Industrial Automation Scenarios Research Articles

Enhancing Robustness within the Collaborative Federated Learning Framework: A Novel Grouping Algorithm for Edge Clients

In this study, we introduce a novel collaborative federated learning (FL) framework, aiming at enhancing robustness in distributed learning environments, particularly pertinent to IoT and industrial automation scenarios. At the core of our contribution is the development of an innovative grouping algorithm for edge clients. This algorithm employs a distinctive ID distribution function, enabling efficient and secure grouping of both normal and potentially malicious clients. Our proposed grouping scheme accurately determines the numerical difference between normal and malicious groups under various network scenarios. Our method addresses the challenge of model poisoning attacks, ensuring the accuracy of outcomes in a collaborative federated learning framework. Our numerical experiments demonstrate that our grouping scheme effectively limits the number of malicious groups. Additionally, our collaborative FL framework has shown resilience against various levels of poisoning attack abilities and maintained high prediction accuracy across a range of scenarios, showcasing its robustness against poisoning attacks.

Reuse-based online joint routing and scheduling optimization mechanism in deterministic networks

Deterministic networks plan the entire network traffic and calculate the scheduling time to meet the critical traffic requirements of specific domains, enabling real-time and deterministic interaction of massive data. However, in dynamic industrial automation scenarios where devices undergo changes, existing mechanisms face challenges in quickly responding to dynamic transmission demand changes caused by rapid traffic migration. To address this issue, this paper proposes a reuse-based online scheduling mechanism that utilizes dynamic path planning of flows and coordinated scheduling of time slots to achieve deterministic transmission of dynamic flows. In the offline phase, the mechanism proposes a backbone link selection and a scalable intelligent routing strategy, constructs a set of routing and scheduling co-design constraints, and generates an offline scheduling table using an iterative scheduling algorithm. In the online scheduling phase, a reuse-based online scheduling algorithm is proposed to achieve rapid scheduling and deterministic transmission of dynamic real-time flows. It utilizes the offline scheduling results and the period offset of migrated flows. The reuse of offline scheduling results reduces computation time and expands the solution space. Experimental results demonstrate that the proposed mechanism achieves a maximum increase in scheduling success rate of 37.3% and reduces time costs by up to 66.6% compared to existing online scheduling algorithms.

Flexible Cyclic Queuing and Forwarding for Time-Sensitive Software-Defined Networks

Time-Sensitive Networking (TSN) is emerging to support critical real-time applications in Industry 4.0. Recent proposals leverage Cyclic Queuing and Forwarding (CQF) to achieve bounded-delay transmission for cyclic flows in TSN. However, the CQF is not flexible enough in two aspects. First, it cannot achieve zero jitter. The Ping-Pong queue-based model in CQF will introduce the jitter of two cycles, which is inapplicable to industrial automation scenarios where isochronous flows require zero jitter. Second, it may require setting the maximum queue length to a fixed value in advance and scheduling the flows offline, which is challenging for dynamic traffic scheduling. In this paper, we firstly present a time-aware cyclic-queuing (TACQ) mechanism to enable zero jitter for CQF. TACQ consists of a novel no-wait shaper (NWS) and a cyclic-queuing shaper (CQS). The NWS handles isochronous flows by strictly limiting the transmission time of flows that do not overlap on each output port and each period. The CQS is extended from CQF to schedule cyclic flows. Then, we propose a variable time slot mechanism and a novel incremental routing and scheduling (IRAS) algorithm based on software-defined networking (SDN) to online schedule dynamic flows. Simulation results show that TACQ significantly reduces the delay of isochronous flows and achieves zero jitter compared with CQF. And the IRAS algorithm approaches 96.1% of the optimal solution in scheduling 2000 flows with a feasible per-flow computational time.

Characterization of Dynamic Blockage Probability in Industrial Millimeter Wave 5G Deployments

5G New Radio (NR) systems promise to expand offered services to enable industrial automation scenarios. To enable ultra-low latency at the air interface and to exploit spatial redundancy for applications such as synchronization and motion control, user equipment (UE) will naturally require device-to-device (D2D) and base station (BS) to UE communications and directional transmissions provided by millimeter wave (mmWave) frequencies. However, the performance of such systems is affected by the blockage phenomenon. In this paper, we propose a simple line-of-sight (LoS) blockage model for Industrial mmWave-based industrial Internet of Things (IIoT) deployments. The model is based on two sub-models, where each part can be changed/replaced to fit the scenario of interest. The first part is based on photogrammetry and provides the transparency probability for a single element on the factory floor. The second one utilizes these models of industrial elements to form the deployment and then applies stochastic geometry to derive the blockage probability. The proposed model can be utilized for any type of industrial machine, accounts for their inherent regular deployments on the factory floor, and provides the final results in an easy-to-compute form. Our results indicate that direct UE-UE communications are feasible in sparse deployments (less than 0.1 machine/m2) or at small communications distances (less than 5–10 m) or in deployments with highly transparent machines (machine transparency less than 0.5). Otherwise, BS-UE communications need to be utilized. In this case, BS height becomes a critical parameter affecting the LoS probability. Specifically, using a BS height of 10 m allows blockage probability to be improved by 20–30% as compared to a BS of height 4 m. Finally, as UE height produces more impact on the blockage probability as compared to a machine height, in real deployments, one needs to ensure that the height of communications modules at UEs are maximized.

An autonomous mobile manipulator to build outdoor structures consisting of heterogeneous brick patterns

This paper describes the implementation of an autonomous mobile manipulator to build outdoor structures consisting of heterogeneous brick patterns, finding applications in different industrial automation, manufacturing and civil construction scenarios. This system was developed for the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020, to demonstrate the novel real-world application of constructing structures using teams of robots, showcasing once again the role of major scientific competitions in advancing the state of the art towards exploring solutions to open problems. The paper presents in detail the hardware and software architectures of the developed mobile manipulator, integrating different research results and developments into a functional complex robot system, while proposing methods to detect, approach and manipulate differently sized/colored bricks to build a wall of predefined pattern given to the robot just before the building task starts.Article HighlightsFull system description of an autonomous mobile manipulator for construction tasks tested in a realistic settingAlgorithms for detection, localization, picking and placement of heterogeneous building blocks to form large structuresVersatile service robot capable of smooth adaptation to other functions developed through scientific robot competitions

Min-Max Decoding-Error Probability-Based Resource Allocation for a URLLC System

This letter considers an industrial automation scenario where a central controller communicates with multiple machines by transmitting data in short blocklengths. This communication is subject to reliability and latency constraints, which can be referred to as ultra-reliable and low-latency communication (URLLC). With the objective of minimizing the worst-case decoding-error probability for all the machines (min-max decoding-error probability), we consider joint power allocation and transmission blocklength optimization under the subject of transmit power and latency constraints. To solve this challenging problem, we propose a novel path-following algorithm. Simulation results clearly demonstrate the merits of the proposed algorithm.

Decentralized and on-the-fly agent-based service reconfiguration in manufacturing systems

Intelligent manufacturing systems rely on the capability to adapt and evolve to face the volatility of dynamic markets. The complexity of these systems increases with the demand of more customized and quality products, which requires more agile and flexible methods to support the dynamic and on-the-fly system reconfiguration aiming to respond quickly to product changes, by offering more efficient services. In this service-oriented manufacturing context, where process functionalities are modelled as services (e.g., quality control, welding and transportation), the dynamic reconfiguration of the services structure (e.g., in terms of quality, processing time and provided features) assumes a critical role to achieve the referred requirements. Despite the current research efforts, the service reconfiguration approaches usually use reactive event triggers, with decisions coming from a centralized decision-maker and performed manually. This means a lack of dynamic and run-time reconfiguration flexibility by discovering opportunities and needs to change, and, thus, exploring possible actions leading to new and appropriate system configurations. To overcome the mentioned issues, it is essential to provide solutions that answer to when and how to reconfigure a manufacturing system in an integrated, automatic and dynamic manner. For this purpose, this paper introduces an agent-based approach for service reconfiguration in manufacturing systems that allows the identification of opportunities in a pro-active and dynamic manner, and the on-the-fly implementation of new configuration solutions leading to a better production efficiency. The experimental results, using a flexible manufacturing system case study, allowed to verify the feasibility and benefits of the proposed agent-based service reconfiguration solution for competitive and collaborative industrial automation scenarios.

EE-Hybrid MAC Protocol for Wireless Sensor Networks

MAC protocol design in Wireless sensor networks becomes vibrant research field for the past several years. In this paper an EE-Hybrid MAC protocol (Energy efficient hybrid Medium Access Control) has been proposed, which is energy efficient and low latency MAC protocol, which uses interrupt method to assign priority for certain wireless sensor nodes assumed to be present in critical loops of industrial process control domain. EE-Hybrid MAC overcomes some of the limitations in the existing approaches. Industrial wireless sensor network require a suitable MAC protocol which offers energy efficiency and capable of handling emergency situations in industrial automation domain. Time critical and mission critical applications demands not only energy efficiency but strict timeliness and reliability. Harsh environmental condition and dynamic network topologies may cause industrial sensor to malfunction, so the developed protocol must adapt to changing topology and harsh environment. Most of the existing MAC protocols have number of limitations for industrial application domain In industrial automation scenario, certain sensor loops are found to be time critical, where data’s have to be transferred without any further delay. The proposed EE-Hybrid MAC protocol is simulated in NS2 environment, from the result it is observed that proposed protocol provides better performance compared to the conventional MAC protocols.

Integrating fieldbuses and factory intranets

Field networks (also known as fieldbuses) are becoming the preferred means for interconnecting devices at the lowest hierarchical level in modern distributed manufacturing systems, particularly to support the real-time communication requirements between controllers, sensors and actuators. On the other hand, internet and intranet solutions are more and more used in the industrial automation scenario at the factory and cell level, and a new generation of applications for manufacturing and process control environments is appearing on the market which is based on popular internet tools and protocols. Very likely, in the near future, a pressing need for interconnecting intranets and fieldbuses in a factory environment will arise, so that the whole production process can be fully integrated. This paper deals with some technical issues that must be considered for accessing fieldbus networks by means of conventional web-based applications in order to enable the remote invocation and execution of configuration, management and control services on field devices. The cases of two international standard fieldbuses which are very popular in Europe, i.e. Process Fieldbus (Profibus) and CANopen, are analysed in detail.