Context Awareness by Noise-Pattern Analysis of a Smart Factory

Recently,to build a smart factory,research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning technology,a field of artificial intelligence.Most of the related studies apply various audio-feature extraction techniques to one-dimensional raw data to extract sound-specific features and then classify the sound by using the derived spectral image as a training dataset.However,compared to numerical raw data,learning based on image data has the disadvantage that creating a training dataset is very time-consuming.Therefore,we devised a two-step data preprocessing method that efficiently detects machine anomalies in numerical raw data.In the first preprocessing process,sound signal information is analyzed to extract features,and in the second preprocessing process,data filtering is performed by applying the proposed algorithm.An efficient dataset was built formodel learning through a total of two steps of data preprocessing.In addition,both showed excellent performance in the training accuracy of the model that entered each dataset,but it can be seen that the time required to build the dataset was 203 s compared to 39 s,which is about 5.2 times than when building the image dataset.

Accurate Multi-Scale Feature Fusion CNN for Time Series Classification in Smart Factory

Time series classification(TSC)has attracted various attention in the community of machine learning and data mining and has many successful applications such as fault detection and product identification in the process of building a smart factory.However,it is still challenging for the efficiency and accuracy of classification due to complexity,multi-dimension of time series.This paper presents a new approach for time series classification based on convolutional neural networks(CNN).The proposed method contains three parts:short-time gap feature extraction,multi-scale local feature learning,and global feature learning.In the process of short-time gap feature extraction,large kernel filters are employed to extract the features within the short-time gap from the raw time series.Then,a multi-scale feature extraction technique is applied in the process of multi-scale local feature learning to obtain detailed representations.The global convolution operation with giant stride is to obtain a robust and global feature representation.The comprehension features used for classifying are a fusion of short time gap feature representations,local multi-scale feature representations,and global feature representations.To test the efficiency of the proposed method named multi-scale feature fusion convolutional neural networks(MSFFCNN),we designed,trained MSFFCNN on some public sensors,device,and simulated control time series data sets.The comparative studies indicate our proposed MSFFCNN outperforms other alternatives,and we also provided a detailed analysis of the proposed MSFFCNN.

Artificial Intelligence,Smart Robots and a New Economic Order

In the process of transition from agricultural society to industrial society,which started with the Industrial Revolution in England,the mechanization process experienced five different stages and in the last stage,with the development of computers,automation in production was achieved.While developments in a certain region or country of the world spread to other parts of the world with technological spread,technological revolutions also spread and paradigm changes occurred.With the development of information processing technologies,productivity has started to increase with the use of automation and robot technology in production.This process,which continued until the 2010s,is thought to lead to the formation of smart factories that can produce under the dominance of robots,after the new point reached in artificial intelligence and robot technology,and this development will further increase productivity in production.Intelligent robots working in the internet of things system will be able to work with greater power and longer periods than humans,and smart factories that are almost never shut down will emerge.In the transformation in this process,which is also called robonomics,changes in the theory of economy may occur and a new economic order may emerge.The question of why behind-the-scenes countries,such as Turkey,could not catch up with the leading ones,is another matter of discussion.However,in such periods of technological paradigm change,an opportunity arises for lagging countries for their economic development.On the other hand,we can say that Turkey will either be able to catch up with the technological level of developed countries by taking advantage of the opportunity,by means of a step-by-step technological development,or it will continue to stay among the countries that lag behind by missing the opportunity.

Optimal Deep Learning Based Intruder Identification in Industrial Internet of Things Environment

With the increased advancements of smart industries,cybersecurity has become a vital growth factor in the success of industrial transformation.The Industrial Internet of Things(IIoT)or Industry 4.0 has revolutionized the concepts of manufacturing and production altogether.In industry 4.0,powerful IntrusionDetection Systems(IDS)play a significant role in ensuring network security.Though various intrusion detection techniques have been developed so far,it is challenging to protect the intricate data of networks.This is because conventional Machine Learning(ML)approaches are inadequate and insufficient to address the demands of dynamic IIoT networks.Further,the existing Deep Learning(DL)can be employed to identify anonymous intrusions.Therefore,the current study proposes a Hunger Games Search Optimization with Deep Learning-Driven Intrusion Detection(HGSODLID)model for the IIoT environment.The presented HGSODL-ID model exploits the linear normalization approach to transform the input data into a useful format.The HGSO algorithm is employed for Feature Selection(HGSO-FS)to reduce the curse of dimensionality.Moreover,Sparrow Search Optimization(SSO)is utilized with a Graph Convolutional Network(GCN)to classify and identify intrusions in the network.Finally,the SSO technique is exploited to fine-tune the hyper-parameters involved in the GCN model.The proposed HGSODL-ID model was experimentally validated using a benchmark dataset,and the results confirmed the superiority of the proposed HGSODL-ID method over recent approaches.

Network Intrusion Detection in Internet of Blended Environment Using Ensemble of Heterogeneous Autoencoders(E-HAE)

Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or data.The growing use of Internet of Things(IoT)technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation,as it facilitates multiple new attack vectors to emerge effortlessly.As such,existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection systems.To address this problem,we designed a blended threat detection approach,considering the possible impact and dimensionality of new attack surfaces due to the aforementioned convergence.We collectively refer to the convergence of different technology sectors as the internet of blended environment.The proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational autoencoder.An extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02%detection accuracy.Furthermore,performance of the proposed approach was compared with various single model(autoencoder)-based network intrusion detection approaches:autoencoder,variational autoencoder,convolutional variational autoencoder,and long short-term memory variational autoencoder.The proposed model outperformed all compared models,demonstrating F1-score improvements of 4.99%,2.25%,1.92%,and 3.69%,respectively.

Challenges and Requirements for the Application of Industry 4.0:A Special Insight with the Usage of Cyber-Physical System

Considered as a top priority of industrial devel- opment, Industry 4.0 （or Industrie 4.0 as the German ver- sion） has being highlighted as the pursuit of both academy and practice in companies. In this paper, based on the review of state of art and also the state of practice in dif- ferent countries, shortcomings have been revealed as the lacking of applicable framework for the implementation of Industrie 4.0. Therefore, in order to shed some light on the knowledge of the details, a reference architecture is developed, where four perspectives namely manufacturing process, devices, software and engineering have been highlighted. Moreover, with a view on the importance of Cyber-Physical systems, the structure of Cyber-Physical System are established for the in-depth analysis. Further cases with the usage of Cyber-Physical System are also arranged, which attempts to provide some implications to match the theoretical findings together with the experience of companies. In general, results of this paper could be useful for the extending on the theoretical understanding of Industrie 4.0. Additionally, applied framework and proto- types based on the usage of Cyber-Physical Systems are also potential to help companies to design the layout of sensor nets, to achieve coordination and controlling of smart machines, to realize synchronous production with systematic structure, and to extend the usage of information and communication technologies to the maintenance scheduling.

Design and Simulation of IoT Systems Using the Cisco Packet Tracer

Design and implementation of Internet of Things (IoT) systems require platforms with smart things and components. Two dominant architectural approaches for developing IoT systems are mashup-based and model-based approaches. Mashup approaches use existing services and are mainly suitable for less critical, personalized applications. Web development tools are widely used in mashup approaches. Model-based techniques describe a system on a higher level of abstraction, resulting in very expressive modelling of systems. The article uses Cisco packet tracer 7.2 version, which consists of four subcategories of smart things—home, smart city, industrial and power grid, to design an IoT based control system for a fertilizer manufacturing plant. The packet tracer also consists of boards—microcontrollers (MCU-PT), and single boarded computers (SBC-PT), as well as actuators and sensors. The model facilitates flexible communication opportunities among things—machines, databases, and Human Machine Interfaces (HMIs). Implementation of the IoT system brings finer process control as the operating conditions are monitored online and are broadcasted to all stakeholders in real-time for quicker action on deviations. The model developed focuses on three process plants;steam raising, nitric acid, and ammonium nitrate plants. Key process parameters are saturated steam temperature, fuel flowrates, CO and SOx emissions, converter head temperature, NOx emissions, neutralisation temperature, solution temperature, and evaporator steam pressure. The parameters need to be monitored in order to ensure quality, safety, and efficiency. Through the Cisco packet tracer platform, a use case, physical layout, network layout, IoT layout, configuration, and simulation interface were developed.

Theoretical research and application of petrochemical Cyber-physical Systems

A petrochemical smart factory is a green,efficient, safe and sustainable modern factory that combines cutting-edge information and communication technology with petrochemical advanced technology and equipment. A Cyber-physical System(CPS) is the infrastructure of a petrochemical smart factory. Based on the future challenges of the petrochemical industry, this paper proposes the definition, connotation and framework of a petrochemical CPS and constructs a CPS system at the enterprise, unit and field levels, respectively. Furthermore,the paper provides theoretical support and implementation reference of a CPS in the petrochemical industry and other industries by investigating the construction practice of a multi-level CPS in the China Petrochemical Corporation(SINOPEC).

Framework and case study of cognitive maintenance in Industry 4.0

We present a new framework for cognitive maintenance (CM) based on cyber-physical systems and advanced artificial intelligence techniques. These CM systems integrate intelligent deep learning approaches and intelligent decision-making tech-niques, which can be used by maintenance professionals who are working with cutting-edge equipment. The systems will provide technical solutions to real-time online maintenance tasks, avoid outages due to equipment failures, and ensure the continuous and healthy operation of equipment and manufacturing assets. The implementation framework of CM consists of four modules, i.e., cyber-physical system, Internet of Things, data mining, and Internet of Services. In the data mining module, fault diagnosis and prediction are realized by deep learning methods. In the case study, the backlash error of cutting-edge machine tools is taken as an example. We use a deep belief network to predict the backlash of the machine tool, so as to predict the possible failure of the machine tool, and realize the strategy of CM. Through the case study, we discuss the significance of implementing CM for cutting-edge equipment, and the framework of CM implementation has been verified. Some CM system applications in manufacturing enterprises are summarized.