Hasil untuk "Industrial directories"

Table of Contents

Jiangfeng Cheng, Weihai Chen, F. Tao et al.

Abstract Smart manufacturing based on cyber-physical manufacturing systems (CPMS) has become the development trend and been widely recognized all over the world. Throughout the development trend of CPMS, one of the key issues is industrial Internet-of-Things (IIoT) with the characteristics of automation, smart connected, real-time monitoring, and collaborative control. Along with the permeation and applications of advanced technologies in manufacturing, massive amounts of data have been generated in the manufacturing process. However, the current 3th generation mobile network (3G), 4G and other communication technologies cannot meet the demands of CPMS for high data rate, high reliability, high coverage, low latency, etc., which hinders the development and implementation of CPMS. As a future advanced wireless transmission technology, 5G has a significant potential to promote IIoT and CPMS. Based on the architecture and characteristics of 5G wireless communication technology, this paper proposes the architecture of 5G-based IIoT, and describes the implementation methods of different advanced manufacturing scenarios and manufacturing technologies under the circumstances of three typical application modes of 5G, respectively, i.e., enhance mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliable and low latency communication (URLLC). Besides, the characteristics, key technologies and challenges of the 5G based IIoT are also analyzed.

E. Kaasinen, Franziska Schmalfuß, C. Öztürk et al.

Abstract Industry 4.0 has potential for qualitative enrichment of factory work: a more interesting working environment, greater autonomy and opportunities for self-development. A central element of Industry 4.0 is human-centricity, described as development towards Operator 4.0. Our Operator 4.0 vision includes smart factories of the future that are perfectly suited for workers with different skills, capabilities and preferences. The vision is achieved by solutions that empower the workers and engage the work community. Empowering the worker is based on adapting the factory shop floor to the skills, capabilities and needs of the worker and supporting the worker to understand and to develop his/her competence. Engaging the work community is based on tools, with which the workers can participate in designing their work and training, and share their knowledge with each other. We gathered requirements from three manufacturing companies in different industries and interviewed 44 workers in four factories in order to study their expectations and concerns related to the proposed Operator 4.0 solutions. Adaptation was considered useful both in manufacturing systems and in production planning. However, worker measuring and modelling raised many doubts within workers and also with factory management. Therefore it is important to provide early demonstrations of the ideas and to design them further with the workers in order to find acceptable and ethically sustainable ways for worker modelling. The workers would like to be more involved in the design of the work place and manufacturing processes, and they thought that participation would decrease many problems that they currently face in their work. However, there were also doubts concerning whether they really could have possibilities to impact on their work. The results show that there are clear needs for knowledge sharing and adaptive learning solutions that would support personalized competence development and learning while working. An easily accessible platform for knowledge sharing could evolve to a forum where good work practices and ways to solve problems are shared not only within the work community, but also with machine providers and other stakeholders. The interviewees saw the virtual factory as a promising platform for participatory design and training.

C. Liu, Qiuxia Lin, Shilin Wen

With the rapid development of smart mobile terminals (MTs), various industrial Internet of things (IIoT) applications can fully leverage them to collect and share data for providing certain services. However, two key challenges still remain. One is how to achieve high-quality data collection with limited MT energy resource and sensing range. Another is how to ensure security when sharing and exchanging data among MTs, to prevent possible device failure, network communication failure, malicious users or attackers, etc. To this end, we propose a blockchain-enabled efficient data collection and secure sharing scheme combining Ethereum blockchain and deep reinforcement learning (DRL) to create a reliable and safe environment. In this scheme, DRL is used to achieve the maximum amount of collected data, and the blockchain technology is used to ensure security and reliability of data sharing. Extensive simulation results demonstrate that the proposed scheme can provide higher security level and stronger resistance to attack than a traditional database based data sharing scheme for different levels/types of attacks.

M. S. Hossain, Muneer Al-hammadi, G. Muhammad

Fruit classification is an important task in many industrial applications. A fruit classification system may be used to help a supermarket cashier identify the fruit species and prices. It may also be used to help people decide whether specific fruit species meet their dietary requirements. In this paper, we propose an efficient framework for fruit classification using deep learning. More specifically, the framework is based on two different deep learning architectures. The first is a proposed light model of six convolutional neural network layers, whereas the second is a fine-tuned visual geometry group-16 pretrained deep learning model. Two color image datasets, one of which is publicly available, are used to evaluate the proposed framework. The first dataset (dataset 1) consists of clear fruit images, whereas the second dataset (dataset 2) contains fruit images that are challenging to classify. Classification accuracies of 99.49% and 99.75% were achieved on dataset 1 for the first and second models, respectively. On dataset 2, the first and second models obtained accuracies of 85.43% and 96.75%, respectively.

Mengting Liu, F. Yu, Yinglei Teng et al.

Recent advances in the industrial Internet of things (IIoT) provide plenty of opportunities for various industries. To address the security and efficiency issues of the massive IIoT data, blockchain is widely considered as a promising solution to enable data storing/processing/sharing in a secure and efficient way. To meet the high throughput requirement, this paper proposes a novel deep reinforcement learning (DRL)-based performance optimization framework for blockchain-enabled IIoT systems, the goals of which are threefold: 1) providing a methodology for evaluating the system from the aspects of scalability, decentralization, latency, and security; 2) improving the scalability of the underlying blockchain without affecting the system's decentralization, latency, and security; and 3) designing a modulable blockchain for IIoT systems, where the block producers, consensus algorithm, block size, and block interval can be selected/adjusted using the DRL technique. Simulations results show that our proposed framework can effectively improve the performance of blockchain-enabled IIoT systems and well adapt to the dynamics of the IIoT.

Wanke Yu, Chunhui Zhao

Fault diagnosis, which identifies the root cause of the observed out-of-control status, is essential to counteracting or eliminating faults in industrial processes. Many conventional data-driven fault diagnosis methods ignore the fault tendency of abnormal samples, and they need a complete retraining process to include the newly collected abnormal samples or fault classes. In this article, a broad convolutional neural network (BCNN) is designed with incremental learning capability for solving the aforementioned issues. The proposed method combines several consecutive samples as a data matrix, and it then extracts both fault tendency and nonlinear structure from the obtained data matrix by using convolutional operation. After that, the weights in fully connected layers can be trained based on the obtained features and their corresponding fault labels. Because of the architecture of this network, the diagnosis performance of the BCNN model can be improved by adding newly generated additional features. Finally, the incremental learning capability of the proposed method is also designed, so that the BCNN model can update itself to include new coming abnormal samples and fault classes. The proposed method is applied both to a simulated process and a real industrial process. Experimental results illustrate that it can better capture the characteristics of the fault process, and effectively update diagnosis model to include new coming abnormal samples, and fault classes.

Xin Liu, Xueyan Zhang

The development of Industrial Internet of Things (IIoT) has been limited due to the shortage of spectrum resources. Based on cognitive radio, the cognitive IIoT (CIIoT) has been proposed to improve spectrum utilization via sensing and accessing the idle spectrum. To improve sensing and transmission performance of the CIIoT, a cluster-based CIIoT is proposed, in this article, wherein the cluster heads perform cooperative spectrum sensing to get available spectrum, and the nodes transmit via nonorthogonal multiple access (NOMA). The frame structure of the CIIoT is designed, and the spectrum access probability and average total throughput of the CIIoT are deduced. A joint resource optimization for sensing time, node powers, and the number of clusters is formulated to maximize the average total throughput. The optimal solution is obtained via sensing and power optimization. The clustering algorithm and cluster head alternation are proposed to improve transmission performance and ensure energy balance, respectively. The simulations have indicated that the NOMA for the cluster-based CIIoT can better guarantee the transmission performance of each node, especially the node decoded first, than the traditional NOMA and orthogonal multiple access.

Xiaokang Zhou, Xuesong Xu, Wei Liang et al.

Recently, along with several technological advancements in cyber-physical systems, the revolution of Industry 4.0 has brought in an emerging concept named digital twin (DT), which shows its potential to break the barrier between the physical and cyber space in smart manufacturing. However, it is still difficult to analyze and estimate the real-time structural and environmental parameters in terms of their dynamic changes in digital twinning, especially when facing detection tasks of multiple small objects from a large-scale scene with complex contexts in modern manufacturing environments. In this article, we focus on a small object detection model for DT, aiming to realize the dynamic synchronization between a physical manufacturing system and its virtual representation. Three significant elements, including equipment, product, and operator, are considered as the basic environmental parameters to represent and estimate the dynamic characteristics and real-time changes in building a generic DT system of smart manufacturing workshop. A hybrid deep neural network model, based on the integration of MobileNetv2, YOLOv4, and Openpose, is constructed to identify the real-time status from physical manufacturing environment to virtual space. A learning algorithm is then developed to realize the efficient multitype small object detection based on the feature integration and fusion from both shallow and deep layers, in order to facilitate the modeling, monitoring, and optimizing of the whole manufacturing process in the DT system. Experiments and evaluations conducted in three different use cases demonstrate the effectiveness and usefulness of our proposed method, which can achieve a higher detection accuracy for DT in smart manufacturing.

Anmin Fu, Xianglong Zhang, N. Xiong et al.

Due to the strong analytical ability of big data, deep learning has been widely applied to model on the collected data in industrial Internet of Things (IoT). However, for privacy issues, traditional data-gathering centralized learning is not applicable to industrial scenarios sensitive to training sets, such as face recognition and medical systems. Recently, federated learning has received widespread attention, since it trains a model by only sharing gradients without accessing training sets. But existing research works reveal that the shared gradient still retains the sensitive information of the training set. Even worse, a malicious aggregation server may return forged aggregated gradients. In this article, we propose the VFL, a verifiable federated learning with privacy-preserving for big data in industrial IoT. Specifically, we use Lagrange interpolation to elaborately set interpolation points for verifying the correctness of the aggregated gradients. Compared with existing schemes, the verification overhead of VFL remains constant regardless of the number of participants. Moreover, we employ the blinding technology to protect the privacy of the privacy gradients. If no more than $\boldsymbol{n}$-2 of $\boldsymbol{n}$ participants collude with the aggregation server, VFL could guarantee the encrypted gradients of other participants not being inverted. Experimental evaluations corroborate the practical performance of the presented VFL with high accuracy and efficiency.

Di Wu, Zhongkai Jiang, Xiaofeng Xie et al.

The data generated by millions of sensors in the industrial Internet of Things (IIoT) are extremely dynamic, heterogeneous, and large scale and pose great challenges on the real-time analysis and decision making for anomaly detection in the IIoT. In this article, we propose a long short-term memory (LSTM)-Gauss-NBayes method, which is a synergy of the long short-term memory neural network (LSTM-NN) and the Gaussian Bayes model for outlier detection in the IIoT. In a nutshell, the LSTM-NN builds a model on normal time series. It detects outliers by utilizing the predictive error for the Gaussian Naive Bayes model. Our method exploits advantages of both LSTM and Gaussian Naive Bayes models, which not only has strong prediction capability of LSTM for future time point data, but also achieves an excellent classification performance of the Gaussian Naive Bayes model through the predictive error. We evaluate our approaches on three real-life datasets that involve both long-term and short-term time dependence. Empirical studies demonstrate that our proposed techniques outperform the best-known competitors, which is a preferable choice for detecting anomalies.

Ekrem Bektašević, Kemal Gutić, Zijad Požegić

Driven by rapid urbanization and expanding demand for underground space, tunnel construction has become an increasingly important component of modern infrastructure. However, the confined working environment, complex geological conditions, and intensive construction processes pose substantial occupational safety challenges. This paper provides a multidisciplinary analysis of preventive safety measures in tunnel construction, with the goal of enhancing safety performance and reducing risks to workers' health and well-being. The study classifies safety strategies into three dimensions: technical, organizational, and personal, and examines the role of advanced technologies in optimizing working conditions and supporting risk prevention. It also highlights the importance of employee education and continuous safety training, and presents a statistical analysis of injury patterns during high-risk construction phases to identify major contributing factors. By integrating international safety standards, domestic engineering practices, and representative case studies, this research proposes a comprehensive framework for safety management tailored to the complex context of underground construction.

G. Kontogeorgis, R. Dohrn, I. Economou et al.

This paper reports the results of an investigation of industrial requirements for thermodynamic and transport properties carried out during the years 2019–2020. It is a follow-up of a similar investigation performed and published 10 years ago by the Working Party (WP) of Thermodynamics and Transport Properties of European Federation of Chemical Engineering (EFCE).1 The main goal was to investigate the advances in this area over the past 10 years, to identify the limitations that still exist, and to propose future R&D directions that will address the industrial needs. An updated questionnaire, with two new categories, namely, digitalization and comparison to previous survey/changes over the past 10 years, was sent to a broad number of experts in companies with a diverse activity spectrum, in oil and gas, chemicals, pharmaceuticals/biotechnology, food, chemical/mechanical engineering, consultancy, and power generation, among others, and in software suppliers and contract research laboratories. Very comprehensive answers were received by 37 companies, mostly from Europe (operating globally), but answers were also provided by companies in the USA and Japan. The response rate was about 60%, compared to 47% in the year 2010. The paper is written in such a way that both the majority and minority points of view are presented, and although the discussion is focused on needs and challenges, the benefits of thermodynamics and success stories are also reported. The results of the survey are thematically structured and cover changes, challenges, and further needs for a number of areas of interest such as data, models, systems, properties, and computational aspects (molecular simulation, algorithms and standards, and digitalization). Education and collaboration are discussed and recommendations on the future research activities are also outlined. In addition, a few initiatives, books, and reviews published in the past decade are briefly discussed. It is a long paper and, to provide the reader with a more complete understanding of the survey, many (anonymous) quotations (indicated with “...” and italics) from the industrial colleagues who have participated in the survey are provided. To help disseminate the specific information of interest only to particular industrial sectors, the paper has been written in such a way that the individual sections can also be read independently of each other.

Zhiqiang Geng, Zhiwei Chen, Qingchao Meng et al.

Industrial process data are usually time-series data collected by sensors, which have the characteristics of high nonlinearity, dynamics, and noises. Many existing soft sensor modeling methods usually focus on dominant variables and auxiliary variables at a single time point while ignoring the timing characteristics of industrial process data. Meanwhile, the soft-sensing methods considering timing characteristics based on the deep learning are usually faced with gradient vanishing and the difficulty in parallel computing. Therefore, a novel Gated Convolutional neural network-based Transformer (GCT) is proposed for dynamic soft sensor modeling of industrial processes. The GCT encodes short-term patterns of the time series data and filters important features adaptively through an improved gated convolutional neural network (CNN). Then, the multihead attention mechanism is applied to modeling the correlation between any two moments. Finally, the prediction results are obtained through a linear neural network layer with the highway connection. In this article, the experiments in the dynamic soft sensor modeling of polypropylene and purified terephthalic acid industrial processes show that the proposed method achieves state-of-the-art comparing with the back propagation neural network, the extreme learning machine, the long short-term memory (LSTM) and the LSTM based on the CNN.

Shahid Latif, Zeba Idrees, Jawad Ahmad et al.

Abstract The industrial Internet of Things (IIoT) plays an important role in the industrial sector, where secure, scalable, and easily adopted technologies are being implemented for the smart industry. The traditional IIoT architectures are generally based on centralized architectures that are vulnerable to a single point of failure and to several cyber-attacks. Blockchain technology is frequently adopted in the modern industry because of its security and decentralization. This paper proposes a blockchain-based architecture that ensures secure and trustworthy industrial operations. A private and lightweight blockchain architecture is proposed to regulate access to valuable sensor and actuator data. To enhance the computational performance of the proposed architecture, real-time cryptographic algorithms are processed using a low-power ARM Cortex-M4 processor, and a highly scalable, fast, and energy-efficient consensus mechanism proof of authentication (PoAh) is deployed in the blockchain network. Extensive experiments and analysis proved the effectiveness of the proposed framework for smart industrial environments. Finally, we transform a conventional fruit processing plant into a secure and smart industrial platform by implementing the proposed architecture.

Zlatko Šarić, Sonja Damjanović Dešić, Tina Mudrovčić

Fang Zhao, Ruihua Shu, Shoulong Xu et al.

Marine nuclear power plants (MNPPs) represent items of forward-looking high-end engineering equipment combining nuclear power and ocean engineering, with unique advantages and broad application prospects. When a nuclear accident occurs, it causes considerable economic losses and casualties. The traditional accident analysis of nuclear power plants only considers the failure of a single system or component, without considering the coupling between the system and the operator, the environment, and other factors. In this study, the cause mechanism of nuclear accidents in MNPPs is analyzed from the perspective of a social technology system. The causal analysis model is constructed by using the internal core causal analysis (e.g., technical control) and external stimulation causal analysis (e.g., social intervention) of accidents, after which the mechanism of the coupled evolution of each influencing factor is analyzed. A Bayesian network inference model is used to quantify the coupling relationship between the factors that affect the deterioration of nuclear accidents. The results show that the main influencing factors are pump failure, valve failure, insufficient response time, poor psychological state, unfavorable sea conditions, unfavorable offshore operating environments, communication failure, inappropriate organizational procedures, inadequate research and design institutions, inadequate regulatory agencies, and inadequate policies. These 12 factors have a high degree of causality and are the main factors influencing the deterioration of the small break loss of coolant accident (SBLOCA). In addition, the causal chain that is most likely to influence the development of SBLOCA into a severe accident is obtained. This provides a theoretical basis for preventing the occurrence of marine nuclear power accidents.

Bin Zhao, K. Fan, Kan Yang et al.

Lu Sun, Liangtian Wan, Xianpeng Wang

Forest fire monitoring plays an important role in forest resource protection. Although satellite remote sensing is an effective way for forest fire monitoring, satellite-based methods can only monitor large-scale forest areas, and they are weak in predicting the specific areas of forest fires. In this article, we first propose an unmanned aerial vehicle (UAV)-enabled system architecture consisting of multiple industrial Internet of Things (IIoTs), in which the data collected by sensors in IIoTs can be delivered to UAVs for processing directly. As the sensors of IIoTs are deployed to monitor different indexes of forest fires, fully considering the priority constraints among sensors can guarantee a quick response of forest fire monitoring. Thus, the priority constraints among the sensors are taken into consideration in this system architecture, and the objective is to minimize the maximum response time of forest fire monitoring. To search for the optimal UAV resource allocation strategy, a learning-based cooperative particle swarm optimization (LCPSO) algorithm with a Markov random field (MRF)-based decomposition strategy is proposed. The solution space of UAV resource allocation is decomposed into subsolution spaces according to the decomposed decision variables by the MRF network structure, and the optimal resource allocation strategy is searched by LCPSO in multiple subsolution spaces cooperatively. Three simulation experiments on two datasets are designed, and the simulation results compared with the state-of-the-art methods verify the validity of LCPSO, which are reflected by the quickest response time of forest fire monitoring.

M. Hassaballah, Mohamed Abdel Hameed, A. Awad et al.