Search

Predictive methods represent techniques commonly met in Industry 4.0 that offer a way to early predict or detect faults of machines, devices or tools. This is useful to anticipate failures with the main goal of improving maintenance planning. Making such predictions could decrease the unexpected malfunction operation or manufacturing downtime and consequently the overall maintenance costs. In this paper we present the basis of the architecture designed for predictive maintenance in the project Social Network of Machines (SOON) under the paradigm of Industry 4.0, as well as a brief literature state-of-the-art survey of the topic. A particular implementation of this architecture, a testbed for electrical motors failure detection, is shown and evaluated.

In this research we focus on minimizing the makespan, number of reconfiguration and wastage of materials due to reconfigurations for a set of non identical parallel machines. A mathematical model of the scheduling problem is explained, subjected to various production related constraints and is optimized using a heuristic approach. Optimality of the schedule generated is tested on a simulation platform created as close to real production system, modelling all the important uncertainty in the process. Simulation model also estimates the real order completion time and total wastage in the production process. A real manufacturing process of plastic foil bags is used in the case study to find and test the proposed solution. This approach acts effective in planning and scheduling of orders in small and medium scale industries as the approach is data driven.

This paper proposes a concept of low-cost industrial wireless sensor network integrating the power consumption efficient ESP32 chip. The main focus is given on best practices of various sensors integration into Real-Time Operating System (RTOS) of ESP32 devices. The work proposes an architecture for data collection, security and possibility of data analysis. Energy effectiveness is estimated for battery usage in different modes of the chip. The last part of this work presents the conclusions and guidelines for future work. Road map of a distributed modeling framework for plant-wide process monitoring is also introduced.

Maintenance is a key factor to ensure the production efficiency, since the occurrence of unexpected failures leads to a degradation of the system performance, causing the loss of productivity and business opportunities, which are crucial roles to achieve competitiveness. The article aims to propose a reference architecture which will improve the way maintenance is considered in the current manufacturing world, by enabling an overall increase of production rates, while increasing the operational equipment effectiveness and decreasing the impact of maintenance needs. This objective would be accomplished by establishing an IoT infrastructure for the collection of the huge amount of available shop floor data, which can be analyzed, considering data analytics algorithms, predictive maintenance models and forecasting techniques, to perform the machine/system health assessment and prediction of maintenance needs, e.g. by detecting earlier the occurrence of possible failures and consequently the need to implement maintenance interventions. The scheduling of predictive maintenance needs will be integrated with the existing maintenance planning tools, and especially synchronized with the production planning tools to achieve a non disruptive maintenance impact in the production system. A cloud-based collaborative maintenance services platform allows the secure collection, aggregation and analysis of a large amount of shared data from numerous manufacturers that use the same or similar machinery, and acts as an open market where companies can contract specialized maintenance services. This reference architecture aims to provide replicable architecture to be broadly applicable in a variety of industries, capable to improve the production efficiency through a real-time health monitoring and early detection of failures and outages, to speed up the maintenance delivery, and consequently mitigate their impact. info:eu-repo/semantics/publishedVersion

The paper presents the techniques for supervised information extraction and change notification of the Web resources. The method uses the combination of supervised wrapping or Web scraping techniques integrated to a browser as an extension. A prototype was developed to provide the proof of concept validation and moreover to identify the pros and cons of proposed solution. The paper focuses on the core methods being used for structured data extraction from Web resources and on notification of the users in the most appropriate manner. The approach has a potential to share marked Web elements among users taking advantages of the collaborative annotation. The paper concludes with the research challenges stumbled on during the process on method design.

In this article we aim at achieving trusted data collection from heterogeneous distributed sources including legacy systems and human end users. We adopt an agent-like approach where we are able to send agents to host platforms connected to legacy systems. Functionality of agents may vary while we are solving the trust between host platforms, legacy systems and agents. We had not used any existing multi-agent system but we extended an existing production grade service platform called Jini and implemented agents above Jini services. The core of this work is about how we adopted the Jini platform to host agents. We also provide examples about the implementation and integration of the platform in a real world example — a crisis management domain. We present our current achievements and plans concerning the implementation of the proposed platform.

The paper describes an ontology approach to the modeling of administrative workflow processes. The ontological approach is applied on the RAPORT system. The RAPORT system is a light-weight system based on e-mail communication and internet technology. The description of architecture and basic principles of the RAPORT system is provided in this paper.

During large-scale crisis situations there is an acute demand for relevant and accurate information. The availability of such information to incident commanders assists the ever continuing need to improve the effectiveness of emergency response through the enhancement of agency preparedness and awareness; this also includes the potential offered by volunteers and the general public as well. To address the above mentioned challenges a distributed platform capable of seamlessly collect and aggregate information from engaged users providing information using the web or mobile devices is proposed. At the same time integration of information from sources such as sensors deployed on incident sites, publicly available open data, corporate legacy systems or documents stored on remote locations is enabled. As a result the platform end users can act based on the results of information aggregation and analysis. The work presented in this paper is motivated mainly by requirements identified by first responders during numerous crisis responses.

This paper discusses a process of data collection from remote sensors and presentation on mobile devices. The presented research and work in this paper is done in the scope of REDIRNET project. The main motivation in the project is to support the rescuers facing operational problems in accessing and analyzing information from multiple sources, and providing advanced features for command and control of the emergencies. Timely exchange of information between competent authorities, a common understanding of data and a swift transmission of knowledge can save the lives and protect properties. Useful information are often heterogeneous and distributed between many organizations in the diverse information sources with the different access rights and with the different qualities. This work focuses on delivering the data from remote sensor nodes with intermittent connected networks and dispatching the results to the end users connected by mobile devices. A specific of this work is the means of sensor data collection, where the mobile devices are used as the data producers. The specified information and the data provided by mobile device sensors are collected and aggregated into a centralized system. In addition the sensor data are collected using remote sensors passing through an ad-hoc gateway that may be presented in a convenient way on the mobile devices.

Nowadays technologies aim at interconnecting plethora of electronic devices and data sources to keep users informed about their field of interest. Automated processing of heterogeneous distributed information is still the challenging task which ranges from enterprise and logistic information systems to rescue and military information systems. In this paper we propose a system for semi-automated information collection and integration, especially focused on seamless human information acquisition. In this sense information integration can be viewed as a multi-stage process where information sources (human and computational) could be spread in different locations and stored in various formats. In order to overcome the problems of information acquisition from distributed heterogeneous sources especially from end users, the agent platform, appropriate agents and methods for semiautomated user forms generation were designed and developed.

Supporting emergency responders with mobile software agents promise increasing the efficiency of crisis management. While mobile agents offer many advantages, they also pose new challenges to security. However, security is a key prerequisite in crisis situations. A main security requirement is to create an agent execution environment that will not attack the agents.To secure mobile agents we have created an architecture that uses Trusted Computing to create a trusted execution environment for mobile agents on commodity-of-the-shelf computing hardware. We protect the load-time integrity of the trusted execution environment by measuring its software configuration and using a local attestation verification token to verify the software configuration. This token is the Secure Docking Module, a security chip protecting the cryptographic resources required to join the mobile agent software platform and authorize mobile agents. The SDM is implemented on a modern security chip. With our security architecture we can provide a mobile agent platform that is resilient against malicious agent execution environments, making the use of mobile agents in crisis management viable.

Routine operations of emergency first responders are usually well managed. The situation is different for mass casualty emergencies where more people and properties are threatened. In such situations there are no predefined plans in place and mitigation is solved mostly through crisis management. Teams managing such acute accidents are often working in information insufficiency. Timely information exchange between involved agencies, common understanding of data and fast provision of knowledge can save lives and protect properties. Useful information is heterogeneous and is distributed across many organizations in disparate information sources in many formats with different access policies and in varying quality. The information sources range from sensors deployed on incidence sites, publicly available data sources, corporate legacy systems, documents stored on remote locations to human end-users providing information using mobile devices. This article addresses operational challenges of First Responders and complementary challenges in accessing and analyzing information from multiple sources to provide advanced capabilities for command and control in emergency response. Herein we propose to use an agent-based infrastructure for supporting such interoperability. We propose to build the framework amplifying an agent infrastructure developed in scope of the SECRICOM EU integrated project. In this article we focus mainly on the conceptual architecture of such integration framework.

This paper proposes integration of secure agents with a secure communication infrastructure in order to provide rapid information gathering platform from various information sources and actors participating in a crisis situation. The role of agents is primarily a coordinated collection of information. The secure communication infrastructure (SCI) provides communication services for voice and data exchange between users and systems. A special type of agent called User Communication Agent is described. The communication with users is enacted through dynamically generated XForms-based questionnaires integrated with the user interface of the SCI. Although security and trust aspects are important part of both secure agents and SCI, we concentrate more on integration aspects between these two systems. The presented work is being developed in scope of the SECRICOM 7th FP integrated project.

This article proposes a mobile agent platform based on Jini services deployed over IP-based networks. The role of agents in the proposed architecture is primarily coordinated collection of information. The overall agent infrastructure is designed as a secure, robust and fail resistant system. Trust for agents can be based on a special hardware module which provides trusted computing functionality. In the article we describe such architecture in terms of requirements and design. Core agent types are proposed to access different kinds of distributed resources. Specialized agents for access to legacy information sources, communication with end-users and configuration of IP-based network devices are described. We conclude with current state of the architecture implementation and with further plans concerning the development of the described architecture.

This article proposes a distributed architecture designed for management of crisis situations were multiple actors are involved from various organizations with different competences and communicating over IP-based networks including wireless devices. In such settings requirements exist for secure communication and trusted collection of data from various sources. The role of agents in the proposed architecture is primarily coordinated collection of information. In respect to requirements the overall agent infrastructure must be a secure, robust and fail resistant system. Required level of trust for agents is based on a special hardware module which provides trusted computing functionality. In the article we describe such architecture in terms of detailed requirements, design and decomposition to subsystems. We also provide a sample scenario use case inspired by concrete crisis situation. The architecture herein described is being used in scope of an EU integrated project called Secricom therefore we briefly describe the integration points with other systems involved in the project. We conclude with current state of the architecture implementation and with further plans concerning the development of the described architecture.

Even in Web 2.0 era, email is still the most popular application on the internet. Beset by many problems, such as spam or information overload, yet it yields significant benefits especially to enterprise users when communicating, collaborating or solving business tasks. The email standards, content, services and clients improved a lot, but the integration with the environment and enterprise context remained pretty much the same. We believe that this can be improved by introducing our work in progress – the Acoma context-sensitive recommendation tool. Acoma processes emails on the server or desktop side and attaches the relevant information from various sources to the email messages. It can be used with any email client or mobile device since it is hooked up to email as a proxy to email protocols. In order to provide useful recommendations, emails need to be processed and business objects need to be identified. Thus the paper also discusses the object identification using the information extraction techniques based on the Ontea tool, as well as its customization in the enterprise context.

Many papers, research projects, and software products have tackled the problem of automatic composition of a workflow of computer processes, which computes certain data or performs a specific task. In recent years this has also gained popularity in grid computing, especially in connection with semantic description of resources usable in the workflow. However, most of the works dealing with semantically-aided workflow composition propose solutions only for workflows of processes, without the data necessary to execute them. We describe the design of a system, which will be able to find not only the processes, but also the content for their execution, based solely on the list of available resources and a description of the required target of the workflow. The solution is based on our previous work in the project K-Wf Grid, utilizes semantic description of resources by means of ontologies, and operates on a SOA-based grid composed of web services. It is being developed in the context of a project called SEMCO-WS.

We present a system for semantically-aided workflow management for SOA-based grid environment. The user can construct workflows of grid and web services just by stating the intended result, can see the workflow and its dynamic behavior in a graphical form, and can annotate the whole workflow, its parts, or its results. User experience, constructed workflows, and computed results can be shared between users. The system uses monitoring information to adapt to changes in the underlying infrastructure by extracting ontologically managed information about existing application services. One of its important features is also a transparency of the grid, and resulting ease of use even for application area experts not familiar with grid computing concepts. We also present the way this system is employed to predict flood hazards, using a series of simulation models for meteorology, hydrology, and hydraulics. The system is the result of the IST project K-Wf Grid.

This article proposes an approach for predicting runtime of web services (WS) with state – also called stateful web services. Estimating WS runtime is particularly critical during construction of composite WS workflows. Each workflow job must be scheduled in a way that the overall workflow run time will satisfy the overall workflow constrains. Such workflows are commonly used in Grids for connecting individual Grid WS to large, complicated and distributed applications. Prediction of WS run times optimizes scheduling and supports efficient use of grid resources. In our approach we propose to estimate expected WS run time based on invocation parameters of WS operations, states of resources maintained by a WS and properties of resources used as processing inputs for a WS. We adopt knowledge based approach where the history of WS operations is examined and a model is created and updated for each class and instance of a WS. Such WS run time prediction models can be then used by workflow schedulers to compute expected run times of a range of WS for the purpose of identifying the most appropriate WS for a given job within given constrains.

In this paper we present design and development of the semantic grid services for the flood forecasting simulations. We will highlight the corresponding architecture and the process of service annotation, discovery and composition in the project K-WfGrid [12]. We will describe in detail the challenges of the flood-forecasting application and corresponding design and development of the service oriented model, which is based on the well known Web Service Resource Framework (WSRF). Semantic descriptions of the WSRF services will be presented as well as the architecture, which exploits semantics in discovery and composition of services. Further, we will demonstrate how experience management solutions can help in the process of discovery and composition. The system provides a unique approach in Semantic Grids by combining the advances of semantic web services and grid architectures.

This paper presents a prototype of flood forecasting system based on Grid technologies. The system consists of workflow system for executing simulation cascade of meteorological, hydrological and hydraulic models, data management system for storing and accessing different computed and measured data, and web portals as user interfaces. The whole system is tied together by Grid technology and is used to support a virtual organization of experts, developers and users.