Assembly Sequence Planning Using Artificial Neural Networks for Mechanical Parts Based on Selected Criteria

Suszyński, Marcin; Peta, Katarzyna

doi:10.3390/app112110414

Cited by 15 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, a measuring device is used which resembles the human body in its mechanical properties [15]. Testing the permissible stress level according to existing standards requires the measurement, analysis, and evaluation of the maximum collision force and the local maximum pressure occurring in the plane of collision [16].…”

Section: Design Of Measurement Methodologymentioning

confidence: 99%

Force and Pressure Dependent Asymmetric Workspace Research of a Collaborative Robot and Human

Ponikelský,

Chalupa,

Černohlávek

et al. 2024

Symmetry

View full text Add to dashboard Cite

This article discusses creating a methodology for the asymmetric measuring of values and processes of collision forces and pressures of the collaborative robot dependent on time. Furthermore, it verifies the usefulness of this methodology in practice by successfully performing the experimental measurement and verifying the possibility of using these results by analysing and stating the collaboration level for a robot of the given type. According to the suggested methodology, the measurement results are a specific output based on real measured data, which can be easily rated and can quickly determine the collaborative level of any robot. Measurements were aimed at determining the values of pressure and force with which the robot acts at certain speeds related to distance from the base. Due to the controlled symmetrical impact of the robot on the measuring device, the transfer of energy from the robot to the human body was guaranteed. In theoretical terms, this article primarily provides the assembly of the theoretical foundation of the collaborative environment between humans and robots, and a comprehensive overview of the possibilities of using the technical specification ISO/TS 15066:2016 when deploying a robot in collaboration with humans in a collaborative environment. This new information is highly valuable for both manufacturers and users of collaborative robots. The presented article analyses the possibilities of measuring collaboration and safety elements in cooperation with a robot. The most significant practical benefit is the presentation of a methodology for measuring robot collaboration and verifying its functionality by conducting experimental measurements of robot collaboration according to this methodology. The measurement was performed on a robot made by Universal Robots, model UR10. The measurement coordinates were stationed in a way to create a spatial measurement model. Boundary coordinates of the spatial model were as follows: [450; 200], [450; 500], [850; 200], and [850; 500]. Collisions were measured at 8 different speeds for each coordinate (20 mms−1, 50 mms−1, 100 mms−1, 200 mms−1, 250 mms−1, 300 mms−1, 350 mms−1, and 400 mms−1) to enable the observation of changes in accordance with speed. The measured values indicate a significant fact: the closer the collision is to the robot’s base, the higher the collision forces. An important aspect is that the measured values were only for speeds up to 400 mms−1, which is a very low value for industrial use to meet the desired cycle time. It can be stated with absolute certainty that speed has the greatest impact on collision force values. The speed of the collaborative robot arm can therefore be considered a limiting factor for use in industrial applications with a requirement of a short cycle time. Focusing on the results of the measured values, it can be stated that a new finding is the correct design of robotic movements in relation to possible contact with humans is crucial. The result of the measurement according to the proposed methodology is a specific output of realistically measured data, which can be easily evaluated and the level of collaboration of any robot can be quickly determined. The measured data will also serve as a basis for further processing and preparation of new simulation software. It will be possible to use the intended software for detecting and predetermining the safe asymmetric movements of the collaborative robot already at the stage of production preparations, unlike the method of measuring force and pressure on robots which can be used until the time of implementation into production. In the future, this software may also allow users of collaborative robots to easily and quickly evaluate the robots specified.

show abstract

Section: Design Of Measurement Methodologymentioning

confidence: 99%

Force and Pressure Dependent Asymmetric Workspace Research of a Collaborative Robot and Human

Ponikelský,

Chalupa,

Černohlávek

et al. 2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…Optimization procedures were applied to update these coefficients, minimizing the error between the network’s predictions and experimental outputs. This optimization process involved the sum of squares (SOS) and utilized the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm to expedite and stabilize convergence, as established by Suszyński and Peta [ 29 ] and Stojić et al [ 30 ]. Coefficients of determination served as parameters to assess the performance of the resulting ANN model.…”

Section: Methodsmentioning

confidence: 99%

Unlocking the Potential of the ANN Optimization in Sweet Potato Varieties Drying Processes

Šovljanski,

Lončar,

Pezo

et al. 2023

Foods

View full text Add to dashboard Cite

This study explores the unexploited potential of Artificial Neural Network (ANN) optimization techniques in enhancing different drying methods and their influence on the characteristics of various sweet potato varieties. Focusing on the intricate interplay between drying methods and the unique characteristics of white, pink, orange, and purple sweet potatoes, the presented experimental study indicates the impact of ANN-driven optimization on food-related characteristics such as color, phenols content, biological activities (antioxidant, antimicrobial, anti-hyperglycemic, and anti-inflammatory), chemical, and mineral contents. The results unveil significant variations in drying method efficacy across different sweet potato types, underscoring the need for tailored optimization strategies. Specifically, purple sweet potatoes emerge as robust carriers of phenolic compounds, showcasing superior antioxidant activities. Furthermore, this study reveals the optimized parameters of dried sweet potato, such as total phenols content of 1677.76 mg/100 g and anti-inflammatory activity of 8.93%, anti-hyperglycemic activity of 24.42%. The upgraded antioxidant capability is presented through DPPH●, ABTS●+, RP, and SoA assays with values of 1500.56, 10,083.37, 3130.81, and 22,753.97 μg TE/100 g, respectively. Additionally, the moisture content in the lyophilized sample reached a minimum of 2.97%, holding favorable chemical and mineral contents. The utilization of ANN optimization proves instrumental in interpreting complex interactions and unlocking efficiencies in sweet potato drying processes, thereby contributing valuable insights to food science and technology.

show abstract

“…The challenge has been addressed by embracing meta-heuristic techniques such as the firefly algorithm, 13 genetic algorithm, [14][15][16] ant colony optimization, [17][18][19] particle swarm optimization, 20 immune algorithm, 21 and neural network. 22 3D CAD models based on assembly products have become prevalent in manufacturing. The concept of assembly by disassembly is increasingly widespread due to its ability to obtain optimal feasible ASP with relatively less time.…”

Section: Introductionmentioning

confidence: 99%

“…The challenge has been addressed by embracing meta-heuristic techniques such as the firefly algorithm, 13 genetic algorithm, 14–16 ant colony optimization, 17–19 particle swarm optimization, 20 immune algorithm, 21 and neural network. 22…”

Section: Introductionmentioning

confidence: 99%

Optimal assembly sequence planning with tool uncertainties

Champatiray

Bahubalendruni

Mahapatra

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Developing a practical and feasible assembly sequence plan for industrial applications is still challenging during product design and planning. Because of the need for more consideration of practical uncertainties, most of the assembly sequence plans generated by planners are inapplicable to real industrial-based problems. We have considered a crucial practical uncertainty attribute, tool uncertainties, in the current research. A novel approach has been proposed to generate optimal robotic assembly sequence plans by combining tool accessibility and part geometry. This research introduces two essential assembly tool accessibility attributes: tool-integrated geometric feasibility and tool-swept volume. In addition, the automatic extraction of tool accessibility attributes has been proposed. The proposed method is explained with a proper model and essential details such as liaison data, tool-integrated bounding box coordinates, tool-integrated geometric feasibility, and tool-swept volume data. Finally, the practical feasibility of the proposed method is verified for a different product configuration.

show abstract

Assembly Sequence Planning Using Artificial Neural Networks for Mechanical Parts Based on Selected Criteria

Cited by 15 publications

References 19 publications

Force and Pressure Dependent Asymmetric Workspace Research of a Collaborative Robot and Human

Force and Pressure Dependent Asymmetric Workspace Research of a Collaborative Robot and Human

Unlocking the Potential of the ANN Optimization in Sweet Potato Varieties Drying Processes

Optimal assembly sequence planning with tool uncertainties

Contact Info

Product

Resources

About