Safety Of Industrial Systems Research Articles

Virtual Reality Application for the Safety Improvement of Intralogistics Systems

Immersive technologies from the spectrum of Industry 4.0, such as Virtual Reality (VR), are increasingly used in research and safety analysis in industrial and intralogistics systems, including distribution warehouses and production plants. Safety in intralogistics systems is influenced by design and management processes, human behavior, and device performance. In all these areas, VR can serve as a supportive technology for visualization, testing, and employee training. However, this requires the development of principles for integrating VR into standard procedures for the design, modernization, and analysis of intralogistics and production systems. This article discusses the use of VR to analyze the occupational and functional safety of intralogistics systems. It reviews the literature and VR implementations aimed at examining and improving safety in industrial systems. The article explores the integration of VR into the design and analysis procedures for intralogistics and production systems. The authors present a five-dimensional decision space for assessing the use of VR, including identifying subjects of safety analysis, threats and hazards specific to intralogistics, countermeasures for these threats, factors affecting safety, and mechanisms by which VR can improve safety in intralogistics systems. As a subsequent step, the authors discuss using universal simulation environments that support VR technology to study and enhance safety in intralogistics systems, providing a framework example based on the FlexSim (2023 update 2) environment. Finally, this article addresses the threats and limitations of VR technology, along with the challenges and future prospects of VR in the context of Industry 4.0. The article concludes that VR can be an essential tool for increasing safety in the future, albeit with some reservations about certain features of this technology.

A holistic semi-supervised method for imbalanced fault diagnosis of rotational machinery with out-of-distribution samples

Fault diagnosis plays a critical role in ensuring the reliability and safety of industrial systems. Despite the success of semi-supervised learning in fault diagnosis, challenges persist in dealing with imbalanced datasets and out-of-distribution (OOD) samples, particularly in industrial settings where fault incidents are rare. The rarity of fault incidents in industrial contexts leads to dataset imbalances, while changes in conditions may introduce OOD samples. To address these challenges, this study proposes a novel semi-supervised fault diagnosis method that simultaneously considers the imbalanced distribution of fault categories and OOD samples. Firstly, the semi-supervised framework has been presented, which combines pseudo-labeling and consistency regularization techniques. Then, the self-adaptive threshold has been devised to balance confidence levels among fault classes using dataset-specific and class-specific thresholds, thereby enhancing the model's robustness in real-world scenarios. Additionally, the OOD detection strategy based on contrastive learning has been proposed, wherein predictions from two different views of each sample estimate its “likelihood” of belonging to in-distribution (ID) or OOD categories. This strategy improves system safety by alerting operators to potential anomalies. Comprehensive experimental validations and comparisons were conducted on two rotational machinery fault datasets, demonstrating that the proposed method achieves superior performance compared to the alternative methods and is applicable for practical application.

COMPUTER SIMULATION OF THE DIAGNOSTIC SYSTEM OF BRAKING CIRCUITS OF FREQUENCY-CONTROLLED ASYNCHRONOUS ELECTRIC DRIVES CONVERTERS

This research is essential for improving the reliability and efficiency of frequency-controlled asynchronous electric drives, especially in industrial environments where uninterrupted production processes are critical. The primary goal of the research is to develop a computer model for a brake system diagnostic system that allows for the timely detection of issues and failures in these systems. One of the key aspects of your research is the use of computer modeling, particularly in the MatLab Simulink environment. This enables engineers and researchers to more easily develop and test models, reducing research time and costs. An important element of such a model is the use of logic-time functions and wavelet diagnostics. These methods allow for the analysis of signals from brake systems from different perspectives and the detection of anomalies in their operation. The research also focuses on mathematical models of brake systems that are integrated into computer programs for simulating the operation of electric drives. Analyzing critical parameters and characteristics of brake circuits helps identify potential problems or failures in advance. Diagnostic algorithms based on data obtained from computer models enable the timely determination of the brake system's condition and the necessary decision-making to enhance safety and efficiency in electric drive operation. The results obtained from your research have significant practical importance as they help maintain the reliability and safety of industrial systems at a high level. Brake system diagnostics in frequency-controlled asynchronous electric drives become more accessible and efficient through the use of mathematical models and computer modeling in MatLab Simulink. This contributes to increased productivity and reduced risk of accidents in industrial systems.

Multi-Fault Diagnosis Based on Hybrid Bio-Inspired Algorithm ACO-GA

The fault detection and isolation (FDI) procedure increases the assurance of quality, reliability, and safety of industrial systems. Several faults may appear simultaneously, and the purpose of multi-fault diagnosis is to identify and locate these multiple faults. This work is particularly interested in the diagnosis based on the structural analysis of the system; residuals can be generated and used as fault indicators by model-based fault detection techniques. The isolation is dependent on the structure of the fault signature matrix. A new fault signature that represents the superposition of the fault is produced by simultaneous fault effects, resulting in an additional column in an extended signature matrix. This remedy is rather combinatorial. This research focuses on two methods to isolate multiple faults: (1) A modified enumerative method; (2) A hybrid ant colony optimization algorithm-genetic algorithm (Hybrid ACO-GA) is adapted to the MFD problem which has the advantage of a better research as well as the hybridization with GA.

Synthesis of conducting polymer intercalated sodium vanadate nanofiber composites as active materials for aqueous zinc-ion batteries and NH3 gas sensors at room temperature

Among the key technologies required for building industrial safety systems is portable integrated safety devices based on gas sensors and rechargeable batteries. In preparation for such integrated devices, this study focuses on the synthesis of sodium vanadate nanofibers (SVNF) and poly(3,4-ethylene dioxythiophene) (PEDOT) intercalated SVNF (E-SVNF) composites by a simple sonochemical approach for room temperature NH3 gas sensing and zinc ion battery (ZIB) studies. Applying E-SVNF to ZIBs resulted in superior rate capability, with a capacity of 192.13 mAh g−1 at 15 A g−1. Furthermore, they demonstrated long-term cycling stability, maintaining 83.47% of their capacity at 15 A g−1 even after 3,000 cycles. The gas sensor incorporating E-SVNF showcased a high response and excellent selectivity, even at room temperature, with response values of 1.059 for 10 ppm and 1.113 for 70 ppm of NH3 gas. These remarkable enhancements in the electrochemical performance of ZIBs and the gas sensor are attributed to the insertion of conductive polymers between SVNF layers. This resulted in improved electrical conductivity, increased interlayer distance in the vanadate nanofiber structure, enhanced layered structural stability, increased oxygen vacancies, a decreased work function, and the formation of p-p heterojunctions, all of which contribute to improved functionality of the composites materials. This research is expected to serve as a cornerstone for the development of industrial safety systems.

A novel data augmentation approach to fault diagnosis with class-imbalance problem

Data-driven fault diagnosis techniques are frequently applied to ensure the reliability and safety of industrial systems. However, as a common challenge, the class-imbalance problem reduces the performance of data-driven methods due to the lack of data information. We propose a weighted modified conditional variational auto-encoder (WM-CVAE) as a novel data augmentation technique to tackle the issue. The modified structure can alleviate the existing Kullback–Leibler (KL) divergence vanishing by an adaptive loss. Meanwhile, kernel mean matching (KMM) is proposed on weight computation to reduce the negative effect of dissimilar generated samples. Constructing the WM-CVAE data augmentation framework can effectively improve the data quality and learning capability in class-imbalance fault diagnosis. To validate the proposed WM-CVAE model, three real-world industrial datasets are used as study objects, and the random forest is used as the base learner in the fault classification tasks. The diagnostic results demonstrate that the proposed WM-CVAE data augmentation framework can improve learning results in class-imbalance fault diagnosis.

Explainable multimodal learning for predictive maintenance of steam generators

Prognostics and Health Management (PHM) is identified as an important lever for enhancing the development of predictive maintenance to ensure the reliability, availability, and safety of industrial systems. However, the efficiency of data- driven PHM approaches is dependent on the quality and quantity of data. Therefore, exploiting multiple data sources can provide additional, useful information than single-modal data. For instance, by incorporating multiple data sources, including condition monitoring data, images from cameras, and texts from maintenance technicians’ reports, multi-modal learning can provide a more comprehensive and accurate understanding of the system’s health. However, multi-modal deep learning is complex to understand. To address this complexity, it is crucial to incorporate explainable artificial intelligent techniques to provide clear and interpretable insights into how the model makes decisions. In this light, this paper proposes the application of the model-agnostic-explanation approach, i.e., SHAP, to explain the working mechanism of multimodal learning for the prediction of industrial steam generator degradation. Particularly, we determine the important features of each data modality and investigate how multimodal learning can overcome the issues of low-quality data from a single modality due to the additional information from other data modalities.

Learning Sparse Kernel CCA With Graph Priors for Nonlinear Process Monitoring

Process monitoring (PM) is important for improving product quality and ensuring plant safety in industrial systems. Recently, canonical correlation analysis (CCA)-based PM has shown excellent performance. The core idea is to first seek the relationship between two sets of process variables via CCA, then construct a residual generator and determine test statistics, and finally achieve the best monitoring. However, the global and local structure of process variables is not fully exploited. In this article, we propose a new nonlinear PM approach called joint sparse constrained kernel CCA and graph learning (JSKCCA-GL) by incorporating joint sparse kernel CCA (JSKCCA) and graph priors. Technically, imposing the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\ell _{{2},{0}}$ </tex-math></inline-formula> -norm joint sparse constraints can capture the global row-wise structure, and embedding the graph Laplacian priors can preserve the local structured variable correlation information. Furthermore, an efficient alternating minimization algorithm is developed by integrating least squares and iterative hard thresholding (IHT). The superiority of the proposed JSKCCA-GL is extensively verified on the benchmark Tennessee Eastman process (TEP) and a practical cylinder-piston assembly (CPA) of marine diesel engines. In particular, the fault detection rate (FDR) values for unknown-type faults in the TEP have been improved by around 16.10% on average.

Video-Based Time-Series Feature Extraction Image Encoding Methods for Enhanced Colorimetric Gas Concentration Estimation

Early detection and intervention of gas leaks can reduce industrial risks. Numerous early detection methods have been developed and applied in the industrial field, but they require professional analysis technology, long analysis time, and relatively expensive equipment. Strategies to reduce industrial gas hazards constantly require the development of new, efficient and reliable devices.In the past few decades, various types of gas sensors have been developed based on semiconductors, optical fibers, acoustic waves and other technologies. A significant amount of work has been done in recent years to make sensors smaller, more sensitive, more visually responsive, more manageable, more personal, and more wearable. However, these functions require expensive equipment, complex skills, and large amounts of power. In this regard, colorimetric sensors are of great interest due to their simplicity, ease of manufacture, low cost, visual response, and ease of interpretation without power consumption. However, current colorimetric sensors have some limitations to overcome, such as sensitivity, high cost, early detection and accuracy for use in industrial safety systems. Conventional colorimetric sensor studies use algorithms to compare discoloration with the naked eye, estimate gas concentrations with simple statistical methods, or estimate simple discoloration information using machine learning algorithms to estimate time-series data. Algorithms are trained on measured images or time series data extracted from images. Signal processing focuses on denoising done by scaling time series data. These studies using machine learning and deep learning-based analytics for colorimetric sensor studies did not give sufficient consideration to data coding. Machine learning of time series data is performed using a time series decomposition method that separates time dependencies. I am trying to analyze time-series data through image encoding.In this study, a time series data analysis technique using CNN (Convolutional Neural Network) including multidimensional image encoding was applied to improve the gas concentration estimation accuracy. The estimation accuracy obtained in this study was higher than the estimation accuracy obtained by applying existing statistical methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) and machine learning techniques such as Multi-layer Perceptron (MLP).We focused on estimating gas concentrations using a time-series-based colorimetric analysis method developed based on colorimetric fabric detection data. Time series data obtained through gas experiments were encoded into images to classify the color value change trend of gas concentration. Image encoding improves the efficiency of specifying gas-exposed sections and estimating gas concentrations within the entire section. Compared to the concentration estimation accuracy of the existing data classification method, MLP was improved by more than 2.5%. In addition, the accuracy was improved by applying a CNN that learned multidimensional processing of sensor data through image encoding. As a result, it was confirmed that the estimation accuracy was improved by 6.1% compared to the basic estimation technique. Although this method has limited data form and application fields, it is effective for subjects such as ours. The proposed technology can be applied to the next-generation smart industrial safety system. Figure 1

Cyber-attacks detection in industrial systems using artificial intelligence-driven methods

Modern industrial systems and critical infrastructures are constantly exposed to malicious cyber-attacks that are challenging and difficult to identify. Cyber-attacks can cause severe economic losses and damage the attacked system if not detected accurately and timely. Therefore, designing an accurate and sensitive intrusion detection system is undoubtedly necessary to ensure the productivity and safety of industrial systems against cyber-attacks. This paper first introduces a stacked deep learning method to detect malicious attacks in SCADA systems. We also consider eleven machine learning models, including the Xtreme Gradient Boosting (XGBoost), Random forest, Bagging, support vector machines with different kernels, classification tree pruned by the minimum cross-validation and by 1-standard error rule, linear discriminate analysis, conditional inference tree, and the C5.0 tree. Real data sets with different kinds of cyber-attacks from two laboratory-scale SCADA systems, gas pipeline and water storage tank systems, are employed to evaluate the performance of the investigated methods. Seven evaluation metrics have been used to compare the investigated models (accuracy, sensitivity, specificity, precision, recall, F1-score, and area under curve, or AUC). Overall, results show that the XGBoost approach achieved superior detection performance than all other investigated methods. This could be due to its desirable characteristics to avoid overfitting, decreases the complexity of individual trees, robustness to outliers, and invariance to scaling and monotonic transformations of the features. Unexpectedly, the deep learning models are not providing the best performance in this case study, even with their extended capacity to capture complex features interactions.

An enhanced methodology of Fault Detection and Diagnosis based on Digital Twin

Digital Twins (DT) have been used in a variety of industrial sectors and application areas in recent years. To avoid downtime and problems in manufacturing, DTs strive for real-time monitoring and optimization and anticipate the future status of the physical twin. Fault Detection and Diagnosis (FDD) is a maintenance field that has attracted the interest of the control and automation community as a viable means of ensuring the dependability and safety of industrial systems. An enhanced FDD methodology thought DT can provide significant benefits. The main contribution of this research focuses on the exploration of DT for FDD methodology and provides also a guideline of different alternatives in each step and highlights the importance of DT.

Research on Vibration Characteristics of the Curved Pipes Conveying Fluid Based on Dynamic Stiffness Method

Fluid transmission pipelines, especially curved pipes, are widely used in industrial systems. Vibration characteristics of pipes are highly correlated with the reliability and safety of industrial systems. Therefore, in this paper, a new dynamic stiffness method is proposed to solve the above vibration characteristics of the curved pipes conveying fluid. The dynamic stiffness method can be used to calculate the vibration characteristics of the pipes conveying fluid under arbitrary boundary conditions, By comparing the results of finite element method with those of this method, the correctness of this method is verified. Finally, the vibration characteristics of the pipeline at different angles are calculated by this method. The results show that with the increase of θ value of radian angle in the pipes conveying fluid, both the frequency and critical velocity of in-plane and out-of-plane of the corresponding order decrease, and the natural frequency decreases greatly when θ is small, while the natural frequency decreases little when θ is large.

Guest Editorial for Artificial Intelligence for Machine Fault Diagnosis Special Section

With the rapid technological development and production requirement, machines and equipment in modern industry, such as advanced manufacturing, transportation, aerospace, and civil infrastructure, become increasingly functional and complex. Machine fault diagnosis plays a significant role for the productivity, reliability, and safety of industrial systems. In the recent decade, data-driven solutions have become more effective and promising for fault diagnosis of complex machines due to increasing data availability and processing capacity. Artificial intelligence (AI) techniques, especially deep learning approaches, are the most powerful tools in achieving accurate fault diagnosis of complex systems. However, AI-based fault diagnosis still faces great challenges in feasibility and reliability for real applications, including the lack of fault condition data, varying working conditions, insufficient generalization capability of AI models, the black-box nature of most AI methods, etc. This special section focuses on advanced and innovative solutions to address a broad view of problems about AI-based machine fault diagnosis. Six out of 18 submissions included in this special section summarize some of the research and applications in this field.

О методике оценки состояния промышленной и пожарной безопасности на предприятиях нефтегазового комплекса России

The statistics of fires and accidents at the enterprises of oil and gas complex of Russia is presented. The choice of the method for assessing the state of industrial and fire safety is substantiated. It allows to transform the input information presented in the form of a characteristic description of the assessed event into an output dana that has a weighted numerical value. It is shown that the stable functioning of industrial enterprises depends on the safety margin of industrial and fire safety systems. Their maintenance at a certain level requires the allocation of resources (material, human, temporary, etc.), which are limited and insufficient to meet all the requests from the service managers. It is required to scientifically substantiate the targeted provision of activities that have a high index of risk. The purpose of the article is to obtain the result of the assessment of these measures in the form of a weighted risk indicator. This will allow to normalize each event included in the checklists (control sheets) of the enterprise for both industrial and fire safety. A pairwise comparison of the factors and alternatives using the selected method of hierarchy analysis makes it possible to identify the indicators of local and global priorities for each element under study. The weighting coefficients obtained in the form of local priorities relate to the event being tested. Global priorities are directly related to the services and structural units that ensure the sustainable functioning of the industrial and fire safety systems. Use of the methodology for assessing the state of industrial and fire safety at the objects of oil and gas complex of Russia will allow to transfer the management system of these enterprises to a new qualitative level.

Multi-Dimensional Encoding Image Based Time Series Feature Extraction for Improved Colorimetric Gas Concentration Estimation

Industrial risk can be reduced through the early detection and intervention of gas leaks. Numerous early detection methods have been developed and applied in industrial areas, but they require expert analysis skills, a lengthy analysis time, or relatively expensive equipment. The development of novel, efficient, and reliable devices is continuously required as a strategy to reduce industrial gas risks.In the past decades, various types of gas sensors have been developed based on semiconductor, optical fiber, acoustic wave, and other technologies. A significant amount of work has been undertaken in recent years to make sensors smaller, more sensitive, more visually responsive, easier to handle, more personal, and more wearable. However, these functions require expensive equipment, complex skills, and large amounts of power. In this respect, colorimetric sensors are of great interest owing to their simplicity, easy fabrication, low cost, visual response, and ease of interpretation without power consumption. However, currently, colorimetric sensors have several limitations that need to be overcome, such as sensitivity, high cost, early detection, and accuracy for use in industrial safety systems.Existing colorimetric sensor studies use an algorithm that compares discoloration using the naked eye, estimates gas concentration with a simple statistical method, or uses a machine learning algorithm to estimate time series data by signal processing simple discoloration information. The algorithm learned the measurement image or the time series data extracted from the image. Signal processing was focused on noise removal, which was performed by scaling the time series data. These studies using machine learning and deep learning-based analysis for colorimetric sensor research have not sufficiently considered data coding. Machine learning of time series data is carried out using the time series decomposition method that separates time dependencies. Attempts are being made to perform time series data analysis through image encoding. To the best of our knowledge, the present study is the first to use image encoding for time series colorimetric sensor data.This study applied a time series data analysis technique using a convolutional neural network (CNN) with multi-dimensional image encoding to improve gas concentration estimation accuracy. The estimation accuracy obtained in this study was more than that obtained by applying existing statistical methods, such as auto-regressive integrated moving average (ARIMA) and exponential smoothing (ETS), and machine learning techniques such as multi-layer perceptron (MLP). We focused on gas concentration estimation using a time series-based colorimetric analysis method, which was developed based on colorimetric fabric detection data. The time series data obtained through the gas experiment were subjected to image encoding to classify the trend in the color value change of the gas concentration. Image encoding improves the efficiency with which the gas exposure section is specified, as well as the gas concentration estimation, within the entire section. The concentration estimation accuracy of the existing data classification method was 74.8%, while that of MLP was more than 80.5%. Furthermore, the accuracy was improved by applying a CNN that learned the multi-dimensional processing of sensor data through image encoding. From the results, an estimation accuracy of 90.1% was confirmed. The proposed technique can be applied to next-generation smart industrial safety systems. Figure 1

Insurance Programs in the Renewable Energy Sources Projects

The development of projects using renewable energy sources (RES) necessitates the development of insurance programs and systems. This involves identifying and assessing the risks of renewable energy projects in the transition to new types of energy, determining typical corporate and specific risks, the need and content of the main types, forms of insurance contracts, assessing the financial condition, and choosing insurance organizations and reinsurance programs. This article focuses on the formation of such insurance programs, their interaction with industrial safety systems and ensuring corporate participation in achieving sustainable development goals; as well as selection and assessment of the insurer financial stability and the insurance RES programs economic efficiency.

The Analysis of Network Models for the Design of Industrial and Fire Safety Systems for Oil Refineries

Tensor network models represent the processes and structure of complex systems, including dangerous technological objects of oil refineries. Complex systems tensor method research based on duality invariance. It is the sum constancy of the metric tensors dual networks whenever there is a change in structure. Dual subspaces closed and unclosed paths are responses to external and internal influences, which do not depend on each other. As an example of a network model is considered the atmospheric column oil-refining plant, which is used to organize the work of training stand. Thermal energy flows are presented in a mesh network, and massive flows of mechanical energy - in a junction network. The amount of mechanical and thermal energy flows allows you to determine the load on the nodes of the unit. The results are applied to predict dangerous situations on refining facilities to assess changes in restructuring processes and the risk of accidents. Calculations, such as heat and mass flow change if you change the control actions, disable installation elements and assess change critical settings.

An efficient Dijkstra’s semaphore based [formula omitted]-out-of-[formula omitted] Petri net voting model: An application to shutdown actuation system reliability

Petri Net is a widely used mathematical model for reliability analysis of industrial safety systems. Often, there is a need to model k-out-of-n voting present in these high redundancy safety systems. The model suggested in IEC 62551 guidelines for k-out-of-n low-level Petri Net voting has factorial O(n!) modeling complexity. To improve the modeling efficiency, a Dijkstra’s semaphore based technique is proposed in this paper which yields linear O(n) modeling complexity. The proposed model of a voter is based on the counting technique, where a counter is used to count the number of failures/successes from n redundancies, and then voting for k failures are carried out to get the result of voter. Validation of the improved low-level Petri Net model of k-out-of-n voting is illustrated by applying it to the reliability modeling of a high redundancy shutdown actuation system of a nuclear reactor including common cause failure modeling with Petri Nets.

Цифровая трансформация открытых горных работ и новое поколение карьерной техники

The The paper addresses the issues of designing onboard systems and complex digitalization of open-pit mining equipment. A generalized schematic diagram and composition of the On-Board Robotic Control System for open-pit equipment (OBRCS OPE) are provided. The option of the On-Board Robotic Control System for mining dump trucks (OBRCS MDT) and schematics of the on-board robotic system of the BELAZ dump truck are described in more detail. A layout option is suggested for an autonomous ready dump truck, a modification that meets all the requirements for the digital transformation (DT) generation of dump trucks i.e. the ability to operate as part of the mine fleet management systems and robotic control systems, as well as the availability of modern on-board industrial safety systems and remote diagnostics. The DT Generation of mining equipment will allow mining companies to achieve the up-to-date level in digital transformation of surface mining operations and will cut the amount of investments required in upgrading the mining transport system.

Assessment and potential levels of technosphere industrial safety

The article discusses approaches to assessing cause-effect relationships determining the causes of emergencies at the enterprise, including the identification of direct and indirect factors, the direction and intensity of emergencies at the enterprise using the methods (risk sessions) of hazard research. The article poses the classical problem of hazard identification based on methods (risk sessions) in a matrix format with subsequent decision-making based on identification results. The authors of the article provide justifications, conclusions and recommendations regarding the development and launch of measures to improve the efficiency and reliability of industrial safety systems at a hazardous production facility. The principal distinguishing feature of the research results are: the variability of the managerial decision on the corresponding challenge of the industrial safety system of a particular facility and the security of the region in which the subject operates; “Ideal” solution to the potential problem of loss of efficiency and reliability of industrial safety systems at a hazardous production facility.