Search

The utilization of robotic systems has been increasing in the last decade. This increase has been derived by the evolvement in the computational capabilities, communication systems, and the information systems of the manufacturing systems which is reflected in the concept of Industry 4.0. Furthermore, the robotics systems are continuously required to address new challenges in the industrial and manufacturing domain, like keeping humans in the loop, among other challenges. Briefly, the keeping humans in the loop concept focuses on closing the gap between humans and machines by introducing a safe and trustworthy environment for the human workers to work side by side with robots and machines. It aims at increasing the engagement of the human as the automation level increases rather than replacing the human, which can be nearly impossible in some applications. Consequently, the collaborative robots (Cobots) have been created to allow physical interaction with the human worker. However, these cobots still lack of recognizing the human emotional state. In this regard, this paper presents an approach for adapting cobot parameters to the emotional state of the human worker. The approach utilizes the Electroencephalography (EEG) technology for digitizing and understanding the human emotional state. Afterwards, the parameters of the cobot are instantly adjusted to keep the human emotional state in a desirable range which increases the confidence and the trust between the human and the cobot. In addition, the paper includes a review on technologies and methods for emotional sensing and recognition. Finally, this approach is tested on an ABB YuMi cobot with commercially available EEG headset. publishedVersion

The literature on the modeling and management of data generated through the lifecycle of a manufacturing system is split into two main paradigms: product lifecycle management (PLM) and product, process, resource (PPR) modeling. These paradigms are complementary, and the latter could be considered a more neutral version of the former. There are two main technologies associated with these paradigms: ontologies and databases. Database technology is widespread in industry and is well established. Ontologies remain largely a plaything of the academic community which, despite numerous projects and publications, have seen limited implementations in industrial manufacturing applications. The main objective of this paper is to provide a comparison between ontologies and databases, offering both qualitative and quantitative analyses in the context of PLM and PPR. To achieve this, the article presents (1) a literature review within the context of manufacturing systems that use databases and ontologies, identifying their respective strengths and weaknesses, and (2) an implementation in a real industrial scenario that demonstrates how different modeling approaches can be used for the same purpose. This experiment is used to enable discussion and comparative analysis of both modeling strategies.

The handling of flexible materials is complicated task in robotics and automation. Due to deformability and fragility of flexible materials, robots are equipped with the state-of-the-art sensors and grippers to perform such tasks. Nonetheless, industry still lacks for approaches and techniques for handling these materials. Therefore, several industries and mass production systems require hiring human to perform the deformable materials-related task. These tasks might include usage of toxic martials (e.g. carbon fiber sheets) or dangerous tools (e.g. sharp cutting knives). In this regard, this paper presents an approach for selecting grasping configuration of objects based on the product’s properties such as rigidity, surface roughness and shape, and the required task. Briefly, this research is based on several published taxonomies for modeling the hand of the human while grasping different objects. After refining the taxonomy, an ontology model is populated which will be queried for specifying the gripper’s properties such as number of fingers and required grasping force that can perform the selected task on the selected product. Finally, this research presented a use case form the REMODEL (Robotic tEchnologies for the Manipulation of cOmplex DeformablE Linear objects) project in order to assess and validate the approach. For the future, this research expected to include the selection of the grippers, the robotic arm and its approach for grasping the product. acceptedVersion

Robot programming and training depends on the task that needs to be completed, the end-effector properties and functionalities and the working space. These considerations can complicate the programming process, which in return, increase the time that is needed for training the robot. Thus, several research approaches have been introduced to address training the robots intuitively. In this regard, this paper presents an approach for training an under-actuated gripper and the robot attached to it for grasping shallow objects. The research work started by detailed analysis of the fingers of human hand during the grasping process. Then, a modified design of the gripper has been produced. This modification includes adding an artificial nail among other hardware-related modifications. Then, a Q-Learning algorithm has been used for training the gripper on grasping the shallow object. With two fingers, three actions were configured, and 625 states were configured for the learning algorithm. For the validation, a coin has been used for representing the shallow object. The results showed reduction in both the grasping time and the number of movements. acceptedVersion

Manufacturing-oriented enterprises are investing in novel solutions to adapt their cyber and physical resources to the fast and, yet, unexpected changes of global industrial environment. One of the important trends is to work towards development of cognitive systems which are capable to process and analyze complex data using Artificial Intelligence (AI)-based tools and techniques. Therefore, cognition can be already viewed as a requirement for hyper-connected environments e.g., the factories of the future or the Internet of Things (IoT). In this context, there is a need to represent and store the data collected from machines in a format that can be understood and manipulated by both humans and machines. This is feasible by designing and implementing semantic models i.e., ontologies which, in turn, enable inferring implicit data of explicit knowledge, leading to cognition. Moreover, there is a need of granting the access to such information remotely and at system runtime. Within this conceptual article, the authors present a semantic workbench that was developed during a European project aiming at utilization of ontologies for knowledge representation and reasoning in industrial automation systems. Further, this research work proposes the encapsulation of semantic workbench as a service in order to be deployed in cloud-based platforms, hence, enabling remote access of authorized clients at system runtime. The proposed functionalities are also of critical importance in highly complex and distributed environments, like the IoT or industrial ecosystems. acceptedVersion

One of the major objectives of international projects in the field of Industrial Automation is to achieve a proper and safe human-robot collaboration. This will permit the coexistence of both humans and robots at factory shop floors, where each one has a clear role along the industrial processes. It’s a matter of fact that machines, including robots, have specific features that determine the kind of operation(s) that they can perform better. Similarly, human operators have a set of skills and knowledge that permits them to accomplish their tasks at work. This article proposes the adaptation of robots to the skills of human operators in order to implement an efficient, safe and comfortable synergy between robots and humans that are working at the same workspace. As a representative case of study, this research work describes an approach for adapting a cobot workstation to human operators within an installed deep learning camera on the cobot. First, the camera is used to recognize the human operator that collaborates with the robot. Then, the corresponding profile is processed and serves as an input to a module in charge of adapting specific features of the robot. In this manner, the robot can adapt e.g., to the speed of operation according to the skills of the worker or deliver parts to be manipulated according to the handedness of the human worker. In addition, the deep learning camera is used for stopping the process at any time that the worked leaves unexpectedly the workstation. acceptedVersion

Over the last decades, the Industrial Automation domain has exhibited an exponential growth of robots’ deployment at factory shop floors. The main objective is to increase efficiency and productivity at a reasonable cost, which is lowered thanks to the robot lifespan. But not all the manual tasks, the tasks requiring high-level of dexterity, are yet replaced by robots. In fact, Europe is moving towards the creation of efficient workspaces where both robots and human operators can work safely. In this context, there is a clear intention of achieving solutions that involve collaborative robots, a.k.a. "cobots" or co-robots, for permitting a safe interaction between robots and humans working for the same or interrelated processes. Many manufactures started to present their products but those arrived before the industry have clear and several needs of this particular technology. This article presents a human-robot collaborative assembly workstation, composed by the ABB YuMi robot that interacts with a human operation in order to assembly a product box, as a part of a large-scale process. Assembly process, workstation design, implementation and its validation are illustrated. Then, this paper aims to summarize advantages and challenges of implementing cobots by exemplifying a real scenario of collaborative interaction between a cobot and a human operator, feasible to implement at any industrial facility. acceptedVersion

Industry 4.0 is about the interconnectivity and digitalisation of industrial systems that need to be integrated in order to improve the efficiency of resources and, in turn, processes. Both research and commercial sectors are working towards addressing specific challenges, such as data modelling, collection and processing. A correct manipulation and interpretation of data is critical and, now, more difficult than ever due to the dramatic increment of the amount of data generated at different levels of enterprises. Ultimately, this research work presents a solution, integrated with an existing cloud-based platform, for collecting and processing real-time factory shop floor streams of data. Such solution is an IoT-based development, which consist on both IoT hub and gateway that permit the consumption and communication of device information. The required message exchange is done within state of the art technologies and protocols e.g., MQTT protocol and REST-based interface. The implementation of the solution is demonstrated through an industrial-based scenario. acceptedVersion

Cyber-physical Systems (CPS) in industrial manufacturing facilities demand a continuous interaction with different and a large amount of distributed and networked computing nodes, devices and human operators. These systems are critical to ensure the quality of production and the safety of persons working at the shop floor level. Furthermore, this situation is similar in other domains, such as logistics that, in turn, are connected and affect the overall production efficiency. In this context, this article presents some key steps for integrating three pillars of CPS (production line, logistics and facilities) into the current smart manufacturing environments in order to adopt an industrial Cyber-Physical Systems of Systems (CPSoS) paradigm. The approach is focused on the integration in several digital functionalities in a cloud-based platform to allow a real time multiple devices interaction, data analytics/sharing and machine learning-based global reconfiguration to increase the management and optimization capabilities for increasing the quality of facility services, safety and energy efficiency and industrial productivity. Conceptually, isolated systems may enhance their capabilities by accessing to information of other systems. The approach introduces particular vision, main components, potential and challenges of the envisioned CPSoS. In addition, the description of one scenario for realizing the CPSoS vision is presented. The results herein presented will pave the way for the adoption of CPSoS that can be used as a pilot for further research on this emerging topic. acceptedVersion

Performance measurement tools and techniques have become very significant in today's industries for increasing the efficiency of their processes in order to face the competitive market. The first step towards performance measurement is the real-time monitoring and gathering of the data from the manufacturing system. Applying these performance measurement techniques on real-world industry in a way that is more general and efficient is the next challenge. This paper presents a methodology for implementing the key performance indicators defined in the ISO 22400 standard-Automation systems and integration, Key performance indicators (KPIs) for manufacturing operations management. The proposed methodology is implemented on a multi robot line simulator for measuring its performance at runtime. The approach implements a knowledge-based system within an ontology model which describes the environment, the system and the KPIs. In fact, the KPIs semantic descriptions are based on the data models presented in the Key Performance Indicators Markup Language (KPIML), which is an XML implementation of models developed by the Manufacturing Enterprise Solutions Association (MESA) international organization. acceptedVersion

Information technologies grow rapidly nowadays with the advance and extension of computing capabilities. This growth affects several fields, which consume these technologies. Industrial Automation is not an exception. This publication describes a general and flexible architecture for implementing Manufacturing Execution System (MES) function, which can be deployed in multiple industrial cases. These features are achieved by combining the flexibility of knowledge-driven systems with the vendor-independent property of RESTful web services. With deployment of this solution, MES functions may gain more versatility and independency. This research work is a continuation of the development of the OKD-MES (Open Knowledge-Driven Manufacturing Execution System) framework during the execution of the eScop project. The OKD-MES framework consists on a semantic-based solution for controlling and enhancing the flexibility and re-configurability of MES. In such scope, this research presents MES functions architecture that might be implemented in the OKD-MES framework in order to increase the flexibility of event-driven manufacturing systems. acceptedVersion

The advances in virtual engineering brought about the creation of models of physical systems. This has been enhanced by the use of relevant standards and web technologies to develop interfaces for monitoring and controlling industrial systems at the shop floor or remotely over the internet. However, owing to the open nature of the internet as well as vulnerabilities associated with internet-based technologies, it becomes imperative to put in place security measures. This will allow to mitigate this particularly as it concerns the management, control, and monitoring of entities making use of the interface. The first step is to ensure an efficient user access control for web-based solutions. This article proposes an approach for developing an access control layer to web applications. In addition, a web-based application, i.e., the FASTory simulator, is used as the test-bed for implementing this approach. acceptedVersion

Enterprise Resource Planning (ERP) represents the highest level of the manufacturing systems according to ISA-95 standard. It includes supply chain management, and customer-manufacturer-supplier interactions, essential to a successful business relationship in the frame of Industry 4.0. Many research efforts are being put in place to follows the latest ICT advances, combining them with manufacturing systems technologies. In this manner, the C2NET factories of future project (c2net-project.eu) has been put in place to provide a cloud-based collaborative network for supply chain interactions. This research paper focuses on providing a solution for retrieving ERP data via a Legacy System Hub, which is powered by the previous PlantCockpit project (www.tut.fi/plantcockpit-os/) outcomes. This solution allows the C2NET users to transfer the ERP data from the company side to the C2NET platform via the Data Collection Framework (DCF). Thus, the contribution of this research work is a generic solution that enables the interaction between systems owned by different organizations involved in the same supply chain. As C2NET targets the Small and Medium-sized Enterprises (SMEs), three data adapters are developed for MS Excel, SQL and RESTful data sources. The result of this research enhances the users experience in terms of interface and it might help in the C2NET databases for controlling and monitoring the instance changes in the ERP data on the company side. acceptedVersion

The industry is constantly moving towards the research, implementation and deployment of new solutions that permit the optimization of processes. Nowadays, such solutions consist mostly on ICT developments, which permit the collection, distribution, integration, analysis, and manipulation of heterogeneous data. The under way Cloud Collaborative Manufacturing Networks (C2NET) project targets the development of cloud-enabled tools for supporting the SMEs supply network optimization of manufacturing and logistic assets. The C2NET solution includes the implementation of paradigms as e.g. cloud computing or service-oriented and event-driven architectures, used for wide data integration. Among its requirements, the C2NET platform needs a solution for catch, process and react to events triggered in different locations of collaborative manufacturing networks, which are endowed with devices that permits the integration of Cyber-Physical Systems (CPS). This paper presents the architecture and main functionality of a knowledge-based approach that allows processing supply chain events handled by CPS devices. The main component of the presented solution is the SECA ontology, which is a knowledge base that can be updated at runtime. The main purpose of the ontology is to describe events, their status and the actions to be performed once a set of events are triggered in certain order. This research work offers a solution that can be employed by the C2NET platform not only to catch and process events; but also to notify linked data consumers. acceptedVersion

Virtualization has become a supportive approach for simulating system behaviour efficiently thanks to the revolution of computer and smart devices. In fact, the employment of running virtual tools that mimic the real physical world is nowadays a requirement in some fields as in e.g. industrial automation. This research work presents a virtual tool that simulates a real assembly line. The main features of this simulator are listed as; web application that can be accessed with any devices that supports html web pages, animated application that provides a UI for the user, discovery mechanism that allows web applications to interact with the simulator automatically and RESTful-based services, which increases the flexibility and versatility in terms of deployment. FASTory simulator has been developed and deployed during the eScop project. In addition, presented simulator has been employed by C2NET (Cloud Collaborative Manufacturing Networks) project for development some of its tools. Furthermore, the exploitation of the FASTory simulator is extended to cover as well the education of next generation of engineers for design and implementation of modern CPS. As Tampere University of Technology provides a M.Sc. degree in automation engineering, students use the simulator for their experiments, ensuring that mistakes are recoverable and harmless. acceptedVersion

The employment of tools and techniques for monitoring and supervising the performance of industrial systems has become essential for enterprises that seek to be more competitive in today&rsquo, s market. The main reason is the need for validating tasks that are executed by systems, such as industrial machines, which are involved in production processes. The early detection of malfunctions and/or improvable system values permits the anticipation to critical issues that may delay or even disallow productivity. Advances on Information and Communication Technologies (ICT)-based technologies allows the collection of data on system runtime. In fact, the data is not only collected but formatted and integrated in computer nodes. Then, the formatted data can be further processed and analyzed. This article focuses on the utilization of standard Key Performance Indicators (KPIs), which are a set of parameters that permit the evaluation of the performance of systems. More precisely, the presented research work demonstrates the implementation and visualization of a set of KPIs defined in the ISO 22400 standard-Automation systems and integration, for manufacturing operations management. The approach is validated within a discrete manufacturing web-based interface that is currently used for monitoring and controlling an assembly line at runtime. The selected ISO 22400 KPIs are described within an ontology, which the description is done according to the data models included in the KPI Markup Language (KPIML), which is an XML implementation developed by the Manufacturing Enterprise Solutions Association (MESA) international organization.

The C2NET project aims to provide cloud-based platform for the supply chain interactions. The architecture of such platform includes a Data Collection Framework (DCF) for managing the collection of the company's data. The DCF collects, transforms and stores data from both Internet of Things (IoT) devices in the factory shopfloor and company enterprises data via two types of hub; Legacy system hub (LSH) and IoT hub. Since the C2NET, targets the Small and Medium-sized Enterprises (SMEs), the enterprise data, or legacy data as called in the C2NET project, can be provided via excel files. Thus, this research work highlights a technique for processing the excel files in the LSHs. This technique adopts the concept of Multi-Agent Systems for processing the data as table in the excel files in the LSH. The multi-agent approach allows the LSH to process any excel file regardless the complexity in the data structure or in the file table. Furthermore, the presented approach enhances the processing of the excel files in different aspects, such as the size of the excel file or the required processing power. acceptedVersion

The Internet of Things (IoT) considers interconnected things e.g., devices that consumes web services through the internet. Such kind of devices may vary from smart phones, smart TVs, medical devices or industrial devices. Thanks to the development of the ICT field, many standards supports the existence of the IoT devices: HTTP (Hypertext Transferring Protocol), MQTT (Message Queue Telemetry Transport), and EtherCAT, among others. The challenge is to allow these devices to communicate with cloud applications wherein the mismatch of communication protocols may occur. In this context, this research work presents an approach for connecting industrial Remote Terminal Units (RTUs) with the Cloud Collaborative Manufacturing Networks (C2NET) project cloud-based platform for publishing the factory shopfloor data. In this manner, the C2NET platform exploits data that is generated by industrial equipment for further actions, such as the optimization of production plans. The presented approach is tested within the deployment of web-service enabled controllers in a real industrial case known as the FASTory line. acceptedVersion

Human operators play an important role especially in high added value manufacturing. The use of knowledge representation for decision making at runtime becomes more important. Modern automatic control systems should be capable to seamlessly include and assist operators. This paper describes how to represent information on operator's skills and include it into service-oriented orchestration approach for a production line. This approach allows operator to act not as a passive element, but as active asset for the orchestration engine to consider in production plans. acceptedVersion