Industrial Cyber-physical Systems Research Articles

Industrial Process Modeling and Monitoring Based on Jointly Specific and Shared Dictionary Learning

With the development of Industrial Cyber-Physical Systems, data of industrial processes is collected and be used for data-driven process monitoring. But due to the variation of working conditions, the data samples are always featured by characteristics and commonalities. Generally, in industrial process data, characteristics are sparse and commonalities are strongly correlated. The presence of characteristics hampers the feature extract of industrial data, thus further bringing difficulties to process monitoring. To solve this problem, this paper proposes a Jointly Specific and Shared Dictionary Learning (JSSDL) method. Specifically, we first build a specific dictionary and a shared dictionary to reconstruct characteristics and commonalities feature respectively. Then, considering the sparsity of characteristics and the strong correlation of commonalities, we add sparsity constraint to specific dictionary and low-rank constraint to shared dictionary. After that, an iterative optimization algorithm is proposed to optimize the two dictionaries. When online data samples arrive, we use the two dictionaries to reconstruct the data and determine the data is normal or faulty according to the reconstruction error. To verify the superiority of the proposed JSSDL method in process monitoring, we do extensive experiments. The experimental results demonstrate that the proposed method can achieve satisfactory monitoring results when compared with several state-of-the-art methods.

Wireless/wired integrated transmission for industrial cyber-physical systems: risk-sensitive co-design of 5G and TSN protocols

Wireless/wired integrated transmission for industrial cyber-physical systems: risk-sensitive co-design of 5G and TSN protocols

Plant Factory: A New Playground of Industrial Communication and Computing.

Plant Factory is a newly emerging industry aiming at transforming crop production to an unprecedented model by leveraging industrial automation and informatics. However, today’s plant factory and vertical farming industry are still in a primitive phase, and existing industrial cyber-physical systems are not optimal for a plant factory due to diverse application requirements on communication, computing and artificial intelligence. In this paper, we review use cases and requirements for future plant factories, and then dedicate an architecture that incorporates the communication and computing domains to plant factories with a preliminary proof-of-concept, which has been validated by both academic and industrial practices. We also call for a holistic co-design methodology that crosses the boundaries of communication, computing and artificial intelligence disciplines to guarantee the completeness of solution design and to speed up engineering implementation of plant factories and other industries sharing the same demands.

CycleStyleGAN-Based Knowledge Transfer for a Machining Digital Twin.

Digitalisation of manufacturing is a crucial component of the Industry 4.0 transformation. The digital twin is an important tool for enabling real-time digital access to precise information about physical systems and for supporting process optimisation via the translation of the associated big data into actionable insights. Although a variety of frameworks and conceptual models addressing the requirements and advantages of digital twins has been suggested in the academic literature, their implementation has received less attention. The work presented in this paper aims to make a proposition that considers the novel challenges introduced for data analysis in the presence of heterogeneous and dynamic cyber-physical systems in Industry 4.0. The proposed approach defines a digital twin simulation tool that captures the dynamics of a machining vibration signal from a source model and adapts them to a given target environment. This constitutes a flexible approach to knowledge extraction from the existing manufacturing simulation models, as information from both physics-based and data-driven solutions can be elicited this way. Therefore, an opportunity to reuse the costly established systems is made available to the manufacturing businesses, and the paper presents a process optimisation framework for such use case. The proposed approach is implemented as a domain adaptation algorithm based on the generative adversarial network model. The novel CycleStyleGAN architecture extends the CycleGAN model with a style-based signal encoding. The implemented model is validated in an experimental scenario that aims to replicate a real-world manufacturing knowledge transfer problem. The experiment shows that the transferred information enables the reduction of the required target domain data by one order of magnitude.

$R$-Print: A System Residuals-Based Fingerprinting for Attack Detection in Industrial Cyber-Physical Systems

Industrial cyber-physical systems (ICPSs) are widely used to facilitate accurately remote control in industrial application fields using cyberspace technologies. However, it is easily suffered from internal vulnerabilities and other external threats from cyberspace, e.g., the attacker can bypass the intrusion detection systems to access inner network and destroy devices, due to the deployed old-fashioned hardware and software. From the view of the system control level, we propose a system residuals-based fingerprinting for attack detection, namely, R-print. We first abstract the actual water-level system as a physical model. Then, the measurement noise and the process noise from the sensor and system operation, respectively, are extracted as the input of model, and the output residual is synthesized into the unique fingerprint. Furthermore, we also propose a data resampling strategy to focus on the problem that how to fast detect the injection attack with small-value false data. Finally, a small water-level control testbed was built to simulate the real-scenario of the industrial water treatment process. The experimental results verify the effectiveness of the proposed attack detection approach.

Control, computing and communication in industrial cyberphysical systems with feedback

The cyber-physical production base technologies are control, computing and connection being applied altogether in the industrial object technological processes automatic regulation systems. They use control technologies in multi-loops and multi-channel regulation systems forming a hierarchy structure. Automatics functional elements unite in the intermediary regulation scheme stabilizing hierarchy control objects, which states are detected with sensors. Computing technologies are used in the cyber-physical production imitation virtual environment and provide processes simulation based on control models and cyber-physical systems digital twins structured in hierarchy levels. The regulation accuracy increase is provided with physical and model processes results comparison detecting non-definition factors acting production processes accuracy. The communication technology is used for the cyber-physical systems net information exchange given with the Internet of Things parameters. The cyber-physical systems continuous work in the non-ideal communication net regulation interval is provided with preventive control signals compensating operation and information delay of automatic conveyor lines. There is a scheme given of multi-loop and multi-channel automatic cyber-physical production using control objects hierarchy based on cyber-physical systems hierarchy and item manufacturing technological tasks.

ALPHA: An Anonymous Orthogonal Code-Based Privacy Preserving Scheme for Industrial Cyber–Physical Systems

Internet of Things has revolutionized the ways and means of use and management of electric grid systems. Now, the old mechanical grids are equipped with smart devices that not only automate the traditional grid but enable two way communications between the user and power suppliers called smart grid. Although, a lot of protocols have been developed to enable a secure communication between suppliers and consumers, cyber-physical systems (CPSs) are prone to privacy issues where adversaries may have access to particular users' information. In this article, an anonymous orthogonal code-based privacy preserving scheme, named ALPHA, is proposed for CPSs. The CPS is considered as a basic unit of the modern smart grid, which aggregates the power consumption from smart devices by keeping the user information confidential, anonymous, and untraceable. The proposed scheme, ALPHA, uses orthogonal bit codes and a systematized method to authenticate and manage the anonymity and untraceablity of user data along with low communication and computation overheads.

Artificial Intelligence-Based Decision-Making Algorithms, Internet of Things Sensing Networks, and Deep Learning-Assisted Smart Process Management in Cyber-Physical Production Systems

With growing evidence of deep learning-assisted smart process planning, there is an essential demand for comprehending whether cyber-physical production systems (CPPSs) are adequate in managing complexity and flexibility, configuring the smart factory. In this research, prior findings were cumulated indicating that the interoperability between Internet of Things-based real-time production logistics and cyber-physical process monitoring systems can decide upon the progression of operations advancing a system to the intended state in CPPSs. We carried out a quantitative literature review of ProQuest, Scopus, and the Web of Science throughout March and August 2021, with search terms including “cyber-physical production systems”, “cyber-physical manufacturing systems”, “smart process manufacturing”, “smart industrial manufacturing processes”, “networked manufacturing systems”, “industrial cyber-physical systems,” “smart industrial production processes”, and “sustainable Internet of Things-based manufacturing systems”. As we analyzed research published between 2017 and 2021, only 489 papers met the eligibility criteria. By removing controversial or unclear findings (scanty/unimportant data), results unsupported by replication, undetailed content, or papers having quite similar titles, we decided on 164, chiefly empirical, sources. Subsequent analyses should develop on real-time sensor networks, so as to configure the importance of artificial intelligence-driven big data analytics by use of cyber-physical production networks.

AI-empowered, blockchain and SDN integrated security architecture for IoT network of cyber physical systems

Internet of things (IoT) is one of the most emerging technologies nowadays and it is one of the key enablers of industrial cyber physical system (CPSs). It has started to participate in almost every aspect of our social life, ranging from financial transactions to the healthcare system, communication to national security, battlefield to smart homes, and so on. However, the wide deployment of IoT suffers certain issues as well, such as interoperability, compatibility, heterogeneity, large amount of data, processing of heterogeneous data etc. Among others, energy efficiency and security are the utmost prominent issues. Scarce computing resources of IoT devices put hindrances on information sharing across edge or IoT network. Indeed, unintentional or malicious interference with IoT data may lead to severe concerns. In this study, the researcher exploits the potential benefits of a blockchain system and integrates it with software-defined networking (SDN) while justifying energy and security issues. More in detail, the researcher proposed a new routing protocol with the cluster structure for IoT networks using blockchain-based architecture for SDN controller. The proposed architecture obviates proof-of-work (PoW) with private and public blockchains for Peer-to-Peer (P2P) communication between SDN controllers and IoT devices. In addition to this, distributed trust-based authentication mechanism makes blockchain even more adoptive for IoT devices with limited resources. The experimental results show that the proposed cluster structure based routing protocol outperforms the state-of-the-art Ad-hoc On-demand Distance Vector (AODV), Destination-Sequenced Distance Vector (DSDV), Secure Mobile Sensor Network (SMSN), Energy efficient secured cluster based distributed fault diagnosis (EESCFD), and Ad-hoc On-demand Multipath Distance Vector (AOMDV), in terms of energy consumption, network throughput, and packet latency. Proposed protocol help overcome the issues especially, energy management and security of the next generation industrial cyber physical systems.

Fault-Resilience for Bandwidth Management in Industrial Software-Defined Networks

Industrial Cyber-Physical Systems (ICPS) expect assurances of timely delivery of data even during the occurrence of distinct faults. It is a challenge to manage the required bandwidth by providing resilience to link failures and dynamically changing bandwidth requirements. In this paper, we address the aforementioned challenge by exploring Software-Defined Networks (SDN). We present a framework coined SDN-RMbw (Software-Defined Networking Resilience Management for Bandwidth), which is a contract-based framework, where the components are bound to bandwidth contracts and a resilience manager. The bandwidth contracts state the bandwidth requirements of traffic flows. With each such contract, a monitor is associated, which is responsible to detect two events, run-time changes and link failures. Directly after receiving the event trigger reports from the monitor, new routes are calculated by a path-finding algorithm. Based on newly calculated routes, an observer detects whether the contract requirements are still satisfied, or the contract gets violated (termed as fault). To provide resilience to such faults in the network, a resilience manager integrated with control logic decides and executes a suitable response strategy. The proposed SDN-based framework aims at providing fault-resilience as well as adapting to different network-state changes. The proposed framework is evaluated using a Ryu SDN controller on a hardware testbed. Our results show that the proposed framework provides enhanced network resilience as compared to baseline mechanisms and improves the success rate up to 21% and bandwidth up to 111 Mbps under distinct network scenarios. Furthermore, extensive experimental emulations on the Mininet tool depicts the scalability of the proposed framework.

Continuous detection of concept drift in industrial cyber-physical systems using closed loop incremental machine learning

The embedded, computational and cloud elements of industrial cyber physical systems (CPS) generate large volumes of data at high velocity to support the operations and functions of corresponding time-critical and mission-critical physical entities. Given the non-deterministic nature of these entities, the generated data streams are susceptible to dynamic and abrupt changes. Such changes, which are formally defined as concept drifts, leads to a decline in the accuracy and robustness of predicted CPS behaviors. Most existing work in concept drift detection are classifier dependent and require labeled data. However, CPS data streams are unlabeled, unstructured and change over time. In this paper, we propose an unsupervised machine learning algorithm for continuous concept drift detection in industrial CPS. This algorithm demonstrates three types of unsupervised learning, online, incremental and decremental. Furthermore, it distinguishes between abrupt and reoccurring drifts. We conducted experiments on SEA, a widely cited synthetic dataset of concept drift detection, and two industrial applications of CPS, task tracking in factory settings and smart energy consumption. The results of these experiments successfully validate the key features of the proposed algorithm and its utility of detecting change in non-deterministic CPS environments.

Accelerating privacy-preserving momentum federated learning for industrial cyber-physical systems

Federated learning (FL) is a distributed learning approach, which allows the distributed computing nodes to collaboratively develop a global model while keeping their data locally. However, the issues of privacy-preserving and performance improvement hinder the applications of the FL in the industrial cyber-physical systems (ICPSs). In this work, we propose a privacy-preserving momentum FL approach, named PMFL, which uses the momentum term to accelerate the model convergence rate during the training process. Furthermore, a fully homomorphic encryption scheme CKKS is adopted to encrypt the gradient parameters of the industrial agents’ models for preserving their local privacy information. In particular, the cloud server calculates the global encrypted momentum term by utilizing the encrypted gradients based on the momentum gradient descent optimization algorithm (MGD). The performance of the proposed PMFL is evaluated on two common deep learning datasets, i.e., MNIST and Fashion-MNIST. Theoretical analysis and experiment results confirm that the proposed approach can improve the convergence rate while preserving the privacy information of the industrial agents.

An intelligent cognitive computing based intrusion detection for industrial cyber-physical systems

Advanced developments of Industrial Cyber-Physical Systems (CPSs), comprising Internet of Things (IoT) finds useful in several application areas such as transportation, smart cities, healthcare, energy distribution, agriculture, etc. At the same time, the increased utilization of industrial CPS offers many threats which could have major significances for users. Recently, cognitive computing and artificial intelligence techniques offer new opportunities for the revolution of industrial CPSs. Therefore, to achieve security in industrial CPS, AI based intrusion detection system (IDS) can be developed to detect anomalies and prevent their harmful effects. With this motivation, this paper presents a novel cognitive computing based IDS technique to achieve security in industrial CPS. The proposed model involves different stages of operations such as data acquisition, preprocessing, feature selection, classification, and parameter optimization. The proposed model involves preprocessing to discard the noise that exists in the data. Then, the presented model uses binary bacterial foraging optimization (BBFO) based feature selection technique to elect an optimal subset of features. Besides the gated recurrent unit (GRU) model is applied to identify the presence of intrusions in the industrial CPS environment. Finally, Nesterov-accelerated Adaptive Moment Estimation (NADAM) optimizer is applied for the hyperparameter optimization of the GRU model in such a way that the detection rate can be enhanced. In order to validate the performance of the BBFO-GRU model, a series of experiments were carried out using the data from industrial CPS and the resultant values highlighted the promising performance of the proposed model with an accuracy of 98.45%.

Mask-RCNN with spatial attention for pedestrian segmentation in cyber–physical systems

With the application of industrial cyber–physical systems in various fields such as transportation systems, smart cities, and medical systems, pedestrian scenarios are becoming more and more complex, which brings difficulties to pedestrian segmentation. The difficulty of pedestrian segmentation lies in the scene’s complexity where the pedestrian is located, including the pedestrian’s shooting angle, light, and obstructions, which makes it difficult to distinguish accurately. This paper proposes an S-Mask-RCNN network that integrates spatial attention mechanisms for pedestrian segmentation. Mask-RCNN uses residual neural networks in the feature extraction network, and the effect of model feature extraction is not ideal. Based on transfer learning, a spatial attention mechanism is introduced to focus more spatially on areas that need attention. The force mechanism focuses more on the areas that need attention in space. Experiments show that the S-Mask-RCNN method proposed in this paper has better performance than traditional Mask-RCNN in pedestrian segmentation. Experiments show that the S-Mask-RCNN method proposed in this paper has better performance than traditional Mask-RCNN in pedestrian segmentation, also can provide more comprehensive and practical information for the construction of cyber–physical systems.

Privacy-enhanced momentum federated learning via differential privacy and chaotic system in industrial Cyber–Physical systems

By leveraging Industrial Cyber–Physical Systems (ICPSs), deep learning-based methods are applied to address various industrial issues. Due to privacy policy reasons, conventional centralized learning (CL) may be improper for some industrial scenarios with sensitive data, such as smart medicine. Recently, federated learning (FL) as a novel collaboration learning approach has received extensive attention, which can break data barriers between different institutions to improve the model performance. However, the privacy information of the industrial agents may be inferred from their shared parameters. In this paper, we propose a Privacy-Enhanced Momentum Federated Learning framework, named PEMFL, that amalgamates differential privacy (DP), Momentum FL (MFL) and chaos-based encryption method. During the training, differentially privacy is used to disturb the industrial agents’ gradient parameters in order to preserve their privacy information. Meanwhile, each industrial agent uses the chaos system-based encryption method to encrypt the weight parameters of their local models, which has two advantages: (1) the encryption method can enhance privacy protection; (2) the cloud server cannot access the truth value of the global model parameters which is a vital asset to the industrial agents. In addition, Momentum Gradient Descent (MGD) and an adjusting learning rate schedule are adopted to improve training efficiency for the PEMFL. The performance of the PEMFL is evaluated based on two non-i.i.d datasets. Theoretical analysis and experimental results demonstrate the excellent performance of the PEMFL in terms of accuracy and privacy security.

Modelling and platform application of the behaviour of a cyber physical production system

ABSTRACT Cyber physical production systems (CPPSs) exemplify the application of cyber physical systems in the manufacturing industry and are the basis for realising Industry 4.0. However, the adaptivity, reconfigurability, and interoperability of CPPSs result in high complexity and uncertainty in their design and implementation. To rectify this problem, this paper proposes a behavioural model-driven modelling method for lifecycle support of CPPSs. To this end, the general framework and operating mechanism of the proposed model are first specified and a meta-modelling language is developed based on object-oriented timed coloured knowledge Petri net. Subsequently, the hierarchical modelling and platform application of the CPPS behaviour is realised, and a laboratory-scale case study that demonstrates the efficacy of the proposed approach is presented.

The Fourth IEEE International Conference On Industrial Cyber-Physical Systems [Society News

Presents information on the Fourth IEEE International Conference On Industrial Cyber-Physical Systems.

Few-Shot Bearing Fault Diagnosis Based on Model-Agnostic Meta-Learning

The rapid development of artificial intelligence and deep learning has provided many opportunities to further enhance the safety, stability, and accuracy of industrial Cyber-Physical Systems (CPS). As indispensable components to many mission-critical CPS assets and equipment, mechanical bearings need to be monitored to identify any trace of abnormal conditions. Most of the data-driven approaches applied to bearing fault diagnosis up-to-date are trained using a large amount of fault data collected a priori. In many practical applications, however, it can be unsafe and time-consuming to collect sufficient data samples for each fault category, making it challenging to train a robust classifier. In this paper, we propose a few-shot learning framework for bearing fault diagnosis based on model-agnostic meta-learning (MAML), which targets for training an effective fault classifier using limited data. In addition, it can leverage the training data and learn to identify new fault scenarios more efficiently. Case studies on the generalization to new artificial faults show that the proposed framework achieves an overall accuracy up to 25% higher than a Siamese network-based benchmark study. Finally, the robustness and the generalization capability of the proposed framework are further validated by applying it to identify real bearing damages using data from artificial damages, which compares favorably against 6 state-of-the-art few-shot learning algorithms using consistent test environments.

Ant colony resource optimization for Industrial IoT and CPS

Internet-of-Things (IoT) enabled cyber-physical systems (CPS) is a system in which communication between the physical devices and the cyber environment runs independently without any user interaction. Several optimization algorithms have been used for determining the optimal solutions that can reduce the production cost and/or enhance the production efficiency with in limited time-periods. However, existing optimization approaches have failed to solve the issues in the complex manufacturing process. To overcome this issue, a novel technique called directed acyclic graph theory based multiobjective oppositional learnt artificial ant colony resource optimization (DAGT-MOLAACRO) technique has been introduced in this study for solving the complex manufacturing process in the industry. Initially, IoT devices are used in the industrial sector for sensing and collecting data. Then the collected data is sent to the cyberspace of the CPS system with the least latency. Then, the CPS system collects the data generated from the industrial IoT devices that is stored in cyberspace with lesser memory consumption. MOLAACRO is applied to find the optimal solution among the population that satisfies the resource constraints by constructing the directed acyclic graph. In this way, the DAGT-MOLAACRO technique reduces the time complexity with minimal latency and computation overhead. For verification purposes, our experimental work has been carried out using different performance metrics such as data latency, time complexity, and computation overhead with respect to the number of IoT devices and the amount of data collected. The results show that the DAGT-MOLAACRO technique has better performance with reductions in terms of time complexity by 10%, latency by 17%, and the computation overhead by 11% against the existing works in literature.

Engineering human-focused Industrial Cyber-Physical Systems in Industry 4.0 context.

The world is increasingly interconnected, and this can also be seen in industry, where an ecosystem of digitalized assets, and humans with appropriate digital interfaces, constantly interact with each other. Digital transformation efforts in the industry rely on Industrial Cyber-Physical Systems that are driven by service-based cooperation among humans and digitalized industrial assets. This implies a radical paradigm change in their engineering and operation, which is focused on the symbiosis of digitalized assets and humans that cohabit a collaboration-driven industrial ecosystem. This work discusses how a digital transformation can effectively be achieved in an industrial ecosystem via a digitalization process performed along the three dimensions of the Reference Architecture Model for Industry 4.0, facilitated by the specification, development and implementation of an Asset Administration Shell. The discussion focus is put on humans and how the digitally transformed industrial environments empower her/his capabilities and interactions. It is also critically pointed out how one should go beyond technology and consider additional aspects. Therefore, it is argued that human-centred efforts in Industry 4.0 (I4.0) should be seen in the larger context of sustainability and circular economy in order to properly consider the interplay of the involved socio-technical dimensions. This article is part of the theme issue 'Towards symbiotic autonomous systems'.