Search

Optimizing energy consumption is an important aspect of industrial competitiveness, as it directly impacts operational efficiency, cost reduction, and sustainability goals. In this context, anomaly detection (AD) becomes a valuable methodology, as it supports maintenance activities in the manufacturing sector, allowing for early intervention to prevent energy waste and maintain optimal performance. Here, an AD-based method is proposed and studied to support energy-saving predictive maintenance of production lines using time series acquired directly from the field. This paper proposes a deep echo state network (DeepESN)-based method for anomaly detection by analyzing energy consumption data sets from production lines. Compared with traditional prediction methods, such as recurrent neural networks with long short-term memory (LSTM), although both models show similar time series trends, the DeepESN-based method studied here appears to have some advantages, such as timelier error detection and higher prediction accuracy. In addition, the DeepESN-based method has been shown to be more accurate in predicting the occurrence of failure. The proposed solution has been extensively tested in a real-world pilot case consisting of an automated metal filter production line equipped with industrial smart meters to acquire energy data during production phases; the time series, composed of 88 variables associated with energy parameters, was then processed using the techniques introduced earlier. The results show that our method enables earlier error detection and achieves higher prediction accuracy when running on an edge device. [ABSTRACT FROM AUTHOR]

Production efficiency is used to determine the best conditions for manufacturing goods at the lowest possible unit cost. When achieved, production efficiency leads to increased revenues for the manufacturer, enhanced employee safety, and a satisfied customer base. Production efficiency not only measures the amount of resources that are needed for production but also considers the productivity levels and the state of the production lines. In this context, online anomaly detection (AD) is an important tool for maintaining the reliability of the production ecosystem. With advancements in artificial intelligence and the growing significance of identifying and mitigating anomalies across different fields, approaches based on artificial neural networks facilitate the recognition of intricate types of anomalies by taking into account both temporal and contextual attributes. In this paper, a lightweight framework based on the Echo State Network (ESN) model running at the edge is introduced for online AD. Compared to other AD methods, such as Long Short-Term Memory (LSTM), it achieves superior precision, accuracy, and recall metrics while reducing training time, CO2 emissions, and the need for high computational resources. The preliminary evaluation of the proposed solution was conducted using a low-resource computing device at the edge of the real production machine through an Industrial Internet of Things (IIoT) smart meter module. The machine used to test the proposed solution was provided by the Italian company SIFIM Srl, which manufactures filter mats for industrial kitchens. Experimental results demonstrate the feasibility of developing an AD method that achieves high accuracy, with the ESN-based framework reaching 85 % compared to 80.88 % for the LSTM-based model. Furthermore, this method requires minimal hardware resources, with a training time of 9.5 s compared to 2.100 s for the other model. [ABSTRACT FROM AUTHOR]

The factory of the future scenario asks for new approaches to cope with the incoming challenges and complexity of cyber-physical systems. The role of database management systems is becoming central for control and automation technology in this new industrial scenario. This article proposes database-centric technology and architecture that aims to seamlessly integrate networking, artificial intelligence, and real-time control issues into a unified model of computing. The proposed methodology is also viable for the development of a framework that features simulation and rapid prototyping tools for smart and advanced industrial automation. The full expression of the potentialities in the presented approach is expected in particular for applications where tiny and distributed embedded devices collaborate to a shared computing task of relevant complexity.

Featured Application: This work aims to review the use of ROS2 as middleware to integrate heterogeneous hardware and software components in order to enable fixed-base robots to perform complex tasks by increasing their autonomy and flexibility. It shows how the open-source framework can be used in industry to overcome the limitations of commercially available cobots. An extensive review of the features and tools currently provided by ROS2, as well as its main fields of application, is provided. Moreover, as a proof of concept, a high-level modular architecture to increase autonomy in industrial operations is first proposed and then applied to one of the various commercially available industrial cobots. Future challenges in manufacturing will require automation systems with robots that are increasingly autonomous, flexible, and hopefully equipped with learning capabilities. The flexibility of production processes can be increased by using a combination of a flexible human worker and intelligent automation systems. The adoption of middleware software such as ROS2, the second generation of the Robot Operating System, can enable robots, automation systems, and humans to work together on tasks that require greater autonomy and flexibility. This paper has a twofold objective. Firstly, it provides an extensive review of existing literature on the features and tools currently provided by ROS2 and its main fields of application, in order to highlight the enabling aspects for the implementation of modular architectures to increase autonomy in industrial operations. Secondly, it shows how this is currently potentially feasible in ROS2 by proposing a possible high-level and modular architecture to increase autonomy in industrial operations. A proof of concept is also provided, where the ROS2-based framework is used to enable a cobot equipped with an external depth camera to perform a flexible pick-and-place task. [ABSTRACT FROM AUTHOR]

The dynamically changing environment forces companies to introduce changes in production processes and the need for employees to adapt quickly to new tasks. Therefore, it is expected to implement solutions to support employees. The system that will manage the work on a manufacturing line should work in real time to support the ongoing activities and, to be implemented in SMEs, must not be expensive. The authors identified important system components and expected functionalities. The methodology of the work is based on humancentered design. A concept of a cyber-physical system is proposed. The aim of the proposed edge computing-based system is to manage the work on the manufacturing line in which certain elements communicate with each other to achieve common goals. The paper presents what the system can consist of, how information and knowledge are managed in the system, and what can be the benefits for enterprises from its implementation. [ABSTRACT FROM AUTHOR]

Industrial collaborative robots (cobots) are known for their ability to operate in dynamic environments to perform many different tasks (since they can be easily reprogrammed). Due to their features, they are largely used in flexible manufacturing processes. Since fault diagnosis methods are generally applied to systems where the working conditions are bounded, problems arise when defining condition monitoring architecture, in terms of setting absolute criteria for fault analysis and interpreting the meanings of detected values since working conditions may vary. The same cobot can be easily programmed to accomplish more than three or four tasks in a single working day. The extreme versatility of their use complicates the definition of strategies for detecting abnormal behavior. This is because any variation in working conditions can result in a different distribution of the acquired data stream. This phenomenon can be viewed as concept drift (CD). CD is defined as the change in data distribution that occurs in dynamically changing and nonstationary systems. Therefore, in this work, we propose an unsupervised anomaly detection (UAD) method that is capable of operating under CD. This solution aims to identify data changes coming from different working conditions (the concept drift) or a system degradation (failure) and, at the same time, can distinguish between the two cases. Additionally, once a concept drift is detected, the model can be adapted to the new conditions, thereby avoiding misinterpretation of the data. This paper concludes with a proof of concept (POC) that tests the proposed method on an industrial collaborative robot. [ABSTRACT FROM AUTHOR]

Featured Application: This work aimed to enhance the current state of the art regarding the Condition Monitoring of industrial collaborative manipulators providing a general architecture which can be used in many different industrial scenarios. This solution is helpful in overcoming current limits regarding the definition of algorithms for the automatic detection of failures in collaborative robots working on flexible manufacturing. The Condition Monitoring (CM) of industrial collaborative robots (cobots) has the potential to decrease downtimes in highly automated production systems. However, in such complex systems, defining a strategy for effective CM and automatically detecting failures is not straightforward. In this paper, common issues related to the application of CM to collaborative manipulators are first introduced, discussed, and then, a solution based on the Robot Operating System (ROS) is proposed. The content of this document is highly oriented towards applied research and the novelty of this work mainly lies in the proposed CM architecture, while the methodology chosen to assess the manipulator's health is based on previous research content. The CM architecture developed and the relative strategy used to process data are useful for the definition of algorithms for the automatic detection of failures. The approach is based on data labeling and indexing and aims to extract comparable data units to easily detect possible failure. The end of this paper is provided with a proof of concept (PoC) applied to an industrial collaborative manipulator where the proposed CM strategy has been implemented and tested in a real application scenario. Finally, it is shown how the proposed methodology enables the possibility of defining standard Health Indicators (HIs) to detect joint anomalies using torque information even under a highly dynamic and non-stationary environmental conditions. [ABSTRACT FROM AUTHOR]