Complex Industrial Systems Research Articles

A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring

Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.

Deep-Compact-Clustering Based Anomaly Detection Applied to Electromechanical Industrial Systems.

The rapid growth in the industrial sector has required the development of more productive and reliable machinery, and therefore, leads to complex systems. In this regard, the automatic detection of unknown events in machinery represents a greater challenge, since uncharacterized catastrophic faults can occur. However, the existing methods for anomaly detection present limitations when dealing with highly complex industrial systems. For that purpose, a novel fault diagnosis methodology is developed to face the anomaly detection. An unsupervised anomaly detection framework named deep-autoencoder-compact-clustering one-class support-vector machine (DAECC-OC-SVM) is presented, which aims to incorporate the advantages of automatically learnt representation by deep neural network to improved anomaly detection performance. The method combines the training of a deep-autoencoder with clustering compact model and a one-class support-vector-machine function-based outlier detection method. The addressed methodology is applied on a public rolling bearing faults experimental test bench and on multi-fault experimental test bench. The results show that the proposed methodology it is able to accurately to detect unknown defects, outperforming other state-of-the-art methods.

Application of Characteristic Model-Based Principal Component Analysis in Optimization of Flowmeter Parameters

In complex industrial processes, it is necessary to perform modeling analysis on some industrial systems and find and optimize the factors that have the greatest impact on the results, in order to achieve the optimization of the industrial systems. However, due to the high-level nature or complex working mechanism of complex industrial systems, traditional principal component analysis methods are difficult to apply. Therefore, this paper proposes a characteristic model-based principal component analysis (CMPCA) to perform principal component analysis on complex industrial systems. The differential pressure flowmeter is taken as an example to verify the effectiveness of the method. Flowmeter is an indispensable instrument in measurement, and its accuracy depends on its own structural parameters. However, the measurement accuracy of some flow meters is not high, and the measurement error is large, which affects the normal industrial production process. This method is used to analyze the influence of the structural parameters of the flowmeter on its measurement accuracy, and the four most important structural parameters are found and optimized. The measurement error of the Bitoba flowmeter is reduced from 1% to 0.2%, and the measurement repeatability is reduced from 0.3 to 0.06, which proves the effectiveness of the method.

On the fretting fatigue crack nucleation of complete, almost complete and incomplete contacts using an asymptotic method

In this work, the fretting crack nucleation of an aeronautical Ti-10V-2Fe-3Al titanium alloy is investigated. The main difficulty when designing complex industrial systems, especially helicopters rotor parts, lies in the prediction of the assembly interfaces behaviour. Those areas can be subjected to fretting loading characterized by a very confined multiaxial high stress gradient, leading to fatigue crack nucleation. This kind of failure reduces the parts potential lifetime and increases therefore the security margin that can be considered.The aim of this paper is to provide a criterion to prevent crack nucleation on industrial contacts configurations. To reach this objective, this study focuses on the geometrical conditions, loadings and material properties linked to crack initiation. Two dedicated fretting test campaigns are used to study crack initiation conditions with various contact shapes and loadings on the same material. The crack initiation conditions are compared with a contact mechanics representation based on asymptotic methods. This method allows the stress field evaluation at the hot spot location by using the problem’s eigenvalues.The combination of the asymptotic method with contact mechanics and the Goodman approach allows to represent the key parameters of the fretting fatigue crack initiation. They include the impacted material volume, the shear intensity and the bulk stress. A fretting fatigue crack initiation criterion is proposed. It is based on classical material properties and the bulk stress ratio Rσ0 only and is applicable to all sorts of contact shapes. The main interests of this prediction method are the absence of size effect parameters for industrial contacts and its efficiency, as it is only based on analytical formulations.

A low cost fault-attack resilient AES for IoT applications

The Internet of Things (IoT) as an emerging infrastructure has an essential rule in daily lives in many domains, ranging from healthcare wearable devices to complex industrial systems. Nevertheless, its security is a challenging issue that has to be addressed. The security can be settled by utilizing cryptographic techniques such as Advanced Encryption Standard (AES) for encryption and authentication. In this paper, we propose 32-bit architecture AES encryption/decryption for utilizing in IoT infrastructure and similar resource-constrained applications. On the other hand, providing robustness against existing malicious attacks is a significant factor in ensuring communication reliably and so securely. Therefore, we propose a low-cost fault-resilient integrated architecture, named LC-FRAES, for data-path and also on-the-fly key expansion unit by exploiting of resource sharing between encryption and decryption processes. The results of both ASIC and FPGA implementations of the proposed architecture are reported and also compared with those of similar recent designs. The comparisons illustrate that the LC-FRAES outperforms its counterparts in many architectural features which make it suitable for IoT applications. Moreover, we provide a comparison between our proposal and lightweight cryptographic designs from literature. The comparisons verify the consistency and appropriateness of proposed architecture for IoT applications. Finally, through the extensive experimental results, we show that LC-FRAES can detect almost all injected faults.

A Review of the Reliability Analysis of the Complex Industrial Systems

A Review of the Reliability Analysis of the Complex Industrial Systems

An Efficient Universal Generating Function-Based Analyzing Approach for Multistate System with Imperfect Coverage Failure

A system with more than two states is called a multistate system (MSS), and such systems have already become a general trend in the arena of complex industrial products and/or systems. Fault-tolerant technology often plays a very important role in improving the reliability of an MSS. However, the existence of imperfect coverage failure (ICF) in a work-sharing group (WSG) decreases the reliability of MSS. A method is proposed to assess the reliability and sensitivity of an MSS with ICF. The components in a WSG can cooperate so as to improve overall efficiency by increasing performance levels. Using the technique of the universal generating function (UGF), a component’s UGF expression with ICF can be incorporated in two steps. During the computation of the system’s UGF, an algorithm based on matrix (ABM) is developed to reduce the computational complexity. Consequently, indices of reliability can be easily calculated based on the UGF expression of an MSS. Sensitivity analysis can help engineers judge which WSG should be eliminated first under various resource limitations. Examples illustrate and validate this method.

Soft-Sensor for Class Prediction of the Percentage of Pentanes in Butane at a Debutanizer Column.

Refineries are complex industrial systems that transform crude oil into more valuable subproducts. Due to the advances in sensors, easily measurable variables are continuously monitored and several data-driven soft-sensors are proposed to control the distillation process and the quality of the resultant subproducts. However, data preprocessing and soft-sensor modelling are still complex and time-consuming tasks that are expected to be automatised in the context of Industry 4.0. Although recently several automated learning (autoML) approaches have been proposed, these rely on model configuration and hyper-parameters optimisation. This paper advances the state-of-the-art by proposing an autoML approach that selects, among different normalisation and feature weighting preprocessing techniques and various well-known Machine Learning (ML) algorithms, the best configuration to create a reliable soft-sensor for the problem at hand. As proven in this research, each normalisation method transforms a given dataset differently, which ultimately affects the ML algorithm performance. The presented autoML approach considers the features preprocessing importance, including it, and the algorithm selection and configuration, as a fundamental stage of the methodology. The proposed autoML approach is applied to real data from a refinery in the Basque Country to create a soft-sensor in order to complement the operators’ decision-making that, based on the operational variables of a distillation process, detects 400 min in advance with precision if the resultant product does not reach the quality standards.

Microfluidic-based processors and circuits design

Droplets produced within microfluidics have not only attracted the attention of researchers to develop complex biological, industrial and clinical testing systems but also played a role as a bit of data. The flow of droplets within a network of microfluidic channels by stimulation of their movements, trajectories, and interaction timing, can provide an opportunity for preparation of complex and logical microfluidic circuits. Such mechanical-based circuits open up avenues to mimic the logic of electrical circuits within microfluidics. Recently, simple microfluidic-based logical elements such as AND, OR, and NOT gates have been experimentally developed and tested to model basic logic conditions in laboratory settings. In this work, we develop new microfluidic networks, control the shape of channels and speed of droplet movement, and regulate the size of bubbles in order to extend the logical elements to six new logic gates, including AND/OR type 1, AND/OR type 2, NOT type 1, NOT type 2, Flip-Flop, Synchronizer, and a parametric model of T-junction as a bubble generator. We further designed and simulated a novel microfluidic Decoder 1 to 2, a Decoder 2 to 4, and a microfluidic circuit that combines several individual logic gates into one complex circuit. Further fabrication and experimental testing of these newly introduced logic gates within microfluidics enable implementing complex circuits in high-throughput microfluidic platforms for tissue engineering, drug testing and development, and chemical synthesis and process design.

Digital Twin: Origin to Future

Digital Twin (DT) refers to the virtual copy or model of any physical entity (physical twin) both of which are interconnected via exchange of data in real time. Conceptually, a DT mimics the state of its physical twin in real time and vice versa. Application of DT includes real-time monitoring, designing/planning, optimization, maintenance, remote access, etc. Its implementation is expected to grow exponentially in the coming decades. The advent of Industry 4.0 has brought complex industrial systems that are more autonomous, smart, and highly interconnected. These systems generate considerable amounts of data useful for several applications such as improving performance, predictive maintenance, training, etc. A sudden influx in the number of publications related to ‘Digital Twin’ has led to confusion between different terminologies related to the digitalization of industries. Another problem that has arisen due to the growing popularity of DT is a lack of consensus on the description of DT as well as so many different types of DT, which adds to the confusion. This paper intends to consolidate the different types of DT and different definitions of DT throughout the literature for easy identification of DT from the rest of the complimentary terms such as ‘product avatar’, ‘digital thread’, ‘digital model’, and ‘digital shadow’. The paper looks at the concept of DT since its inception to its predicted future to realize the value it can bring to certain sectors. Understanding the characteristics and types of DT while weighing its pros and cons is essential for any researcher, business, or sector before investing in the technology.

Time dependent network resource optimization in cyber–physical systems using game theory

The social and economic stability of a country is dependent on critical infrastructures (CIs) whose services range from financial to healthcare and power to transportation and communications. Most of these CIs are cyber–physical systems (CPSs), which integrate the network’s computational and communication capabilities to facilitate the monitoring and controlling of physical processes. Such systems are vulnerable to damage due to natural disasters, physical incidents, or cyber-attacks impacting the CPS organizations managing complex industrial control systems and data acquisition systems. When these CPSs are exposed to systemic cyber risks and cascaded network failures, network administrators need to recover from the compromise under limited resources. This is formulated as an attacker-defender game model to emulate the decision-making process in choosing an appropriate attack/defence mechanism in response to cybersecurity incidents using game theory. To further improve the assumptions made in the pure game-theoretic model, we relax the constraints on the rationality of the players, monetary payoff, and completeness of information by incorporating learning in games using reinforcement learning technique and compute the expected payoff using linguistic fuzzy variables.

Multi Agent System Based Approach for Industrial Process Simulation

Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.Industrial systems become more and more complex. This complexity is due to the great number of elements that compose them and their interactions. This paper describes a multi-agent approach for modeling such systems. All of their parts are considered and are modeled by using adequate agents. The set of preoccupations were identified to find convenient multi agent models for their resolutions. Then, we implemented our application by using a MADKIT multi-agent platform. The main goal of this work is to build a simulator based on reactive agents able to translate this complex industrial system into a data processing programs that can represent its structure, its behavior, its interaction, its control loops and verify the integrity and its proper functioning. A concrete application of this approach was materialized by building an industrial gas process simulator.

Exemplification of Detecting Gas Turbine Blade Structure Defects Using the X-ray Computed Tomography Method

X-ray computed tomography is more often applied in non-destructive testing the quality of construction elements significantly crucial for reliability and safety of device elements, machines and complex industrial systems. This article describes the computed tomography (CT) system used to inspect the technical condition of turbine blades of the aircraft engine. The impact of the experimental conditions on the correctness of the obtained results was determined. The appropriate selection of parameters for the experiment was given, and the correct test results of gas turbine blades were presented. Failures, manufacturing defects, material deviations of nickel-cobalt alloyed blades were identified. The thickness of walls was measured in the selected cross-sections with the accuracy of 0.01 mm, and selected manufacturing defects of cooling passages were diagnosed. It was demonstrated that the application of the CT system allows for detailed non-destructive inspection of the technical condition of machine parts. The test results proved that the X-ray computed tomography could be applied in the production and repairs of machines.

A new risk assessment method based on belief rule base and fault tree analysis

Risk assessment methods are often used in complex industrial systems to avoid risks and reduce losses. The existing methods have not effectively solved the problems of lack of evaluation data and the interpretability of the entire evaluation process. This paper proposes a new risk assessment model based on the belief rule base (BRB) and Fault Tree Analysis (FTA). The FTA algorithm overcomes the difficulties of traditional BRB model in obtaining expert knowledge, clear indicators, and establishing logical relationships. This method establishes FTA rules based on the BRB model and expands the knowledge base through the FTA algorithm. A Bayesian network is applied as a conversion bridge between the FTA and BRB model. In addition, the model is optimized to reduce the uncertainty in the model. The method proposed is described by a case and its effectiveness is verified.

A Security Scheme Based on Intranal-Adding Links for Integrated Industrial Cyber-Physical Systems.

With the advent of the Internet of Everything era, the Industrial Internet is increasingly showing mutual integration and development. Its core framework, the industrial CPS (Cyber-Physical Systems), has received more and more attention and in-depth research in recent years. These complex industrial CPS systems are usually composed of multiple interdependent sub-networks (such as physical networks and control networks, etc.). Minor faults or failure behaviors between sub-networks may cause serious cascading failure effects of the entire system. In this paper, we will propose a security scheme based on intranal-adding links in the face of the integrated and converged industrial CPS system environment. Firstly, by calculating the size of the largest connected component in the entire system, we can compare and analyze industrial CPS systems’ security performance under random attacks. Secondly, we compare and analyze the risk of cascading failure between integrated industrial CPS systems under different intranal-adding link strategies. Finally, the simulation results verify the system security strategy’s effectiveness under different strategies and show a relatively better exchange strategy to enhance the system’s security. In addition, this paper’s research work can help us design how to further optimize the interdependent industrial CPS system’s topology to cope with the integrated and converged industrial CPS system environment.

Special Issue on “Advances in Condition Monitoring, Optimization and Control for Complex Industrial Processes”

Complex industrial automation systems and processes, such as chemical processes, manufacturing systems, wireless network systems, power and energy systems, smart grids and so forth, have greatly contributed to our daily life [...]

An integrated scheme for dynamic security assessment considering misclassification constraint based on umbrella Neyman-Pearson classifiers

Power system is one of the most complex dynamic industrial systems with the continuous expansion of the system scale and extensive application of phasor measurement units (PMUs). Dynamic security assessment (DSA) misclassification of the system will bring unpredictable consequences. Therefore, an integrated scheme for DSA that considers misclassification constraint is proposed in this paper to satisfy practical applications. The scheme includes a feature selection process and a DSA model, which are based on the bagging nearest-neighbor prediction independence test (BNNPT) and umbrella Neyman-Pearson (NP) classifiers, respectively. The BNNPT can explore the relationships between variables and the dynamic security index (DSI) to screen out the crucial features highly related to the DSI. By controlling the Type I error threshold and the cyclic split training mode, umbrella NP classifiers can effectively constrain Type I error, reduce the effect of misclassification, and improve DSA for the secure operation of the system. The performance of this integrated scheme is demonstrated through tests on the IEEE 39-bus system and a practical 500-bus system.

IE Tools for Boosting Competitiveness in Iron and Steel Industry: A Review

Integrated steelmaking operations, from ironmaking to final steel categories/forms, are a complex industrial system. Decision-makers, in addition to the domain knowledge, need to understand many facets related to operations management, process execution, involved risk factors and material handling aspects, etc. The solution approach must address trade-offs, uncertainties, multiple stages, multiple objectives, many decision variables, and constraints. Literature has presented several Industrial Engineering approaches like multi-objective optimisation, heuristics, evolutionary algorithm, Simulations, lean six-sigma, etc., to address the iron and steel industry's complex problems like integrated production planning. The manuscript reviews recent application of these IE tools/solution approaches in iron and steel industries to enhanced productivity/competitiveness. A Systematic Literature Review (SLR) methodology has been adopted. The review will help the practitioners and academicians to know the different problem areas about iron and steel industries discussed in the literature, and the solution approaches used to solve the problem.

Building a database for complex industrial monitoring systems

Problem statement. When creating monitoring systems for industrial facilities for a range of purposes, it becomes necessary to solve processing and storing objects with a complex data structure. The user must be provided with tools for processing and storing the defined data and object types that they have defined.Objective. Development of a software implementation of the interface for interaction with the database built into industrial facilities’ monitoring system.Results. A software interface for interacting with an object-oriented database has been developed. Three programming classes are used to describe various types of industrial system objects. Class methods have been developed that allow setting a variable number of attributes for different object types. The authors propose a method for extracting an object with specified attribute values, similar to the QBE method, and a method for complex (natural) queries written in the application development language.Practical implications. The proposed software implementation of the interface for interaction with the built-in database can be used to create a wide range of industrial monitoring systems. This approach allows to significantly reduce the computing resources required for the implementation of such systems, reduces the time and cost of their development.

Reliability engineering applications in electronic, software, nuclear and aerospace industries: A 20 year review (2000–2020)

A review on reliability engineering applications in 4 industrial domains namely electronic, software, nuclear and aerospace from the 2000′s to the present day is compiled. The progress in industrial maintenance activities and Human Reliability Analysis (HRA) linked to these domains are explored. Then, the mathematical aspect of reliability evaluation, in particular multi-state system (MSS), which characterizes the system complexity in these domains are presented. Trends progression are obtained through literature of respective areas as well as available technical information and industrial circulations. Through this review, trend similarities between the mentioned domains and the challenges in reliability science implementation are uncovered. The methods employed in respective industry are explained, with each strength and weakness analysed, together with application examples. This work reveals the role of Prognostic and Health Management (PHM), HRA and analytical methodologies such as MSS and Probabilistic Risk Assessment (PRA) in managing reliability of complex industrial systems. Finally, it stresses on the importance of synergy between these frameworks to ensure a complete reliability assessment in the industry.