Industrial Vision Research Articles

Recent Scope for AI in the Food Production Industry Leading to the Fourth Industrial Revolution

In today's situation, Artificial intelligence and computer vision collectively join together to analyze the big data obtained from predicted models. The role of AI in the agri-based food industry helps the stakeholders to access and monitor the supply chain. The phenomenon of applying AI and computer vision in the food industry would improve the entire operations. This research paper tries to provide an assisting model for farmers in food-processing and agriculture through the state-of-the-art method. Several concepts related to sustainability in food processing have been estimated through machine learning, and the deep learning model as a worldwide concept. The demand for the usage of AI and computer vision in the Ag-TECH industry has increased which impacts sustainable food production to feed the future. Certain implications have been suggested for real-time monitoring of the farming process, politics behind sustainable food production, and investment which is the main game-player in the present situation. The 4th Industrial Revolution [IR-4.0] was ushered in by the deployment of computer vision and AI in the food business, with computer vision robotics playing a crucial role in ensuring sustainable food production.

Analysis of the Possibilities of Applying Mobile Robotic Platforms Using Machine Vision in Industry

The article considers the possibilities of automated use of robotic equipment in order to form an infrastructure for moving goods at enterprises. Areas of application of algorithmic programming languages of object-oriented type in robotics are investigated. The algorithm of operation of a transport vehicle, the movement, which is based on the recognition of the line of motion, describing the route of movement, is presented. The analysis of the peculiarities of the implementation of such problems with the use of OpenCv software library was carried out. The structure of the vehicle is proposed, in particular: its driving mechanisms, control scheme, engines and wheelbase. Further development was made to the algorithms for the management of crawler lorries and the ways of their program realization in various spheres of entrepreneurial activity, where there is a need for the transfer of cargoes in the ordinary areas (construction sites, forest lands, open warehouses, airports, etc.). Based on the proposals for creating a cargo robot that can be moved according to a given route, the model of control system of conveyor systems, which solve the issues of automation of technological processes in the part of the addition of conveyor systems, is presented. The analysis of literary sources describing the necessity of creating mobile conveyor systems in production, which enables to quickly re-equip production processes to unforeseen needs, was carried out.

Surface defects inspection of cylindrical metal workpieces based on weakly supervised learning

Weakly supervised learning applies image tag labels to train convolutional neural networks to locate defect. In industrial vision system, metal surface is anisotropic under light in all directions and it is inevitable to cause local overexposure due to the natural reflection of active strong light, especially on the cylindrical metal surface. In this paper, injector valve is taken as the representative of cylindrical metal workpieces. Since the variety and complexity of cylindrical metal workpiece defects which cause pixel-level annotation require expensive manual work. This problem hinders the application of convolutional neural network in industries. In order to solve these above challenges, this paper proposed an end-to-end weakly supervised learning framework named Integrated Residual Attention Convolutional Neural Network (IRA-CNN). IRA-CNN only uses image tag annotation for training and performs defect classification and defect segmentation simultaneously. Weakly supervised learning is achieved by extracting category-related spatial features from defect classification scores. IRA-CNN is composed of multiple Integrated Residual Attention Block (IRA-Block) as the feature extractor which improves the accuracy and achieves real-time performance. IRA-Block adds Integrated Attention Module (IAM) which includes channel attention submodule and spatial attention submodule. The channel attention submodule adaptively extracts the channel attention feature map to improve its bilateral nonlinearity and the robustness. IAM can be well integrated into the IRA-CNN makes the neural network suppress the interference of useless background area and highlight the defect area. Satisfied performance is achieved by the proposed method in our own defect dataset which could meet the requirements in the industrial process. Experimental results show that the method has good generalization ability. The accuracy of defect classification reaches 97.84% and the segmentation accuracy is significantly improved compared with the benchmark method.

Interoperability between OPC UA and oneM2M

A key requirement of realizing the connected world featured by IoT is to ensure interoperability among different connected devices. Interoperability is also at the basis of the realization of the novel vision of Industry 4.0; a lot effort is put to make interoperable the interchange of information between industrial applications, also including IoT ecosystems. For this reason, during these last years, several approaches aimed to enhance interoperability between industrial applications and IoT appeared in the literature. In this paper an interoperability proposal is presented. It is based on the idea to realize interworking between the two standards considered among the reference ones in the industrial and IoT domains. They are the OPC UA for the industrial domain and oneM2M for the IoT. Interworking is realized in such a way to allow industrial applications based on OPC UA to acquire information coming from oneM2M-based IoT devices. The proposal allows an OPC UA Server to publish each piece of information produced by oneM2M-based IoT devices, so that this information may be consumed by industrial applications playing the OPC UA Client role.

R-CNN-Based Large-Scale Object-Defect Inspection System for Laser Cutting in the Automotive Industry

A car side-outer is an iron mold that is applied in the design and safety of the side of a vehicle, and is subjected to a complicated and detailed molding process. The side-outer has three features that make its quality inspection difficult to automate: (1) it is large; (2) there are many objects to inspect; and (3) it must fulfil high-quality requirements. Given these characteristics, the industrial vision system for the side-outer is nearly impossible to apply, and indeed there is no reference for an automated defect-inspection system for the side-outer. Manual inspection of the side-outer worsens the quality and cost competitiveness of the metal-cutting companies. To address these problems, we propose a large-scale Object-Defect Inspection System based on Regional Convolutional Neural Network (R-CNN; RODIS) using Artificial Intelligence (AI) technology. In this paper, we introduce the framework, including the hardware composition and the inspection method of RODIS. We mainly focus on creating the proper dataset on-site, which should be prepared for data analysis and model development. Additionally, we share the trial-and-error experiences gained from the actual installation of RODIS on-site. We explored and compared various R-CNN backbone networks for object detection using actual data provided by a laser-cutting company. The Mask R-CNN models using Res-net-50-FPN show Average Precision (AP) of 71.63 (Object Detection) and 86.21 (Object Seg-mentation), which indicates a better performance than that of other models.

An Investigation to the Industry 4.0 Readiness of Manufacturing Enterprises

The visions of what constitutes Industry 4.0 is an industry based on gains in efficiency and productivity enhancements supported by integrated, smart information systems. This has caused information systems strategic misalignment that present a severe barrier to national and organizational aspirations. This paper studies the readiness of manufacturing companies for Industry 4.0 by using a case study of Chinese multinational enterprise in the aluminum production sector. The research design follows a rigorous grounded theory approach, which consisted of 41 semi-structured interviews in 7 different company branches. Based on this case study, the paper proposes an IS strategic misalignment model that identifies three levels of misalignment that need to be resolved before the vision of the smart industry can be realized. Six main categories of causes and five main categories of consequences of IS strategic misalignment are presented. This study contributes to the IS alignment literature and provides important implications for the achievement of Industry 4.0 in practice.

Novel object motion estimation method for industrial vision systems in aligning machines

Industrial vision systems have been adopted in many manufacturing processes for monitoring manufacturing procedures. With the recent proposed concept of industrial information integration engineering (IIIE) (Da Xu, 2020 [1]), the adoption of industrial vision systems involves a wider IIIE context as a data acquisition measurement, and thus higher level intelligence like control automation is expected. Industrial vision systems have been used for object alignment in aligning machines. By coping with a pneumatic device, misaligned objects can be detected by vision systems and rejected. Since alignment efficiency depends on the appropriateness of the blown timing/pressure, which is casually manifested in the motion of the observed blown objects, a motion estimation method for industrial vision systems must be adopted. Although conventional motion estimation methods in this field typically use pre-prepared templates, this paper proposed a novel object motion estimation method based on the properties of industrial images. A bounding box within a confined observation area is first initialized for each object, and then motion estimation is achieved by updating the bounding box following the expectation–maximization principle. Experiments revealed that our proposed method achieved robust and continuous motion estimation of the parts and reduced the processing time compared to conventional template matching methods.

Electric drives as fog nodes in a fog computing‐based industrial use case

Electric drives, which are a main component in industrial applications, control electric motors and record vital information about their respective industrial processes. The development of electric drives as Fog nodes within a fog computing platform (FCP) leads to new abilities such as programmability, analytics, and connectivity, increasing their value. In this study, the FORA FCP reference architecture is used to implement electric drives as Fog nodes, which is called “fogification”. The fogified drive architecture and its components are designed using Architecture Analysis and Design Language (AADL). The design process was driven by the high-level requirements that the authors elicited. Both the fogified drive architecture and the current drive architecture are used to implement a self baggage drop system in which electric drives are the key components. The fog-based design was then evaluated using several key performance indicators (KPIs), which reveal its advantages over the current drive architecture. The evaluation results show that safety-related isolation is enabled with only 9% overhead on the total Fog node utilization, control applications are virtualized with zero input–output jitter, the hardware cost is reduced by 44%, and machine learning at the edge is performed without interrupting the main drive functionalities and with an average 85% accuracy. The conclusion is that the fog-based design can successfully implement the required electric drive functionalities and can also enable innovative uses needed for realizing the vision of Industry 4.0.

A Roadmap for Disruptive Applications and Heterogeneous Integration Using Two-Dimensional Materials: State-of-the-Art and Technological Challenges.

This Mini Review attempts to establish a roadmap for two-dimensional (2D) material-based microelectronic technologies for future/disruptive applications with a vision for the semiconductor industry to enable a universal technology platform for heterogeneous integration. The heterogeneous integration would involve integrating orthogonal capabilities, such as different forms of computing (classical, neuromorphic, and quantum), all forms of sensing, digital and analog memories, energy harvesting, and so forth, all in a single chip using a universal technology platform. We have reviewed the state-of-the-art 2D materials such as graphene, transition metal dichalcogenides, phosphorene and hexagonal boron nitride, and so forth, and how they offer unique possibilities for a range of futuristic/disruptive applications. Besides, we have discussed the technological and fundamental challenges in enabling such a universal technology platform, where the world stands today, and what gaps are required to be filled.

Cobots in Industry 4.0: A Roadmap for Future Practice Studies on Human–Robot Collaboration

With the vision of Industry 4.0 and cobots, working conditions in industrial settings are starting to change. We review related literature from the fields of human-robot interaction, work and organizational psychology, and sociology of work, as well as an exemplary project case study, and identify research gaps regarding the implications of cobots for work environments. We argue that we are in a transition phase from automation to actual collaboration with robots in manufacturing, and that this will open up a new problem space for investigations, in which a practice lens will be crucial. Based on this, we propose a research agenda for social practice and workplace studies to explore the sociotechnical environment of Industry 4.0 involving cobots at the individual, team, and organizational levels.

Inclusion of IoT, ML, and Blockchain Technologies in Next Generation Industry 4.0 Environment

Industry 4.0 is a revolutionizing concept which has a more significant implication to numerous industries of various sectors worldwide. Industry 4.0 acts as a technical catalyst in accelerated growth through systematic adaptation and new-generation cutting-edge engineering tools. IoT, Blockchain, Artificial Intelligence, Augmented Reality, 3D printing, Big-data analytics, cloud-computing are some of the primary technologies which work in join hand to make the vision of Industry 4.0 successful. In addition, it promotes autonomous industry, which in turn considerably reduces human intervention, thus resulting in efficient working and safeguard companies' interests. Due to the faster adaption of Industry 4.0, authors have attempted to define each and every concept related to it and to explore a futuristic roadmap, special focusing on its implication in the contemporary market. In the 21st century Industry, 4.0 is the need of the hour, so it has become essential to understand the state-of-the-art technologies involved.

How pandemic and the industry 4.0 era constraint: the perspective of authentic leadership on innovation

The COVID-19 crisis brought the importance of interdisciplinary knowledge to the forefront. Scholars carry out online communication and learning, instead of relying on face-to-face meetings at the conference, and are more proactive in disseminating their research online, which will achieve more success due to the higher number of readers citations. Remote work behaviour facilitated technology adoption in the era of industry 4.0 will affect company innovation. Then the authentic leaders who have the vision and views in industry 4.0 and are faced with pandemics will increase the level of innovation of these leaders. This research cannot be generalized to the industry in general but can be a reference for future researchers. 4.0 and corporate culture

A real-time two-stage and dual-check template matching algorithm based on normalized cross-correlation for industrial vision positioning

A real-time two-stage and dual-check template matching algorithm based on normalized cross-correlation for industrial vision positioning

Trust Based Secure Multipath Routing Protocol for MANET

MANETs gained popularity due to various notable features like dynamic topology, rapid setup, multihop data transmission, and so on. These prominent features make MANETs suitable for many real-time applications like environmental monitoring, disaster management, and covert and combat operations. Moreover, MANETs can also be integrated with emerging technologies like cloud computing, IoT, and machine learning algorithms to achieve the vision of Industry 4.0. All MANET-based sensitive real time applications require secure and reliable data transmission that must meet the required QoS. In MANET, achieving secure and energy-efficient data transmission is a challenging task. )e main strength of the proposed protocol is that it considers multiple factors like congestion control, packet loss reduction, malicious node detection, and secure data transmission to intensify the MANET’s QoS. The performance of the proposed protocol is analyzed through the simulation in NS2.

DIGITAL EFFECT

Digital Effect: Visions of business and Industry 5.0 is a new book on digitization and innovation and the importance of applying decision making models.

Increasing Minority Recall Support Vector Machine Model for Imbalanced Data Classification

Imbalanced data classification is gaining importance in data mining and machine learning. The minority class recall rate requires special treatment in fields such as medical diagnosis, information security, industry, and computer vision. This paper proposes a new strategy and algorithm based on a cost-sensitive support vector machine to improve the minority class recall rate to 1 because the misclassification of even a few samples can cause serious losses in some physical problems. In the proposed method, the modification employs a margin compensation to make the margin lopsided, enabling decision boundary drift. When the boundary reaches a certain position, the minority class samples will be more generalized to achieve the requirement of a recall rate of 1. In the experiments, the effects of different parameters on the performance of the algorithm were analyzed, and the optimal parameters for a recall rate of 1 were determined. The experimental results reveal that, for the imbalanced data classification problem, the traditional definite cost classification scheme and the models classified using the area under the receiver operating characteristic curve criterion rarely produce results such as a recall rate of 1. The new strategy can yield a minority recall of 1 for imbalanced data as the loss of the majority class is acceptable; moreover, it improves the g -means index. The proposed algorithm provides superior performance in minority recall compared to the conventional methods. The proposed method has important practical significance in credit card fraud, medical diagnosis, and other areas.

Industrial objects recognition in intelligent manufacturing for computer vision

PurposeThe overall goal of this research is to develop algorithms for feature-based recognition of 2D parts from intensity images. Most present industrial vision systems are custom-designed systems, which can only handle a specific application. This is not surprising, since different applications have different geometry, different reflectance properties of the parts.Design/methodology/approachComputer vision recognition has attracted the attention of researchers in many application areas and has been used to solve many ranges of problems. Object recognition is a type of pattern recognition. Object recognition is widely used in the manufacturing industry for the purpose of inspection. Machine vision techniques are being applied in areas ranging from medical imaging to remote sensing, industrial inspection to document processing and nanotechnology to multimedia databases. In this work, recognition of objects manufactured in mechanical industry is considered. Mechanically manufactured parts have recognition difficulties due to manufacturing process including machine malfunctioning, tool wear and variations in raw material. This paper considers the problem of recognizing and classifying the objects of such mechanical part. Red, green and blue RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. Artificial neural network (ANN) is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.FindingsOne important finding is that there is not any considerable change in the network performances after 500 iterations. It has been found that for data smaller network structure, smaller learning rate and momentum are required. The relative sample size also has a considerable effect on the performance of the classifier. Further studies suggest that classification accuracy is achieved with the confusion matrix of the data used. Hence, with these results the proposed system can be used efficiently for more objects. Depending upon the manufacturing product and process used, the dimension verification and surface roughness may be integrated with proposed technique to develop a comprehensive vision system. The proposed technique is also highly suitable for web inspections, which do not require dimension and roughness measurement and where desired accuracy is to be achieved at a given speed. In general, most recognition problems provide identity of object with pose estimation. Therefore, the proposed recognition (pose estimation) approach may be integrated with inspection stage.Originality/valueThis paper considers the problem of recognizing and classifying the objects of such mechanical part. RGB images of five objects are used as an input. The Fourier descriptor technique is used for recognition of objects. ANN is used for classification of five different objects. These objects are kept in different orientations for invariant rotation, translation and scaling. The feed forward neural network with back-propagation learning algorithm is used to train the network. This paper shows the effect of different network architecture and numbers of hidden nodes on the classification accuracy of objects as well as the effect of learning rate and momentum.

Optimized, Automated, and Protective: An Operator’s View on Future Networks

The current pandemic crisis has highlighted the utmost importance of communication networks. The dramatic development of teleworking imposed by strict confinement measures, the need to access educational materials from home, the likely degradation of social relationships are among the impacts of the pandemic that inevitably affect the operation and the performance of networks. The design and the operation of tomorrow’s networks will have to learn from the outbreak that exacerbates the critical need for massive digital inclusion, robust and resilient infrastructures, as well as dynamically adaptive networking to better cope with various, possibly degraded, network access conditions. Of course, the virus is not the only reason to rethink network design: current 5G deployments are among the networking technologies that encourage the emergence of new services, such as immersive services based upon Augmented Reality/Virtual Reality techniques that are pretty demanding in terms of QoS. This industry vision paper provides a network operator’s perspective on some of the forthcoming networking challenges. It explores a few technical options that are likely to be instrumental in the conception and the delivery of optimized, automated and protective networks, for the benefits of the end-user, regardless of his/her connectivity capabilities, whether he/she is in motion or not, and regardless of the nature of the service or contents he/she needs to access.

TBSMR: A Trust-Based Secure Multipath Routing Protocol for Enhancing the QoS of the Mobile Ad Hoc Network

Mobile ad hoc network (MANET) is a miscellany of versatile nodes that communicate without any fixed physical framework. MANETs gained popularity due to various notable features like dynamic topology, rapid setup, multihop data transmission, and so on. These prominent features make MANETs suitable for many real-time applications like environmental monitoring, disaster management, and covert and combat operations. Moreover, MANETs can also be integrated with emerging technologies like cloud computing, IoT, and machine learning algorithms to achieve the vision of Industry 4.0. All MANET-based sensitive real-time applications require secure and reliable data transmission that must meet the required QoS. In MANET, achieving secure and energy-efficient data transmission is a challenging task. To accomplish such challenging objectives, it is necessary to design a secure routing protocol that enhances the MANET’s QoS. In this paper, we proposed a trust-based multipath routing protocol called TBSMR to enhance the MANET’s overall performance. The main strength of the proposed protocol is that it considers multiple factors like congestion control, packet loss reduction, malicious node detection, and secure data transmission to intensify the MANET’s QoS. The performance of the proposed protocol is analyzed through the simulation in NS2. Our simulation results justify that the proposed routing protocol exhibits superior performance than the existing approaches.

Detection Of Vacant Parking Spaces Through The Use Of Convolutional Neural Network

This paper focuses on the application of computer vision and convolutional neural network techniques in the automotive industry to reduce the amount of time required to locate a vacant parking spot and to reduce driving time. The main motivation for a vacant parking spot detector is such that today’s drivers are facing major difficulties in finding available spots in largely populated cities. This often time leads to increased congestion and frustration for the driver because they are forced to continue their search for a parking spot. Our approach is able to solve this issue and provide the driver with useful information through the use of transfer learning methodologies. The main contribution of this paper is to examine and improve on previously implemented transfer learning methods in order to better increase the detection accuracy. This paper differs from previous attempts such that it considers all environmental factors such as weather and time of day. Other models are not able to handle these conditions with a high accuracy and subsequently falter. When compared to previous attempts, our implementation focuses solely on the reliance of transfer learning. The results indicate that our model is capable of identifying vacant parking spaces under all conditions with competitive accuracies. The proposed model is able to surpass the accuracy of the latest attempt at solving this issue.