Application of reinforcement learning for the optimization of clinch joint characteristics

Due to increasing challenges in the area of lightweight design, the demand for time- and cost-effective joining technologies is steadily rising. For this, cold-forming processes provide a fast and environmentally friendly alternative to common joining methods, such as welding. However, to ensure a sufficient applicability in combination with a high reliability of the joint connection, not only the selection of a best-fitting process, but also the suitable dimensioning of the individual joint is crucial. Therefore, few studies already investigated the systematic analysis of clinched joints usually focusing on the optimization of particular tool geometries against shear and tensile loading. This mainly involved the application of a meta-model assisted genetic algorithm to define a solution space including Pareto optima with all efficient allocations. However, if the investigation of new process configurations (e. g. changing materials) is necessary, the earlier generated meta-models often reach their limits which can lead to a significantly loss of estimation quality. Thus, it is mainly required to repeat the time-consuming and resource-intensive data sampling process in combination with the following identification of best-fitting meta-modeling algorithms. As a solution to this problem, the combination of Deep and Reinforcement Learning provides high potentials for the determination of optimal solutions without taking labeled input data into consideration. Therefore, the training of an Agent aims not only to predict quality-relevant joint characteristics, but also at learning a policy of how to obtain them. As a result, the parameters of the deep neural networks are adapted to represent the effects of varying tool configurations on the target variables. This provides the definition of a novel approach to analyze and optimize clinch joint characteristics for certain use-case scenarios.

Studying effects of joint characteristics on the performance of a cantilever beam shaped piezoelectric energy harvester through joint identification

In energy harvesting systems, specifications of the generated electrical energy depend on the structure’s dynamics. This dependence can be used to identify the system’s joint characteristics. To this end, an innovative frequency-response-function (FRF) based identification method is presented. The investigated system is a cantilever beam shaped structure with an embedded bimorph piezoelectric bender, connected to a base via bolted joint as a depiction for wing of a UAV connected to fuselage. The implemented FRF is ratio of the piezoelectric output voltage to the base input displacement. The joint identification procedure consists of analytical modeling of the system with joint, experimental testing of the system and a real-coded Genetic Algorithm (GA) method. The joint is modeled as a combination of longitudinal and torsional springs, whose stiffnesses are obtained using the GA method. The obtained results indicate that the analytical model has good correlation with the experimental data. Then, effects of the joint characteristics on the energy harvester’s performance are investigated by comparison of the system with two different joint assumptions, namely, rigid and realistic joint. Finally, the effects of various joint characteristics on the energy harvester’s performance are presented and approaches to achieve the maximum performance of the system are suggested.

Effect of Joint Characteristics and Geometries on Tunnel-Type Anchorage for Suspension Bridge

In this study, the pull-out behavior of a tunnel-type anchorage was examined by considering both geometric and rock joint characteristics. Three-dimensional finite element analyses were performed with reference to the tunnel-type anchorage cases designed and constructed in Korea. The factors influencing the anchorage response were analyzed: the enlarged part, anchorage spacing, joint orientation, spacing, and the shear strength of the rock joints. According to the numerical studies, the size of the enlarged part influenced the failure shape of the tunnel-type anchorage. It was found that the anchorage spacing, the relationship between the tunnel-type anchorage, and the joint orientation and spacing greatly influenced the pull-out behavior of the anchorage. Additionally, the friction angle had a larger impact on the anchorage’s pull-out resistance than the cohesion between the rock joints.

Periprosthetic Infections of the Shoulder Joint: Characteristics and 5-Year Outcome of a Single-Center Series of 19 Cases

Periprosthetic shoulder infection (PSI) remains a devastating complication after total shoulder arthroplasty (TSA). Furthermore, there is a paucity in the literature regarding its diagnostic and therapeutic management, especially the absence of therapy concepts devised exclusively for PSI. The aim of the presenting study is to examine the characteristics and outcome of patients with PSI who were treated according to well-established algorithms developed originally for periprosthetic joint infection (PJI) of the hip and knee and determine if these algorithms can be applied to PSI. This single-center case series included all patients with a PSI presenting between 2010 and 2020. Recorded parameters included age, sex, affected side, BMI, ASA score, Charlson comorbidity index, preoperative anticoagulation, indication for TSA (fracture, osteoarthritis or cuff-arthropathy), and type of infection (acute or chronic PSI). The outcome was divided into treatment failure or infect resolution. Staphylococcus epidermidis and aureus were the commonest infecting pathogens. Acute PSI was mainly treated with debridement, irrigation, and retention of the prosthesis (DAIR) and chronic cases with two/multiple-stage exchange. The treatment failure rate was 10.5%. C-reactive protein was preoperatively elevated in 68.4% of cases. The mean number of operative revisions was 3.6 ± 2.6, and the mean total duration of antibiotic treatment was 72.4 ± 41.4 days. The most administered antibiotic was a combination of clindamycin and fluoroquinolone. In summary, the data of the current study suggest that therapeutical algorithms and recommendations developed for the treatment of PJI of the hip and knee are also applicable to PSI.

Approach for the Automated Analysis of Geometrical Clinch Joint Characteristics

Due to their cost-efficiency and environmental friendliness, the demand of mechanical joining processes is constantly rising. However, the dimensioning and design of joints and suitable processes are mainly based on expert knowledge and few experimental data. Therefore, the performance of numerical and experimental studies enables the generation of optimized joining geometries. However, the manual evaluation of the results of such studies is often highly time-consuming. As a novel solution, image segmentation and machine learning algorithm provide methods to automate the analysis process. Motivated by this, the paper presents an approach for the automated analysis of geometrical characteristics using clinching as an example.