Hybrid intelligent systems for pneumatic sequential circuit design: Hybridizing genetic algorithms and rule-based logic programming

This book presents cutting-edge emerging technologies and approaches in the areas of service-oriented architectures, intelligent devices and cloud-based cyber-physical systems. It provides a clear view on their applicability to the management and automation of manufacturing and process industries. It offers a holistic view of future industrial cyber-physical systems and their industrial usage and also depicts technologies and architectures as well as a migration approach and engineering tools based on these. By providing a careful balance between the theory and the practical aspects, this book has been authored by several experts from academia and industry, thereby offering a valuable understanding of the vision, the domain, the processes and the results of the research. It has several illustrations and tables to clearly exemplify the concepts and results examined in the text and these are supported by four real-life case-studies. We are witnessing rapid advances in the industrial automation, mainly driven by business needs towards agility and supported by new disruptive advances both on the software and hardware side, as well as the cross-fertilization of concepts and the amalgamation of information and communication technology-driven approaches in traditional industrial automation and control systems. This book is intended for technology managers, application designers, solution developers, engineers working in industry, as well as researchers, undergraduate and graduate students of industrial automation, industrial informatics and production engineering.

We present Timing Diagram Testing for Verification & Validation (T4V, which is red as tav) for Industrial Automation Systems. T4V is our approach to address the problem of generating test sequence to verify & validate (V&V) industrial automation systems software. T4V aims to solve this problem by generating test sequences from the timing diagrams of software specifications. Then, run them in Real-Time (RT) onto the PLC, check part of their conformance on-the-run, save the test outlines, and automatically analyze the outlines through an algorithmic verification. We currently implemented T4V for IEC61131-3 platforms (e.g. Beckhoff TwinCAT3) and Rockwell Automation PLCs, but we are integrating it only in our testing and V&V platform for Beckhoff PLCs. We believe that T4V may simplify and/or face the challenges of V&V in order to enable a more efficient and effective testing. Moreover, we believe that it could help PLC providers to understand the needs of an environment with testing and V&V features integrated.

The aim of this research paper is to propose an alternative but possible practical solution to basic key and common security threats such as overloading (Flooding Attacks) and their associated risks to a typical industrial automation system. For this purpose, countermeasures that can be directly implemented in end points regardless of any specific hardware or deployment platform are considered here. These proposed solutions include developing new control systems that can defend associated industrial automation processes and themselves against such attacks, i.e., identifying and building a defense mechanism in control algorithm, and hence named self-defending control strategies. For demonstration an example of such control algorithms was developed and simulation results are presented.

Industrial automation and control systems (IACS) are tremendously employing supervisory control and data acquisition (SCADA) network. However, their integration into IACS is vulnerable to various cyber-attacks. In this article, we first present population extremal optimization (PEO)-based deep belief network detection method (PEO-DBN) to detect the cyber-attacks of SCADA-based IACS. In PEO-DBN method, PEO algorithm is employed to determine the DBN's parameters, including number of hidden units and the size of mini-batch and learning rate, as there is no clear knowledge to set these parameters. Then, to enhance the performance of single method for cyber-attacks detection, the ensemble learning scheme is introduced for aggregation of the proposed PEO-DBN method, called EnPEO-DBN. The proposed detection methods are evaluated on gas pipeline system dataset and water storage tank system dataset from SCADA network traffic by comparing with some existing methods. Through performance analysis, simulation results show the superiority of PEO-DBN and EnPEO-DBN.

With the increasing use of Internet of Things (IoT) devices in various industries, the challenge of efficient use of energy and reducing the amount of device downtime is a key concern in sustainable and reliable systems usage. The paper deals with energy consumption optimization and the forecasting of device failures in the IoT systems in industrial automation. More precisely, we suggest the hybrid solution consisting of reinforcement learning (RL) to optimize energy consumption, Long Short-Memory (LSTM) networks to predictive maintenance, and edge-cloud offloading solutions to improve the performance of devices and their sustainability. We use the modeling of heterogeneous IoT devices in our methodology, but with different energy profiles, different workloads, and operational modes. We use RL to dynamically tweak devices modes, which saves energy and does not impact task completion. We combine predictive maintenance, in which we use LSTM to forecast device failures using historical data to give timely warnings on maintenance. Moreover, the edge-cloud offloading decisions are also integrated into our system to further optimize the energy consumption and optimize the efficiency of performing tasks. The principal results are that our method is highly energy efficient and device uptime, and reinforcement learning is the most energy saving method. The predictive maintenance model is an effective way of cutting on the downtime, as the correct prediction of the occurrence of failure results in the taking of preventive measures. Task offloading, especially when there are resource constraints, improves system reliability without affecting the performance. Such findings indicate that adaptive IoT systems could be used to optimize energy use and system performance and, therefore, make industrial automation more sustainable. Our solution is informative to the design of future IoT systems in which energy efficiency and predictable stability will be the most crucial attributes. Keywords: IoT Energy Optimization, Predictive Maintenance, Reinforcement Learning, LSTM Networks, Edge-Cloud Offloading.

We describe our ongoing work and view on simulation, validation and visualization of cyber-physical systems in industrial automation during development, operation and maintenance. System models may represent an existing physical part - for example an existing robot installation - and a software simulated part - for example a possible future extension. We call such systems cyber-virtual systems. In this paper, we present the existing VITELab infrastructure for visualization tasks in industrial automation. The new methodology for simulation and validation motivated in this paper integrates this infrastructure. We are targeting scenarios, where industrial sites which may be in remote locations are modeled and visualized from different sites anywhere in the world. Complementing the visualization work, here, we are also concentrating on software modeling challenges related to cyber-virtual systems and simulation, testing, validation and verification techniques for them. Software models of industrial sites require behavioural models of the components of the industrial sites such as models for tools, robots, workpieces and other machinery as well as communication and sensor facilities. Furthermore, collaboration between sites is an important goal of our work.

[Context and motivation] Cyber-physical systems, like modern cars and industrial automation systems, are highly connected and complex. [Question/problem] Their various interconnections open interfaces for attackers, and their complexity increases the risk of undetected security vulnerabilities. Hence, an important part of requirements engineering is threat modeling. It is a means to elicit security assets, goals, and assumptions, and to derive required security controls. Effective threat modeling needs a systematic workshop setup. [Principal ideas/results] In this paper, we report our experiences and lessons learned from threat modeling workshops that we conducted with industry partners from the domains of industrial automation, health care, smart home, and automotive. [Contribution] In conclusion, we derive a set of open challenges.

Today's industrial automation systems are undergoing a digital transformation that implies a shift towards the Internet of Things (IoT), leading to the Industrial Internet of Things (IIoT) paradigm. Existing Industrial Automated Control Systems (IACS), enriched with a potentially large number of IoT devices are expected to make systems more efficient, flexible, provide intelligence, and ultimately enable autonomous control. In general, the majority of such systems come with high level of criticality that calls for well-established methods and approaches when achieving cybersecurity, preferably prescribed by a standard. IEC 62443 is an industrial standard that provides procedures to manage risks related to cybersecurity threats in IACS. Given the new IIoT paradigm, it is likely that existing standards are not sufficiently aligned with the challenges related to developing and maintaining cybersecurity in such systems. In this paper we review the applicability of the IEC 62443 standard in IIoT contexts and discuss potential challenges the process owners might encounter. Our analysis underlines that some areas within the standard could prove difficult to reach compliance with. In particular, handling of cross zone communication and software updates require additional guidance.

This papers presents a design and implementation technique to develop an IIoT gateway that works as Device-to-Cloud gateway. The gateway is specifically designed and implemented based on industrial automation systems. It is designed to support traditional sensors and actuators that operate on standard current and voltage values (4–20mA, 0–12V or 0–24V). Also it can communicate to Modbus devices using Modbus-RTU protocol. With these design features, the proposed system can be used in many industrial automation applications. To achieve the real-time ability of the system, the WebSocket protocol is implemented in both microcontroller (MCU) and Cloud system. The IIoT gateway is implemented on a 16-bit MCU. The MCU is preprogrammed with special firmware. The firmware is designed and implemented based on real-time multitasking and interrupt-driven to be sure it can serve all required tasks on time. To make the MCU can communicate to the Cloud system, the WiFi module that supports TCP/IP protocol is connected to the MCU. To fully evaluate and examine the proposed system, four channels of sensors, four channels of actuators, and six Modbus devices (Power meters) are used to construct an experimental system. There are three web-applications developed to examine the data communication between the IIoT gateway and the Cloud system. The experimental results show that the proposed IIoT gateway can exchange desired data to the Cloud system, back and forth as real-time data streaming.

A lot of emphasis is being placed on the research experience at undergraduate level both by institutions of higher learning as well as industries focusing on research&development (R&D). This requires a twofold effort. First is to develop research competency in teaching faculty so that they can act like mentors and second is to develop a process so that the students develop basic research skills through practice. Parallels can be drawn between the Engineering Design (ED) process and research skill building process in terms of creativity and problem solving. Similar to the ED process, a converging and diverging process can be used to creative problem research. This process has been introduced as part of a course project at the third year level for the course Programming Industrial Automation Systems. This paper tries to demonstrate the process through which a structured literature survey is carried out by the students leading to a variety of research problems. This process is carried out as a team activity. Research assignments have been integrated in the course, which requires students to find information on automation related topic using both print and electronic resources available at the college library and on the Internet. Aiming to foster the development of technical information literacy and communication skills, the students are required to prepare a report based on a specific set of guidelines, followed by implementation of the solution and oral presentations of the topics researched. A lecture on the subject of identifying and using information resources is included in the syllabus. Preliminary results of the study are presented along with directions for designing and implementing an enriched curriculum for Automation course.

There have been considerable advances in low power, integration and micro-systems technologies, enabling wireless communication for very small, affordable, lightweight and high performance devices. These technologies are still mainly used for consumer and office applications, but significant advantages can be obtained by applying the technologies to new areas. One area of particular interest industrial is automation and control systems, such as robotics and factory automation. In this paper we discuss the main challenges involved with realizing a reliable, wireless, and energy autonomous communication system suited for industrial automation. Special emphasis is placed on providing an overview of suitable power supply possibilities and describing a novel magnetic medium frequency power supply concept enabling true wireless energy supply within cell-volumes of more than 100 m/sup 3/ with sufficiently small infrastructure. The novel resonant power supply concept uses medium frequencies (/spl sim/120 kHz) in a coreless transformer, enabling the supply of devices within a certain volume, for example a production cell, surrounded by coils. By using omni-directional or rotating magnetic fields, together with three orthogonal receiver coils, it enables a shielding tolerant supply system with unique properties. Compared to primary battery technologies, the new approach offers approximately 50 times higher energy densities over the application lifetime.

In recent years, the industrial automation of cigarette enterprises has made great progress, and the underlying data acquisition, centralized control and condition monitoring systems have been established. The management has also established a large number of application systems. There are a large number of equipment data resources in these industrial automation systems and application systems, but incremental data value mining is difficult to really solve the problem. The exploration of big data and machine learning has gradually encountered bottlenecks and ceilings, Lack of integration of domain knowledge, it is difficult to mine high-value application scenarios. From the point of view of "semantic analysis" and "equipment management", it is necessary to establish a unified method of data collection and application, which is the basis of effective data collection and management. From the perspective of "semantic analysis" and "equipment management", it is necessary to establish a unified method of data collection and application.

In today's competitive industry marketplace, the companies face growing demands to improve process efficiencies, comply with environmental regulations, and meet corporate financial objectives. Given the increasing age of many industrial systems and the dynamic industrial manufacturing market, intelligent and low-cost industrial automation systems are required to improve the productivity and efficiency of such systems. The collaborative nature of industrial wireless sensor networks (IWSNs) brings several advantages over traditional wired industrial monitoring and control systems, including self-organization, rapid deployment, flexibility, and inherent intelligent-processing capability. In this regard, IWSN plays a vital role in creating a highly reliable and self-healing industrial system that rapidly responds to real-time events with appropriate actions. In this paper, first, technical challenges and design principles are introduced in terms of hardware development, system architectures and protocols, and software development. Specifically, radio technologies, energy-harvesting techniques, and cross-layer design for IWSNs have been discussed. In addition, IWSN standards are presented for the system owners, who plan to utilize new IWSN technologies for industrial automation applications. In this paper, our aim is to provide a contemporary look at the current state of the art in IWSNs and discuss the still-open research issues in this field and, hence, to make the decision-making process more effective and direct.

Artificial Intelligence (AI) is revolutionizing industrial process automation by introducing intelligent decision-making and adaptive control to traditionally deterministic systems. In the petrochemical and oil & gas industries where safety, efficiency, and reliability are paramount, AI technologies such as machine learning, deep learning, and digital twins enhance plant operations through predictive maintenance, process optimization, and asset integrity management. Despite challenges in certification, data quality, and cybersecurity, AI continues to evolve as an indispensable enabler of smart and self-optimizing industrial plants. This research examines the integration of AI within programmable logic controllers (PLCs), distributed control systems (DCS) and supervisory control and data acquisition (SCADA) frameworks, the improvements it brings in efficiency, energy management, and maintenance scheduling as well as examines the real-world implementations from major automation vendors such as Honeywell, Emerson, Yokogawa and Siemens.

Future industrial process automation systems will be underpinned by wireless communication technology. The use of wireless networks in industrial applications cannot be viewed simply as a cable replacement mechanism: instead, it has the potential to enhance the functionality of the entire system by exploiting the complexity of the network topology and the massively-interacting communication paradigm. In this paper we develop a wireless cloud platform that efficiently exploits intelligence at field device side to handle critical conditions that require fast transfer of data under stringent reliability and latency constraints. The cloud system acts as a self-contained network and it is designed to interact with devices supporting the Time Synchronized Channel Hopping protocol (TSCH) such as the commercial WirelessHART systems (IEC 62591 standard). The cloud platform handles the delivery of critical data by acting as a hardware as a service (HaaS) provider and implementing a cooperative-multihop forwarding scheme. Experimental activities are presented to show the feasibility of the approach in a real industrial plant. System validation shows substantial improvements compared with standard industrial solutions, both in terms of observed throughput (for high data transfer applications) and latency (for delay-sensitive data publishing services).