Industrial Systems Research Articles

Mutation-Based Multivariate Time-Series Anomaly Generation on Latent Space with an Attention-Based Variational Recurrent Neural Network for Robust Anomaly Detection in an Industrial Control System

Anomaly detection involves identifying data that deviates from normal patterns. Two primary strategies are used: one-class classification and binary classification. In Industrial Control Systems (ICS), where anomalies can cause significant damage, timely and accurate detection is essential, often requiring analysis of time-series data. One-class classification is commonly used but tends to have a high false alarm rate. To address this, binary classification is explored, which can better differentiate between normal and anomalous data, though it struggles with class imbalance in ICS datasets. This paper proposes a mutation-based technique for generating ICS time-series anomalies. The method maps ICS time-series data into a latent space using a variational recurrent autoencoder, applies mutation operations, and reconstructs the time-series, introducing plausible anomalies that reflect multivariate correlations. Evaluations of ICS datasets show that these synthetic anomalies are visually and statistically credible. Training a binary classifier on data augmented with these anomalies effectively mitigates the class imbalance problem.

SIR-Aided Dynamic Canonical Correlation Analysis for Fault Detection and Isolation of Industrial Automation Systems

SIR-Aided Dynamic Canonical Correlation Analysis for Fault Detection and Isolation of Industrial Automation Systems

Promoting digital twin technology application for process industry: A novel generation modelling platform and its implementations

AbstractOne key concept of Industry 4.0 is the industrial digital twin (DT)—a virtual replica of physical assets, processes, and systems. DTs optimise operations, enhance productivity, and facilitate innovation across various industries, including manufacturing, energy, healthcare, and transportation. This paper presents a multi‐domain and multi‐time scale modelling and simulation platform, featuring built‐in model libraries that represent diverse physical, chemical, and behavioural properties. A comprehensive system modelling approach and a closed‐loop industrial control system based on DTs are developed, showcasing advanced control, optimisation, and system security research capabilities. The architecture and advantages of the novel generation modelling platform are detailed, with specific applications highlighted, underscoring its contributions to the process industry.

Monitoring and control of air filtration systems: Digital twin based on 1D computational fluid dynamics simulation and experimental data

This study presents the development of a digital model based on one-dimensional computational fluid dynamics for the monitoring and control of filtering systems used for removing flour, dust, and other particulates from the airflow arriving from various sections of industrial production plants.Focusing on a pilot plant equipped with a cyclone bag filter, historical experimental data was integrated with the results of a one-dimensional fluid dynamics simulation model to create a digital twin capable of real-time control and regulation of industrial plants. In particular, measured pressure drop data under different clogging conditions were interpolated to generate the characteristic curves of the filter under various clogging conditions, to be implemented within the digital model of the plant. The generated model, validated through a dedicated experimental campaign, accurately predicted the airflow rate and pressure distribution across the plant. The system’s capability to adapt to changing operational conditions, such as clogging, was demonstrated through simulation, highlighting the model’s utility in maintaining the desired operation levels while minimizing the need for extensive sensor networks.The analyzed case study in the field of air filtration systems aims to fill the gap in the scientific literature related to the application of Digital Twin technology to the control of industrial manufacturing plants. The findings highlight the potential of digital twins in monitoring and control, as well as predictive maintenance, of industrial systems. The findings highlight the potential of Digital Twins in monitoring and control, as well as predictive maintenance, of industrial systems. Future research activities will explore the model’s applicability in failure and anomaly detection, to further enhance predictive maintenance of air filtering systems.

An explainable unsupervised anomaly detection framework for Industrial Internet of Things

Industrial Internet of Things (IIoT) systems require effective anomaly detection techniques to ensure optimal operational efficiency. However, constructing a suitable anomaly detection framework for IIoT poses challenges due to the scarcity of labeled data. Additionally, most existing anomaly detection frameworks lack interpretability. To tackle these issues, an innovative unsupervised framework based on time series data analysis is proposed. This framework initially detects anomalous patterns in IIoT sensor data by extracting local features. An improved Time Convolutional Network (TCN) and Kolmogorov–Arnold Network (KAN) based Variational Auto-Encoder (VAE) is then constructed to capture long-term dependencies. The framework is trained in an unsupervised manner and interpreted using Explainable Artificial Intelligence (XAI) techniques. This approach offers insightful explanations regarding the importance of features, thereby facilitating informed decision-making and enhancements. Experimental results demonstrate that the framework is capable of extracting informative features and capturing long-term dependencies. This enables efficient anomaly detection in complex, dynamic industrial systems, surpassing other unsupervised methods.

Method for remaining useful life prediction of rolling bearings based on deep reinforcement learning.

In contemporary industrial systems, the prediction of remaining useful life (RUL) is recognized as a valuable maintenance strategy for health management due to its ability to monitor equipment operational status in real time and ensure the safety of industrial production. Current studies have largely concentrated on deep learning (DL) techniques, leading to a shortage of RUL prediction methods that utilize deep reinforcement learning (DRL). To further enhance application and research, this paper introduces a novel approach to RUL prediction based on DRL, specifically using a combination of Convolutional Neural Network-Bidirectional Long Short-Term Memory Network (CNN-BiLSTM) and the Deep Deterministic Policy Gradient (DDPG) algorithm. The proposed method reframes the conventional task of estimating RUL as a Markov decision process (MDP), effectively integrating the feature extraction capabilities of DL with the decision-making abilities of DRL. Initially, a hybrid CNN-BiLSTM is employed to establish an agent that can extract degradation features from raw signals. Subsequently, the DDPG algorithm within DRL is leveraged to develop the RUL prediction mechanism, completing the MDP by defining appropriate action spaces and reward functions. The agent, through repeated trials and optimization, learns to map the current operational state of the rolling bearing to its remaining service life. Validation analysis was performed on the intelligent maintenance systems (IMS) bearing dataset. The findings suggest that the DRL-based approach outperforms the current methodologies, demonstrating a superior performance in root mean square error (MSE) and MSE metrics. The predicted outcomes align more closely with the actual lifespan values.

Process deviations, early sensemaking, and enabling operators: Thinking beyond the traditional alarm-based practice to enhance industrial resilience

In the dynamic landscape of modern industrial systems, there is an emerging important need for new thinking and practice to facilitate risk-informed decision-making, especially in high-risk industrial sectors. Such novel solutions should enable operators to proactively counteract and prevent unwanted events and incidents. Efforts to harness and convert relevant data to meaningful information with unique meanings, in fact represents new opportunities to create relevant knowledge of the actual context. This paper examines this through early sensemaking of process deviations, facilitating a seamless integration of information towards context-sensitive decision-making processes. Two industrial approaches are discussed in the paper: a conventional alarm-based practice, as well as an enhanced approach. The research underscores the application of such techniques through two industrial cases, aiming at fostering enhanced resilience, reliability, and safety within high-risk industrial settings.

Developing innovative software solutions for effective energy management systems in industry

Developing innovative software solutions for effective energy management systems in industry

Integrated Model of Risk Management in Business Processes in Industrial Systems

Integrated Model of Risk Management in Business Processes in Industrial Systems

Fuzzy Backstepping Control of Industrial Liquid Level System

Fuzzy Backstepping Control of Industrial Liquid Level System

Adaptive Industrial Control Systems via IEC 61499 and Runtime Enforcement

Adaptive Industrial Control Systems via IEC 61499 and Runtime Enforcement

Универсальная централизованная защита от однофазных замыканий на землю в кабельных сетях напряжением 6–10 кВ

Selective protection against single phase earth faults in distribution 6–10 kV cable networks can be performed both with the use of individual (per connection) and centralized devices covering all connections of the protected object. The advantages of centralized devices are reduction of specific (per connection) costs of protection, simplification of its operation and design. Well-known technical solutions in terms of centralized protection devices against this type of damage do not always provide versatility (the possibility to use neutral cables of 6–10 kV in various grounding modes) and high technical perfection (selectivity and stability of operation). Thus, it is relevant to develop a universal centralized protection against single-phase earth faults, ensuring high technical perfection for all types of earth faults in 6–10 kV cable networks with different neutral grounding modes. The authors have used a comprehensive simulation model "cable network – protection device" to study the selectivity and stability of the developed principles of implementation and algorithms for centralized protection against earth faults. The model is designed in SimPowerSystems and Simulink software. The configuration and parameters of the cable network model have been selected considering the key features of 6–10 kV distribution cable networks of industrial and urban power supply systems. A universal centralized protection against all types of earth faults in 6–10 kV cable networks with various neutral grounding modes has been developed. The results of functional tests on the simulation model have confirmed the effectiveness of the developed algorithms of the developed centralized protection for all types of earth faults both in uncompensated and compensated cable networks of 6–10 kV. The proposed technical solution implements a multifunctional multiparametric centralized protection against earth faults. It has such properties as versatility, selectivity, and high stability of operation for all types of earth faults, recognition of types of single-phase earth faults, continuity of action in stable and most dangerous arc intermittent earth faults.

Automated Sorting Conveyor Using Pneumatic Actuators for Industrial Applications at Morowali Metal Industry Polytechnic

The use of automatic sorting systems in industry plays a crucial role in saving time and reducing manual labor through automation. The main challenges are the high error rate and slow manual sorting processes. This research aims to design and develop an automatic sorting conveyor system using Arduino technology and pneumatic actuators to enhance sorting efficiency and accuracy. The proposed solution is a system capable of detecting and sorting objects based on size with very low error rates, thereby increasing productivity and reducing human error. The design and development of this system involve creating a 3D model of components such as the conveyor frame, belt, motor, pneumatic actuators, and sensors, and integrating them into a complete system. Testing was conducted with seven differently sized test objects to evaluate the system's performance in detecting and sorting objects based on size and height. Input and output voltage measurements ensure performance in line with the expected specifications. The research results demonstrate that the developed automatic sorting conveyor system effectively sorts objects with high accuracy. The system can detect and sort objects based on size with a 0% error rate, reducing the time required for the sorting process compared to manual methods. The use of pneumatic actuators and appropriate sensors ensures consistent and reliable system performance. The test results indicate that the system can be integrated into various industrial applications to enhance production efficiency. The developed automatic sorting conveyor system successfully improves the efficiency and accuracy of the sorting process in industry. It shows significant potential for reducing human error and increasing productivity, making it a practical solution for various industrial applications.

Bibliometric Analysis on the Application of IoT in Smart Manufacturing System in Industry 4.0

The rapid integration of Internet of Things (IoT) technologies in smart manufacturing systems has been a pivotal development within the framework of Industry 4.0. This study conducts a comprehensive bibliometric analysis to examine the evolution, current trends, and emerging research areas related to IoT applications in smart manufacturing. By analyzing data from a decade of scholarly publications, this research identifies key themes, influential authors, and collaborative networks that have shaped the field. The findings reveal that foundational technologies such as the internet, cloud computing, and big data are central to the development of smart manufacturing, while newer innovations like digital twins and blockchain are gaining prominence. The study also emphasizes the importance of strategic collaboration among researchers and industry professionals in advancing IoT adoption. The practical implications suggest that manufacturers should prioritize both foundational digital infrastructure and emerging IoT applications to enhance efficiency, security, and sustainability. This analysis provides a roadmap for future research and practical implementation, highlighting the critical areas where IoT can further revolutionize smart manufacturing systems.

Synergistic effects of multi-segmented magnetic fields, wavy-segmented cooling, and distributed heating on hybrid nanofluid convective flow in tilted porous enclosures

This study investigates the complex thermal-fluid behavior within a tilted porous enclosure filled with a Cu−Al2O3-water hybrid nanofluid, subject to segmented magnetic fields, wavy cooling segments, and distributed heat sources. The research explores the intricate interplay between geometric factors and thermal-magnetic forces to enhance heat transfer in industrial applications. The finite volume method (FVM), coupled with the SIMPLE algorithm and a TDMA solver, is employed to solve the governing transport equations. A comprehensive parametric analysis examines the effects of key dimensionless parameters: Darcy-Rayleigh number (10–104), Darcy number (10-4–10-1), Hartmann number (0–70), magnetic field angle (0°-180°), nanoparticle volume fraction (0–2 %), porosity (0.1–1.0), wavy cooler undulation height (0–0.3), magnetic segment width (0–1), number of segmental magnetic fields (0–4), and enclosure tilting angle (0°–180°). The study elucidates the physical mechanisms underlying the transition from uniform to segmented heating scenarios. Results reveal a remarkable enhancement of up to 38 % in heat transfer performance when transitioning from a conventional square enclosure to the proposed configuration with partial waviness on opposing walls. This improvement stems from increased surface area and disrupted thermal boundary layers, promoting better fluid mixing. The application of a segmented magnetic field with strategic orientation resulted in up to 26 % enhancement by modulating flow patterns and creating localized convection cells. The segmented heating generates thermal plumes that interact with the magnetic field-induced Lorentz forces, further improving thermal transport. The findings provide valuable insights into the design and optimization of efficient heat transfer systems in various industries, including electronics cooling, solar thermal collectors, and nuclear reactors, demonstrating significant potential for energy savings and improved thermal management through the strategic integration of hybrid nanofluids, magnetic fields, and geometric modifications in porous media applications.

Utilization of solar and wind power-generation systems in the mining industry: recent trends and future prospects

Utilization of solar and wind power-generation systems in the mining industry: recent trends and future prospects

Achieving productivity and operator well-being: a dynamic task allocation strategy for collaborative assembly systems in Industry 5.0

Collaborative robots, or cobots, offer a unique combination of productivity and flexibility that has led to significant growth in adoption over the past decade. Moreover, recently, there has been a shift towards a human-centered design of the workspace, known as one of the drivers of Industry 5.0, which prioritizes the well-being of operators. To achieve this, various human factors such as ergonomics, mental workload, personal skills, and capabilities need to be considered in the workspace design, and their impact on system productivity must be evaluated. The integration of a human and a cobot in the same workplace can affect the performance of the human operator, as the perception of the cobot can impact their work. This highlights the importance of taking human factors into account, as a lack of consideration in these aspects has contributed to the failure of many implementations. To link the objectives of productivity, flexibility, and human factors consideration, a dynamic real-time multi-objective task allocation strategy for collaborative assembly systems is developed. This approach considers the different characteristics of the resources and optimizes for two objectives, makespan, and energy expenditure of the operator. By using this approach, it is possible to modify the behavior of the cobot by reallocating tasks between the two resources based on the operator’s current needs. In other words, if the operator appears too stressed due to time constraints or their energy rate level is too high, some of their assigned tasks can be transferred to the cobot. This helps to maintain a balanced system while reducing the operator’s stress.

Research on carbon emission accounting and carbon emission reduction path of coal preparation plant

“Peak carbon dioxide emissions、Carbon neutrality” is the two stage goal of carbon emission reduction proposed by China. Carbon emission accounting is the basic premise for effectively carrying out various carbon emission reduction work and promoting the green transformation of the economy. The coal industry is one of the key objects of carbon emission reduction. Taking Zhenneng Coal Preparation Plant as the research object, this paper studies the carbon emission in the production process of the coal preparation plant and the selection of carbon emission factors, and constructs the carbon emission accounting model of the coal preparation plant. It is calculated that the carbon dioxide equivalent emission per 1 t of coal products produced by the coal preparation plant in 2018–2022 is 15.4391 kgCO2e. Based on the carbon emission reduction path at home and abroad, the development suggestions for carbon emission reduction in coal preparation plants are put forward. It is of great significance to establish a unified and standardized carbon emission accounting system for the coal industry, achieve the goal of “double carbon” and promote the comprehensive green and low-carbon transformation of economic and social development.

Physical model-assisted deep reinforcement learning for energy management optimization of industrial electric-hydrogen coupling system with hybrid energy storage

Utilizing renewable energy sources (RESs), such as wind and solar, to convert electrical energy into hydrogen energy for industrial users with different types of energy storage can enhance the integration of green electricity, thereby replacing fossil fuels like natural gas. In the energy management optimization of industrial electric‑hydrogen coupling system (EHCS) with high RESs integration, the traditional optimization methods cannot effectively address the nonlinear characteristics of equipment and stochastic RES generation, while the model-free reinforcement learning methods struggle to improve the training efficiency and may lead to constraint violation. To address this challenge, this paper proposes a short time scale energy management approach for EHCS based on physical models assisted deep reinforcement learning (DRL). Firstly, the energy management optimization model of the EHCS is developed based on the operation characteristics of the equipment within the system. Secondly, the energy management model of EHCS is formulated as a DRL framework. The DRL agent is efficiently trained with the assistance of the action transformation which takes into account the physical characteristics of the equipment during operation. Finally, a case study is conducted to verify the effectiveness of the proposed model for achieving high-efficiency agent training, reducing decision-making time for equipment scheduling, addressing the stochastic RES generation, and realizing the economic operation of EHCS with good performance based on the equipment characteristics.

SpecRep: Adversary Emulation Based on Attack Objective Specification in Heterogeneous Infrastructures.

Cybercriminals have become an imperative threat because they target the most valuable resource on earth, data. Organizations prepare against cyber attacks by creating Cyber Security Incident Response Teams (CSIRTs) that use various technologies to monitor and detect threats and to help perform forensics on machines and networks. Testing the limits of defense technologies and the skill of a CSIRT can be performed through adversary emulation performed by so-called "red teams". The red team's work is primarily manual and requires high skill. We propose SpecRep, a system to ease the testing of the detection capabilities of defenses in complex, heterogeneous infrastructures. SpecRep uses previously known attack specifications to construct attack scenarios based on attacker objectives instead of the traditional attack graphs or a list of actions. We create a metalanguage to describe objectives to be achieved in an attack together with a compiler that can build multiple attack scenarios that achieve the objectives. We use text processing tools aided by large language models to extract information from freely available white papers and convert them to plausible attack specifications that can then be emulated by SpecRep. We show how our system can emulate attacks against a smart home, a large enterprise, and an industrial control system.