| 1. |
- Pettersson, Julius, 1994, et al.
(författare)
-
Cognitive Ability Evaluation using Virtual Reality and Eye Tracking
- 2018
-
Ingår i: 2018 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND VIRTUAL ENVIRONMENTS FOR MEASUREMENT SYSTEMS AND APPLICATIONS (CIVEMSA). - : IEEE. - 2377-9314. - 9781538646182 - 9781538646182
-
Konferensbidrag (refereegranskat)abstract
- This work aims to create a virtual reality (VR) representation of Ravens progressive matrices (RPM) and apply available eye tracking (ET) technology to determine where the test person's eye gaze is located during the test. RPM are developed to evaluate abstract reasoning and there is a possibility to further understand the mental processes of the test person by adding ET. The result of this project is a test scenario where the user completes ten tasks from RPM in a VR environment. Reports containing heat maps and trajectories describing the eye gaze together with times and results of the tasks are automatically generated after the test has been completed. This extended information which is automatically gathered is meant to further expand the toolbox that psychologists use when performing psychological testing and might aid them in improving the accuracy of the results obtained from these tests.
|
|
| 2. |
- Albo, Anton, 1991, et al.
(författare)
-
A framework concept for data visualization and structuring in a complex production process
- 2019
-
Ingår i: Procedia Manufacturing. - : Elsevier BV. - 2351-9789. ; 38, s. 1642-1651
-
Konferensbidrag (refereegranskat)abstract
- This paper provides a concept study for a visual interface framework together with the software Sequence Planner for implementation on a complex industrial process for extracting process information in an efficient way and how to make use of a lot of data to visualize it in a standardized human machine interface for different user perspectives. The concept is tested and validated on a smaller simulation of a paint booth with several interconnected and supporting control systems to prove the functionality and usefulness in this kind of production system. The paper presents the resulting five abstraction levels in the framework concept, from a production top view down to the signal exchange between the different resources in one production cell, together with additional features. The simulation proves the setup with Sequence Planner and the visual interface to work by extract and present process data from a running sequence.
|
|
| 3. |
- Andersson, Alf, et al.
(författare)
-
Inline Process Control – a concept study of efficient in-line process control and process adjustment with respect to product geometry
- 2016
-
Ingår i: Swedish Production Symposium 2016 SPS 2016. - Lund, Sweden.
-
Konferensbidrag (refereegranskat)abstract
- All manufacturing processes have variation which may violate the fulfillment of assembly, functional, geometrical or esthetical requirements and difficulties to reach desired form in all areas. The cost for geometry defects rises downstream in the process chain. Therefore, it is vital to discover these defects as soon as they appear. Then adjustments can be done in the process without losing products or time. In order to find a solution for this, a project with the overall scope “development of an intelligent process control system” has been initiated. This project consists of five different work packages: Inline measurement, Process Evaluation, Corrective actions, Flexible tooling and demonstrator cell. These work packages address different areas which are necessary to fulfill the overall scope of the project. The system shall both be able to detect geometrical defects, propose adjustments and adjust simple process parameters. The results are demonstrated in a demo cell located at Chalmers University of Technology. In the demonstrator all the different areas have been verified in an industrial case study – assembly of GOR Volvo S80. Efficient offline programming for robot based measurement, efficient process evaluation based on case base reasoning (CBR) methodology, flexible fixtures and process adjustments based on corrective actions regarding in going part positioning.
|
|
| 4. |
- Bergagård, Patrik, 1984, et al.
(författare)
-
Modeling and automatic calculation of restart states for an industrial windscreen mounting station
- 2015
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 48:3, s. 1030-1036
-
Konferensbidrag (refereegranskat)abstract
- The production in an automated manufacturing system will not always progress as intended. A wide variety of possible faults may cause errors that lead to an unsynchronization between the control system and the physical system that consequently lead to production stoppages. The common industrial practice to deal with such non-intended progress is to extend the control system with tailor-made solutions to account for errors. This extension is both time consuming and there is no guarantee that all relevant errors are handled.This paper models the control system to enable automatic derivation of restart states applied to an existing station for automatic mounting of windscreens onto car bodies. These restart states are states in the control system where it is correct to resynchronize the control and the physical systems so that the automated production can be resumed. This aids the preparation phase by letting the developer focus on modeling the nominal production and on specifying (un-)desired behavior during the restarted production, and then automatically retrieve the restart states for all control states. The online restart process is then reduced to a semi-automatic process where an operator can be supported with instructions for how to correctly resynchronize the control and the physical systems in a selected restart state.
|
|
| 5. |
- Dahl, Martin, 1984, et al.
(författare)
-
Automatic modeling and simulation of robot program behavior in integrated virtual preparation and commissioning
- 2017
-
Ingår i: Procedia Manufacturing. - : Elsevier BV. - 2351-9789. ; 11, s. 284-291
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a method where the behavior of a robot cell is automatically modeled based on existing robot programs and a simulation model of the cell. Robot programs from the shop floor are uploaded into a virtual manufacturing tool, and a formal model is then generated from the robot programs. Then, control logic is automatically calculated, and the fastest possible execution order is found by using the generated model to formulate an optimization problem. The result is continuously analyzed and validated by simulation in the virtual manufacturing tool.
|
|
| 6. |
- Dahl, Martin, 1984, et al.
(författare)
-
Control components for Collaborative and Intelligent Automation Systems
- 2019
-
Ingår i: IEEE International Conference on Emerging Technologies and Factory Automation, ETFA. - 1946-0759 .- 1946-0740. ; 2019-September, s. 378-384
-
Konferensbidrag (refereegranskat)abstract
- Collaborative and intelligent automation systems need intelligent control systems. Some of this intelligence exist on a per-component basis in the form of vision, sensing, motion, and path planning algorithms. To fully take advantage of this intelligence, also the coordination of subsystems need to exhibit intelligence. While there exist middleware solutions that eases communication, development, and reuse of such subsystems, for example the Robot Operating System (ROS), good coordination also requires knowledge about how control is supposed to be performed, as well as expected behavior of the subsystems. This paper introduces lightweight components that wraps ROS2 nodes into composable control components from which an intelligent control system can be built. The ideas are implemented on a use case involving collaborative robots with on-line path planning, intelligent tools, and human operators.
|
|
| 7. |
- Dahl, Martin, 1984, et al.
(författare)
-
Integrated Virtual Preparation and Commissioning: supporting formal methods during automation systems development
- 2016
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 49:12, s. 1939-1944
-
Konferensbidrag (refereegranskat)abstract
- Virtual commissioning – the development and validation of industrial control systems against a simulation model – is attracting interest in the automotive industry. The main motivation for its use is that control systems can start to be integrated and tested before the construction of the physical system. In addition to this, the ability to continuously test can lead to increased reliability and enables better coping with late changes. At the same time, using formal methods during production preparation and control system design promise similar benefits. Formal methods however, are not seeing the same surge in interest – they are rarely used in the automotive industry. In this paper a framework is proposed, Integrated Virtual Preparation and Commissioning, where virtual commissioning models are used as a base for preparation and control system implementation assisted by formal methods. The extensive use of simulation in virtual commissioning allows computation results from formal methods to be continuously validated by visual inspection and using existing analysis tools (e.g. collision detection methods). The framework is applied in a case study, where the combination of a simulation model and a formal model is used as an aid in generating operation sequences for validation during production preparation. The resulting formal model can be used to study the behavior of the production system before a control system has been implemented.
|
|
| 8. |
- Dahl, Martin, 1984, et al.
(författare)
-
Sequence Planner: Supporting Integrated Virtual Preparation and Commissioning
- 2017
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 50:1, s. 5818-5823
-
Konferensbidrag (refereegranskat)abstract
- It is essential to understand the operation sequences of a production system when designing or changing it. This paper will demonstrate how the software tool Sequence Planner (SP) not only supports this understanding by sequence visualization, but also improves the solution using optimization and verification. SP is a tool for modeling and analyzing automation systems. The tool has been developed since 2007 with an initial focus on supporting engineers when developing control code for programmable logical controllers. Today, SP is a micro-service architecture, usable in various areas like runtime control, online monitoring, energy optimization, and even emergency department patient planning. This paper presents a use case at an automotive company, where the operation sequences in a large number of automated robot stations, need to be modified. SP, together with virtual commissioning tools, automates this modification by identifying, optimizing, verifying and simulating operation sequences, and then updates the robot and control programs. This use case demonstrates the strength of SP and its architecture and how it is used for integrated virtual preparation and commissioning.
|
|
| 9. |
- Dahl, Martin, 1984, et al.
(författare)
-
Virtual Reality Commissioning in Production Systems Preparation
- 2017
-
Ingår i: IEEE International Conference on Emerging Technologies and Factory Automation, ETFA. - 1946-0740 .- 1946-0759. - 9781509065059
-
Konferensbidrag (refereegranskat)abstract
- Virtual commissioning (VC) is a method used to virtually visualize and test production systems, control logic and material flows. The focus of this paper is to further extend this concept using Virtual Reality (VR). The introduction of VR in VC enhances the concept by adding a more realistic visualization and movement tracking which extends the possibilities of its validation. The changes to the validation aspect are mainly due to the fact that it is now possible to interact with the running virtual production in a realistic and intuitive way. The interaction gives designers and operators a new possibility to go from being observers to actors in the design phase. They are now able to validate the production system, test security protocols and validate the human interaction with the system, using VR.
|
|
| 10. |
|
|
| 11. |
|
|
| 12. |
- Farooqui, Ashfaq Hussain, 1990, et al.
(författare)
-
Error handling within highly automated automotive industry: Current practice and research needs
- 2016
-
Ingår i: IEEE International Conference on Emerging Technologies and Factory Automation, ETFA. - 1946-0759 .- 1946-0740. - 9781509013142 ; 2016-November, s. Art no 7733628-
-
Konferensbidrag (refereegranskat)abstract
- Fault tolerant systems, commonly found in literature, are implemented in various computer applications. Some of these methods have been studied and developed to aid manufacturing systems; however, they have rarely been integrated into the manufacturing process. Broadly, the problem seems to be integration of error handling procedures towards the end of physically building the manufacturing line, lack of a defined workflow, untested program logic and inadequately equipped personnel to name a few. To this end, a survey was conducted within the Swedish automotive industry to get an understanding of current error handling procedures and its shortcomings, and are presented here. Based on this data, and looking at the trends within the manufacturing industry, this paper also identifies research topics aimed towards defining methods to create next generation fault tolerant manufacturing systems.
|
|
| 13. |
- Farooqui, Ashfaq Hussain, 1990, et al.
(författare)
-
From factory floor to process models: A data gathering approach to generate, transform, and visualize manufacturing processes
- 2019
-
Ingår i: CIRP Journal of Manufacturing Science and Technology. - : Elsevier BV. - 1755-5817 .- 1878-0016. ; 24, s. 6-16
-
Forskningsöversikt (refereegranskat)abstract
- The need for tools to help guide decision making is growing within the manufacturing industry. The analysis performed by these tools will help operators and engineers to understand the behaviour of the manufacturing stations better and thereby take data-driven decisions to improve them. The tools use techniques borrowed from fields such as Data Analytics, BigData, Predictive Modelling, and Machine Learning. However, to be able to use these tools efficiently, data from the factory floor is required as input. This data needs to be extracted from two sources, the PLCs, and the robots. In practice, methods to extract usable data from robots are rather scarce. The present work describes an approach to capture data from robots, which can be applied to both legacy and current state-of-the-art manufacturing systems. The described approach is developed using Sequence Planner - a tool for modelling and analyzing production systems - and is currently implemented at an automotive company as a pilot project to visualize and examine the ongoing process. By exploiting the robot code structure, robot actions are converted to event streams that are abstracted into operations. We then demonstrate the applicability of the resulting operations, by visualizing the ongoing process in real-time as Gantt charts, that support the operators performing maintenance. And, the data is also analyzed off-line using process mining techniques to create a general model that describes the underlying behaviour existing in the manufacturing station. Such models are used to derive insights about relationships between different operations, and also between resources.
|
|
| 14. |
- Farooqui, Ashfaq Hussain, 1990, et al.
(författare)
-
Real-time Visualization of Robot Operation Sequences
- 2018
-
Ingår i: IFAC-PapersOnLine. - : Elsevier BV. - 2405-8963. ; 51:11, s. 576-581
-
Konferensbidrag (refereegranskat)abstract
- Evaluation of manufacturing systems requires large amounts of accurate data from the factory floor. This data is then processed to calculate Key Performance Indicators (KPIs), evaluation metrics used within the manufacturing industry by engineers and managers in order to make data-driven decisions. Mechanisms to capture large scales of usable data, which is both reliable and scalable is, more often than not, scarce. In this paper, we provide an approach to capture data from robot actions, which can be applied to both legacy and current state-of-the-art manufacturing systems. By exploiting the robot code structure, robot actions are converted to event streams that are transformed into a higher usable abstraction of data. Applicability of this data is demonstrated, primarily, by visualizations. The described approach is developed in Sequence Planner - a tool for modeling and analyzing production systems - and is currently implemented at an automotive company as a pilot project to visualize and examine what goes on on the factory floor.
|
|
| 15. |
- Farooqui, Ashfaq Hussain, 1990, et al.
(författare)
-
Towards Automatic Learning of Discrete-Event Models from Simulations
- 2018
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. ; 2018-August, s. 857-862
-
Konferensbidrag (refereegranskat)abstract
- Model-based techniques are, these days, being embraced by the manufacturing industry in their development frameworks. While model-based approaches allow for offline verification and validation before physical commissioning, and have other advantages over existing methods, they do have their own challenges. Firstly, models are typically created manually and hence are prone to errors. Secondly, once a model is created, tested, and put into use on the factory floor, there is an added effort required to maintain and update it. This paper is a preliminary study of the feasibility of automatically obtaining formal models from virtual simulations. We apply the foundational algorithm from the active automata learning community to study the requirements and enhancements needed to be able to derive discrete event models from virtual simulations. An abstract model in the form of operations is learned by applying this algorithm on a simulation model composed of discrete operations. While a major bottleneck to be solved is the generation of counterexamples, the results seem promising to apply model learning in practice.
|
|
| 16. |
- Khan, Adnan, 1984, et al.
(författare)
-
Digital Twin for Legacy Systems: Simulation Model Testing and Validation
- 2018
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. ; 2018-August, s. 421-426
-
Konferensbidrag (refereegranskat)abstract
- In this paper, an approach to incorporate a digitaltwin for legacy production systems is presented. Hardware-in-the-loop setups are routinely used by manufacturing companiesto carry out virtual commissioning. However, manufacturingcompanies having online legacy production systems are stillstruggling to incorporate a digital twin due to the absence ofverified and validated simulation models. Companies that usevirtual commissioning as a part of their engineering tool chain,usually perform offline verification of the simulation model.This approach is typically based on visual inspection and is atedious task as each aspect of the model has to be visuallyvalidated. For legacy systems, only assessing the behaviorvisually in the absence of updated documents can result in anincorrect simulation model, i.e. simulating incorrect behaviorwith respect to the specification. Due to this, such simulationmodels cannot be incorporated in the engineering tool chain,as the simulated results can lead to improper decisions and caneven cause equipment damage. This paper presents a platformand an approach, based on model-based testing, that is a firststep for manufacturing companies to incorporate a validatedsimulation model for existing online production systems thatwill serve as a digital twin.
|
|
| 17. |
- Khan, Adnan, 1984, et al.
(författare)
-
On the Equivalence of Controllability and the Input Output Conformance Testing Relation
- 2018
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In this paper, the relation between controllability and the IOCO testing relationis examined. Based on a natural and common notion of controllability, where uncontrollableevents are interpreted as outputs from the plant, and viewing an implementation under testas a plant, the IOCO testing relation is equivalent to controllability. Further, it is shownhow supervisor synthesis can be used to algorithmically make an implementation IOCO withrespect to its specification. This can be done either by restricting the implementation to thesupremal controllable sublanguage, or extending the specification to the infimal controllablesuperlanguage, of the implementation and the specification. Both alternatives seem to be equallyviable, and the choice between them seem strongly application dependent.
|
|
| 18. |
- Khan, Adnan, 1984, et al.
(författare)
-
Testing and validation of safety logic in the virtual environment
- 2019
-
Ingår i: CIRP Journal of Manufacturing Science and Technology. - : Elsevier BV. - 1755-5817 .- 1878-0016. ; 26, s. 1-9
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents an approach for testing safety PLC logic in a virtual environment, using the IOCO testing relation as validation criteria. Manufacturing companies more and more rely on virtual commissioning to reduce the physical commissioning time by testing and debugging the PLC logic of the nominal behavior prior to physical commissioning. However, safety PLC logic testing is still carried out on real systems manually. This manual practice of safety logic validation hinders industry to exploit the full potential of virtual commissioning to reduce the physical commissioning time. The proposed approach assists manufacturing companies in the validation of safety PLC logic using a simulation model before the factory acceptance testing phase. Using the proposed approach, a simulation model can be used to test the safety PLC logic and prepare better for the factory acceptance testing phase, hence, further reduction in physical commissioning time can be achieved.
|
|
| 19. |
- Khan, Adnan, 1984, et al.
(författare)
-
Virtual Engineering Framework forAutomatic Generation of Control Logic including Safety
- 2017
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. ; 2017-August
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a new virtual engineering framework based on clever components for automatic generation of control logic including safety is presented. Manual practices of modeling plant components and writing PLC programs is an error-prone and time-consuming task. This new virtual engineering framework enables automatic generation of control solutions based on cloud based repositories, containing clever components with formalized logic descriptions provided by vendors. Consequently, reduced time for virtual engineering and commissioning can be achieved by avoiding current manual practices. Other advantages include testing and validation of PLC logic and plant models in the engineering phase, and less human errors due to automatic generation of both plant models and logic. In addition, this framework will help in the development of more reliable and robust safety logic and assist the procedure of issuing safety certificate.
|
|
| 20. |
- Riazi, Sarmad, 1986, et al.
(författare)
-
Scheduling and routing of agvs for large-scale flexible manufacturing systems
- 2019
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. ; 2019-August, s. 891-896
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we propose a new heuristic as well as several improvements to an existing approach based on Benders decomposition for solving the conflict free scheduling and routing of automated guided vehicles (AGVs), with promising results. The existing method solves the problem in two stages; task assignment/sequencing, and feasibility check of the first stage's solution subject to collision-avoidance constraints. The method is not suitable for large-scale AGV systems. We proposed several improvements and speedup strategies that result in fast methods capable of scheduling AGVs in a realistic layout with a graph of several hundred nodes and arcs. This is done by reformulating the mathematical model of the problem. We also introduce a new heuristic based on the improved method that yields high-quality solutions quickly. Moreover, we solve a real large-scale industrial instance by a commercial constraint programming solver and an open-source SMT solver. The results show that both of these general-purpose solvers can effectively solve our proposed models.
|
|
| 21. |
- Semeniuta, O., et al.
(författare)
-
Discrete event dataflow as a formal approach to specification of industrial vision systems
- 2015
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. - 9781467381833 ; 2015-October, s. 849-854
-
Konferensbidrag (refereegranskat)abstract
- The need for more flexible manufacturing systems stimulates the adoption of industrial robots in combination with intelligent computing resources and sophisticated sensing technologies. In this context, industrial vision systems play a role of inherently flexible sensing means that can be used for a variety of tasks within automated inspection, process control and robot guidance. When vision sensing is used within a large complex system, it is of particular importance to handle the complexity by introducing the appropriate formal methods. This paper overviews the challenges arising during design, implementation and application of industrial vision systems, and proposes an approach, dubbed Discrete Event Dataflow (DEDF), allowing to formally specify vision dataflow in the context of larger systems.
|
|
| 22. |
- Semeniuta, Oleksandr, 1990, et al.
(författare)
-
EPypes: a framework for building event-driven data processing pipelines
- 2019
-
Ingår i: PeerJ Computer Science. - : PeerJ. - 2376-5992. ; 2019:2
-
Tidskriftsartikel (refereegranskat)abstract
- Many data processing systems are naturally modeled as pipelines, where data flows though a network of computational procedures. This representation is particularly suitable for computer vision algorithms, which in most cases possess complex logic and a big number of parameters to tune. In addition, online vision systems, such as those in the industrial automation context, have to communicate with other distributed nodes. When developing a vision system, one normally proceeds from ad hoc experimentation and prototyping to highly structured system integration. The early stages of this continuum are characterized with the challenges of developing a feasible algorithm, while the latter deal with composing the vision function with other components in a networked environment. In between, one strives to manage the complexity of the developed system, as well as to preserve existing knowledge. To tackle these challenges, this paper presents EPypes, an architecture and Python-based software framework for developing vision algorithms in a form of computational graphs and their integration with distributed systems based on publish-subscribe communication. EPypes facilitates flexibility of algorithm prototyping, as well as provides a structured approach to managing algorithm logic and exposing the developed pipelines as a part of online systems.
|
|
| 23. |
- Semeniuta, Oleksandr, et al.
(författare)
-
Event-driven industrial robot control architecture for the Adept V+ platform
- 2019
-
Ingår i: PeerJ Computer Science. - : PeerJ. - 2376-5992. ; 2019:7
-
Tidskriftsartikel (refereegranskat)abstract
- Modern industrial robotic systems are highly interconnected. They operate in a distributed environment and communicate with sensors, computer vision systems, mechatronic devices, and computational components. On the fundamental level, communication and coordination between all parties in such distributed system are characterized by discrete event behavior. The latter is largely attributed to the specifics of communication over the network, which, in terms, facilitates asynchronous programming and explicit event handling. In addition, on the conceptual level, events are an important building block for realizing reactivity and coordination. Eventdriven architecture has manifested its effectiveness for building loosely-coupled systems based on publish-subscribe middleware, either general-purpose or robotic-oriented. Despite all the advances in middleware, industrial robots remain difficult to program in context of distributed systems, to a large extent due to the limitation of the native robot platforms. This paper proposes an architecture for flexible event-based control of industrial robots based on the Adept V+ platform. The architecture is based on the robot controller providing a TCP/IP server and a collection of robot skills, and a high-level control module deployed to a dedicated computing device. The control module possesses bidirectional communication with the robot controller and publish/subscribe messaging with external systems. It is programmed in asynchronous style using pyadept, a Python library based on Python coroutines, AsyncIO event loop and ZeroMQ middleware. The proposed solution facilitates integration of Adept robots into distributed environments and building more flexible robotic solutions with eventbased logic.
|
|
| 24. |
- Semeniuta, Oleksandr, 1990, et al.
(författare)
-
Flexible image acquisition service for distributed robotic systems
- 2018
-
Ingår i: Proceedings - 2nd IEEE International Conference on Robotic Computing, IRC 2018. ; 2018-January, s. 106-112
-
Konferensbidrag (refereegranskat)abstract
- The widespread use vision systems in robotics introduces a number of challenges related to management of image acquisition and image processing tasks, as well as their coupling to the robot control function. With the proliferation of more distributed setups and flexible robotic architectures, the workflow of image acquisition needs to support a wider variety of communication styles and application scenarios. This paper presents FxIS, a flexible image acquisition service targeting distributed robotic systems with event-based communication. The principal idea a FxIS is in composition of a number of execution threads with a set of concurrent data structures, supporting acquisition from multiple cameras that is closely synchronized in time, both between the cameras and with the request timestamp.
|
|
| 25. |
- Semeniuta, O., et al.
(författare)
-
Towards increased intelligence and automatic improvement in industrial vision systems
- 2018
-
Ingår i: Procedia CIRP. - : Elsevier BV. - 2212-8271. ; 67, s. 256-261
-
Konferensbidrag (refereegranskat)abstract
- Robots and in-process inspection systems equipped with machine vision solutions are used for increased flexibility and quality in automated manufacturing. Although vision systems have found wide industrial use, there are still problems regarding optimization of vision system robustness and capabilities. This paper presents a comprehensive case study of vision system functions, techniques and capabilities in an automotive 1-tiers supplier. Based on the study, the paper further describes a method for systematic improvement of industrial vision systems on a continuous basis. This is proposed to be done by establishing a data store and data analysis system, based on training machine learning models in an off-line mode using the historical data, as well as on on-line stream processing.
|
|
| 26. |
- Semeniuta, O., et al.
(författare)
-
Vision-based robotic system for picking and inspection of small automotive components
- 2016
-
Ingår i: IEEE International Conference on Automation Science and Engineering. - 2161-8070 .- 2161-8089. - 9781509024094 ; 2016-November, s. 549-554
-
Konferensbidrag (refereegranskat)abstract
- The use of vision systems for industrial robot guidance and quality control becomes much harder when the manufactured products and their components are small and possess reflective surface. To assure an effective automated visual inspection of such components, novel solutions are required, able to perform more advanced image analysis and tackle noise and uncertainty. This paper proposes a concept of multi-camera/multi-pose inspection station for star washers inspection, and presents the first results of a functional prototype implementation of it in a robotic cell. The processes of vision-guided part picking from a flexible feeder and close-range inspection in a dedicated rig are described. Solutions for the vision-based tasks of parts identification, machine learning-based classification, circular objects image analysis and star washer teeth segmentation are presented, and further directions are outlined. © 2016 IEEE.
|
|
