Industrial Control Research Articles

PdGAT-ID: An intrusion detection method for industrial control systems based on periodic extraction and spatiotemporal graph attention

The stable operation of Industrial Control Systems (ICS) is critical to industrial production. However, with the advancement of industrialization and informatization, ICS face increasing security threats, particularly from cyber-attacks. As a core technology for ICS security, intrusion detection has garnered significant attention in recent years. Traditional intrusion detection methods typically rely on models constructed from network event logs, but these methods have notable limitations in capturing the spatiotemporal correlations among multiple variables (sensors/actuators) and the periodicity of data within the system. To address these challenges, this paper proposes an ICS intrusion detection method, PdGAT-ID, which integrates periodicity extraction with spatiotemporal graph attention networks. This method aggregates multi-scale periodic information from time series and utilizes spatiotemporal graph attention networks to capture the system's spatiotemporal features, thereby enhancing the accuracy and reliability of detection. Experimental results on three publicly available datasets, SWaT, WADI, and Gas Pipeline Dataset, demonstrate that PdGAT-ID performs exceptionally well in detecting abnormal behaviors and intrusion events. Specifically, its F1 score outperforms the best existing models by 1.55 % to 5.51 %, significantly improving the effectiveness and reliability of ICS anomaly detection.

A Reconfigurable Architecture for Industrial Control Systems: Overview and Challenges

The closed architecture and stand-alone operation model of traditional industrial control systems limit their ability to leverage ubiquitous infrastructure resources for more flexible and intelligent development. This restriction hinders their ability to rapidly, economically, and sustainably respond to mass customization demands. Existing proposals for open and networked architectures have failed to break the vicious cycle of closed architectures and stand-alone operation models because they do not address the core issue: the tight coupling among the control, infrastructure, and actuator domains. This paper proposes a reconfigurable architecture that decouples these domains, structuring the control system across three planes: control, infrastructure, and actuator. The computer numerical control (CNC) system serves as a primary example to illustrate this reconfigurable architecture. After reviewing open and networked architectures and discussing the characteristics of this reconfigurable architecture, this paper identifies three key challenges: deterministic control functionality, the decoupling of control modules from infrastructures, and the management of control modules, infrastructures, and actuators. Each challenge is examined in detail, and potential solutions are proposed based on emerging technologies.

A Novel Defect Segmentation Model via Integrating Enhanced U-Net with Convolutional Block Attention Mechanisms

Abstract. Defect segmentation in industrial quality control is pivotal for maintaining high product surface standards, but it remains a challenge due to complex defect patterns and varying backgrounds. Traditional segmentation methods often struggle with sensitivity and specificity, leading to either missed defects or false positives. In order to address the above issues this paper presents an advanced defect segmentation model that integrates a Convolutional Block Attention Module (CBAM) with an enhanced U-Net architecture. Our method leverages the spatial and channel-wise attention mechanisms to focus more accurately on subtle defects and remove background interference, enhancing the discriminative power of the feature maps generated by the U-Net. Experimental results on SD-saliency-900 industrial datasets demonstrate significant improvements in segmentation accuracy and robustness compared to existing state-of-the-art methods, confirming the effectiveness of integrating attention mechanisms in deep learning models for complex defect segmentation tasks. Specifically, our model achieved a mean Intersection over Union (mIoU) of 0.87, which is an increase of 5% over the traditional U-Net model and a 4% improvement compared to the DeepLabv3+ model. These results indicate a substantial enhancement in defect detection performance, validating the superiority of our approach.

A Security Situation Prediction Model for Industrial Control Network Based on Explainable Belief Rule Base

Industrial Control Systems (ICSs) are vital components of industrial production, and their security posture significantly impacts operational safety. Given that ICSs frequently interact with external networks, cyberattacks can disrupt system symmetry, thereby affecting industrial processes. This paper aims to predict the network security posture of ICSs to ensure system symmetry. A prediction model for the network security posture of ICSs was established utilizing Evidence Reasoning (ER) and Explainable Belief Rule Base (BRB-e) technologies. Initially, an evaluation framework for the ICS architecture was constructed, integrating data from various layers using ER. The development of the BRB prediction model requires input from domain experts to set initial parameters; however, the subjective nature of these settings may reduce prediction accuracy. To address this issue, an ICS network security posture prediction model based on the Explainable Belief Rule Base (BRB-e) was proposed. The modeling criteria for explainability were defined based on the characteristics of the ICS network, followed by the design of the inference process for the BRB-e prediction model to enhance accuracy and precision. Additionally, a parameter optimization method for the explainable BRB-e prediction model is presented using a constrained Projection Equilibrium Optimization (P-EO) algorithm. Experiments utilizing industrial datasets were conducted to validate the reliability and effectiveness of the prediction model. Comparative analyses indicated that the BRB-e model demonstrates distinct advantages in both prediction accuracy and explainability when compared to other algorithms.

Using machine learning to detect network intrusions in industrial control systems: a survey

Using machine learning to detect network intrusions in industrial control systems: a survey

Characterization of heat-treated bearing rings via measurement of electromagnetic properties for pulsed eddy current evaluation

Nondestructive evaluation of heat-treated bearing rings is a critical technique for quality control in industries. However, there are few reports addressing the complex mapping between hardness and electromagnetic properties due to the intricate changes in the microstructure. This paper proposes a dual-method approach, combining magnetic saturation eddy current techniques and Barkhausen noise reconstruction hysteresis loop techniques, to independently establish the relationship between hardness and electromagnetic properties. The results show that the electrical properties of unqualified specimens are significantly higher than those of other specimens, with qualified specimens have slightly higher properties than untreated ones. Additionally, an inverse relationship between hardness and magnetic properties is observed. Based on the obtained electromagnetic parameters, a pulsed eddy current hardness detection simulation model is established, which has the potential to improve purely data-driven methods for hardness detection in deep learning.

A Security Posture Assessment of Industrial Control Systems Based on Evidential Reasoning and Belief Rule Base.

With the rapid advancements in information technology and industrialization, the sustainability of industrial production has garnered significant attention. Industrial control systems (ICS), which encompass various facets of industrial production, are deeply integrated with the Internet, resulting in enhanced efficiency and quality. However, this integration also introduces challenges to the continuous operation of industrial processes. This paper presents a novel security assessment model for ICS, which is based on evidence-based reasoning and a library of belief rules. The model consolidates diverse information within ICS, enhancing the accuracy of assessments while addressing challenges such as uncertainty in ICS data. The proposed model employs evidential reasoning (ER) to fuse various influencing factors and derive security assessment values. Subsequently, a belief rule base is used to construct an assessment framework, grounded in expert-defined initial parameters. To mitigate the potential unreliability of expert knowledge, the chaotic mapping adaptive whale optimization algorithm is incorporated to enhance the model's accuracy in assessing the security posture of industrial control networks. Finally, the model's effectiveness in security assessment was validated through experimental results. Comparative analysis with other assessment models demonstrates that the proposed model exhibits superior performance in ICS security assessment.

Integrated physical safety–cyber security risk assessment based on layers of protection analysis

The extensive application of information technology in process industries has increased production efficiency but has also introduced new risks. Therefore, it is necessary to systematically analyse the risks within factories to ensure the stable operation of their production systems. This study proposes an integrated risk assessment method based on layers of protection analysis (LOPA), which combines physical safety and cyber security analyses to provide comprehensive risk assessments for the process industry. The method first identifies the hazardous scenarios and protection layers relevant to a process facility. It then identifies potential cyberattack types and existing countermeasures. Subsequently, the functional impacts of attacks on protection layers and potential coupling relationships are discussed. Using common vulnerability scoring system (CVSS) and semi-quantitative methods, the probability of attack is determined to optimize the probability of failure on demand (PFD) of the protection layers. Finally, a case study of a steam separator in a catalytic cracking unit is used to quantitatively explore the potential attacks and risks of coupled protection layers. The application of Bayesian network (BN) is used for further validation of the method. This study offers a novel quantitative tool for risk assessment in the process industry, which can enhance the security and reliability of industrial production and control systems.

Artificial intelligence-driven tool for spectral analysis: identifying pesticide contamination in bees from reflectance profiling

Pesticide poisoning constantly threatens bees as they forage for resources in pesticide-treated crops. This poisoning requires thorough investigation to identify its causes, underscoring the importance of reliable pesticide detection methods for bee monitoring. Infrared spectroscopy provides reflectance data across hundreds of spectral bands (hyperspectral reflectance), presumably enabling the efficient classification of pesticide contamination in bee carcasses using artificial intelligence (AI) models, such as machine learning. In this study, bee contamination by commercial formulations of three insecticides—dimethoate (organophosphate), fipronil (phenylpyrazole), and imidacloprid (neonicotinoid)—as well as glyphosate, the most widely used herbicide globally, was detected using machine learning models. These models classified the hyperspectral reflectance profiles of the body surfaces of contaminated bees. The best-performing model, the linear discriminant analysis, achieved 98 % accuracy in discriminating contamination across species Apis mellifera, Melipona mondury, and Partamona helleri, with prediction speeds of 0.27 s. Our pioneering study introduced an effective method for discerning multiple classes of bees contaminated with pesticides using hyperspectral reflectance. An AI-driven spectral data analysis tool (https://github.com/bernardesrodrigoc/MACSS) was developed for the purpose of identifying and characterizing new samples through their spectral characteristics. This platform aids efforts to monitor and conserve bee populations and holds potential importance in environmental monitoring, agricultural research, and industrial quality control.

Improving the Dynamics of an Electrical Drive Using a Modified Controller Structure Accompanied by Delayed Inputs

This paper presents the operation of a modified speed controller with a standard PI/PID structure that includes the preprocessing of the controller’s input signal, focusing on the past behavior of control errors. The modification involves adding a delay line, with the outputs of the individual line segments summed with a weighting method, as detailed in the paper. One of the significant advantages of this method is its use of a standard industrial controller structure, which makes it highly practical and easily implementable in existing systems. By relying on well-established control frameworks, this approach reduces the need for specialized hardware or complex modifications, allowing for smoother integration and lower implementation costs. The delay-based signal shaping shows excellent properties for the electric drive system powered by a hard-switching PWM converter. The set of weighted delays acts as a filter whose parameters are chosen using the quality function to test different configurations for optimal performance. When tested in a speed control system for a Permanent Magnet Synchronous Motor, the modifications improved the control quality index, indicating better performance and efficiency. Importantly, the system allows for reducing or eliminating the gain in the differentiating part of the controller, which decreases motor current chattering and noise. This paper includes an experimental verification of the proposed solution in a laboratory setting under semi-industrial conditions.

Exploring the effects of RNNs and deep learning frameworks on real‐time, lightweight, adaptive time series anomaly detection

SummaryReal‐time, lightweight, adaptive time series anomaly detection is increasingly critical in cybersecurity, industrial control, finance, healthcare, and many other domains due to its capability to promptly process time series and detect anomalies without requiring extensive computation resources. While numerous anomaly detection approaches have emerged recently, they generally employ a single type of recurrent neural network (RNN) and are implemented using a single type of deep learning framework. The impacts of using various RNN types across different deep learning frameworks on the performance of these approaches remain unclear due to a lack of comprehensive evaluations. In this article, we aim to investigate the impact of different RNN variants and deep learning frameworks on real‐time, lightweight, and adaptive time series anomaly detection. We reviewed several state‐of‐the‐art anomaly detection approaches and implemented a representative approach using several RNN variants supported by three popular deep learning frameworks. A thorough evaluation was conducted to analyze the detection accuracy, time efficiency, and resource consumption of each implementation using four real‐world, open‐source time series datasets. The results show that RNN variants and deep learning frameworks have a significant impact. Therefore, it is crucial to carefully select appropriate RNN variants and deep learning frameworks for the implementation.

Pengendalian Biaya Kedelai Home Industry Tahu-Tempe Mbak Sri

This study aims to analyze the material cost control in Mbak Sri's home industry of tofu and tempeh production. Material costs constitute a significant portion of the total production costs, and effective control measures are crucial for ensuring profitability. The research employs a qualitative approach, utilizing observation and in-depth interviews to gather data. The findings reveal that Mbak Sri implements several cost control strategies, including careful material selection, efficient utilization, and waste minimization. However, challenges arise due to fluctuating raw material prices and limited bargaining power. The study recommends implementing a comprehensive material management system, establishing strategic supplier relationships, and exploring alternative sourcing options to enhance cost control measures. By addressing these recommendations, Mbak Sri's home industry can improve its overall operational efficiency and profitability.

Potential of water-soluble chitosan Schiff bases extracted from Metapenaeus dobsoni shells as effective corrosion inhibitors

Corrosion causes significant economic losses and structural failures in industries, highlighting the need for eco-friendly inhibitors. Chitosan (CS), a biodegradable and non-toxic biopolymer, shows potential, though its limited water solubility restricts its applications. To overcome this challenge, this study presents the synthesis of two water-soluble chitosan Schiff bases (CSBs) derived from the shells of Metapenaeus dobsoni (M. dobsoni). The extracted CS exhibits a remarkable degree of deacetylation exceeding 95 %, which was subsequently modified through reactions with o-vanillin (2-hydroxy-3-methoxybenzaldehyde) (CSB I) and 2,3-dihydroxybenzaldehyde (CSB II). Structural characterization using spectroscopic techniques confirmed the successful formation of CSBs. Electrochemical measurements were employed to assess the corrosion resistance of mild steel in 0.5 M HCl with varying concentrations of CSB I and CSB II. The results revealed superior corrosion inhibition by CSB II (% IE = 94.48 %) compared to CSB I (% IE = 88.80 %). The methoxy group in CSB II contributed to its higher electron density and enhanced adsorption, leading to better surface coverage and corrosion resistance. Both inhibitors followed the Langmuir isotherm, suggesting a mix of physisorption and chemisorption. These CSBs are promising for corrosion control in industries like pipelines, storage tanks, construction materials, and acid pickling.

The Impact of Hemp Derived Cannabinoid Potency from Consumer Product Goods on in vitro Lung and Liver Cells

Background: The surge in the popularity of cannabis has led to an increase in the number of companies producing hemp-derived consumable cannabinoid products. Despite extensive exploration of cannabinoid efficacy, safety remains underreported. Any contaminants that are not deemed analytes of interest are ignored, leaving their identities and safety profiles a mystery. The unregulated nature of the cannabinoid market places the onus on reputable companies to set industry standards for product cleanliness. Objective: This study aimed to address this gap by assessing high and low potency forms of three popular hemp-derived cannabinoids – Delta 8-tetrahydrocannabinol (Δ8-THC), Hexahydrocannabinol (HHC), and Delta 9-tetrahydrocannabiphorol (Δ9-THCP). Methods: After identifying contaminants, the products were evaluated for toxicity in vitro using one liver and two lung cell lines in an effort to simulate the effects of oral consumption and inhalation. Results: Our study revealed that none of the compounds exhibited toxicity in the liver cell line, while all of the compounds exhibited toxicity in both of the lung cell lines – with the exception of one high-potency HHC sample. Conclusion: These findings highlight the critical need for stringent quality control in the cannabinoid industry, emphasizing the importance for both companies and consumers to prioritize clean, well-tested products to ensure safety in an increasingly unregulated market.

In-space cybernetical intelligence perspective on informatics, manufacturing and integrated control for the space exploration industry

The integration of cybernetic principles into space technology has led to a significant shift in spacecraft guidance systems and space station operations. This scholarly work provides a comprehensive analysis of the profound impact that cybernetics has had on space technology, particularly focusing on the development and implementation of closed-loop control systems. Building on foundational contributions to cybernetics, this paper offers a detailed analysis of the complex interplay between control mechanisms, behavioral dynamics, and information management in space informatics. The essential role of cybernetic control systems is highlighted through their critical function in enabling precise spacecraft maneuvers, as demonstrated by the guidance systems used in Apollo lunar missions during the crucial descent and landing phases. In modern space station programs, cybernetic intelligence operates much like a neural network, processing data in real-time and coordinating the various elements of the station's infrastructure. This cybernetic system excels in a wide range of tasks, from space docking maneuvers to waste management, thereby safeguarding astronaut welfare and ensuring mission success. Information serves as the cornerstone of problem analysis and processing, providing a holistic understanding of information flow within complex systems. The study concludes by highlighting the application of a cybernetically intelligent neural network in developing adaptive learning systems for nonlinear and intricate industrial processes. Ultimately, this paper underscores the transformative role of cybernetics in shaping the future of space exploration, emphasizing the seamless integration of control, information, and behavior in space technology to advance our understanding of celestial systems while enhancing the efficiency and safety of space missions.

Hybrid Model using Bond Graph-TCN Network and Event Triggered Predictive Control of pH Neutralization Process

The pH neutralization process is a concrete decisive unit in major reactor units of industrial process control loops. This article presents a new fuzzy-based hybrid 'Bond Graph-Temporal Convolution Network' (BG-TCN) model, structured for the convoluted dynamics of a real-time pH neutralization unit, known for its complexity and high nonlinearity. The TCN scheme suggested in this article, exploits a one-dimensional causal convolution strategy within a residual learning framework to execute dilated causal convolutions through time series data analysis. Conversely, Bond Graph (BG) is a graphical tool, designed on an energy-centric approach, to represent energy transfer and interactions across different compartments of the nonlinear pH neutralization system. Furthermore, a linguistic fuzzy rule-based inference system is encompassed to handle uncertainties from BG and TCN models, allowing smooth integration and flexible transition between these two approaches. Additionally, the performance of the hybrid BG-TCN model is assessed against the individual TCN and BG models in a Python environment. On top of that, this article also envisions an event-triggered predictive control utilizing a fuzzy event handler mechanism to demonstrate the efficacy of the proposed hybrid BG-TCN in attaining precise set point tracking for closed-loop servo and regulatory problems.

Fault diagnosis of pneumatic control valve based on Bat Optimization algorithm and BP neural network

Abstract This article proposes a fault diagnosis model for pneumatic control valves based on a bat optimization (BA) algorithm and backpropagation (BP) neural network. The DAMADICS platform simulates the pneumatic industrial process control valve failures, and the fault signals are collected to construct the data set. A fault diagnosis model combining the Bat Optimization algorithm and Back Propagation neural network (BA-BP) is built, and four common faults are injected for experiments. The method is compared with Support Vector Machine (SVM), BP, and Bayesian optimized BP (BO-BP). Experimental results indicate that BA-BP has high diagnostic precision in the diagnosis of malfunctions in pneumatic valves.

Design of a six-axis integrated drive-control industrial robot controller

Abstract This paper designs a six-axis industrial robot servo system based on Advanced RISC Machine (ARM) + Field Programmable Gate Array (FPGA), which combines the advantages of small size, smooth speed, high precision and low jitter, and the parallel processing of FPGA realizes the multiple Field-Oriented Control (FOC) algorithms to collect the output data efficiently. The FPGA parallel processing implements the multi-way Field-Oriented Control (FOC) algorithm to efficiently collect the output data, and the ARM reads the FPGA data through the Flexible Memory Controller (FMC) bus to configure the FPGA to drive the robot, which enhances the flexibility and real-time performance, and the system is able to control the six servo motors synchronously. Through experiments, we found that the industrial robot exhibited no significant changes in current feedback under both no-load and full-load conditions. Additionally, the proposed controller demonstrated higher precision in joint movement control compared to conventional controllers, achieving a maximum improvement of 0.088° and maintaining an error margin within 0.099°. The experiments validate its high-precision control, effectively addressing issues of speed smoothness and jitter, thereby providing substantial practical application value.

The combustion biased dual cross-limited control strategy for industrial boiler furnaces

Abstract The combustion process in boilers is a crucial aspect of industrial boiler operation, and the quality of this process is closely related to the industrial boiler’s operational efficiency and pollutant emissions. This paper focuses on furnace combustion control within the industrial boiler control system and proposes an improved variable bias control method to address the issues associated with over-oxygen and oxygen-deficient combustion, which are prevalent in current double-closed-loop cascade proportional control technologies. First, the working principle of the variable bias double cross-limit combustion process is analyzed, and the variable bias cross-limit combustion control system is designed. Second, by introducing a bias variable, the paper addresses the problem that fixed bias parameters in the double cross-limit control system cannot accommodate the variable loading and rapid response requirements. Finally, the range of bias coefficients is estimated using the trial-and-error method. Experimental results demonstrate that the variable bias double cross-limit control strategy resolves the issues of oxygen deficiency and over-oxygen combustion, along with the slow response speed of conventional combustion control modes, enhances fuel heat utilization efficiency, and reduces pollutant and harmful gas emissions.

Smart Grids Excellence – Cybersecurity in Empowering Digital Transformation

This paper is intended to elaborate on the 4th Industrial Revolution (Industry 4.0) that will alter and shift technologies and the utilities sector. Alongside advanced Cybersecurity technologies to be aligned with the need for more resilience and secured environments that empower digital transformation. Where we explore the drivers and applications of Cybersecurity considering 4thIR as an engine of digital transformation, that is governed and measured by complying with digital transformation rules, flowing from modern technology to the evolution where the quality of life is measured by its speed, energy, and security. As such, Industrial Control Systems (ICS) are a solid infrastructure for such a digital transformation. As the acceleration of cyberattacks are becoming more sophisticated, a well Cybersecurity strategies must be applied. Furthermore, we propose advanced Cybersecurity solutions for the smart grid that can be addressed by the efficiency of the Next Generation (SOC) and the utilization of Distributed Ledger Technology (DLT).