Industrial Monitoring Research Articles

Simulation and quantitative analysis of Raman spectra in chemical processes with autoencoders

Raman spectroscopy represents an advanced process analytical technology to monitor and control chemical and biochemical processes. This study presents an autoencoder-based methodology that simulates Raman spectra from process variables and predicts the concentrations of different chemicals. The methodology accurately predicts concentrations from the spectra, even considering the temperature influences, and can work as an anomaly detector in process monitoring. The proposed methodology has significant implications for the optimization of industrial processes, improving process efficiency, reducing waste, and minimizing costs. It can also be extended to other industrial processes and imaging spectroscopy techniques, making it a valuable tool for process monitoring. This study highlights the effectiveness of autoencoders in simulating spectra and quantitative analysis, contributing significantly to the field of process monitoring. It has the potential to revolutionize industrial process monitoring and optimization, leading to substantial improvements in productivity and sustainability.

Enhancing quality control in emulsion-type sausage production: Predicting chemical composition of intact samples with near infrared spectroscopy

This research actively explores the potential of near infrared spectroscopy (NIR) for analyzing the chemical composition of emulsion-type sausages, focusing on critical factors like residual nitrite, moisture, protein, and fat content. To establish robust and generalizable models, we utilized a dataset of 100 experimentally prepared sausages encompassing a wide range of pork back fat replacement levels (5%, 15%, 30%, 45%, and 60%) and added sodium nitrite amounts (0, 80, 125, 250, and 375 ppm). An external validation set of 20 commercially sourced sausages further assessed the model’s real-world applicability. Partial least squares (PLS) regression calibration models with multiplicative scatter correction (MSC) pre-treatment demonstrated impressive accuracy for moisture (RMSECV = 0.57%, RPD = 9.8), fat (RMSECV = 1.17%, RPD = 9.5), and protein (RMSECV = 0.30%, RPD = 7.6). While residual nitrite prediction presented challenges due to its inherent complexity, the external validation yielded a competitive root mean square error of prediction (RMSEP) of 12.02 ppm, surpassing the average performance reported in similar studies (RMSEP ∼15 ppm) by 3 ppm. Importantly, sample homogenization did not significantly affect parameter prediction, highlighting the robustness of the NIR-based approach. These findings suggest that NIR spectroscopy, with its non-destructive, rapid, and cost-effective nature, could provide valuable tools for quality control and monitoring in the emulsion-type sausage industry. More importantly, improved nitrite prediction could pave the way for enhanced precision and control in sausage production, ultimately contributing to improved food safety and sustainability.

Structured Data Ontology for AI in Industrial Asset Condition Monitoring

This paper proposes an ontology for prognostics and health management (PHM) applications involving sensor networks monitoring industrial machinery. Deep learning methods show promise for the development of autonomous PHM systems but require vast quantities of structured and representative data to realize their potential. PHM systems involve unique and specialized data characterized by time and context, and thus benefit from tailored data management systems. Furthermore, the use of dissimilar standards and practices with respect to database structure and data organization is a hinderance to interoperability. To address this, this paper presents a robust, structured data ontology and schema that is designed to accommodate a wide breadth of PHM applications. The inclusion of contextual and temporal data increases its value for developing and deploying enhanced ML-driven PHM systems. Challenges around balancing the competing priorities of structure and flexibility are discussed. The proposed schema provides the benefits of a relational schema with some provisions for noSQL-like flexibility in areas where PMH applications demand it. The selection of a database engine for implementation is also discussed, and the proposed ontology is demonstrated using a Postgres database. An instance of the database was loaded with large auto-generated fictitious data via multiple Python scripts. CRUD (create, read, update, delete) operations are demonstrated with several queries that answer common PHM questions.

Industry 4.0 Enabling Technologies Contribution to the Sustainable Development Goals Achieving: A Content Analysis

The aim of the paper consists in the monitoring of Industry 4.0 enabling technologies (ET) adopting by the most innovative companies ranked by BCG classification, for Sustainable Development Goals (SDG) reaching. The development of Industry 4.0 ET has been considerably studied in the literature and its relationship to sustainability in its three pillars has been much investigated in recent years. The results show the three-years temporary dynamics of Industry 4.0 ET application in sustainability practices based on the communication process in the firms’ Sustainability Reports (SR) with the proven prevalence of IoT technology.

Energy-efficient mobile node localization using CVA technology and SAI algorithm

In the evolving landscape of the Internet of Things (IoT), Mobile Wireless Sensor Networks (MWSN) play a pivotal role, particularly in dynamic environments requiring mobile sensing capabilities. A primary challenge in MWSNs is achieving accurate node positioning with minimal energy consumption, as these networks often consist of battery-powered, mobile sensors where energy replenishment is difficult. This paper addresses the critical problem of energy-efficient node localization in MWSNs. We propose a novel positioning approach leveraging Cooperative Virtual Array (CVA) technology, which strategically utilizes the mobility of nodes to enhance positioning accuracy while conservatively using energy resources. The methodology revolves around optimizing the number of transceiver nodes, considering factors such as node moving speed, total energy consumption, and positioning errors. Central to our approach is the Signal Arrival and Interaction (SAI) algorithm, an innovative technique devised for efficient and precise mobile node localization, replacing traditional Time of Arrival (ToA) methods. Our simulations, conducted under various scenarios, demonstrate the significant advantages of the CVA-based positioning algorithm. Results show a marked reduction in energy consumption and robust performance in mobile node scenarios. Key findings include substantial improvements in localization accuracy and energy efficiency, highlighting the potential of our approach in enhancing the operational sustainability of MWSNs. The implications of this research are far-reaching for IoT applications, particularly those involving mobile sensors, such as in smart cities, industrial monitoring, and disaster management. By introducing a novel, energy-efficient positioning method, our work contributes to the advancement of MWSN technology, offering a sustainable solution to the challenge of mobile node localization.

Quasicrystal Nanosheet/α-Fe2O3 Heterostructure-Based Low Power NO2 Sensors: Experimental and DFT Studies.

Industrial emissions, environmental monitoring, and medical fields have put forward huge demands for high-performance and low power consumption sensors. Two-dimensional quasicrystal (2D QC) nanosheets of metallic multicomponent Al70Co10Fe5Ni10Cu5 have emerged as a promising material for gas sensors due to their excellent catalytic and electronic properties. Herein, we demonstrate highly sensitive and selective NO2 sensors developed by low-cost and scalable fabrication techniques using 2D QC nanosheets and α-Fe2O3 nanoparticles. The sensitivity (ΔR/R%) of the optimal amount of 2D QC nanosheet-loaded α-Fe2O3 sensor was 32%, which is significantly larger about 3.5 times than bare α-Fe2O3 sensors for 1 ppm of NO2 at 150 °C operating temperature. The sensors exhibited p-type conduction, and resistance was reduced when exposed to NO2, an oxidizing gas. The enhanced sensing characteristics are a result of the formation of nanoheterojunctions between 2D QC and α-Fe2O3, which improved the charge transport and provided a large sensing signal. In addition, the heterojunction sensor demonstrated excellent NO2 selectivity over other oxidizing and reducing gases. Furthermore, density functional theory calculation examines the adsorption energy and charge transfer between NO2 molecules on the α-Fe2O3(110) and QC/α-Fe2O3(110) heterostructure surfaces, which coincides well with the experimental results.

Classification of Sand-Binder Mixtures from the Foundry Industry Using Electrical Impedance Spectroscopy and Support Vector Machines.

Molding sand mixtures used in the foundry industry consist of various sands (quartz sands, chromite sands, etc.) and additives such as bentonite. The optimum control of the processes involved in using the mixtures and in their regeneration after the casting requires an efficient in-line monitoring method that is not available today. We are investigating whether such a method can be based on electrical impedance spectroscopy (EIS). To establish a database, we have characterized various sand mixtures by EIS in the frequency range from 0.5 kHz to 1 MHz under laboratory conditions. Attempts at classifying the different molding sand mixtures by support vector machines (SVM) show encouraging results. Already high assignment accuracies (above 90%) could even be improved with suitable feature selection (sequential feature selection). At the same time, the standard uncertainty of the SVM results is low, i.e., data assigned to a class by the presented SVMs have a high probability of being assigned correctly. The application of EIS with subsequent evaluation by machine learning (machine-learning-enhanced EIS, MLEIS) in the field of bulk material monitoring in the foundry industry appears possible.

Monitoring Transformation Processes in the Economy Using the Example of the IT Industry

The purpose of the research is to develop and test a methodology for monitoring transformation processes in the economy that intensified after the introduction of sanctions by Western countries (on the example of the IT-industry). The methodology is based on the Harvard paradigm of industry analysis (Structure- Conduct- Performance) and includes five stages. At the first, the basic conditions of the industry are assessed and the demographics of enterprises, industry barriers, intensity of competition and economies of scale are analyzed. The second analyzes the market structure that has developed in the industry and the intensity of competition using the concentration coefficient and the Herfindahl- Hirschman index. At the third stage, the behavior of industry enterprises is analyzed on the basis of summary statements and consolidated reports, as well as median values of indicators for enterprises. In the course of analyzing the behavior of enterprises, their market and operational efficiency, investment and financial activity are assessed. The type of growth and productivity of production factors is established by constructing the industry production function. Particular attention is paid to indicators of transformation processes — added value, labor productivity and return on capital. At the fourth stage, industry enterprises are grouped into four groups according to D. Birch’s method: fast-growing enterprises, large businesses, enterprises implementing an aggressive investment strategy and the rest of small businesses. At the fifth stage, indicators of the effectiveness of state economic policy are assessed. Calculations performed based on data from 2,451 enterprises in the IT industry showed that transformation processes in the industry have intensified, new enterprises are entering the industry, their operational and market activity is increasing, non-current assets and equity capital are growing. However, payments for investment activities do not allow us to draw an unambiguous conclusion about high investment activity; in addition, there is no significant influx of long-term borrowed capital into the industry, which hinders its development. Positive changes in the industry are largely associated with active government policy, which promotes the transition to domestic software, influencing the methods of fiscal policy, while monetary policy instruments are not used actively enough. The methodological basis of the study was formed by general scientific principles and methods: abstraction, generalisation of approaches of foreign and domestic authors to sectoral analysis, grouping, comparison, generalisation, as well as economic and mathematical methods. The result of the work is the methodology of industry monitoring, as well as the indicators of IT-industry development for the period 2018–2022 obtained during its testing. The article may be useful for analysts assessing the development of industries within the framework of industry analysis or industrial policy monitoring.

The Challenges and Opportunities for TiO2 Nanostructures in Gas Sensing.

Chemiresistive gas sensors based on metal oxides have been widely applied in industrial monitoring, medical diagnosis, environmental pollutant detection, and food safety. To further enhance the gas sensing performance, researchers have worked to modify the structure and function of the material so that it can adapt to different gas types and environmental conditions. Among the numerous gas-sensitive materials, n-type TiO2 semiconductors are a focus of attention for their high stability, excellent biosafety, controllable carrier concentration, and low manufacturing cost. This Perspective first introduces the sensing mechanism of TiO2 nanostructures and composite TiO2-based nanomaterials and then analyzes the relationship between their gas-sensitive properties and their structure and composition, focusing also on technical issues such as doping, heterojunctions, and functional applications. The applications and challenges of TiO2-based nanostructured gas sensors in food safety, medical diagnosis, environmental detection, and other fields are also summarized in detail. Finally, in the context of their practical application challenges, future development technologies and new sensing concepts are explored, providing new ideas and directions for the development of multifunctional intelligent gas sensors in various application fields.

Euclidean-Riemannian Joint Low-Rank Projections for Industrial Process Monitoring

Euclidean-Riemannian Joint Low-Rank Projections for Industrial Process Monitoring

Anomaly Detection Using CNN with I3D Feature Extraction

Anomaly detection is a critical task in various fields such as surveillance, healthcare, and industrial monitoring, aiming to identify patterns that deviate significantly from normal behavior.Video anomaly detection is inherently difficult due to visual complexity and variability. This work proposes a unique anomaly detection technique leveraging Convolutional Neural Networks (CNN) with Inflated 3D Convolutional Networks (I3D) for feature extraction. This involves training the CNN on a large dataset to learn normal behavior, enabling it to identify anomalies by recognizing deviations from learned patterns. Furthermore, our approach exhibits promising results in detecting various types of anomalies, including sudden changes, abnormal trajectories, and rare events. Upon detection of such activity, mail(notification) can be raised concerned people who can take immediate action.This research contributes a significant advancement in the field of anomaly detection, and holds potential for applications in surveillance, security, and industrial monitoring systems. Keywords—Anomaly detection,I3D(Inflated3D) feature extraction,Convolutional neural network, Spatio-Temporal Features,Normal and abnormal event detection.

Machine learning algorithms for in-line monitoring during yeast fermentations based on Raman spectroscopy

Given the intricacies and nonlinearity inherent to industrial fermentation systems, the application of process analytical technology presents considerable benefits for the direct, real-time monitoring, control, and assessment of synthetic processes. In this study, we introduce an in-line monitoring approach utilizing Raman spectroscopy for ethanol production by Saccharomyces cerevisiae. Initially, we employed feature selection techniques from the realm of machine learning to reduce the dimensionality of the Raman spectral data. Our findings reveal that feature selection results in a noteworthy reduction of over 90% in model training time, concurrently enhancing the predictive performance of glycerol and cell concentration by 14.20% and 17.10% at the root mean square error (RMSE) level. Subsequently, we conducted model retraining using 15 machine learning algorithms, with hyperparameters optimized through grid search. Our results illustrate that the post-hyperparameter adjustment model exhibits improvements in RMSE for ethanol, glycerol, glucose, and biomass by 9.73%, 4.33%, 22.22%, and 13.79%, respectively. Finally, specific machine learning algorithms, namely BaggingRegressor, Support Vector Regression, BayesianRidge, and VotingRegressor, were identified as suitable models for predicting glucose, ethanol, glycerol, and cell concentrations, respectively. Notably, the coefficient of determination (R2) ranged from 0.89 to 0.97, and RMSE values ranged from 0.06 to 2.59 g/L on the testing datasets. The study highlights machine learning's effectiveness in Raman spectroscopy data analysis for improved industrial fermentation monitoring, enhancing efficiency, and offering novel modeling insights.

Methane gas sensor based on direct absorption spectroscopy and the laser self-heating effect.

In this paper, a methane detection sensor based on direct absorption spectroscopy and the self-heating effect of lasers is proposed, which abandons the traditional method of relying on a thermoelectric cooler (TEC) to ensure stable gas concentration detection. The sensor can achieve stable concentration measurement in the temperature range of -10∘ to 40°C without the need for a TEC, which greatly simplifies the structure of the sensor and reduces the cost. The results of gas concentration calibration experiments show that the sensor has a good linear correlation (R 2=0.9993). Long-term continuous detection experiments show that the sensor maintains a relative detection error between -2.667% and 4.3% over the full test temperature range. In addition, signal-to-noise ratio analysis experiments further determine that the minimum detection limit of the sensor for methane gas is 27.33p p m⋅m (1σ). Given its advantages of simple structure, low cost, high accuracy, and stability, this methane detection sensor is well suited for natural gas leakage monitoring in home environments and can also be widely used in industrial safety detection and environmental monitoring applications. This technology provides a cost-effective solution for domestic and industrial methane detection.

Single ferroelectric liquid crystal compounds targeted for optical voltage sensing

Nine compounds containing fluorine or chlorine atoms in the lateral position in the rigid core with a chiral terminal octyloxy-chain were synthesized mainly using Suzuki-Miyaura coupling, Mitsunobu, hydrogenation, and esterification reactions. New compounds were investigated using polarized optical microscopy (POM), differential scanning calorimetry (DSC), spectrophotometry, and electro-optical methods. A computational analysis of the effect of lateral substitution by halogen atoms on the phenyl ring on the dipole moment of the compound was provided and discussed. The designed compounds exhibit a wide temperature range of the ferroelectric phase (>40.0 °C), a low melting point (in most cases below 50.0 °C), low melting enthalpy (around 10.0–20.0 kJ/mol), a short helical pitch (in most cases below 200 nm at room temperature) and high tilt angle that ensures a cone angle of up to 90°; all those properties make them of great potential for the deformed helix ferroelectric (DHF) mode. Revealed features allow synthesized compounds in fully integrated polarization-based photonic transducers to have excellent linearity and the highest sensitivity observed in ferroelectric liquid crystals for DHF mode. For the first time, the DHF effect was reached for the single molecule FLC material in a broad temperature range down to 38 °C. These findings pave the way for a new class of optical sensors for, among others, industrial monitoring networks and brain/machine interfaces with unprecedented performance.

Vibration Monitoring in Industry: Then and Now

Vibration Monitoring in Industry: Then and Now

Finite element modeling of infrasound resonance in an underground tunnel structure

Recent observations of acoustic/infrasound signals emanating from an underground mine in central Utah show a spectral signature consisting of several dominant harmonics whose amplitude decay rate increases with frequency. This spectral character is consistent with a model in which the observed signals are generated from acoustic resonance within the mine tunnels. I present models of these signals computed using a discontinuous-Galerkin finite element formulation. The mesh geometry of these models is based on the known geometry of the mine tunnels obtained using traditional survey methods. Explosion source locations in the mine are known from previous analysis of seismic signals and operator logs and are associated with observations of infrasound resonance at multiple far-field stations. I explore the sensitivity of the modeled signals to changes in the source spectrum, boundary conditions within in the mine and perturbations to tunnel geometry. I discuss the possible application of my results to volcanic monitoring, industrial monitoring of underground structures, and the possible determination of underground tunnel geometries using far-field observations of acoustic resonance.

AI-enabled industrial equipment monitoring, diagnosis and health management

Abstract Artificial intelligence (AI) has achieved significant progress in recent years and its applications cover a wide range of fields such as computer vision, natural language processing, autonomous driving and medical diagnosis. In industry, the rapid development of real-time-sensor measurement techniques promotes equipment surveillance and maintenance into the era of big data. It is still challenging to manually analyze this big data and establish general physical modelling by using the information hidden in these data. To this end, AI technology, such as machine learning and neural networks, has emerged as a promising tool to extract useful knowledge from measured data, and to tackle the real-time monitoring, diagnosis problems as well as enhancing the health management and reliability of modern industrial equipment. With the vision of establishing a strong link between AI and industrial equipment surveillance and maintenance, this special feature is designated to select, organize and exhibit the latest research progress on the cutting-edge research topics relevant to AI-Enabled Industrial Equipment Monitoring, Diagnosis and Health Management. Submissions for this topic in Measurement Science and Technology are open from 23 March 2022 to 30 September 2022 and contains 42 outstanding papers in above research fields.

Use of the raw material base of marine fish in Russian waters of the Far Eastern seas and adjacent areas of the open part of the Pacific Ocean in 2000–2020

The purpose of the work: characteristics of the raw material base of marine fish in the Far Eastern fishery basin and an assessment of the effectiveness of its use by domestic fisheries at the present stage (2000–2020).Methods used: to achieve this goal, data on biomass, catch and development of the main commercial marine fish were analyzed. Fish catches were reviewed based on operational information about the fishery based on daily ship reports from the industry monitoring system.Novelty: elements of novelty are generalized modern materials on biomass, catch and development of marine fish resources in the Far Eastern seas and adjacent waters of the Pacific Ocean. The current state of commercial fish stocks (walleye pollock, Pacific cod, saffron cod, Pacific herring, Righteye flounders, greenlings, Japanese pilchard, Chub mackerel, Pacific saury) in the Far Eastern fishing basin can be characterized as stable, and the distribution of the catch of these objects among individual fishing areas due to their significant volumes is practically determines the distribution of catch of both quota and non-quota species of marine fish. Scientific information support for the above-m entioned fish is at a high level, their biological condition is generally favorable, and the dynamics of their numbers is regulated mainly by habitat variability.Practical significance: the results of this study can be used in forecasting the dynamics of aquatic biological resources, and the results obtained on marine fish stocks and fisheries will improve the efficiency of using their raw material base.

Joint structure bipartite graph projection and its application for industrial process monitoring

Process monitoring plays a crucial role in maintaining the safety and stable operation of industrial processes. One of its key tasks is to improve the accuracy of detecting abnormal conditions. To this end, we propose a dimensionality reduction method called Joint Structure Bipartite Graph Projection. This method not only captures global information, but also incorporates manifold learning and anchor strategy to capture the local structure of data in an adaptive neighbor manner. In constructing the bipartite graph between projected samples and projected anchors, structural information between samples and anchors is fully considered to ensure an effective graph. Furthermore, we introduce an information entropy-based method to compute the balance parameters, reducing costs of parameter tuning. Ultimately, we develop a process monitoring model based on JSBGP method, achieving the goals of anomaly detection and abnormal variables isolation. Through experiments on benchmark dataset and actual industrial process demonstrate the effectiveness of the proposed method.

Russian fisheries in 2000–2020

Purpose of the work: analysis of the development of fisheries development in Russia in the first two decades of the 21st century, assessment of stock state and catches of fish resources, and identification of major factors of influence on these resources and fisheries. Methods used: the main source of information on the production in Russian fisheries was annual data on catches of fish and other aquatic biological resources and data on aquaculture production — Form No. 1-P (fish). Сatches and yields of fish resources were analyzed based on the operative reporting of enterprises and data of the industry monitoring system. For access and initial processing, the FMS analyst software was used.Novelty: an analysis of the regulatory and legal framework development is presented, materials from Russian fisheries for 2000–2020 are summarized and analyzed.Practical significance: the development of any type of economic activity is a continuous, but heterogeneous process, with periods of growth and decline of varying duration. Fishery is no exception. Throughout its history, the industrial fisheries in Russia have gone through a series of stages associated with changes in fisheries technology and evolution of fishing vessel design. The development of industrial fisheries was also related to such objective conditions as long-term climate changes, which influenced the state of fisheries resources.