Browsing by Author "Melo, Victória"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
- Cloud-enabled integration of IoT applications within the farm to fork to reduce the food wastePublication . Funchal, Gustavo Silva; Melo, Victória; Leitão, PauloThe climate change, the loss of productive land area and the exponential population growth are demanding new and more efficient ways to produce, transform and consume food resources that respect the planet's sustainability. The achievement of these challenges require the use of emerging ICT technologies, such as Internet of Things (IoT), Artificial Intelligence (AI) and Cloud Computing, to promote the real-time information exchange along the farm to fork value chain, i.e. from the primary production to the food consumption, as well as to develop smart applications that take advantage of integrated information, e.g., aiming the process monitoring, prediction, optimization and traceability. This paper presents the development of a digital cloud-based ecosystem, built upon the open-source FIWARE platform, to enable the integration of smart applications and assets along the farm to fork chain, aiming to reduce the food waste. Furthermore, the feasibility of the proposed system is analysed through the integration of several IoT sensing nodes and a smart monitoring application, showing its benefits in terms of modularity, interoperability, scalability and robustness.
- DDoS attacks on smart manufacturing systems: a cross-domain taxonomy and attack vectorsPublication . Zahid, Farzana; Funchal, Gustavo Silva; Melo, Victória; Kuo, Matthew M.Y.; Leitão, Paulo; Sinha, RoopakDenial of Service is a significant availability threat in Industrial Cyber-Physical systems and smart manufacturing is not an exception. The types, methods, and duration of these attacks have been evolving rapidly and their number has increased dramatically, reaching a new record in history. In particular, digitisation of the manufacturing process and increased connectivity have created a battleground between product quality of service and threats associated with cross-domains and multi-vector attacks that affect the manufacturing system performance. The existing research on cyber-threats related to smart manufacturing system does not consider the comprehensive landscape of denial of service attacks. In this study, we classify well-accepted (distributed) denial of service attacks according to a proposed taxonomy, focusing on both the multi-vector attacks and cross-domain attacks. Utilising the taxonomy, more than fifty different denial of service attacks on smart manufacturing system were classified in terms of Endpoint and Network (distributed) denial of service attacks. As an example, a Cyber-Physical Conveyor System was used to examine the proposed taxonomy.
- Digital twin experiments focusing virtualisation, connectivity and real-time monitoringPublication . Pires, Flávia; Melo, Victória; Almeida, João; Leitão, PauloIndustry 4.0 is re-shaping the manufacturing world, and amongst the several associated emerging methods and technologies, Digital Twin is becoming a popular approach both in industry and academia. However, the lack of knowledge about the characteristics, functionalities, best practices and benefits that it can provide, especially for small and medium enterprises, constraints its wider adoption. The use of real applications and demonstrators can contribute to exposing stakeholders to these new and innovative technologies and approaches, showing the applicability of Digital Twins. This paper presents several experiments in implementing Digital Twin for automation scenarios, considering different technologies and functionalities, namely in terms of virtualisation, connectivity and monitoring. Lessons learnt and challenges are also provided as a result of the experimental implementations.
- A fuzzy logic approach for self-managing energy efficiency in IoT nodesPublication . Melo, Victória; Funchal, Gustavo Silva; Queiroz, Jonas; Leitão, PauloThe collection and analysis of data assume a crucial importance in the digital transformation era. Internet of Things (IoT) technologies allow to gather data from heterogeneous sources and make them available for data-driven systems aiming, e.g., monitoring, diagnosis, prediction and optimization. Several applications require that these IoT nodes be located remotely without connection to the electrical grid and being powered by batteries or renewable sources, thus requiring a more efficient management of the energy consumption in their operation. This paper aims to study and develop intelligent IoT nodes that embed Artificial Intelligence techniques to optimize their operation in terms of energy consumption when operating in constrained environments and powered by energy harvesting systems. For this purpose, a Fuzzy Logic system is proposed to determine the optimal operation strategy, considering the node’s current resource demands, the current battery condition and the power charge expectation. The proposed approach was implemented in IoT nodes measuring environmental parameters and placed in a university campus with Wi-Fi coverage. The achieved results show the advantage of adjusting the operation mode taking into consideration the battery level and the weather forecasts to increase the energy efficiency without compromising the IoT nodes’ functionalities and QoS.
- Machine vision to empower an intelligent personal assistant for assembly tasksPublication . Talacio, Matheus Teixeira; Funchal, Gustavo Silva; Melo, Victória; Piardi, Luis; Vallim, Marcos; Leitão, PauloIn the context of the fourth industrial revolution, the integration of human operators in emergent cyber-physical systems assumes a crucial relevance. In this context, humans and machines can not be considered in an isolated manner but instead regarded as a collaborative and symbiotic team. Methodologies based on the use of intelligent assistants that guide human operators during the execution of their operations, taking advantage of user friendly interfaces, artificial intelligence (AI) and virtual reality (VR) technologies, become an interesting approach to industrial systems. This is particularly helpful in the execution of customised and/or complex assembly and maintenance operations. This paper presents the development of an intelligent personal assistant that empowers operators to perform faster and more cost-effectively their assembly operations. The developed approach considers ICT technologies, and particularly machine vision and image processing, to guide operators during the execution of their tasks, and particularly to verify the correctness of performed operations, contributing to increase productivity and efficiency, mainly in the assembly of complex products.
- Monitoring electrical and operational parameters of a stamping machine for failure predictionPublication . Pecora, Pedro; Garcia, Fernando Feijoo; Melo, Victória; Leitão, Paulo; Pellegri, UmbertoGiven the industrial environment, the production efficiency is the ultimate goal to achieve a high standard. Any deviation from the standard can be costly, e.g., a malfunction of a machine in an assembly line tends to have a major setback in the overall factory efficiency. The data value brought by the advent of Industry 4.0 re-shaped the way that processes and machines are managed, being possible to analyse the collected data in real-time to identify and prevent machine malfunctions. In this work, a monitoring and prediction system was developed on a cold stamping machine focusing on its electrical and operational parameters, based on the Digital Twin approach. The proposed system ranges from data collection to visualization, condition monitoring and prediction. The collected data is visualized via dashboards created to provide insights of the machine status, alongside with visual alerts related to the early detection of trends and outliers in the machine’s operation. The analysis of the current intensity is carried out aiming to predict failures and warn the maintenance team about possible future disturbances in the machine condition.
- Security experiences in IoT based applications for building and factory automationPublication . Morenas, Javier de las; Silva, Carolina Miller da; Funchal, Gustavo Silva; Melo, Victória; Vallim, Marcos; Leitão, PauloIndustry 4.0 and Industrial Internet of Things (IIoT) are promoting the connection of millions of devices, that once were seen as unconnectable, into a huge network, to be used in a large number of applications, from autonomous vehicles to industrial control systems, passing through building automation systems. These paradigm rely on the adoption of Cyber Physical Systems complemented with Internet of Things (IoT) technologies and artificial intelligence techniques. These type of systems are responsible for collecting, processing and exchanging a vast amount of data, and for that reason, it is imperative to assure data integrity and protection against malicious modifications and attacks to ensure a safe and reliable operation. Data thefts and cyber attacks in general represent a significant danger, however, cyber attacks on IoT systems can be specially critical due to their proximity with humans, enhancing the risk of physical damage. This paper highlights the importance of securing these systems, pursuing a safer operation, having in mind the amount of security vulnerabilities found in embedded devices. For this purpose, this article studies possible security threats and weakness in two case studies coming from different IoT domains, i.e. building automation and factory automation, while seeking for solutions to improve these systems’ security.
- Self-organized cyber-physical conveyor system using multi-agent systemsPublication . Leitão, Paulo; Barbosa, José; Funchal, Gustavo Silva; Melo, VictóriaThe adoption of industrial cyber-physical systems is facing several challenges, with artificial intelligence and self-organization techniques assuming critical aspects to be considered in the deployment of such solutions to support the dynamic evolution and adaptation to condition changes. This paper describes the implementation of a modular, flexible and self-organized cyber-physical conveyor system build up with different individual modular and intelligent transfer modules. For this purpose, multi-agent systems are used to distribute intelligence among transfer modules supporting pluggability and modularity, complemented with self-organization capabilities to achieve a truly self-reconfigurable system. Furthermore, Internet of Things and Artificial Intelligence technologies are used to enable the real-time monitoring of the system, aiming the detection and prevention of anomalies in advance, and to enable the protection from possible external threats.
- Virtualization and monitoring of a modular and self-organized multi-agent conveyor systemPublication . Melo, Victória; Leitão, Paulo; Barbosa, José; Vallim, MarcosThe digital transformation that is taking place worldwide in the context of Industry 4.0 stimulates the emergence of new concepts and technologies and is reshaping the manufacturing world. As a result, the Digital Twin concept is gaining more and more momentum. In this sense, the creation of a virtual copy of the physical system provides a connection between the real and virtual systems to collect, analyze and simulate data in the virtual model to improve the performance of the real system. This work presents the development of virtualization of a modular and self-organized transport system, based on the use of Cyber-Physical Systems (CPS) and Multi-Agent Systems (MAS), to ensure the monitoring of its operation and allow the early detection of failures through real-time analysis of data collected from the physical system. For this purpose, Internet of Things (IoT) tools and technologies were used, such as Node-RED and the Message Queuing Telemetry Transport (MQTT) communication protocol, and the storage of collected data and cyber-security issues related to the use of IoT technologies during the data collection, suggesting the implementation of solutions to avoid possible threats, such as user authentication and data encryption. Among the results obtained, the control panel displays system data in real-time, in addition to providing statistical information, and supports dynamic monitoring of the transport system’s condition operation, generating alerts through the implementation of control rules.