scholarly journals Application of reinforcement learning for the optimization of clinch joint characteristics

2021 ◽  
Author(s):  
Christoph Zirngibl ◽  
Fabian Dworschak ◽  
Benjamin Schleich ◽  
Sandro Wartzack
Keyword(s):  
Reinforcement Learning ◽  
High Reliability ◽  
Lightweight Design ◽  
Solution Space ◽  
Data Sampling ◽  
Pareto Optima ◽  
Cold Forming ◽  
Joint Characteristics ◽  
Best Fitting ◽  
Efficient Allocations

AbstractDue 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.

Review of Loads Transfer Laws and their Applications in Artillery

2013 ◽  
Vol 328 ◽  
pp. 609-613
Author(s):  
Hui Xiao ◽  
Guo Lai Yang ◽  
Peng Wang
Keyword(s):  
Load Transfer ◽  
Impact Load ◽  
High Reliability ◽  
Lightweight Design ◽  
Strong Impact ◽  
Related Research ◽  
Vibration Load ◽  
Transfer Path ◽  
Technical Performance ◽  
Multi Body

In terms of the requirements of lightweight design, high reliability and long life for dynamic systems, especially heavy machinery and artillery, the methods to achieve the law of loads transfer path were studied based on some history and latest related research. So far, there is no systematic ways to research that in dynamic system, especially in artillery with instantaneous and strong impact load. This paper elaborated the application prospect of loads transfer law in artillery, discussed the main possible methods in research of artillery emission loads transfer laws. Those are topology optimization based on finite element, Multi-body dynamics, and method of vibration load transfer path analysis method. Through simulation and experiments those can be verified their correctness and effectiveness. This article is to find some feasible methods to achieve optimal load-carry structure, so as to improve its tactical and technical performance, especially the mobility, firing accuracy and shooting stability, and it has certain guiding or referenced significance for future related research.

scholarly journals Accelerating Interactive Reinforcement Learning by Human Advice for an Assembly Task by a Cobot

Robotics ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 104
Author(s):  
Joris De Winter ◽  
Albert De Beir ◽  
Ilias El Makrini ◽  
Greet Van de Perre ◽  
Ann Nowé ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Solution Space ◽  
Assembly Sequence ◽  
Assembly Task ◽  
Human Interactions ◽  
Simulated Environment ◽  
Learning Speed ◽  
Reward Shaping ◽  
Feedback Strategies ◽  
Changing Knowledge

The assembly industry is shifting more towards customizable products, or requiring assembly of small batches. This requires a lot of reprogramming, which is expensive because a specialized engineer is required. It would be an improvement if untrained workers could help a cobot to learn an assembly sequence by giving advice. Learning an assembly sequence is a hard task for a cobot, because the solution space increases drastically when the complexity of the task increases. This work introduces a novel method where human knowledge is used to reduce this solution space, and as a result increases the learning speed. The method proposed is the IRL-PBRS method, which uses Interactive Reinforcement Learning (IRL) to learn from human advice in an interactive way, and uses Potential Based Reward Shaping (PBRS), in a simulated environment, to focus learning on a smaller part of the solution space. The method was compared in simulation to two other feedback strategies. The results show that IRL-PBRS converges more quickly to a valid assembly sequence policy and does this with the fewest human interactions. Finally, a use case is presented where participants were asked to program an assembly task. Here, the results show that IRL-PBRS learns quickly enough to keep up with advice given by a user, and is able to adapt online to a changing knowledge base.

scholarly journals Estimation of fatigue life for clinched joints with the Local Strain Approach incorporating the impact of cold forming to cyclic material properties

2021 ◽  
Vol 349 ◽  
pp. 04005
Author(s):  
Boris Spak ◽  
Maximilian Schlicht ◽  
Karina Nowak ◽  
Markus Kästner ◽  
Pascal Froitzheim ◽  
...  
Keyword(s):  
Fatigue Life ◽  
Material Properties ◽  
Lightweight Design ◽  
Base Material ◽  
Local Strain ◽  
Small Scale ◽  
Forming Process ◽  
Cold Forming ◽  
Finite Element Software ◽  
The Impact

Joining by forming is a commonly applied technique in the automotive industry to assemble parts of thin metal sheets to meet the demands of lightweight design. The joining operation induces changes in material behaviour due to cold forming, that can be observed in increased hardness in the area close to the joint neck compared to the base material. Complex geometrical features of clinched joints on a small scale and the lack of non-destructive methods to track local stresses and strains require a combined approach utilizing numerical and experimental techniques. Numerical process and loading simulation are performed utilizing commercial finite element software LS-Dyna®. Hardness measurements in the joint are carried out to assess the impact of forming operation. Cyclic material properties are derived from Vickers hardness to estimate fatigue life with the Local Strain Approach using the damage parameter PSWT. Fatigue life estimation with failure criterion crack initiation obtained from simulation results is compared to those from experiments. The results obtained indicate that the Local Strain Approach is suitable for fatigue life estimations of clinched joints under constant amplitude loading as long as the influence of the forming process is considered.

scholarly journals Clinching in In-situ CT – Experimental Study on Suitable Tool Materials

2021 ◽  
Author(s):  
Daniel Köhler ◽  
Robert Kupfer ◽  
Juliane Troschitz ◽  
Maik Gude
Keyword(s):  
Lightweight Design ◽  
Tool Material ◽  
Single Step ◽  
Ex Situ ◽  
Destructive Testing ◽  
Cold Forming ◽  
High Attenuation ◽  
Tool Materials ◽  
Suitable Tool

In lightweight design, clinching is a cost-efficient solution as the joint is created through localized cold-forming of the joining parts. A clinch point’s quality is usually assessed using ex-situ destructive testing methods. These, however, are unable to detect phenomena immediately during the joining process. For instance, elastic deformations reverse and cracks close after unloading. In-situ methods such as the force-displacement evaluation are used to control a clinching process, though deviations in the clinch point geometry cannot be derived with this method. To overcome these limitations, the clinching process can be investigated using in-situ computed tomography (in-situ CT). However, a clinching tool made of steel would cause strong artefacts and a high attenuation in the CT measurement, reducing the significance of this method. Additionally, when joining parts of the same material, the sheet-sheet interface is hardly detectable. This work aims at identifying, firstly, tool materials that allow artefact-reduced CT measurements during clinching, and, secondly, radiopaque materials that can be applied between the joining parts to enhance the detectability of the sheet-sheet interface. Therefore, both CT-suitable tool materials and radiopaque materials are selected and experimentally investigated. In the clinching process, two aluminium sheets with radiopaque material in between are clinched in a single-step (rotationally symmetric joint without cut section). It is shown that e.g. silicon nitride is suited as tool material and a tin layer is suitable to enhance the detectability of the sheet-sheet interface.

scholarly journals Geometric Multi-Model Fitting by Deep Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 10081-10082
Author(s):  
Zongliang Zhang ◽  
Hongbin Zeng ◽  
Jonathan Li ◽  
Yiping Chen ◽  
Chenhui Yang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Model Fitting ◽  
Simulated Data ◽  
Point Clouds ◽  
Sequential Decision ◽  
Optimal Decisions ◽  
Best Fitting ◽  
Point Set

This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e.g., laser scanned point clouds). We formulate multi-model fitting problem as a sequential decision making process. We then use a deep reinforcement learning algorithm to learn the optimal decisions towards the best fitting result. In this paper, we have compared our method against the state-of-the-art on simulated data. The results demonstrated that our approach significantly reduced the number of fitting iterations.

Efficient Manufacturing Methods for Hybrid Metal-Polymer Components

2016 ◽  
Author(s):  
Dirk Landgrebe ◽  
Roland Müller ◽  
Rico Haase ◽  
Peter Scholz ◽  
Matthias Riemer ◽  
...  
Keyword(s):  
Injection Molding ◽  
Lightweight Design ◽  
Hybrid Process ◽  
Forming Process ◽  
Cold Forming ◽  
Future Production ◽  
Process Chains ◽  
The Right ◽  
Efficient Manufacturing ◽  
Metal Polymer

Lightweight design for automotive applications gains more and more importance for future products, independent from the powertrain concept. One of the key issues in lightweight design is to utilize the right material for the right application using the right value at the right place. This results irrevocably in a multi-material design. In order to increase the efficiency in manufacturing car components, the number of single parts in a component is decreased by increasing the complexity. Examples for the state of the art are tailored welded blanks in cold forming, tailored tempering in press hardening or metallic inlays in injection molding of polymers. The challenge for future production scenarios of multi-material components is to combine existing technologies for metal- and polymer-based applications in efficient hybrid process chains. This paper shows initial approaches of hybrid process chains for efficient manufacturing of hybrid metal-polymer components. These concepts are feasible for flat as well as for tubular applications. Beside the creation of the final geometric properties of the component by a forming process, integrated joining operations are increasingly required for the efficiency of the production process and the performance characteristics of the final component. Main target of this production philosophy is to create 100% ready-to-install components. This is shown in three examples for hybrid process combinations. The first example deals with the combination of metal forming and injection molding of polymers. Example number two is the application of hybrid metal-polymer blanks. Finally, example number three shows the advantages of process integrated forming and joining of single basic components.

scholarly journals Multidisciplinary Design Optimization of Crankshaft Structure Based on Cooptimization and Multi-Island Genetic Algorithm

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Jian Liu ◽  
Gaoyuan Yu ◽  
Yao Li ◽  
Hongmin Wang ◽  
Wensheng Xiao
Keyword(s):  
Genetic Algorithm ◽  
Multiobjective Optimization ◽  
Design Method ◽  
Angular Displacement ◽  
Lightweight Design ◽  
Reliability Optimization ◽  
Data Sampling ◽  
Deterministic Optimization ◽  
Experimental Scheme ◽  
Pareto Optimal Set

The feasibility design method with multidisciplinary and multiobjective optimization is applied in the research of lightweight design and NVH performances of crankshaft in high-power marine reciprocating compressor. Opt-LHD is explored to obtain the experimental scheme and perform data sampling. The elliptical basis function neural network (EBFNN) model considering modal frequency, static strength, torsional vibration angular displacement, and lightweight design of crankshaft is built. Deterministic optimization and reliability optimization for lightweight design of crankshaft are operated separately. Multi-island genetic algorithm (MIGA) combined with multidisciplinary cooptimization method is used to carry out the multiobjective optimization of crankshaft structure. Pareto optimal set is obtained. Optimization results demonstrate that the reliability optimization which considers the uncertainties of production process can ensure product stability compared with deterministic optimization. The coupling and decoupling of structure mechanical properties, NVH, and lightweight design are considered during the multiobjective optimization of crankshaft structure. Designers can choose the optimization results according to their demands, which means the production development cycle and the costs can be significantly reduced.

scholarly journals Coverage Path Planning Using Reinforcement Learning-Based TSP for hTetran—A Polyabolo-Inspired Self-Reconfigurable Tiling Robot

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2577 ◽  
Author(s):  
Anh Vu Le ◽  
Prabakaran Veerajagadheswar ◽  
Phone Thiha Kyaw ◽  
Mohan Rajesh Elara ◽  
Nguyen Huu Khanh Nhan
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Coverage Problem ◽  
Pareto Optima ◽  
Entire Area ◽  
Coverage Path Planning ◽  
Different Shapes ◽  
Cleaning Robots ◽  
Policy Optimization ◽  
Least Energy

One of the critical challenges in deploying the cleaning robots is the completion of covering the entire area. Current tiling robots for area coverage have fixed forms and are limited to cleaning only certain areas. The reconfigurable system is the creative answer to such an optimal coverage problem. The tiling robot’s goal enables the complete coverage of the entire area by reconfiguring to different shapes according to the area’s needs. In the particular sequencing of navigation, it is essential to have a structure that allows the robot to extend the coverage range while saving energy usage during navigation. This implies that the robot is able to cover larger areas entirely with the least required actions. This paper presents a complete path planning (CPP) for hTetran, a polyabolo tiled robot, based on a TSP-based reinforcement learning optimization. This structure simultaneously produces robot shapes and sequential trajectories whilst maximizing the reward of the trained reinforcement learning (RL) model within the predefined polyabolo-based tileset. To this end, a reinforcement learning-based travel sales problem (TSP) with proximal policy optimization (PPO) algorithm was trained using the complementary learning computation of the TSP sequencing. The reconstructive results of the proposed RL-TSP-based CPP for hTetran were compared in terms of energy and time spent with the conventional tiled hypothetical models that incorporate TSP solved through an evolutionary based ant colony optimization (ACO) approach. The CPP demonstrates an ability to generate an ideal Pareto optima trajectory that enhances the robot’s navigation inside the real environment with the least energy and time spent in the company of conventional techniques.

scholarly journals Strength of self-piercing riveted Joints with conventional Rivets and Rivets made of High Nitrogen Steel

2021 ◽  
Author(s):  
Benedikt Uhe ◽  
Clara-Maria Kuball ◽  
Marion Merklein ◽  
Gerson Meschut
Keyword(s):  
Stainless Steel ◽  
Joint Strength ◽  
Lightweight Design ◽  
High Strength ◽  
High Nitrogen Steel ◽  
High Nitrogen ◽  
Forming Process ◽  
Cold Forming ◽  
Local Strength ◽  
Nitrogen Steel

The use of high-strength steel and aluminium is rising due to the intensified efforts being made in lightweight design, and self-piercing riveting is becoming increasingly important. Conventional rivets for self-piercing riveting differ in their geometry, the material used, the condition of the material and the coating. To shorten the manufacturing process, the use of stainless steel with high strain hardening as the rivet material represents a promising approach. This allows the coating of the rivets to be omitted due to the corrosion resistance of the material and, since the strength of the stainless steel is achieved by cold forming, heat treatment is no longer required. In addition, it is possible to adjust the local strength within the rivet. Because of that, the authors have elaborated a concept for using high nitrogen steel 1.3815 as the rivet material. The present investigation focusses on the joint strength in order to evaluate the capability of rivets in high nitrogen steel by comparison to conventional rivets made of treatable steel. Due to certain challenges in the forming process of the high nitrogen steel rivets, deviations result from the targeted rivet geometry. Mainly these deviations cause a lower joint strength with these rivets, which is, however, adequate. All in all, the capability of the new rivet is proven by the results of this investigation.

Sign in / Sign up

Export Citation Format

Share Document