Search

Uncertainties in robotic assembly can substantially influence the quality of assembly task planning, often resulting in suboptimal solutions. It is crucial to account for these uncertainties when developing assembly task plans that are both efficient and practical for multi-part products. To address such issues, the proposed method integrates the NelderMead simplex algorithm with the Class Topper Optimisation Algorithm to create a hybrid NelderMead Class Topper Optimisation Algorithm. This study uses a vibration generator as an example to illustrate the application of the proposed method. Ensuring tool accessibility is emphasised, and the assembly tasks are initialised accordingly. The feasibility of these tasks is determined using liaison and tool-integrated geometric feasibility predicate analysis. Multiple criteria are considered to achieve the most efficient robotic assembly task planning, including part reorientation, gripper or tool change and the energy required to assemble the part. The effectiveness and robustness of the proposed optimisation algorithm are demonstrated by comparing it with other algorithms, such as the teaching-learning-based algorithm, the genetic algorithm, the bees algorithm and the particle swarm optimisation algorithm. The results have shown that the proposed approach is highly effective for real-industrial relevant problems. [ABSTRACT FROM AUTHOR] more...

Pose estimation is crucial for automating assembly tasks, yet achieving sufficient accuracy for assembly automation remains challenging and part-specific. This paper presents a novel, streamlined approach to pose estimation that facilitates automation of assembly tasks. Our proposed method employs deep learning on a limited number of annotated images to identify a set of keypoints on the parts of interest. To compensate for network shortcomings and enhance accuracy we incorporated a Bayesian updating stage that leverages our detailed knowledge of the assembly part design. This Bayesian updating step refines the network output, significantly improving pose estimation accuracy. For this purpose, we utilized a subset of network-generated keypoint positions with higher quality as measurements, while for the remaining keypoints, the network outputs only serve as priors. The geometry data aid in constructing likelihood functions, which in turn result in enhanced posterior distributions of keypoint pixel positions. We then employed the maximum a posteriori (MAP) estimates of keypoint locations to obtain a final pose, allowing for an update to the nominal assembly trajectory. We evaluated our method on a 14-point snap-fit dash trim assembly for a Ford Mustang dashboard, demonstrating promising results. Our approach does not require tailoring to new applications, nor does it rely on extensive machine learning expertise or large amounts of training data. This makes our method a scalable and adaptable solution for the production floors. more...

In the automotive industry, efficient handling of small and irregular components is imperative for production optimization. Traditional methods involving labor or robotic systems can lead to increased costs. The research introduces an innovative, dynamic gating system, integrating a camera module with computing intelligence to process images and orient parts effectively in linear feeders. Theoretical and experimental results validate the most preferred orientation, with orientations 1 and 2 from group 1 identified as the optimum resting positions. The use of both the Markov model and a hidden Markov model in trap module design yields a robust outcome, effectively attaining the necessary part orientation. The dynamic part feeding system is optimized for frequencies of 45 and 50 Hz with trap angles of 30° from the experimental study. The study quantifies efficiency gains, demonstrating that the proposed system outperforms manual or robotic methods. This study offers a quantitative and comprehensive solution for assembling and packaging small and irregular components in the automotive sector. [ABSTRACT FROM AUTHOR] more...

The recent advances in Industry 4.0 have promoted manufacturing industries towards the use of augmented reality (AR), virtual reality (VR), and mixed reality (MR) for visualization and training applications. AR assistance is extremely helpful in assembly task visualization during the stages of product assembly and in disassembly plan visualization during the repair and maintenance of a product/system. Generating such assembly and disassembly task animations consume a lot of time and demands skilled user intervention. In assembly or disassembly processes, each operation must be validated for geometric feasibility regarding its practical implementation in the real-time product. In this manuscript, a novel method for automated assembly task simulation with improved geometric feasibility testing is proposed and verified. The proposed framework considers the assembly sequence plan as input in the form of textual instructions and generates a virtual assembly task plan for the product; furthermore, these instructions are used to ensure there are no collisions using a combination of multiple linear directions. Once the textual instructions achieve geometric feasibility for the entire assembly operation, the visual animations of the assembly operations are successively produced in a game engine and are integrated with the AR platform in order to visualize them in the physical environment. The framework is implemented on various products and validated for its correctness and completeness. [ABSTRACT FROM AUTHOR] more...

Machine vision systems are widely used in assembly lines for providing sensing abilities to robots to allow them to handle dynamic environments. This paper presents a comparison of 3D sensors for evaluating which one is best suited for usage in a machine vision system for robotic fastening operations within an automotive assembly line. The perception system is necessary for taking into account the position uncertainty that arises from the vehicles being transported in an aerial conveyor. Three sensors with different working principles were compared, namely laser triangulation (SICK TriSpector1030), structured light with sequential stripe patterns (Photoneo PhoXi S) and structured light with infrared speckle pattern (Asus Xtion Pro Live). The accuracy of the sensors was measured by computing the root mean square error (RMSE) of the point cloud registrations between their scans and two types of reference point clouds, namely, CAD files and 3D sensor scans. Overall, the RMSE was lower when using sensor scans, with the SICK TriSpector1030 achieving the best results (0.25 mm ± 0.03 mm), the Photoneo PhoXi S having the intermediate performance (0.49 mm ± 0.14 mm) and the Asus Xtion Pro Live obtaining the higher RMSE (1.01 mm ± 0.11 mm). Considering the use case requirements, the final machine vision system relied on the SICK TriSpector1030 sensor and was integrated with a collaborative robot, which was successfully deployed in an vehicle assembly line, achieving 94% success in 53,400 screwing operations. [ABSTRACT FROM AUTHOR] more...

Digital simulation tools are used throughout the entire product development cycle, from designing components using finite element methods to simulating their assembly and planning their production. Especially in research, physics simulators and engines such as MuJoCo are increasingly used for rapid data generation in training machine learning models. The quality of the training data is crucial for successful training and the subsequent deployment of the models in real-world applications. The presented work reports on a systematic benchmark of the physics engine MuJoCo. Representative processes in robotic assembly applications are carried out in simulation and on a physical testbed. The results are compared, focusing on the robot arm's pose and the acting contact forces during the assembly processes using Minimal Jump Cost. Subsequently, a deep reinforcement learning agent takes over the simulation's parameterization, and a first comprehensive system for the process-specifc training of simulation parameters is developed and evaluated to increase the data quality and to partially encapsulate the setup effort involved in digital simulation, aiding offline design and validation. The approach results in overall 8% less dissimilar simulations but not in all the individual scenarios. [ABSTRACT FROM AUTHOR] more...

High-performance physics simulation environments are an excellent option to simulate robot-based assembly processes for training faster-than-real-time and providing the necessary data. However, since established physics engines are rigid multi-body simulators at their core, they cannot simulate the deformation process during the assembly of control cabinet terminals. Thus, appropriate extensions of the simulation are necessary. This paper introduces and evaluates extensions incorporating physical joining models to simulate the snap-fit assembly in electrical cabinets. The presented results showed that the extensions can provide input data of high accuracy for the joining models. In this way, they empower the generation of valid training data for snap-fit assembly from standard rigid body simulations. [ABSTRACT FROM AUTHOR] more...

Novel approaches to robot programming using advanced combinations of Machine Learning and simulation can flexibly adapt to changes and offer promising solutions, even to complex tasks such as assembly. However, feasible training data must model the underlying assembly process adequately. Therefore, detailed physical process models are needed, to increase the accuracy of the simulation. The presented work focusses on data-driven physical models for the prediction of joining forces during the assembly of snap-fits in electrical cabinet assembly using Machine Learning. State-of-the-art Linear Regression models and Deep Neural Networks are trained using data from a physical experimental setup as well as evaluated and compared afterwards. [ABSTRACT FROM AUTHOR] more...

Recent advances in Machine Learning introduce promising solutions for the so-called intelligent automation. Learning robot control offline in a physics simulation environment presents one suitable approach, even for complex assembly tasks with high variance in the products to be manufactured. Beside the continuous development and improvement of efficient learning algorithms, the synthetically generation of feasible training data is of crucial importance. Therefore, this paper focuses on defining and evaluating analytical process models for the assembly of electrical cabinet terminals. Using the geometric and material product data, the predicted assembly forces are described mathematically as a function of the joining path. The presented work covers the development, evaluation and validation of accurate joining models for snap hook-based assembly which in a subsequent step can be implemented in any suitable state of the art physics simulation. [ABSTRACT FROM AUTHOR] more...

To reduce human intervention in the process of manually teaching assembly sequences to industrial robots, we developed an automated sequence planning method using only a 3D CAD model. In the proposed method, first, to find an assembly sequence for many parts, a genetic algorithm generates the initial chromosome based on interference, rather than merely generating a randomized initial chromosome. Second, to generate an assembly sequence satisfying the preferred insertion condition (e.g. male–female parts), we calculate an insertion matrix indicating the insertion relations between the parts. In this paper, the preferred insertion condition is defined as requiring a part with holes to be prepared first, and then other parts are inserted into the holes. In our experiments on assembly sequence generation both with and without the proposed methods, the proposed method was able to generate an assembly sequence for a product composed of 32 parts. The proposed method generated a feasible sequence every time (30 successes in 30 trials) and a preferable sequence, such as fixing by a screw after assembling the fixed part. These results demonstrate the usefulness of the proposed chromosome initialization method and the use of insertion matrices. [ABSTRACT FROM AUTHOR] more...

Insulated faux brick (IFB) is an improvement on traditional faux brick that aims to further reduce weight and installation time while providing insulation characteristics beyond traditional brick. Current production of insulated faux corner bricks relies on human workers to apply adhesive and press together two end pieces until the adhesive has dried. This is a time-consuming step which is not easily scalable to higher production rates. This research explored potential automated solutions to meet the ever-increasing demand. Specifically, the concept discussed in this paper uses a modular array of joining units that can be repeated to achieve the desired scale of production. This concept was verified through the construction of a beta prototype containing two joining units and a low-cost glue dispensing system to service both units. The prototype was operated continuously with an average throughput greater than two bricks per minute and with similar quality to the manual process. Based on a critical path analysis, a production system with eight joining units based on the same modular architecture has the potential for a threefold increase in production rate per worker. [ABSTRACT FROM AUTHOR] more...

Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated capability assessment, mainly leveraged by deep learning systems driven from 3D CAD data, have been presented. Current assessment systems may be able to assess CAD data with regards to abstract features, e.g. the ability to automatically separate components from bulk goods, or the presence of gripping surfaces. Nevertheless, they suffer from the factor of black box systems, where an assessment can be learned and generated easily, but without any geometrical indicator about the reasons of the system's decision. By utilizing explainable AI (xAI) methods, we attempt to open up the black box. Explainable AI methods have been used in order to assess whether a neural network has successfully learned a given task or to analyze which features of an input might lead to an adversarial attack. These methods aim to derive additional insights into a neural network, by analyzing patterns from a given input and its impact to the network's output. Within the NeuroCAD Project, xAI methods are used to identify geometrical features which are associated with a certain abstract feature. Within this work, a sensitivity analysis (SA), the layer-wise relevance propagation (LRP), the Gradient-weighted Class Activation Mapping (Grad-CAM) method as well as the Local Interpretable Model-Agnostic Explanations (LIME) have been implemented in the NeuroCAD environment, allowing not only to assess CAD models but also to identify features which have been relevant for the network's decision. In the medium run, this might enable to identify regions of interest supporting product designers to optimize their models with regards to assembly processes. [ABSTRACT FROM AUTHOR] more...

Deadlock resolution has been an important research topic in the field of automated manufacturing systems (AMSs). Researchers generally assume that AMS resources never break down whereas only a few resolve the issues of resource failures in the discrete-event supervision of AMSs. In fact, an AMS consists of a number of numerically controlled machines interacting with each other. The failure of resources happens unexpectedly. In this article, we allow parallel routes to use unreliable resources. Because of their powerful modeling capabilities, Petri nets are used to model the considered AMSs. By using a look-ahead control strategy, a robust supervisory control policy is developed for AMSs with assembly operations allowing resource failures. Our objective is to advance parts requiring failed resources in their remaining routes into a special position so as to release shared resources in case some unreliable resources fail. Consequently, those parts not necessarily requiring any failed resource can keep progressing all the time. The conventional methods are on the basis of monolithic and structure-oriented control specifications with centralized supervisors. Our policy can be implemented in a distributed, online, and local way. Several examples are given to elucidate our control policy clearly. Note to Practitioners—In automated manufacturing systems (AMSs), resources such as machines and tools with higher reliablity are always expensive. Sometimes, when it is not cost-effective to use resources with higher reliability, manufacturers may choose some resources with possible failures. These resources are thus considered as unreliable ones in our article. Normally, unreliable resources may fail unexpectedly. Their occurrences can lead a system to stagnation, causing unnecessary downtime, and bringing economic loss to enterprises. To resolve such stagnation issues, we develop a robust supervisory control policy to synthesize a robust liveness-enforcing supervisor for AMSs with assembly operations and unreliable resources. The supervisor can guarantee that a controlled system continues to progress without deadlock and blocking states even if some unreliable resources fail to work. [ABSTRACT FROM AUTHOR] more...

Aiming for a higher economic efficiency in manufacturing, an increased degree of automation is a key enabler. However, assessing the technical feasibility of an automated assembly solution for a dedicated process is difficult and often determined by the geometry of the given product parts. Among others, decisive criterions of the automation feasibility are the ability to separate and isolate single parts or the capability of component self-alignment in final position. To assess the feasibility, a questionnaire based evaluation scheme has been developed and applied by Fraunhofer researchers. However, the results strongly depend on the implicit knowledge and experience of the single engineer performing the assessment. This paper presents NeuroCAD, a software tool that automates the assessment using voxelization techniques. The approach enables the assessment of abstract and production relevant geometries features through deep-learning based on CAD files. [ABSTRACT FROM AUTHOR] more...

Purpose. Design, manufacture and test the assembly tools for the self-drilling screws. Devices meet the requirements of hard location the screw, based on the outer diameter of the thread, the inner diameter of the thread or jig bushing, while at the end of the screwing, holding elements pass the head of the screw. Design/methodology/approach. In a paper it is shown that thread-forming screws, known as self-tapping screws capable of forming or rolling a matching thread into the material into which they are installed requires a hard location of the screw in device to prevent action the radial component of the cutting force. And at the same time devices, that meet the requirements of hard location the screw in the locator, at the end of the screwing let the screw head through them. The presented devices hold the screws for the outer diameter of the thread, the inner diameter of the thread or jig bushing. A device designed to align hex parts, such as screw heads, is also described. Such devices are designed for automated production. Findings. The developed devices were manufactured and tested. Self-drilling screws drilled holes under the action of axial load, maintaining the correct position and with a free passage of the screw head at the end of drilling. Two of the devices presented are protected by copyright. Originality/value. In the presented devices assembly with the use of self-drilling forming screws consists in the sequential execution of two diverse operations - first drilling, and then rolling the thread under the action of axial load. In this case, the device rigidly bases the screw, but let the screw head pas sat at the end of drilling. Developed devices can be used in assembly automation more...

Current production systems are required to stay up-to-date with the changing market conditions. To date, most conventional flexible systems are dependent on human flexibility. However, the demand for flexible automation systems is increasing because of rising labor costs and higher quality requirements, even in emerging countries. To implement automation systems in the unpredictable market, cost reduction is essential to reduce the investment risk. However, there is no systematic design method for reducing the cost of automation systems. Thus, in this study, we propose a new method for the design of material handling systems, wherein the waiting time of the equipment is reduced by grouping the operations and allocating certain equipment to each group. The proposed design method uses a genetic algorithm to determine the optimal grouping of operations on the basis of the equipment cost and cycle time. The design method is then applied to an automobile engine control unit to verify its effectiveness. more...

The presentation on SIGMA robot for assembly by A. d'Auria at the 7th International Symposium on Industrial Robots (ISIR) held in Tokyo in October 1977 made an immense impact on engineers studying assembly automation in Japan. The 1970s witnessed the shift fromthemass production of a few types to limited production of a wide variety of products in Japan, and research started for a production system with a quick response to a given type of products and change in a quantity of production. Professor Hiroshi Makino of Yamanashi University was stimulated by SIGMA and got an idea for a robot with Selective Compliance Assembly Robot Arms (SCARA) and started working on the design for prototype 1 two months after the presentation. Further, he organized the SCARA Robot Consortium with Yamanashi University and thirteen domestic companies for three years, from April 1978 to March 1981, and had success in the development and spread of the SCARA robot in the assembly work. After the 1980s, the SCARA robot became one of the de facto standards of industrial robots in the world. In 2019, it is estimated that the SCARA robots will compromise 30% or more of industrial robots working all over the world. The author was one member of a research group as an associate professor, in Yamanashi University, and believes that it is extremely effective to discuss the needs for research and development of the SCARA robot and technological solutions thirty years after the establishment of JRM. [ABSTRACT FROM AUTHOR] more...

Copyright of Mechanics & Advanced Technologies is the property of National Technical University of Ukraine KPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) more...

The paradigm shift from mass production to mass customisation and reduced product lifecycles requires continuous re-engineering/configuration of modern manufacturing systems. Although efforts are being made to design and build manufacturing systems based on the paradigms of changeability, reconfigurability, and flexibility, the knowledge of the system's capability remains unstructured and isolated from product design and engineering tools. As a result, introducing product design changes are costly, time-consuming and error-prone. To address this problem, this research utilises a Product, Process, and Resource (PPR) ontology with a view to supporting changes through information integration and knowledge generation. The approach moves away from product-centric tools such as Product Lifecycle Management (PLM) and thus a heterarchical model of the system is created. The contribution of this work is to demonstrate how modular ontologies can be utilised in a practical and industrially relevant manner by integrating the data structure of a set of component-based virtual engineering tools into the Resource domain. The research presents a proof-of-concept of the proposed approach using an automated engine assembly station as a case study. Inferences are made from explicit knowledge through rules and mapping as to whether both Product and Process requirements are met by Resource domain capabilities. The approach used in this work has the potential to significantly improve the workflow as and when new products are introduced or modifications need to be made as the scope of change can be assessed rapidly resulting in more focused engineering and design work. [ABSTRACT FROM AUTHOR] more...

In this paper, a novel and efficient method is developed and proposed to obtain all valid assembly sequences and optimized assembly sequence for a given assembled product. The working principle of methodology is clearly illustrated with different example products. Four basic predicates namely "liaison predicate, geometrical feasibility, mechanical feasibility, and stability" are considered to validate each sequence. The proposed method is effective and proven efficient in the resulting all set of feasible assembly sequences described. Tool/gripper changes, assembly orientation changes, and part trajectory distances are considered to state the optimality of a valid assembly sequence. Achieving optimized assembly sequence through the proposed method for user-defined objective function is briefly illustrated. The computational performance of the method in achieving all valid assembly sequences is illustrated for various dissimilar products. [ABSTRACT FROM AUTHOR] more...

Most of the mass production industries use automated system for manufacturing and assembling the parts. The problem arises in the implementation of automated system for handling small irregular shaped parts due to its irrespective nature of orientation. To overcome this problem, industries have used manual orientation method, industrial robots, and vision system, but these methods increase the investment cost and production cost. Linear vibratory feeders are used to handle the irregular shaped parts and the set up in which the feeders use gates (or) obstacles and convert them from any orientation into preferred orientation of the part is known as trap. The preferred orientation of the part is found by using drop test and theoretical method. Trap is designed in such a way that preferred orientation should be the outcome from the feeder. Critical orientations of the part are experimented and analyzed using stability method, centroid solid angle method, and the gate for the trap is designed by the Markov chain analysis. Part motion time plays a major role in automated systems, and hence, it is optimized by experimental investigation and dynamic simulation. This research provides a better understanding of the orientation analysis of rocker arm, which is used for actuating inlet and outlet valves of engine. [ABSTRACT FROM AUTHOR] more...

Basic types of auxiliary drives in automated assembly systems are compared in terms of generalized characteristics. Regulation of the pneumatic drive by means of servomechanical positioning systems is considered. Diagrams are presented for assessment of the mean velocities and travel times of mechatronic modules in the angular positioning of loading drives on the basis of kinematic and mechanical characteristics. [ABSTRACT FROM AUTHOR] more...