinforced plastic (CFRP) bonded, riveted, and adhesive-rivet hybrid joints are among the weak parts of a structure. To study their strength characteristics and strength characterization methods, the key parameters of the CFRP constitutive model were obtained by constitutive tests, based on which finite element (FE) models of the three types of CFRP joints were established. The failure modes and F–D (load-displacement) curves of the CFRP joints were obtained through quasi-static tensile tests, and the accuracy of the FE models was verified. Based on the test results, the test strength models of the three types of CFRP joints were established, along with a unified model to characterize the joint strength; however, the strength models were affected by the joint parameters. Therefore, the influence of nine parameters on the joint strength were discussed, and the unified strength models of the three types of CFRP joints under each influencing parameter were established based on the initial strength model. The results showed that the unified strength models were highly correlated with R2 > 0.92. These results provide useful references for the strength check and parameter optimization of CFRP joints.

Numerical simulation of failure and micro-cracking behavior of non-persistent rock joint under direct shear

Persistency, as a key geometric parameter of joints, significantly affects shear strength parameters of jointed rock mass. A good understanding of how persistency affects shear behavior of joint is therefore crucial for better evaluation of stability of rock slope. To investigate the failure and micro-cracking behavior of non-persistent rock joint under direct shear, a novel Voronoi generation algorithm is first used to establish an improved grain-based model (GBM) of granite which considers the shape of feldspar. The calibrated model is then used to simulate the direct shear test of numerical models possessing different joint persistency under various normal stresses. The results reveal that the developed micro-cracks generally increase rapidly when the shear strain reaches to a value approximately 50 % of the peak shear strain and the grain boundary tensile micro-crack is dominant among these initiated micro-cracks. Micro-cracks generally initiate at the ends of rock bridge, and then gradually propagate to the central of rock bridge, forming en-echelon fractures. The failure mode of numerical model is closely related to the generated en-echelon fractures. An increase in both joint persistency and normal stress can lead to a shear failure. The finding in this study provides an important basis for understanding the mechanical behavior and failure mechanism of jointed rock mass.

Automatic interpretation of geometric information of discontinuities and its influence on the stability of highly-jointed rock slopes

The discrete fracture system of a rock mass plays a crucial role in controlling the stability of rock slopes. To fully account for the geometric shape and distribution characteristics of jointed rock masses, terrestrial laser scanning (TLS) was employed to acquire high-resolution point-cloud data, and a developed automatic discontinuity-identification technology was coupled to automatically interpret and characterize geometric information such as orientation, trace length, spacing, and set number of the discontinuities. The discrete element method (DEM) was applied to study the influence of the geometric morphology and distribution characteristics of discontinuities on slope stability by generating a discrete fracture network (DFN) with the same statistical characteristics as the actual discontinuities. Based on slope data from the Yebatan Hydropower Station, a simulation was conducted to verify the applicability of the automatic discontinuity identification technology and the discrete fracture network-discrete element method (DFN-DEM). Various geological parameters, including trace length, persistence, and density, were examined to investigate the morphological evolution and response characteristics of rock slope excavation under different joint combination conditions through simulation. The simulation results indicate that joint parameters affect slope stability, with density having the most significant impact. The impact of joint parameters on stability is relatively small within a reasonable range but becomes significant beyond a certain threshold, further validating that the accuracy of field geological surveys is critical for simulation. This study provides a scientific basis for the construction of complex rock slope models, engineering assessments, and disaster prevention and mitigation, which is of great value in both theory and engineering applications.

Multi-objective optimization of FSW process parameters for AA1100 joints by using a hybrid technique of PCA-TOPSIS

Multi-objective optimization of FSW process parameters for AA1100 joints by using a hybrid technique of PCA-TOPSIS

Optimization and Analysis of Refill Friction Stir Spot Welding (RFSSW) Parameters of Dissimilar Aluminum Alloy Joints by FE and ANN Methods.

The quality of the refill friction stir spot welding (RFSSW) process is heavily dependent on the selected welding parameters that influence the resultant joint characteristics. Thermomechanical phenomena integral to the process were investigated using finite element (FE) analysis on two dissimilar materials. This FE analysis was subsequently validated through controlled experiments to ensure reliability. An artificial neural network (ANN) was employed to create a neural model based on an experimental setup involving 120 different sets of welding parameters. The parameters adjusted in the experimental plan included pin penetration depth, rotational speed, retention time, and positioning relative to material hardness. To assess the neural model's accuracy, outputs such as maximum temperature and normal stress at the end of the welding process were analyzed and validated by six data sets selected for their uniform distribution across the training domain.

Development, calibration and validation of impact-specific cervical spine models: A novel approach using hybrid multibody and finite-element methods

Background and Objective:Spinal cord injuries can have a severe impact on athletes’ or patients’ lives. High axial impact scenarios like tackling and scrummaging can cause hyperflexion and buckling of the cervical spine, which is often connected with bilateral facet dislocation. Typically, finite-element (FE) or musculoskeletal models are applied to investigate these scenarios, however, they have the drawbacks of high computational cost and lack of soft tissue information, respectively. Moreover, material properties of the involved tissues are commonly tested in quasi-static conditions, which do not accurately capture the mechanical behavior during impact scenarios. Thus, the aim of this study was to develop, calibrate and validate an approach for the creation of impact-specific hybrid, rigid body - finite-element spine models for high-dynamic axial impact scenarios. Methods:Five porcine cervical spine models were used to replicate in-vitro experiments to calibrate stiffness and damping parameters of the intervertebral joints by matching the kinematics of the in-vitro with the in-silico experiments. Afterwards, a five-fold cross-validation was conducted. Additionally, the von Mises stress of the lumped FE-discs was investigated during impact. Results:The results of the calibration and validation of our hybrid approach agree well with the in-vitro experiments. The stress maps of the lumped FE-discs showed that the highest stress of the most superior lumped disc was located anterior while the remaining lumped discs had their maximum in the posterior portion. Conclusion:Our hybrid method demonstrated the importance of impact-specific modeling. Overall, our hybrid modeling approach enhances the possibilities of identifying spine injury mechanisms by facilitating dynamic, impact-specific computational models.

Digital twin-based identification of crystal plastic material parameters for weld joints of orthotropic steel decks

The identification of crystal plasticity (CP) material parameters is indispensable for using CP models to simulate and understand the microcrack initiation and propagation of orthotropic steel decks (OSD). This study proposes a digital twin (DT)-based framework for identifying CP material parameters of weld joints of OSD by fusing multiscale CP finite element model (CPFEM) with macroscale stress–strain material tests. The material tests of the specimen (physical entity) cut from the weld joints of OSD and sliced to the centimeter scale are carried out using the standard dynamic test system. The CPFEM simulation is used to develop a multiscale virtual entity to map the physical entity. The particle swarm optimization algorithm is used to fuse the CPFEM simulation with the material test data to identify CP material parameters and produce a DT. The results demonstrate that the CP material parameters identified by the proposed framework are more accurate than those identified by a single representative volume element method. The results also show that the DT-based identification of CP material parameters has high applicability.

Locomotion trajectory optimization for quadruped robots with kinematic parameter calibration and compensation

It is significant to improve the locomotion trajectory accuracy of a quadruped robot for more applications. A compensation approach with kinematic parameter calibration is proposed to enhance the trajectory accuracy. The motion equation of the foot ends in coordinated gait is given. The related kinematic error model is deduced. The model for identifying the joint parameter errors is implemented via the trajectory error in the Z-direction. The trunk trajectory accuracy enhancement is facilitated by compensating the joint parameter error with joint angles as tuning variables. The performance of the methodology is validated in the simulation system by predetermining ten random sets of joint variable errors. The results indicate that both the trajectory and the attitude accuracy of the calibrated robot can be significantly improved. In practical experiments, it is shown that an error reduction rate of 80% in positional deviation and 58% in attitude error can be achieved.

Kinematic and kinetic parameters of prosthetic knee joints during walking – Comparison of gait analysis results and internal sensor data

Kinematic and kinetic parameters of prosthetic knee joints during walking – Comparison of gait analysis results and internal sensor data

Physics and data‐driven approach for online joint state and parameter estimation of electricity and steam networks

Physics and data‐driven approach for online joint state and parameter estimation of electricity and steam networks