No description available.

Yes / This paper presents a self-learning technique for adapting modular automated assembly systems. The technique consists of automatically analysing sensor data and acquiring experience on the changes made on an assembly system to cope with new production requirements or to recover from disruptions. Experience is generalised into operational knowledge that is used to aid engineers in future adaptations by guiding them throughout the process. At each step, applicable changes are presented and ranked based on: (1) similarity between the current context and those in the experience base; (2) estimate of the impact on system performance. The experience model and the self-learning technique reflect the modular structure of the assembly machine and are particularly suitable for plug and produce systems, which are designed to offer high levels of self-organisation and adaptability. Adaptations can be performed and evaluated at different levels: from the smallest pluggable unit to the whole assembly system. Knowledge on individual modules can be reused when modules are plugged into other systems. An experimental evaluation has been conducted on an industrial case study and the results show that, with experience-based learning, adaptations of plug and produce systems can be performed in a shorter time. / European Union [grant number 314762].

Master's thesis is focused on design of robotized workplace for assembly of drill chucks. In the first part the fundamental issue is described. The next part contains an analysis of selected chuck, which continues with design of robotized workplace including components. The thesis is also focused on a work cycle design, risk analysis and economic evaluation. Drawing documentation, 3D workplace model and work cycle simulation video is attached.

This project is being carried out in collaboration with Parker Hannifin. The main objective of this project is to achieve a simulation of an automatic assembly cell for the assembly of the CRVs in the P70 hydraulic valve assembly line. The robotic cell uses the line layout to perform the assembly. It consists of a robot, an automatic feeder system, a conveyor system, an assembly table, and an aligner stand. The tool used to perform the assembly is a combination of two tools mounted on a multi-tool. The first tool is a vacuum gripper, and the second tool is a drill driver. The time taken by the robot to complete one assembly of a P70 module of three sections, with a size of six CRVs on each side, A and B, is eighty-eight seconds which is faster than the speed of a manual operator. The throughput rate of the assembly cell is forty-one complete assemblies per hour, which equals one hundred and twenty-three sections per hour. This result shows clear improvement comparing it to the manual assembly throughput rate. The minimum time for the automatic feeder system to request a refill is approximately twenty-two and a half minutes. A minimal change is required when a new specification is added to the assembly line.

The industry is moving towards a higher degree of automation and connectivity, where previously manual operations are being adapted for interconnected industrial robots. This thesis focuses specifically on the automation of tightening applications with pre-tightened bolts and collaborative robots. The use of 3D computer vision is investigated for direct localization of bolts, to allow for flexible assembly solutions. A localization algorithm based on 3D data is developed with the intention to create a lightweight software to be run on edge devices. A restrictive use of deep learning classification is therefore included, to enable product flexibility while minimizing the computational load. The cloud-to-edge and cluster-to-edge trade-offs for the chosen application are investigated to identify smart offloading possibilities to cloud or cluster resources. To reduce operational delay, image partitioning to sub-image processing is also evaluated, to more quickly start the operation with a first coordinate and to enable processing in parallel with robot movement. Four different hardware architectures are tested, consisting of two different Single Board Computers (SBC), a cluster of SBCs and a high-end computer as an emulated local cloud solution. All systems but the cluster is seen to perform without operational delay for the application. The optimal hardware architecture is therefore found to be a consumer grade SBC, being optimized on energy efficiency, cost and size. If only the variance in communication time can be minimized, the cluster shows potential to reduce the total calculation time without causing an operational delay. Smart offloading to deep learning optimized cloud resources or a cluster of interconnected robot stations is found to enable increasing complexity and robustness of the algorithm. The SBC is also found to be able to switch between an edge and a cluster setup, to either optimize on the time to start the operation or the total calculation time. This offers a high flexibility in industrial settings, where product changes can be handled without the need for a change in visual processing hardware, further enabling its integration in factory devices. / Industrin rör sig mot en högre grad av automatisering och uppkoppling, där tidigare manuella operationer anpassas för sammankopplade industriella robotar. Denna masteruppsats fokuserar specifikt på automatiseringen av åtdragningsapplikationer med förmonterade bultar och kollaborativa robotar. Användningen av 3D-datorseende undersöks för direkt lokalisering av bultar, för att möjliggöra flexibla monteringslösningar. En lokaliseringsalgoritm baserad på 3Ddata utvecklas med intentionen att skapa en lätt mjukvara för att köras på Edge-enheter. En restriktiv användning av djupinlärningsklassificering är därmed inkluderad, för att möjliggöra produktflexibilitet tillsammans med en minimering av den behövda beräkningskraften. Avvägningarna mellan edge- och moln- eller klusterberäkning för den valda applikationen undersöks för att identifiera smarta avlastningsmöjligheter till moln- eller klusterresurser. För att minska operationell fördröjning utvärderas även bildpartitionering, för att snabbare kunna starta operationen med en första koordinat och möjliggöra beräkningar parallellt med robotrörelser. Fyra olika hårdvaruarkitekturer testas, bestående av två olika enkortsdatorer, ett kluster av enkortsdatorer och en marknadsledande dator som en efterliknad lokal molnlösning. Alla system utom klustret visar sig prestera utan operationell fördröjning för applikationen. Den optimala hårdvaruarkitekturen visar sig därmed vara en konsumentklassad enkortsdator, optimerad på energieffektivitet, kostnad och storlek. Om endast variansen i kommunikationstid kan minskas visar klustret potential för att kunna reducera den totala beräkningstiden utan att skapa operationell fördröjning. Smart avlastning till djupinlärningsoptimerade molnresurser eller kluster av sammankopplade robotstationer visar sig möjliggöra ökad komplexitet och tillförlitlighet av algoritmen. Enkortsdatorn visar sig även kunna växla mellan en edge- och en klusterkonfiguration, för att antingen optimera för tiden att starta operationen eller för den totala beräkningstiden. Detta medför en hög flexibilitet i industriella sammanhang, där produktändringar kan hanteras utan behovet av hårdvaruförändringar för visuella beräkningar, vilket ytterligare möjliggör dess integrering i fabriksenheter.

This project is about screw hole detection using neural networks for automated assembly and disassembly. In a lot of industrial companies, such as Ericsson AB, there are products such as radio units or filters that have a lot of screw holes. Thus, the assembly and disassemble process is very time consuming and demanding for a human to assemble and disassemble the products. The problem statement in this project is to investigate the performance of neural networks within object detection and semantic segmentation to detect screw holes in industrial products. Different industrial models were created and synthetic data was generated in Blender. Two types of experiments were done, the first one compared an object detection algorithm (Faster R-CNN) with a semantic segmentation algorithm (SegNet) to see which area is most suitable for hole detection. The results showed that semantic segmentation outperforms object detection when it comes to detect multiple small holes. The second experiment was to further investigate about semantic segmentation algorithms by adding U-Net, PSPNet and LinkNet into the comparison. The networks U-Net and LinkNet were the most successful ones and achieved a Mean Intersection over Union (MIoU) of around 0.9, which shows that they have potential for further development. Thus, conclusions draw in this project are that segmentation algorithms are more suitable for hole detection than object detection algorithms. Furthermore, it shows that there is potential in neural networks within semantic segmentation to detect screw holes because of the results of U-Net and LinkNet. Future work that one can do is to create more advanced product models, investigate other segmentation networks and hyperparameter tuning. / Det här projektet handlar om skruvhålsdetektering genom att använda neurala nätverk för automatiserad montering och demontering. I många industriföretag, såsom Ericsson AB, finns det många produkter som radioenheter eller filter som har många skruvhål. Därmed, är monterings - och demonteringsprocessen väldigt tidsfördröjande och krävande för en människa att montera och demontera produkterna. Problemformuleringen i detta projekt är att undersöka prestationen av olika neurala nätverk inom objekt detektering och semantisk segmentering för skurvhålsdetektering på indutriella produkter. Olika indutriella modeller var skapade och syntetisk data var genererat i Blender. Två typer av experiment gjordes, den första jämförde en objekt detekterings algoritm (Faster R-CNN) med en semantisk segmenterigs algoritm för att vilket område som är mest lämplig för hål detektering. Resultaten visade att semantisk segmentering utpresterar objekt detektering när det kommer till att detektera flera små hål. Det andra experimentet handlade om att vidare undersöka semantiska segmenterings algoritmer genom att addera U-Net, PSPNet och LinkNet till jämförelsen. Nätverken U-Net och PSPNet var de mest framgångsrika och uppnåde en Mean Intersection over Union (MIoU) på cirka 0.9, vilket visar på att de har potential för vidare utveckling. Slutsatserna inom detta projekt är att semantisk segmentering är mer lämplig för hål detektering än objekt detektering. Dessutom, visade sig att det finns potential i neurala nätverk inom semantisk segmentering för att detejtera skruvhål på grund av resultaten av U-Net och LinkNet. Framtida arbete som man kan göra är att skapa flera avancerade produkt modeller, undersöka andra segmenterisk nätverk och hyperparameter tuning.