Intrusion Detection System for Smart Industrial Environments with Ensemble Feature Selection and Deep Convolutional Neural Networks

Smart Industrial environments use the Industrial Internet of Things(IIoT)for their routine operations and transform their industrial operations with intelligent and driven approaches.However,IIoT devices are vulnerable to cyber threats and exploits due to their connectivity with the internet.Traditional signature-based IDS are effective in detecting known attacks,but they are unable to detect unknown emerging attacks.Therefore,there is the need for an IDS which can learn from data and detect new threats.Ensemble Machine Learning(ML)and individual Deep Learning(DL)based IDS have been developed,and these individual models achieved low accuracy;however,their performance can be improved with the ensemble stacking technique.In this paper,we have proposed a Deep Stacked Neural Network(DSNN)based IDS,which consists of two stacked Convolutional Neural Network(CNN)models as base learners and Extreme Gradient Boosting(XGB)as the meta learner.The proposed DSNN model was trained and evaluated with the next-generation dataset,TON_IoT.Several pre-processing techniques were applied to prepare a dataset for the model,including ensemble feature selection and the SMOTE technique.Accuracy,precision,recall,F1-score,and false positive rates were used to evaluate the performance of the proposed ensemble model.Our experimental results showed that the accuracy for binary classification is 99.61%,which is better than in the baseline individual DL and ML models.In addition,the model proposed for IDS has been compared with similar models.The proposed DSNN achieved better performance metrics than the other models.The proposed DSNN model will be used to develop enhanced IDS for threat mitigation in smart industrial environments.

Strengthening network slicing for Industrial Internet with deep reinforcement learning

Industrial Internet combines the industrial system with Internet connectivity to build a new manufacturing and service system covering the entire industry chain and value chain.Its highly heterogeneous network structure and diversified application requirements call for the applying of network slicing technology.Guaranteeing robust network slicing is essential for Industrial Internet,but it faces the challenge of complex slice topologies caused by the intricate interaction relationships among Network Functions(NFs)composing the slice.Existing works have not concerned the strengthening problem of industrial network slicing regarding its complex network properties.Towards this end,we aim to study this issue by intelligently selecting a subset of most valuable NFs with the minimum cost to satisfy the strengthening requirements.State-of-the-art AlphaGo series of algorithms and the advanced graph neural network technology are combined to build the solution.Simulation results demonstrate the superior performance of our scheme compared to the benchmark schemes.

City Network Evolution Characteristics of Smart Industry: Evidence from Yangtze River Delta, China

The dual-path model of industrial evolution and spatial progression has been widely acknowledged and incorporated into the strategic planning to promote the development of urban industries and regional collaborations.However,current research on inter-enter-prise city networks mainly focuses on the single sector of flows on all enterprise branches,such as product value chains and production factors,but neglects that of particular industry department.Built upon the new economic geography and city networks theory,this paper develops a methodological framework that focuses on the analysis of city network evolution characteristics of smart industry.Particu-larly,a conceptual model of smart industry enterprise-industry-city is proposed and then applied to a case study of smart industry in the Yangtze River Delta Region,China.Using enterprise supplier-customer data,a city network of smart industry is constructed and sub-sequently analyzed with the proposed model.Findings indicate that the smart industry network in Yangtze River Delta Region exhibits a hierarchical structure and the expansion of the network presents a small-world network characteristic.The study not only makes a meth-odological contribution for revealing the industrial and spatial evolution path of the current smart industry,but also provides empirical support for the formulation of new economic development policies focused on smart industries,demonstrating the role of city clusters as carriers of regional synergistic development.

The Effect of Key Nodes on theMalware Dynamics in the Industrial Control Network

As industrialization and informatization becomemore deeply intertwined,industrial control networks have entered an era of intelligence.The connection between industrial control networks and the external internet is becoming increasingly close,which leads to frequent security accidents.This paper proposes a model for the industrial control network.It includes a malware containment strategy that integrates intrusion detection,quarantine,and monitoring.Basedonthismodel,the role of keynodes in the spreadofmalware is studied,a comparisonexperiment is conducted to validate the impact of the containment strategy.In addition,the dynamic behavior of the model is analyzed,the basic reproduction number is computed,and the disease-free and endemic equilibrium of the model is also obtained by the basic reproduction number.Moreover,through simulation experiments,the effectiveness of the containment strategy is validated,the influence of the relevant parameters is analyzed,and the containment strategy is optimized.In otherwords,selective immunity to key nodes can effectively suppress the spread ofmalware andmaintain the stability of industrial control systems.The earlier the immunization of key nodes,the better.Once the time exceeds the threshold,immunizing key nodes is almost ineffective.The analysis provides a better way to contain the malware in the industrial control network.

Game theory in network security for digital twins in industry

To ensure the safe operation of industrial digital twins network and avoid the harm to the system caused by hacker invasion,a series of discussions on network security issues are carried out based on game theory.From the perspective of the life cycle of network vulnerabilities,mining and repairing vulnerabilities are analyzed by applying evolutionary game theory.The evolution process of knowledge sharing among white hats under various conditions is simulated,and a game model of the vulnerability patch cooperative development strategy among manufacturers is constructed.On this basis,the differential evolution is introduced into the update mechanism of the Wolf Colony Algorithm(WCA)to produce better replacement individuals with greater probability from the perspective of both attack and defense.Through the simulation experiment,it is found that the convergence speed of the probability(X)of white Hat 1 choosing the knowledge sharing policy is related to the probability(x0)of white Hat 2 choosing the knowledge sharing policy initially,and the probability(y0)of white hat 2 choosing the knowledge sharing policy initially.When y0?0.9,X converges rapidly in a relatively short time.When y0 is constant and x0 is small,the probability curve of the“cooperative development”strategy converges to 0.It is concluded that the higher the trust among the white hat members in the temporary team,the stronger their willingness to share knowledge,which is conducive to the mining of loopholes in the system.The greater the probability of a hacker attacking the vulnerability before it is fully disclosed,the lower the willingness of manufacturers to choose the"cooperative development"of vulnerability patches.Applying the improved wolf colonyco-evolution algorithm can obtain the equilibrium solution of the"attack and defense game model",and allocate the security protection resources according to the importance of nodes.This study can provide an effective solution to protect the network security for digital twins in the industry.

Decent Work and Industrial Upgrading in Global Production Network: a Case of China Apparel Industry

China apparel industry, which is deeply embedded in the global production network (GPN), faces two urgent issues, social upgrading and economic upgrading. The study of GPN places great emphasis on the two issues. Based on the survey of Ningbo apparel industry, four key components of decent work in China apparel industry are discussed. The role of buyers in promoting decent work in suppliers can't be neglected. There are significant correlations between business type and some indicators of decent work. Though the majority of the apparel firms are engaging in processing, more and more firms are involved in marketing and branding. The upgrading trajectory of China apparel industry leads to the economic and social performances.

Cooperative Game Analysis of Tourism Enterprise Coupling from the Perspective of Industrial Eco-Network

Based on the introduction of the connotations and characteristics of tourism industrial eco-network,it has expatiated on the connotations of and approaches to enterprise coupling in tourism industrial eco-network.As there are different understandings and definitions of these connotations,the following four aspects must be achieved in order to realize coupling in the real sense for the enterprises in the network.① Establish the idea of "the whole is larger than the sum of all the parts",and construct interests community of tourism industrial eco-network.② Construct cooperation mechanism of joint struggle to transfer the advantages of the single to the advantages of the whole.③ Create and maintain strong service culture.④ Avoid as many service blunders as possible and construct damage warning mechanism in industrial eco-network.With the construction of the game model of tourism enterprise coupling and corresponding analysis,the results indicate that the mode of loose cooperation between enterprises in the tourism industry could hardly reach any forceful binding agreements.Consequently it is hard to realize the coordinated effects brought about by the cooperative game of tourism enterprise coupling and these enterprises would often come to a "prisoner dilemma" because of present tiny benefits.In the end,it suggests that during the process of competition tourism enterprises should also strengthen mutual cooperation as relying upon the platform of industrial eco-network.

Evolution Characteristics of Government-Industry-University Cooperative Innovation Network of Electronic Information Industry in Liaoning Province, China

It is important to optimize the cooperative innovation network for the improvement of economic competence and innovative power. Based on the patent information services platform, we obtain invention patent data for the electronic information industry in Liaoning from 1985 to 2015. This paper analyzes the cooperative innovation network structure, its spatiotemporal evolution and the triple helix relationship of government-industry-university(GIU) by using the social network analysis method and the triple helix theory as well as UCINet, ArcGIS and NetDraw. The empirical results show that: 1) the number of the subjects of the electronic information industry GIU cooperative innovation network in Liaoning demonstrates a gradual increase from 1985 to 2015, with the same trend in concentration. In terms of its subject and its centrality, the universities have a higher position, and the industries have a lower position,while the status of the government is still unclear. 2) The cooperative innovation network presents a core-periphery structure, and the polarization effect of innovation subjects tends to be obvious. There is certain distance-decay regularity in the cooperative innovation network, and a strong geographical proximity to cooperative innovation. 3) The compactness shows a downward trend as a whole. In terms of the extent of participation, the industries are better than the government but worse than the universities. This means that the cooperative innovation network of GIU in the electronic information industry in Liaoning is in the initial stage of formation.

A Methodology for Reliability of WSN Based on Software Defined Network in Adaptive Industrial Environment

As communication technology and smart manufacturing have developed, the industrial internet of things(IIo T)has gained considerable attention from academia and industry.Wireless sensor networks(WSNs) have many advantages with broad applications in many areas including environmental monitoring, which makes it a very important part of IIo T. However,energy depletion and hardware malfunctions can lead to node failures in WSNs. The industrial environment can also impact the wireless channel transmission, leading to network reliability problems, even with tightly coupled control and data planes in traditional networks, which obviously also enhances network management cost and complexity. In this paper, we introduce a new software defined network(SDN), and modify this network to propose a framework called the improved software defined wireless sensor network(improved SD-WSN). This proposed framework can address the following issues. 1) For a large scale heterogeneous network, it solves the problem of network management and smooth merging of a WSN into IIo T. 2) The network coverage problem is solved which improves the network reliability. 3) The framework addresses node failure due to various problems, particularly related to energy consumption.Therefore, it is necessary to improve the reliability of wireless sensor networks, by developing certain schemes to reduce energy consumption and the delay time of network nodes under IIo T conditions. Experiments have shown that the improved approach significantly reduces the energy consumption of nodes and the delay time, thus improving the reliability of WSN.

Time Delay Characteristic of Industrial Wireless Networks Based on IEEE 802.15.4a

The IEEE 802.15.4a standard provides a framework for low-data-rate communication systems,typically sensor networks.In this paper,we established a realistic environment for the time delay characteristic of industrial network based on IEEE 802.15.4a.Several sets of practical experiments are conducted to study its various features,including the effects of 1） numeral wireless nodes,2） numeral data packets,3） data transmissions with different upper-layer protocols,4） physical distance between nodes,and 5） adding and reducing the number of the wireless nodes.The results show that IEEE 802.15.4a is suitable for some industrial applications that have more relaxed throughput requirements and time-delay.Some issues that could degrade the network performance are also discussed.

Effects of Network Closure on Cooperative Innovation: Evidence from Dongying's Petroleum Equipment Industry in China

There are two opposing viewpoints on which kind of network configuration provides a more competitive advantage, namely,network closure or structural holes, with the latter occupying the dominant position in the literature. Using social network analysis and negative binomial regression methods, we graph the co-patent network of Dongying's petroleum equipment industry in China and explore its impact on enterprise innovation. The analysis is based on 17 face-to-face interviews, 31 enterprise questionnaires, and 354 co-patent records from the China State Intellectual Property Office identifying cooperative innovation for the years 1988–2013. We find that this network is closed, controlled by state-owned enterprises, and its closure has positive effects on enterprise innovation performance. This may be related to China's unique industrial development history, state system and policies, regional culture and circumstances, and enterprise characteristics. Therefore, for some industries in specific regions, the advantages usually attributed to structural holes and open innovation may not necessarily apply.

Groundwater Level Prediction Using Artificial Neural Networks: A Case Study in Tra Noc Industrial Zone, Can Tho City, Vietnam

The objective of this study is to predict groundwater levels (GWLs) under different impact factors using Artificial Neural Network (ANN) for a case study in Tra Noc Industrial Zone, Can Tho City, Vietnam. This can be achieved by evaluating the current state of groundwater resources (GWR) exploitation, use and dynamics;setting-up, calibrating and validating the ANN;and then predicting GWLs at different lead times. The results show that GWLs in the study area have been found to reduce rapidly from 2000 to 2015, especially in the Middle-upper Pleistocene (qp2-3) and upper Pleistocene (qp3) due to the over-withdrawals from the enterprises for production purposes. Concerning this problem, an Official Letter of the People’s Committee of Can Tho City was issued and taken into enforcement in 2012 resulting in the reduction of exploitation. The calibrated ANN structures have successfully demonstrated that the GWLs can be predicted considering different impact factors. The predicted results will help to raise awareness and to draw an attention of the local/central government for a clear GWR management policy for the Mekong delta, especially the industrial zones in the urban areas such as Can Tho city.

Variational Inference Based Kernel Dynamic Bayesian Networks for Construction of Prediction Intervals for Industrial Time Series With Incomplete Input

Prediction intervals(PIs)for industrial time series can provide useful guidance for workers.Given that the failure of industrial sensors may cause the missing point in inputs,the existing kernel dynamic Bayesian networks(KDBN),serving as an effective method for PIs construction,suffer from high computational load using the stochastic algorithm for inference.This study proposes a variational inference method for the KDBN for the purpose of fast inference,which avoids the timeconsuming stochastic sampling.The proposed algorithm contains two stages.The first stage involves the inference of the missing inputs by using a local linearization based variational inference,and based on the computed posterior distributions over the missing inputs the second stage sees a Gaussian approximation for probability over the nodes in future time slices.To verify the effectiveness of the proposed method,a synthetic dataset and a practical dataset of generation flow of blast furnace gas(BFG)are employed with different ratios of missing inputs.The experimental results indicate that the proposed method can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.

Exploring Enterprise Performance Indicators Network： A Case Study of China Telecommunication Industry

Perforrmnce indicators play some important roles in enterprise operation. Both researchers and managers have recently pointed out that the identification of correlation between different performmance indicators may lead to a better understanding of business. However, it is becoming more and more difficult to measure and analyze these indicators since the fast growing number of performance indicators and the complex relationships between them The existing categories failed to reflect these changes in an adequate way, and the quantitative analysis methods for identifying the characters of those pefformance indicators are still worthy of investigation. The main objective of this paper is to propose a practical methodology for managing and analyzing performance indicators in enterprises, which focuses on building up a performance indicator system and discovering the characters of those performance indicators by applying complex network methods. The empirical results of a telecommunieation enterprise show that the proposed method can be effective in understanding the correlations between performance indicators.

Novel MAC Layer Proposal for URLLC in IndustrialWireless Sensor Networks

Ultra-reliable and low-latency communications(URLLC) has become a fundamental focus of future industrial wireless sensor net-works(IWSNs). With the evolution of automation and process control in industrial environments, the need for increased reliabilityand reduced latencies in wireless communications is even pronounced. Furthermore, the 5G systems specifically target the URLLCin selected areas and industrial automation might turn into a suitable venue for future IWSNs, running 5G as a high speed inter-process linking technology. In this paper, a hybrid multi-channel scheme for performance and throughput enhancement of IWSNsis proposed. The scheme utilizes the multiple frequency channels to increase the overall throughput of the system along with theincrease in reliability. A special purpose frequency channel is defined, which facilitates the failed communications by retransmis-sions where the retransmission slots are allocated according to the priority level of failed communications of different nodes. Ascheduler is used to formulate priority based scheduling for retransmission in TDMA based communication slots of this channel.Furthermore, in carrier-sense multiple access with collision avoidance(CSMA/CA) based slots, a frequency polling is introducedto limit the collisions. Mathematical modelling for performance metrics is also presented. The performance of the proposed schemeis compared with that of IEEE802.15.4e, where the performance is evaluated on the basis of throughput, reliability and the num-ber of nodes accommodated in a cluster. The proposed scheme offers a notable increase in the reliability and throughput over theexisting IEEE802.15.4e Low Latency Deterministic Networks(LLDN) standard.

A New Model for Network Security Situation Assessment of the Industrial Internet

To address the problem of network security situation assessment in the Industrial Internet,this paper adopts the evidential reasoning(ER)algorithm and belief rule base(BRB)method to establish an assessment model.First,this paper analyzes the influencing factors of the Industrial Internet and selects evaluation indicators that contain not only quantitative data but also qualitative knowledge.Second,the evaluation indicators are fused with expert knowledge and the ER algorithm.According to the fusion results,a network security situation assessment model of the Industrial Internet based on the ER and BRB method is established,and the projection covariance matrix adaptive evolution strategy(P-CMA-ES)is used to optimize the model parameters.This method can not only utilize semiquantitative information effectively but also use more uncertain information and prevent the problem of combinatorial explosion.Moreover,it solves the problem of the uncertainty of expert knowledge and overcomes the problem of low modeling accuracy caused by insufficient data.Finally,a network security situation assessment case of the Industrial Internet is analyzed to verify the effectiveness and superiority of the method.The research results showthat this method has strong applicability to the network security situation assessment of complex Industrial Internet systems.It can accurately reflect the actual network security situation of Industrial Internet systems and provide safe and reliable suggestions for network administrators to take timely countermeasures,thereby improving the risk monitoring and emergency response capabilities of the Industrial Internet.

Simulation of Low TDS and Biological Units of Fajr Industrial Wastewater Treatment Plant Using Artificial Neural Network and Principal Component Analysis Hybrid Method

Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. With regard to environmental issues, proper operation of wastewater treatment plants is of par- ticular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems mostly have two major characteristics: they are dependent on many variables;and there are complex relationships between its components which make them very difficult to analyze. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant (WWTP), powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the treatment plant was divided into two main subsystems including: Low TDS (Total Dissolved Solids) treatment unit and Biological unit (extended aeration). The multilayer perceptron feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant, located in Mahshahr—Iran that qualita- tive and quantitative characteristics of its units were used for training, calibration and validation of the neural model. Also, Principal Component Analysis (PCA) technique was applied to improve performance of generated models of neural networks. The results of L-TDS unit showed good accuracy of the models in estimating qualitative profile of wastewater but results of biological unit did not have sufficient accuracy to being used. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of outputs.

Performance Simulation of H-TDS Unit of Fajr Industrial Wastewater Treatment Plant Using a Combination of Neural Network and Principal Component Analysis

Nowadays, with regard to environmental issues, proper operation of wastewater treatment plants is of particular importance that in the case of inappropriate utilization, they will cause serious problems. Processes that exist in environmental systems and environmental engineers are dealing with them mostly have two major characteristics: they are dependent on many variables;and there are complex relationships between its components which make them very difficult to analyze. Being familiar with characteristics of industrial town effluents from various wastewater treatment units, which have high qualitative and quantitative variations and more uncertainties compared to urban wastewaters, plays very effective role in governing them. In order to achieve a better and efficient control over the operation of an industrial wastewater treatment plant, powerful mathematical tool can be used that is based on recorded data from some basic parameters of wastewater during a period of treatment plant operation. In this study, the multilayer perceptron (MLP) feed forward neural network with a hidden layer and stop training method was used to predict quality parameters of the industrial effluent. Data of this study are related to the Fajr Industrial Wastewater Treatment Plant located in Mahshahr—Iran that qualitative and quantitative characteristics of its units were used for training, calibration and evaluation of the neural model. Also, Principal Component Analysis technique was applied to modify and improve performance of generated models of neural networks. The results of this model showed good accuracy of the model in estimating qualitative pro- file of wastewater. This model facilitates evaluating the performance of each treatment plant units through comparing the results of prediction model with the standard amount of output.

Comprehensive Analysis of Secure Data Aggregation Scheme for Industrial Wireless Sensor Network

As an Industrial Wireless Sensor Network(IWSN)is usually deployed in a harsh or unattended environment,the privacy security of data aggregation is facing more and more challenges.Currently,the data aggregation protocols mainly focus on improving the efficiency of data transmitting and aggregating,alternately,the aim at enhancing the security of data.The performances of the secure data aggregation protocols are the trade-off of several metrics,which involves the transmission/fusion,the energy efficiency and the security in Wireless Sensor Network(WSN).Unfortunately,there is no paper in systematic analysis about the performance of the secure data aggregation protocols whether in IWSN or in WSN.In consideration of IWSN,we firstly review the security requirements and techniques in WSN data aggregation in this paper.Then,we give a holistic overview of the classical secure data aggregation protocols,which are divided into three categories:hop-by-hop encrypted data aggregation,end-to-end encrypted data aggregation and unencrypted secure data aggregation.Along this way,combining with the characteristics of industrial applications,we analyze the pros and cons of the existing security schemes in each category qualitatively,and realize that the security and the energy efficiency are suitable for IWSN.Finally,we make the conclusion about the techniques and approach in these categories,and highlight the future research directions of privacy preserving data aggregation in IWSN.

Rationalizing the Use of Water in Industry—Part 1: Summary of the Instruments Developed by the Clean Technology Network in the State of Bahia and Main Results Obtained

Based on cleaner production concepts, a method for water use minimization has been developed by the Clean Technology Network of Bahia (TECLIM) at one of the largest industrial complexes in Latin America located in the State of Bahia, Brazil. This method is concerned with an area of secondary interest to the productive sector: the use of water. Based on the best cleaner production principles (CP), nine instruments have been developed during cooperative projects with chemical, petrochemical and copper metallurgical industries. These instruments are described in Part 2 of this paper [1]. The main benefits derived from partnership schemes include: a reduction in water consumption and effluent generation;the development of a techno-operational culture to increase eco-efficiency;and the introduction of conceptual projects to ensure the continuity of the activities in the company after the projects have been completed. The specific consumption of water was reduced by 20% as a consequence of the application of this method in Company A;a specific reduction in the generation of effluents of more than 40% was observed in Company B;a 42% fall in fresh water consumption in Company C;and a 20% decrease in the cost of effluent treatment in Company D. Among the difficulties encountered were the limited time availability of the operators and engineers for the project, the lack of measurement and calibration of available flow meters and the lack of detailed technical data.