Today, failure modes characterization and early detection is a key issue in complex assets. This is due to the negative impact of corrective operations and the conservative strategies usually put in practice, focused on preventive maintenance. In this paper anomaly detection issue is addressed in new monitoring sensor data by characterizing and modeling operational behaviors. The learning framework is performed on the basis of a machine learning approach that combines constrained K-means clustering for outlier detection and fuzzy modeling of distances to normality. A final score is also calculated over time, considering the membership degree to resulting fuzzy sets and a local outlier factor. Proposed solution is deployed in a CBM+ platform for online monitoring of the assets. In order to show the validity of the approach, experiments have been conducted on real operational faults in an auxiliary marine diesel engine. Experimental results show a fully comprehensive yet accurate prognostics approach, improving detection capabilities and knowledge management. The performance achieved is quite high (precision, sensitivity and specificity above 93% and ?=0.93?=0.93), even more so given that a very small percentage of real faults are present in data

Robot control software endows robots with advanced capabilities for autonomous operation, such as navigation, object recognition or manipulation, in unstructured and dynamic environments. However, there is a steady need for more robust operation, whe

Purpose: IEEE Ontologies for Robotics and Automation Working Group were divided into subgroups that were in charge of studying industrial robotics, service robotics and autonomous robotics. This paper aims to present the work in-progress developed by the autonomous robotics (AuR) subgroup. This group aims to extend the core ontology for robotics and automation to represent more specific concepts and axioms that are commonly used in autonomous robots. Design/methodology/approach: For autonomous robots, various concepts for aerial robots, underwater robots and ground robots are described. Components of an autonomous system are defined, such as robotic platforms, actuators, sensors, control, state estimation, path planning, perception and decision-making. Findings: AuR has identified the core concepts and domains needed to create an ontology for autonomous robots. Practical implications: AuR targets to create a standard ontology to represent the knowledge and reasoning needed to create autonomous systems that comprise robots that can operate in the air, ground and underwater environments. The concepts in the developed ontology will endow a robot with autonomy, that is, endow robots with the ability to perform desired tasks in unstructured environments without continuous explicit human guidance. Originality/value: Creating a standard for knowledge representation and reasoning in autonomous robotics will have a significant impact on all R&A domains, such as on the knowledge transmission among agents, including autonomous robots and humans. This tends to facilitate the communication among them and also provide reasoning capabilities involving the knowledge of all elements using the ontology. This will result in improved autonomy of autonomous systems. The autonomy will have considerable impact on how robots interact with humans. As a result, the use of robots will further benefit our society. Many tedious tasks that currently can only be performed by humans will be performed by robots, which will further improve the quality of life. To the best of the authors’knowledge, AuR is the first group that adopts a systematic approach to develop ontologies consisting of specific concepts and axioms that are commonly used in autonomous robots.

Increasing industrial development and digital transformations have given rise to a technology called Digital Twin (DT) that has the potential to break the barrier between physical and cyberspace. DT is a virtual and dynamic model enabled through a bidirectional data flow that creates high-reliability models with interconnection and fusion between the physical and digital systems for full integration. In smart manufacturing, this technology is increasingly used in research and industry. However, the studies conducted do not provide a definition or a single integrally connected model. To develop the Digital Twin shown in this research, the literature was reviewed to learn about the enabling technologies and architectures used at the industrial level. Then, a methodology was used to obtain the physical process information, create the digital environment, communicate the physical environment, apply simulation models in the digital environment, and parameterize the simulation environment with the physical process in real-time to obtain the digital twin supported with augmented reality. The system was implemented in the MPS-500 modular production station that has industrial sensors and actuators. The virtual environment was designed with Blender and Vuforia to create the augmented reality environment. In the proposed methodology, robust devices (field and control level) and low-cost embedded systems were used for the creation and communication of the virtual environment (monitoring and control); for the joint work of these technologies, they were carried out through the use of the following protocols: Open Platform Communications United Architecture (OPC UA), Ethernet, and machine to machine (M2M), with which a communication was achieved between the different levels of the automation pyramid. The results show that the proposed methodology for the implementation of the DT allows bidirectional communication between the physical and virtual environment and can also be visualized with the support of AR, thus providing its characteristics to the proposed DT. Digital Twin is an essential factor in creating virtual environments and improving applications between the real and digital world, establishing a bidirectional communication through the Ethernet protocol, with a communication time of approximately 100 ms. This technology interacts with the virtual environment and performs mappings, thus achieving timely and dynamic adjustment. This improves data management and production and incorporates process simulation and physical control in real-time, allowing to execute and trigger actions in the physical equipment simultaneously.