Insulation is an essential part of power transformers, which guarantees an efficient and reliable operational life. It mainly consists of mineral oil and insulation paper. Most of the major failures of power transformers originate from internal insulation failures. Monitoring aging and thermal behaviour of the transformer’s insulation paper is achieved by different techniques, which consider the Degree of Polymerization (DP) to evaluate the cellulose degradation and other chemical factors accumulated in mineral oil. Given the physical and chemical nature of the problem of degradation, we couple it with machine learning models to predict the desired parameters for considered equations. In particular, the equation used applies the Arrhenius relation, which comprises parameters like the pre-exponential factor, which depends on the cellulose’s contamination content, and the activation energy, which is connected to the temperature dependence; both of the factors need to be estimated for our problem. For this reason, Physics-Informed Neural Networks (PINNs) are considered for solving the data-driven discovery of the DP equation.

Physics-Informed Neural Networks (PINNs) are a novel approach to the integration of physical models into Neural Networks when solving supervised learning problems. PINNs have shown potential in mapping spatio-temporal input and the solution of a partial differential equation (PDE). However, despite their advantages for many applications, they often fail to train when target PDEs contain high frequencies or multi-scale features. Thermal modelling of power transformers is fundamental for improving their efficiency and extending their lifetime. In this work, we investigate the performance of different PINN architectures applied to a 1D heat diffusion equation with a specific heat source representing the heat distribution inside a transformer. Measurements, which include the top-oil temperature, the ambient temperature and the load factor are taken from a transformer in service. We demonstrate the limitations of PINNs, propose possible remedies, and provide an overall assessment of the potential of using PINNs for transformer thermal modelling.

Wireless communication is evolving to support critical control in automation systems. The fifth-generation (5G) mobile network air interface New Radio adopts a scalable numerology and mini-slot transmission for short packets that make it potentially suitable for critical control systems. The reliable minimum cycle time is an important indicator for industrial communication techniques but has not yet been investigated within 5G. To address such a question, this article considers 5G-based industrial networks and uses the delay optimization based on data-driven channel characterization (CCDO) approach to propose a method to evaluate the reliable minimum cycle time of 5G. Numerical results in three representative industrial environments indicate that following the CCDO approach, 5G-based industrial networks can achieve, in real-world scenario, millisecond-level minimum cycle time to support several hundred nodes with reliability higher than 99.9999%.

The papers in this special section focus on industrial cyber-physical systems (CPS), with an emphasis on computing and communications applications. CPS systems are defined by integrating computation and communication facilities on the one hand and the monitoring and control of physical processes on the other hand. Industrial cyber–physical systems (ICPS) refer to the science and art of designing and using cyber–physical systems for industrial and process control applications, for example in smart factories, smart energy grids, smart transportation systems, smart cities, and several other areas. Many of these applications are time- and mission-critical and hence often require low latency and high reliability. In parallel, there has been a strong growth in integrating intelligence, often in the form of machine/deep learning, into applications, which also leads to vastly increasing computational requirements. These innovations then will be integrated into complex systems, which need to be properly engineered to become safe, reliable, trustworthy, and secure while at the same time being cost-efficient.

Wireless communication is gaining popularity in the industry for its simple deployment, mobility, and low cost. Ultralow latency and high reliability requirements of mission-critical industrial applications are highly demanding for wireless communication, and the indoor industrial environment is hostile to wireless communication due to the richness of reflection and obstacles. Assessing the effect of the industrial environment on the reliability and latency of wireless communication is a crucial task, yet it is challenging to accurately model the wireless channel in various industrial sites. In this article, based on the comprehensive channel measurement results from the National Institute of Standards and Technology at 2.245 and 5.4 GHz, we quantify the reliability degradation of wireless communication in multipath fading channels. A delay optimization based on the channel characterization is then proposed to minimize packet transmission times of a cyclic prefix orthogonal frequency division multiplexing system under a reliability constraint at the physical layer. When the transmission bandwidth is abundant and the payload is short, the minimum transmission time is found to be restricted by the optimal cyclic prefix duration, which is correlated with the communication distance. Results further reveal that using relays may, in some cases, reduce end-to-end latency in industrial sites, as achievable minimum transmission time significantly decreases at short communication ranges.

To meet the extremely low latency constraints of industrial wireless control in critical applications, the wireless high-performance scheme (WirelessHP) has been introduced as a promising solution. The proposed design showed great improvements in terms of latency, but its performance in terms of reliability have not been fully tested yet. While traditional wireless systems achieve high reliability through packet retransmissions, this would impair the latency, and an approach based on channel coding is preferable in industrial applications. In this paper, a set of packet error rate (PER) tests is performed by applying concatenated Reed Solomon and convolutional codes to the WirelessHP physical layer, using a demonstrator based on a universal software radio peripheral platform. The effectiveness of channel coding to achieve 10-7level PER without retransmissions is shown in typical laboratory and factory environments.

An innovative feature of the 5th Generation mobile network (5G) is to consider industrial applications as use cases for which its new radio access, 5G New Radio, aims to provide ultra low latency and ultra high reliability performance. These requirements are fulfilled by minimizing standard performance indicators such as end-to-end latency and packet error rate. However, industrial control applications typically require periodic exchange of small data, where the ability of networks to support short and deterministic cycle times is the main key performance indicator. This paper proposes a methodology to evaluate the achievable cycle time of an industrial network deployed over the 5G New Radio specifications. Numerical results shows that 5G can achieve millisecond level cycle time with network size of several hundred, which is promising for many factory automation applications.

Ultra-high reliable and low-latency communication (URLLC) is envisaged to support emerging applications with strict latency and reliability requirements. Critical industrial control is among the most important URLLC applications where the stringent requirements make the deployment of wireless networks critical, especially as far as latency is concerned. Since the amount of data exchanged in critical industrial communications is generally small, an effective way to reduce the latency is to minimize the packet's synchronization overhead, starting from the physical layer (PHY). This paper proposes to use a short one-symbol PHY preamble for critical wireless industrial communications, reducing significantly the transmission latency with respect to other wireless standards. Dedicated packet detection and synchronization algorithms are discussed, analyzed, and tuned to ensure that the required reliability level is achieved with such extremely short preamble. Theoretical analysis, simulations, and experiments show that detection error rates smaller than 10-6can be achieved with the proposed preamble while minimizing the latencies.

Wireless networks are ever more deployed in the industrial control scenario, thanks to the numerous benefits they can bring, especially in terms of costs and flexibility. However, some critical fields of application, such as motion control, power systems automation, or power electronics control, to mention some, have extremely tight requirements in terms of timeliness, reliability, and determinism, which nowadays can only be satisfied by wired communication networks. Indeed, the available industrial wireless solutions are far from offering adequate performance levels, especially in the timing budget, due to the native limitations of their physical (PHY) layers. In this paper, an innovative approach for high-performance industrial wireless networks [wireless high performance (WirelessHP)] is presented, based on a substantial redesign of the lower layers of the industrial wireless protocol stack, with the aim of supporting the requirements of critical industrial control applications. The required levels of timeliness, reliability, and determinism are first derived through a comprehensive survey that looks at real-world application scenarios as well as at the performance of wired networks for industrial control, such as real-time Ethernet networks. The design of a new solution, which is able to satisfy these targets, is then discussed in detail, introducing a low-latency PHY layer that aims at reducing the transmission time of short packets to 1 μs, or even less. The feasibility of the proposed solution is presented through an experimental demonstrator based on software-defined radios, while its performance bounds are computed through theoretical analyses. Finally, future activities in the context of WirelessHP are widely discussed, providing an overview of the directions that will have to be addressed, particularly in the design of the upper layers.

Wireless industrial cyber-physical systems are increasingly popular in critical manufacturing processes. These kinds of systems, besides high performance, require strong security and are constrained by low computational capabilities. Physical layer authentication (PHY-AUC) is a promising solution to meet these requirements. However, the existing threshold-based PHY-AUC methods only perform ideally in stationary scenarios. To improve the performance of PHY-AUC in mobile scenarios, this article proposes a novel threshold-free PHY-AUC method based on machine learning (ML), which replaces the traditional threshold-based decision-making with more adaptive classification based on ML. This article adopts channel matrices estimated by the wireless nodes as the authentication input and investigates the optimal dimension of the channel matrices to further improve the authentication accuracy without increasing too much computational burden. Extensive simulations are conducted based on a real industrial dataset, with the aim of tuning the authentication performance, then further field validations are performed in an industrial factory. The results from both the simulations and validations show that the proposed method significantly improves the authentication accuracy.

The demand for fast and reliable wireless connectivity in industrial applications is always increasing. Several new technologies have been proposed in recent years to improve the performance of wireless networks, including full-duplex wireless, which allows a terminal to simultaneously transmit and receive in the same frequency band. This paper explores the potential impact of this technology in real-time industrial networks, showing that it can be useful to increase the reliability of latency-constrained applications.

Physical layer authentication based on channel state information is an effective solution to preventing spoofing attacks in wireless communications by comparing the channel impulse responses. Existing theoretical analyses and experiments have proved the feasibility and efficiency in labs or offices. However, the environment of industrial wireless communication is significantly different. This paper applies physical layer authentication based on channel state information to measurements from four different industrial wireless communication scenarios, including indoor, outdoor, moving, and stationary scenarios. The analysis of the results allows to derive meaningful insights on the applicability of such a method to industrial wireless communications.

In the last years, the advancements in signal processing and integrated circuits technology allowed several research groups to develop working prototypes of in-band full-duplex wireless systems. The introduction of such a revolutionary concept is promising in terms of increasing network performance, but at the same time poses several new challenges, especially at the MAC layer. Consequently, innovative channel access strategies are needed to exploit the opportunities provided by full-duplex while dealing with the increased complexity derived from its adoption. In this direction, this paper proposes RTS/CTS in the Frequency Domain (RCFD), a MAC layer scheme for full-duplex ad hoc wireless networks, based on the idea of time-frequency channel contention. According to this approach, different OFDM subcarriers are used to coordinate how nodes access the shared medium. The proposed scheme leads to efficient transmission scheduling with the result of avoiding collisions and exploiting full-duplex opportunities. The considerable performance improvements with respect to standard and state-of-the-art MAC protocols for wireless networks are highlighted through both theoretical analysis and network simulations.

Low‐Power Wide‐Area Networks (LPWANs) have recently emerged as appealing communication systems in the context of the Internet of Things (IoT). Particularly, they proved effective in typical IoT applications such as environmental monitoring and smart metering. Such networks, however, have a great potential also in the industrial scenario and, hence, in the context of the Industrial Internet of Things (IIoT), which represents a dramatically growing field of application. In this paper we focus on a specific LPWAN, namely, LoRaWAN, and provide an assessment of its performance for typical IIoT employments such as those represented by indoor industrial monitoring applications. In detail, after a general description of LoRaWAN, we discuss how to set some of its parameters in order to achieve the best performance in the considered industrial scenario. Subsequently we present the outcomes of a performance assessment, based on realistic simulations, aimed at evaluating the behavior of LoRaWAN for industrial monitoring applications. Moreover, the paper proposes a comparison with the IEEE 802.15.4 network protocol, which is often adopted in similar application contexts. The obtained results confirm that LoRaWAN can be considered as a strongly viable opportunity, since it is able to provide high reliability and timeliness, while ensuring very low energy consumption.

The possibility of extending real-time Ethernet networks employed in industrial applications with wireless links can lead to several benefits in terms of cost reduction and easier deployment. However, delays and jitter introduced by both the wireless medium and the interconnection systems may degrade the network performance significantly. This paper describes the advantages introduced by the IEEE 802.11n WLAN amendment in this scenario and considers, as an example of application, its use for the wireless extension of an Ethernet Powerlink network. Different configurations are compared through experimental measurements, showing that an adequate setting of the IEEE 802.11 MAC parameters, as well as the use of a suitable rate adaptation technique, allow to achieve effective performance. Particularly, a bounded polling time can be obtained, which represents a fundamental aspect for real-time communications.

Wireless sensor networks (WSNs) can provide numerous benefits in industrial automation. By removing the cable infrastructure, the wireless architecture enables the possibility for nodes in a network to dynamically and autonomously group into clusters according to the communication features and the data they collect. This capability allows to leverage the flexibility and robustness of industrial WSNs in supervisory intelligent systems for high-level tasks, such as, for example, environmental sensing, condition monitoring, and process automation. In this paper, a clustering strategy is studied that partitions a sensor network into a nonfixed number of nonoverlapping clusters according to the communication network topology and measurements distribution: To this aim, both a centralized and a distributed algorithm are designed that do not require a cluster-head structure or other network assumptions. As a validation, these strategies are tested on a real dataset coming from a structured environment and the effectiveness of the clustering procedure is also investigated to perform anomalies detection in an industrial production process.

Industrial applications aimed at real-time control and monitoring of cyber-physical systems pose significant challenges to the underlying communication networks in terms of determinism, low latency, and high reliability. The migration of these networks from wired to wireless could bring several benefits in terms of cost reduction and simplification of design, but currently available wireless techniques cannot cope with the stringent requirements of the most critical applications. In this paper, we consider the problem of designing a high-performance wireless network for industrial control, targeting at Gbps data rates and 10-μs-level cycle time. To this aim, we start from analyzing the required performance and deployment scenarios, then we take a look at the most advanced standards and emerging trends that may be applicable. Building on this investigation, we outline the main directions for the development of a wireless high-performance system.

The next generations of industrial control systems will require high-performance wireless networks (named WirelessHP) able to provide extremely low latency, ultrahigh reliability, and high data rates. The current strategy toward the realization of industrial wireless networks relies on adopting the bottom layers of general purpose wireless standards and customizing only the upper layers. In this paper, a new bottom-up approach is proposed through the realization of a WirelessHP physical layer specifically targeted at reducing the communication latency through the minimization of packet transmission time. Theoretical analysis shows that the proposed design allows a substantial reduction in packet transmission time, down to 1 μs, with respect to the general purpose IEEE 802.11 physical layer. The design is validated by an experimental demonstrator, which shows that reliable communications up to 20 m range can be established with the proposed physical layer.

The multirate support feature has been introduced by the IEEE 802.11 standard to improve the system performance, and has been widely exploited by means of rate adaptation (RA) strategies within general purpose wireless LANs. These strategies revealed ineffective for real-time industrial communications, and alternative solutions, better tailored for such a specific field of application, were investigated. The preliminary outcomes of the analyses carried out were promising, even if they clearly indicated that further efforts were necessary. In this direction, this paper first proposes rate selection for industrial networks (RSIN), an innovative RA algorithm specifically conceived for the real-time industrial scenario with the goal of minimizing the transmission error probability, while taking into account the deadline imposed to packet delivery. Then, it describes the practical implementation of RSIN on commercial devices, along with that of other formerly introduced RA techniques. Finally, the paper presents a thorough performance analysis, carried out to investigate the behavior of the addressed RA schemes. Such an assessment was performed via both experimental campaigns and simulations. The obtained results, on one hand, confirm the effectiveness of the RA techniques purposely designed for real-time industrial communication. On the other hand, they clearly indicate that RSIN outperforms all the other strategies.

Recently, several working implementations of inband full-duplex wireless systems have been presented, where the same node can transmit and receive simultaneously in the same frequency band. The introduction of such a possibility at the physical layer could lead to improved performance but also poses several challenges at the MAC layer. In this paper, an innovative mechanism of channel contention in full-duplex OFDM wireless networks is proposed. This strategy is able to ensure efficient transmission scheduling with the result of avoiding collisions and effectively exploiting full-duplex opportunities. As a consequence, considerable performance improvements are observed with respect to standard and state-of-the-art MAC protocols for wireless networks, as highlighted by extensive simulations performed in ad hoc wireless networks with varying number of nodes.

In this paper, statistical Quality of Service provisioning in next generation heterogeneous mobile cellular networks is investigated. To this aim, any active entity of the cellular network is regarded as a queuing system, whose statistical QoS requirements depend on the specific application. In this context, by quantifying the performance in terms of effective capacity, we introduce a lower bound for the system performance that facilitates an efficient analysis. We exploit this analytical framework to give insights about the possible improvement of the statistical QoS experienced by the users if the current heterogeneous cellular network architecture migrates from a Half Duplex to a Full Duplex mode of operation. Numerical results and analysis are provided, where the network is modeled as a Matérn point processes with a hard core distance. The results demonstrate the accuracy and computational efficiency of the proposed scheme, especially in large scale wireless systems.

IEEE 802.11 wireless LANs introduced the Multi-Rate Support as an effective tool for performance tuning. This feature is implemented by means of specific Rate Adaptation (RA) algorithms, that in general have been designed with the goal of throughput maximization, targeting at general purpose communication networks. Unfortunately, industrial real-time communication systems are characterized by very different performance requirements, and hence dedicated, more tailored, RA algorithms have to be devised. The proposed algorithm called Rate Selection for Industrial Networks (RSIN) is a significant step in this direction, being designed from its beginning as an optimization problem, in which the knowledge of the signal-to-noise-ratio is exploited to cope with the industrial traffic requirements. A preliminary assessment has indicated that the performance figures of RSIN are promising. In this paper, we aim at providing a complete characterization of such algorithm, assessing the impact of possible uncertainties in the estimation of the channel status and evaluating the scalability of the proposed strategy from one link to a network. The outcomes of these analyses revealed that RSIN is able to enhance timeliness and reliability of a wireless network in a robust and scalable way, making it suitable for adoption in industrial contexts.

The Multirate Support feature has been introduced by the IEEE 802.11 standard to improve system performance. It has been widely exploited within general purpose Wireless LANs by means of Rate Adaptation (RA) strategies, that unfortunately revealed ineffective for the case of real-time industrial communications. This paper presents the innovative Rate Selection for Industrial Networks (RSIN) algorithm, specifically conceived for the real-time industrial scenario with the goal of minimizing the transmission error probability, while taking into account the deadlines imposed to packet delivery.

In the last years, IEEE 802.11 Wireless LANs (WLANs) have proved their effectiveness for a wide range of real-time industrial communication applications. Nonetheless, the introduction of the important IEEE 802.11n amendment, which is commonly implemented in commercial devices, has not been adequately addressed in this operational framework yet. IEEE 802.11n encompasses several enhancements at both physical (PHY) and medium access control (MAC) layers that may bring considerable improvements to the performance of WLANs deployed in real-time industrial communication systems. To this regard, in this paper, we present a thorough investigation of the most important IEEE 802.11n features, addressing in particular, specific performance indicators such as timeliness and reliability, which are crucial for industrial communication systems. To this aim, after an accurate theoretical analysis, we implemented a suitable experimental setup and carried out several measurement sessions to obtain an exhaustive performance assessment. The outcomes of these experiments, on one hand, revealed that the adoption of IEEE 802.11n can actually provide significant improvements to the performance of the IEEE 802.11 WLAN in the industrial communication scenario. On the other hand, the assessment allowed to select, among the various options of IEEE 802.11n, the parameter settings which may ensure the best behavior in this specific (and demanding) field of application.

The IEEE 802.11 standard, since its earliest versions, provides the multi-rate support feature typically exploited by Rate Adaptation (RA) techniques to dynamically select the most suitable transmission rate, based on an estimation of the channel status. With the release of the IEEE 802.11n amendment, several enhancements have been introduced to the standard, notably the support for MIMO architectures, whose benefits can be effectively combined with multi-rate support. In an industrial communication scenario, the RA algorithms commonly available for general purpose applications revealed ineffective. This led to the definition of purposely designed algorithms, with the aim of improving the real-time behavior of IEEE 802.11 networks. In this paper we take into consideration these techniques, as well as some general purpose RA strategies, and analyze their implementation on an IEEE 802.11n communication system deployed in an industrial scenario. Furthermore, we propose an effective parameters tuning for the considered RA algorithms, as well as some enhancements conceived to enforce their timeliness. An exhaustive assessment, carried out via numerical simulations, shows that the improved techniques allow to achieve excellent performance.

IEEE 802.11 systems are drawing an ever increasing interest for wireless industrial communication, also thanks to the interesting features provided by the most recent and advanced amendments to this standard, such as IEEE 802.11n. Due to the intrinsic unreliability of the wireless medium, the current research efforts aim at improving both timeliness and reliability of such a protocol in view of its adoption for real-time applications. A significant issue in this context is represented by the reduction of the randomness that affects packet delivery times. An important benefit in this direction can be obtained by the deactivation of the standard legacy carrier sensing and backoff procedures. In this paper we show, through a simulative assessment, that a fine control of such features leads to improved real-time performance.

In the last years, IEEE 802.11 Wireless LANs (WLANs) have proved their effectiveness for a wide range of real-time industrial communication applications. Nonetheless, the enhancements at the PHY and MAC layers introduced by the IEEE 802.11n amendment have not yet been adequately addressed in the context of industrial communication. In this paper we investigate the impact of some IEEE 802.11n new features on some important performance figures for industrial applications, such as timeliness and reliability.

This paper investigates an original system for wireless control and monitoring of an agricultural machine. The system is implemented by means of an IEEE 802.11-based soft realtime communication architecture which enables the connection of the machine with off-the-shelf mobile devices, like widespread tablet PCs, that could hence replace traditional ad-hoc developed operator panels. The harsh surrounding environment, however, introduces severe requirements. Hence, focusing on the wireless communication behavior, the paper yields a thorough performance analysis derived by extensive experimental campaigns. By investigating the outcomes of these measurement sessions, the paper assesses some causes of performance degradation, and provides viable and easy to implement solutions to improve the overall system behavior.