Industrial Process Automation Research Articles

Edge architecture for the automation and control of flexible manufacturing lines

The automation and control of industrial machines and processes is a task traditionally performed by PLCs and SCADA systems. However, with the advent of Industry 4.0 paradigm, which merges OT and IT domains, this task can also be performed inside the IT domain. This paper proposes an edge architecture where a flexible manufacturing line is led by a state machine programmed and running on the IT domain inside the Manufacturing Execution System. Each industrial asset has been modelled as a black-box, where security and hard real-time functionalities are programmed and controlled inside each black-box by traditional OT tools. Functionalities and variables required to synchronize each black-box, have been modelled as inputs and outputs. These input and output variables and methods are available using Industry 4.0 industrial communication protocols, such as OPC UA or MQTT. Then, a state machine programmed on a high-level IT language model inside the MES, automates the manufacturing line reacting to the inputs and outputs of each black-box. This architecture has been successfully validated automating a manufacturing line composed by a conveyor, a robot and a vision based quality control system.

Autonomous Cycles of Data Analysis Tasks for the Automation of the Production Chain of MSMEs for the Agroindustrial Sector

In this paper, we propose autonomous cycles of data analysis tasks for the automation of the production chains aimed to improve the productivity of Micro, Small and Medium Enterprises (MSMEs) in the context of agroindustry. In the autonomous cycles of data analysis tasks, each task interacts with the others and has different functions, in order to reach the goal of the cycle. In this article, we identify three industrial-automation processes within the production chain, in which autonomous cycles can be applied. The first cycle is responsible to identify the type of input to be transformed—such as quantity, quality, time, and cost—based on information from the organization and its context. The second cycle selects the technological level used in the raw-material transformation, characterizing the platform of plant processing. The last cycle identifies the level of specialization of the generated product, such as the quality and value of the product. Finally, we apply the first autonomous cycle to define the type of input to be transformed in a coffee factory.

Design automation system synchronization for cyber physical system with dynamic voltage and frequency scaling in industry 5.0

Recent innovations in determining power—including the Internet of Things, M2M, online services, computational AI, and ARM-based big little multicores for encased applications—have aided in developing industrial process automation. Advanced IP-enabled, the fifth edition of Industry guidelines, are being implemented via actuators, sensing devices, and processors in machinery automation. This allows for increased degrees of competence with less human participation. Because of these novel innovations, the SCPS (Smart et al.) will be pivotal in the next industrialization phase. Multiple integrated systems with varying software are interconnected in an SCPS to perform tasks such as calculation, interaction, supervision, and action. Based on our findings, we propose an inconsistent structure for SCPS that facilitates the execution of composite workflow dynamics via electrical, pneumatic, and hydrodynamic operations. By modeling system problems, instrument postponement, operator interruption, and translation interruption, the proposed design allows for the separation of all components of an operational change, including calculation, oversight, interactions, and activation. This allows us to disentangle these many components. Voltage frequency islands (VFI) with an elevated level of flexibility are used to allocate intellectually integrated components to the many different physical operations, with the amount of flexibility varying from procedure to procedure. All modeled process parameters are fine-tuned using the Variable Volt and Fundamental Shifting methods. In the coming era of manufacturing 5.0, where human involvement is also a part of the procedure in different industries like fuel, compost, paper goods, concrete, space travel, and motor vehicle manufacturing, the suggested layout would be best suited for implementation.

The Place of Descriptive Geometry in the Face of Industry 4.0 Challenges

Industrial process automation has long been the main goal in production lines that seek to decrease human involvement. However, it is broadly agreed that a collaboration between humans and technologies must still exist as human capital is required to provide certain skills and abilities that machines cannot offer yet. For instance, in the context of design and simulation, CAD, CAM, and CAE professionals must count not only on a deep knowledge of the technology employed but also on specific skills that make the human factor an integral piece of the transition. These abilities are considered fundamental to achieving sustainable development in the industrial sector. This work focuses on analyzing through four study cases where whether specular o bilateral symmetry, a.k.a. planar symmetry is present, the weaknesses found in the human factor related to CAD training of future industrial engineers. The most common mistakes found when developing the different symmetric pieces proposed are thoroughly examined in order to define their origin, which mainly lies in students’ lack of descriptive geometry (DG) understanding. This is aggravated in some cases by the lack of spatial visualization abilities. The unstoppable and fast advances in design and simulation tools and technologies require humans to update their capabilities almost in real time. However, results show that this should not threaten the need for the human mind to spatially understand the changes being made on the screen. Otherwise, humans are at risk of ending up at the service of machines and technologies instead of the opposite.

Industry 4.0 in the electric sector: Findings from a systematic review of the literature

Also known as the Fourth Industrial Revolution, the concept of Industry 4.0 emerged in 2011 from a German government project, which stimulated the computerization of production lines in industries due to the increased demand for specific and personalized products using the growing evolution of new technologies that enabled the integration between machines in their production environment. Through a systematic literature review, this study seeks to understand the concepts of Industry 4.0 in the electricity sector, considering the aspects of its planning and the expected structural benefits, both in the quality of distributed energy and, consequently, in the application of this energy for the automation of industrial productive processes and smart cities. This study found twelve main dimensions most cited by the authors, of which five constructs of Industry 4.0 in the electricity sector were formed: infrastructure, technologies, smart solutions, sustainability, and energy management. Such constructs are interconnected like a gear system, on which each construct depends on the other. This study seeks to analyze the impacts, support elements, benefits, disadvantages, and the possibility of developing new procedures, products, and services that the technologies of Industry 4.0 can bring to the electrical sector and indirectly to its customers. It also aims to identify the factors that lead the top management to the right decision regarding the choice of technologies to increase efficiency and quality never previously achieved with current processes and technologies.

Development of an experimental prototype of a manufacturing cell for process automation teaching

For the industrial sector, the filling, sealing and labeling system represents one of the most used processes with several applications, that involves the food and beverage industry until the chemical plants, among many others applications. The propouse of this work is to develop an academic prototype of a manufacturing cell for teaching the automation of industrial processes, in order to emulate the filling, sealing and labeling system. The goal is to design a learning methodology such that the acquired academic knowledge can be transported to a real industrial environment. To achieve this, the PLC S7-300, industrial proximity sensors, pneumatic cylinders of the Festo brand, as well as their respective solenoid valves, are used. The programming methodology is based on a functional graph controlled by stages and transitions (GRAFCET). In contrart with other project based on Arduino, this project employs standard signals and variable scaling.

Importance of computational tools and artificial intelligence to improve drying processes for food preservation

Computational tools, including mathematical algorithms, specialized software, and artificial neural networks, along with the advancements in artificial intelligence, have brought significant advancements to industrial processes. Specifically, in food drying processes, such as those employed for grains, fruits, and vegetables, these tools have been demonstrated to play a crucial role in preserving the food itself and its nutritional value. This work highlights how artificial intelligence and computational tools have facilitated the automation of industrial processes (Engineering 4.0). Furthermore, it sheds light on the future potential of the man-machine interface, which is expected to give rise to Industry 5.0. The application of artificial intelligence in drying processes has demonstrated its impact on optimizing this unit operation by reducing process times, improving operating conditions, and predicting final quality characteristics of the products with remarkable accuracy, without requiring extensive experimentation or pilot tests.

Short Distance Detection and Control System Based on Photoelectric Sensor and Its Application in Target Detection of Handling Robot

The photoelectric sensor is an electronic device that is widely used in industrial automation processes. The device uses light to detect whether an object exists. The photoelectric sensor detection control system is the core part of the photoelectric sensor. The system includes sensor processing chip, control circuit, detection optical structure and automatic teaching control algorithm. In this research, the core control chip of the automatic teaching system and the core part of the control circuit of the short-distance photoelectric sensor are set up. The modular circuit around the above chip is designed. The optical structure of the sensor is designed by Position sensitive sensor (PSD) photoelectric accessories and triangulation method. Meanwhile, the core circuit control chip (CSP) is applied to complete the basic functions of the short-distance photoelectric sensor. Among them, the optical structure is designed to collect and process the optical signal of the detected object. Based on this, the I/V conversion is needed after collecting the optical signal by PSD, and then the signal processing is carried out. The fuzzy PID control model is used to solve the problem that the control object cannot accurately establish the mathematical model. The designed photoelectric sensor is used for the handling robot, and the D-H mathematical model of the handling robot is established. The Robotics toolbox provided by MatLab is used to simulate the movement of the robot, and the sensor is used to detect the target of the robot grabbing. The experimental results show that the sensor uploads the coordinate information of the object to be grabbed to the software interface, and the handling robot can accurately grab the object with the help of the photoelectric sensor, and place it in the corresponding position according to the appearance color of different objects to be grabbed.

A Real-Time Object Counting and Collecting Device for Industrial Automation Process Using Machine Vision

An efficient product packing system through a simplified automatic counting and collecting process is a critical aspect of the manufacturing industry. In the present paper, we propose a real-time tool for simultaneous counting and collection of the objects into different bins using machine vision. The system employs a minimum distance classifier for object detection, Counting on the conveyor belt is done by tracking the Euclidian distances between the centroids of the objects in successive frames. Furthermore, the required number of object collection is carried out in two steps. In the first step, multiple objects nearest to the required count are collected. In the second step, the difference of objects that remained from the previous step are added one by one. Object collection is carried out by integrating software output to the hardware, which collects them in required numbers in the different bins. To meet the fast counting requirements, a high-speed conveyor system constituting vision sensor with pixel resolution of 1920x1200 and 41 frames per second frame rate is employed. The high computational power requirements for implementing the algorithm is accomplished by employing a dedicated graphics microcontroller, whose GPIO pins are used for interfacing the hardware for the object collection. The testing results of the proposed device with 30 variants of different plumbing industry objects confirm an accuracy of 100% for a period of 3 hours. Moreover, the proposed module is scalable and could boost the productivity of the company in a complex environment without affecting the accuracy of the system.

INTELLIGENT PROCESS CONTROL SYSTEM IN AUTOMATION INDUSTRY

Intelligent process control (IPC) has indeed been identified as one of the most promising and essential technological techniques for achieving enterprise digitalization. This study covers key principles for developing IPC in industry and provides a framework for effectively implementing IPC technology. Today, operators in the control rooms of large plants are expected to rely heavily on their own judgement and experience. The present hot point intelligent control technology and means are outlined in conjunction with the forefront of industrial process automation development. As management criteria, technical and economic indicators can serve, for example, increasing productivity, improving product quality, reducing losses, reducing the cost of production, etc. The transition from automation systems in industry to the intelligent process control systems at one time was caused by the intensification of technological processes, the use of high-power units, as well as progress in the development of control systems. An intelligent process control (IPC)system is a set of technical means and algorithms for collecting, processing and presenting information that provides control of an industry, production, enterprise or individual processes based on cybernetics methods and partially using artificial intelligence. The specific use of intelligent control is then explained. Keywords: Controller, Intelligent Process Control (IPC), System, Software, Programmable Logic Controller (PLC).

Industry 4.0 from the perspective of Education 4.0

Industry 4.0, or the fourth industrial revolution, means the automation of industrial processes, digitalization and the use of data in order to increase the efficiency and quality of production processes. Industry 4.0 also affects other areas of the economy, as well as education. The concept of Education 4.0 strives to modernize and apply education to the age of Industry 4.0 using new technologies and methods.
 The main goal of Education 4.0 is to prepare students for the challenges of Industry 4.0 and to give them skills and knowledge that they will need in the digital age. This new educational model is no longer only about the transfer of information, but also focuses on developing students' abilities and renewing their problem-solving skills. Education for student-centered education aims to increase student motivation, develop individual skills and improve learning outcomes.
 To implement Education 4.0, educational institutions need to provide the infrastructure and infrastructure that enables students to use digital technologies and virtual learning. For students, Education 4.0 also includes interactive learning opportunities such as online courses, videos, and interactive learning materials.
 In this article, we present the methods and thematic units that should be taught so that students can meet the challenges of Industry 4.0.

FDD: a deep learning-based steel defect detectors.

Surface defects are a common issue that affects product quality in the industrial manufacturing process. Many companies put a lot of effort into developing automated inspection systems to handle this issue. In this work, we propose a novel deep learning-based surface defect inspection system called the forceful steel defect detector (FDD), especially for steel surface defect detection. Our model adopts the state-of-the-art cascade R-CNN as the baseline architecture and improves it with the deformable convolution and the deformable RoI pooling to adapt to the geometric shape of defects. Besides, our model adopts the guided anchoring region proposal to generate bounding boxes with higher accuracies. Moreover, to enrich the point of view of input images, we propose the random scaling and the ultimate scaling techniques in the training and inference process, respectively. The experimental studies on the Severstal steel dataset, NEU steel dataset, and DAGM dataset demonstrate that our proposed model effectively improved the detection accuracy in terms of the average recall (AR) and the mean average precision (mAP) compared to state-of-the-art defect detection methods. We expect our innovation to accelerate the automation of industrial manufacturing process by increasing the productivity and by sustaining high product qualities.

Custom Grasping: A Region-Based Robotic Grasping Detection Method in Industrial Cyber-Physical Systems

Industrial Cyber Physical Systems can use data and information gained from across a variety of different environments to enable robots that are reconfigurable. Custom grasping is a basic operation a robot must be able to carry out for a given task, i.e., finding the best grasping point for emergent behaviors. However, environmental disturbance and limited data degrade the precision and speed of many tailored machine learning models on robot grasping detection. This paper proposes a region-based method to enable fast custom grasping through fewer RGB-D data. The grasping detection problem is simplified as a two-stage prediction problem. At the first stage, a robust grasp candidate generation strategy is proposed based on the Sobel operator. At the second stage, a region-based predictor is designed to locate the best grasping point-pair for an emergent task. The predictor is trained by a modified consistency based self-training method to realize semi-supervised learning. Experimental results show that the success rate of custom grasping of new emergent object can be increased by 3.4% on average using the proposed method. By introducing data augmentation strategies in training, the success rate is further increased by 9.2% on average. A robot is able to grasp new object with 91.5% success rate using less than 100 training samples. The number of training samples required for the proposed method is less than to 1% of which for the previous works. Note to Practitioners—This research was motivated by the problem of robot reconfigurability for various industrial automation processes and focuses mainly on the recognition of grasping point-pair of emergent object for different task. Existing approaches on robotic grasping detection are tailored to a given object and require expensive training with large amount of labeled data. This paper presents a region-based few shot learning approach that enables the robot to detect the best grasping point-pair autonomously and quickly. We show how to generate candidate point-pairs with image distortion and background disturbance. We then demonstrate how the best grasping point-pair can be located with much less training cost. Experiments suggest that this approach is feasible in robot automation for handling a class of objects. In future research, we will construct behavior learning module to enable evolving cyber-physical robotic system for more purposes.

Performance optimization of 5G NR technology for industrial automation

Communication over the wireless has significantly evolved to the level where it is capable of supporting the essential controlling mechanisms of the high-definition automated industrial process. The Fifth-Generation (5G) mobile networking air-based interface, named New Radio (5GNR), is presently capable of adopting scalable control and subband data transmission for small data packets, which has made it efficiently compatible for the critical controlling application of industrial automation processes. The minimum cycle time is used as a reliable parameter for an indication of the healthy techniques for industrial wireless telecommunication, but it has not undergone deep investigation within the framework of modern 5G technology. For addressing such types of challenges, this paper has taken into consideration 5G-based industrial automation process control through wireless networking by using a delay optimization approach associated with data-base channel control using the Ant Colony Optimization (ACO) approach for solving the proposed evaluation of a reliable minimum cycle time over 5G network communication.

Role of Modern Technology in Industry 4.0: An Empirical Study in the Context of Artificial Intelligence

Artificial intelligence (AI) is a key component of current technology that is revolutionizing the Indian industrial landscape in the context of Industry 4.0. India is embracing AI's potential as a major engine of economic development and industrial change. Automation of diverse industrial processes is one of the key functions of contemporary technology, especially AI, in Industry 4.0. In sectors including manufacturing, shipping, and warehousing, AI-powered robots and machines are being utilized to improve productivity, streamline production lines, and decrease human error. The use of AI in predictive maintenance helps to reduce downtime and boost productivity by analyzing data from sensors and other sources to anticipate equipment problems. In order to prepare the Indian workforce for the demands of Industry 4.0, AI is playing a crucial role. In order to prepare workers for the changing industrial landscape and the digital economy, training programmes and initiatives are being designed to teach them about AI and other cutting-edge technology. Overall, modern technology, in particular AI, is propelling the transformation of Indian companies in the era of Industry 4.0, resulting in increasing automation, data-driven decision-making, and workforce upskilling, placing India as a global leader in the Fourth Industrial Revolution.

Digital twins creation based on discrete modelling of non-destructive evaluation objects

Nowadays, the implementation of digital industrial technologies for maximal industrial processes automation and unmanned technologies creation is the main direction of technological development in the key of Industry 4.0 and NDE 4.0 paradigms. Service-oriented approach is proposed for the implementation of digital non-destructive evaluation as an effective solution for obtaining, processing and storing data and testing results. The model of industrial radiography laboratory simulator is considered, discrete models of digital twin objects are built when obtaining an image, for which the basic statements and tools of set theory are used. Examples illustrating the correspondence of digital twins’ mathematical models to their graphical analogues as well as the image generated on the detector are presented. The subject of extending CAD systems tools in the context of practical design of digital twins geometric image is considered. It is noted that virtualization of such a complex technical object as industrial radiography laboratory allows to check feasibility of technical solutions and engineering hypotheses with regard to real industrial conditions and needs in a short period of time and with minimum costs, thus providing, variability in implementation of process steps, and increasing the number of trained qualified specialists in radiation kind of non-destructive evaluation.

Semantic Interconnection Scheme for Industrial Wireless Sensor Networks and Industrial Internet with OPC UA Pub/Sub.

In the Industry 4.0 era, with the continuous integration of industrial field systems and upper-layer facilities, interconnection between industrial wireless sensor networks (IWSNs) and industrial Internet networks is becoming increasingly pivotal. However, when deployed in real industrial scenarios, IWSNs are often connected to legacy control systems, through some wired industrial network protocols via gateways. Complex protocol translation is required in these gateways, and semantic interoperability is lacking between IWSNs and the industrial Internet. To fill this gap, our study focuses on realizing the interconnection and interoperability between an IWSN and the industrial Internet. The Open Platform Communications Unified Architecture (OPC UA) and joint publish/subscribe (pub/sub) communication between the two networks are used to achieve efficient transmission. Taking the Wireless Networks for Industrial Automation Process Automation (WIA-PA), a typical technology in IWSNs, as an example, we develop a communication architecture that adopts OPC UA as a communication bridge to integrate the WIA-PA network into the industrial Internet. A WIA-PA virtualization method for OPC UA pub/sub data sources is designed to solve the data mapping problem between WIA-PA and OPC UA. Then, the WIA-PA/OPC UA joint pub/sub transmission mechanism and the corresponding configuration mechanism are designed. Finally, a laboratory-level verification system is implemented to validate the proposed architecture, and the experimental results demonstrate its promising feasibility and capability.

A Quality 4.0 Model for architecting industry 4.0 systems

The increasing importance of automation and smart capabilities for factories and other industrial systems has led to the concept of Industry 4.0 (I4.0). This concept aims at creating systems that improve the vertical and horizontal integration of production through (i) comprehensive and intelligent automation of industrial processes, (ii) informed and decentralized real-time decision making, and (iii) stringent quality requirements that can be monitored at any time. The I4.0 infrastructure, supported in many cases by robots, sensors, and algorithms, demands highly skilled workers able to continuously monitor the quality of both the items to be produced and the underlying production processes.While the first attempts to develop smart factories and enhance the digital transformation of companies are under way, we need adequate methods to support the identification and specification of quality attributes that are relevant to I4.0 systems. Our main contribution is to provide a refined version of the ISO 25010 quality model specifically tailored to those qualities demanded by I4.0 needs. This model aims to provide actionable support for I4.0 software engineers that are concerned with quality issues. We developed our model based on an exhaustive analysis of similar proposals using the design science method as well as expertise from seasoned engineers in the domain. We further evaluate our model by applying it to two important I4.0 reference architectures further clarifying its application.

A conceptual framework for smart production planning and control in Industry 4.0

This article aims to introduce the challenge (i.e., integration of new collaborative models and tools) posed by the automation and collaboration of industrial processes in Industry 4.0 (I4.0) smart factories. Small- and medium-sized enterprises (SMEs) are particularly confronted with new technological and organisational changes, but a conceptual framework for production planning and control (PPC) systems in the I4.0 context is lacking. The main contributions of this article are to: (i) identify the functions making up traditional PPC and smart production planning and control in I4.0 (SPPC 4.0); (ii) analyse the impact of I4.0 technologies on PPC systems; (iii) propose a conceptual framework that provides the systematic structuring of how a PPC system operates in the I4.0 context, dubbed SPPC 4.0. Thus SPPC 4.0 is proposed by adopting the axes of the RAMI 4.0 reference architecture model, which compiles and contains the main concepts of PPC systems and I4.0. It also provides the technical description, organisation and understanding of each aspect, which can provide a guide for academic research and industrial practitioners to transform PPC systems towards I4.0 implementations. Finally, theoretical implications and research gaps are provided.

Deep Learning–Based Soft Sensors for Improving the Flexibility for Automation of Industry

Automation in industries offers the benefits of enhancing quality and productivity while minimizing waste and errors, raising safety and adds stability to the production process. Industrial automation offers high profitability, reliability, and safety. It is beneficial to employ machine learning in the field of industrial automation as it helps in monitoring and performing maintenance on industrial machinery. Rational industrial development is closely associated with efforts for automating industrial techniques in all existing ways. Latest improvements in the automation of industrial systems resulted in decrease in cost of energy consumption and hardware. The proposed system is dealt with deep learning–based soft sensors for automation of industrial processes. The eminent benefits of soft sensors are versatility, flexibility, and low cost. With deep learning, many number of features could be processed. Thus, deep learning–based soft sensor encapsulates the above benefits. Soft sensors offer another way for the measurement of process variables, which are measured offline. Deep learning techniques are famous in the design of soft sensors for tough nonlinear systems due to the robustness and accuracy. The work depicted here designs a soft sensor based on deep learning algorithm for automation of industry. In the proposed system, a soft sensor contemplated on deep learning such as the deep neural network (DNN) is presented. The application of deep learning–based soft sensors in the automation of some industrial processes is also discussed here. The proposed system is tested on automatic control on solar power plants and in the measurement of reactive energy in industries. It was found that the proposed system yielded better results with its application in the automated industrial processes.