Industrial Data Research Articles

Industry data on alcohol sales in South Africa between 1995 and 2022 and its value in detecting the impact of policy interventions related to packaging and Covid-19 alcohol availability

Aims: To assess changes in total alcohol consumed over time, changes in consumption of different alcoholic beverages and the utility of industry sales data to evaluate the impact of policy changes related to a packaging ban on wine products in September 2007 and bans on alcohol sales during the Covid-19 pandemic in 2020 and 2021 in South Africa. Design. Alcohol industry sales data as a proxy for consumption was assessed using statistics presented in South African Wine Industry Information & Systems (SAWIS) booklets released annually between 1995 and 2022 and used to describe changes over time in consumption overall, and by product, and the impact on consumption from changes in policy. Results. Per capita consumption of alcoholic beverages overall has held steady or declined over time, but declines were noted in the market share of wine and beer (especially) and a massive increase for RTDs. The consumption data also indicated short term effects of Covid-19 interventions (especially in 2020) in terms of reducing overall alcohol consumption, with a return to prior levels in 2022. Industry data on packaging for wine was able to show the immediate and longer-term impact of the 2007 ban on wine sold in foil-bags. Conclusion. Industry data are a useful adjunct to consumer measures of alcohol use, as well as in detecting the impact of policy changes related to availability and packaging, notwithstanding gaps in information on illicit/unrecorded sales and other limitations.

Indium Phosphide Semiconductor Technology for Next-Generation Communication Systems: Sustainability and Material Considerations

Indium phosphide (InP) semiconductor technology is being explored for radiofrequency (RF) applications, targeting frequencies exceeding 100 GHz, to support the next generation of 6G communication systems. When taking into account sustainability in designing this future generation, growing concerns are emerging regarding the environmental impact of communication networks and the reliance on raw materials for the production of Information and Communication Technologies (ICTs). The extraction, processing, and manufacturing of such materials and semiconductor technologies result in environmental impacts, but these impacts remain insufficiently documented. Firstly, this study evaluates the environmental impacts of manufacturing indium phosphide (InP) wafers based on industrial data and those of InP-based heterojunction bipolar transistors (HBTs) based on early-stage research data. Secondly, this study attempts to highlight the challenges posed by the increasing demand for high-tech solutions, involving raw materials, by evaluating the potential demand for indium for RF 6G applications, with a deployment scenario.

DUKPT for Software POS: A Technical Key Management Approach for Safeguarding Payment Data

Purpose: The paper explores how the Derived Unique Key per Transaction (DUKPT) encryption technique enhances the security of software-based Point of Sale (POS) systems, addressing rising cyber threats and safeguarding sensitive financial data. It aims to educate stakeholders across industries on DUKPT's implementation and long-term benefits in meeting evolving regulatory and customer demands for data security. Methodology: A thorough literature research and a hands-on examination of DUKPT's use in software-based point-of-sale systems comprise the methodology. Existing research on key management, encryption of payment systems, and the weaknesses of conventional key management techniques are all included in the literature review. The report also provides case studies that show how DUKPT has been implemented in various industries, looking at both technical details and practical results. The examination covers network communication protocols, device security measures, secure key storage, and PCI DSS (Payment Card Industry Data Security) compliance. The conclusions are further supported by quantitative data from security breach statistics and qualitative data from interviews with industry professionals. Findings: The findings of this paper reveal that DUKPT significantly enhances the security of software-based POS systems. Key results include: The Derived Unique Key per Transaction (DUKPT) encryption technique offers several advantages. It enhances security by generating a unique encryption key for every transaction, effectively reducing the risk of data breaches and preventing key reuse attacks. Additionally, DUKPT improves operational efficiency by allowing businesses to manage encryption keys securely without significant overhead, resulting in streamlined processes. Its implementation also demonstrates a stronger commitment to regulatory compliance, particularly with PCI DSS standards, minimizing the risk of penalties for non-compliance. Furthermore, the enhanced data security fosters greater customer trust, which ultimately strengthens client loyalty and retention Unique Contribution to Theory, Practice, and Policy: The study makes a unique contribution to the field by providing a thorough analysis of DUKPT's benefits, enhancing theoretical discussions on cryptographic techniques, educating policymakers about the need for updated security regulations to improve cybersecurity in payment systems, and providing useful case studies and suggestions for businesses looking to successfully integrate DUKPT in software POS environments.

Advancing Blast Furnace Thermal State Prediction: A Data‐Driven Approach Using Thermocouple Integration and Multimodal Modeling

This study develops a data‐driven framework to predict the thermal state of blast furnaces using feature fusion from thermocouple data and spatial temperature distribution. The article proposes a hybrid framework based on multimodal integration and clustering algorithms, utilizing data extracted from thermocouples and the temperature distribution features around the furnace hearth. Through these fused features, multiple ensemble models are constructed to predict the thermal state of the blast furnace, with a focus on the thermocouple readings at the hearth. This method enhances understanding of the thermal state of the blast furnace, aiming to improve prediction accuracy and operational reliability. By validating the model with actual industrial data, its effectiveness in thermal state monitoring is demonstrated. The integration of multimodal data sources allows for the extraction of rich information from the thermocouple data, significantly enhancing the model's predictive performance.

Control Design for Electronic Voltage Stabilizer

Vietnam's electrical infrastructure has undergone notable advancements in recent times. Nevertheless, concerns pertaining to under-voltage, over-voltage, and voltage fluctuations persist in rural, mountainous, and industrial regions. This results in the inefficient operation of electrical equipment, disruptions in industrial production processes, data loss, and equipment damage. This paper puts forth a novel control design methodology for electronic voltage stabilizers, with the objective of mitigating the detrimental effects of grid voltage fluctuations on electrical apparatus. A compact and cost-effective AC-AC converter is proposed as a means of regulating the compensation voltage. The paper puts forth the use of the state-space averaging method for system modeling and proposes the combination of feedback and feed-forward controllers to achieve high accuracy and rapid response times. Furthermore, the moving average method is proposed for measuring the Root Mean Square (RMS) voltage, which significantly enhances the control response speed and accuracy. A 10 kVA single-phase electronic voltage stabilizer was constructed and tested in a laboratory setting under a range of grid voltage conditions, from 150V to 290V, and with varying loads. The results demonstrate that the electronic voltage stabilizer is effective in maintaining the load voltage within the desired range. The maximum response time recorded was found to be half a cycle of the grid voltage in the simulation and one cycle in the experiments, which is a significantly faster response time than that of similar designs. Furthermore, the low total harmonic distortion provides additional confirmation of the effectiveness of the designed electronic voltage stabilizer.

Bridging the Industrial Data Gap: Top-down Approach from National Statistics to Site-Level Energy Consumption Data

Bridging the Industrial Data Gap: Top-down Approach from National Statistics to Site-Level Energy Consumption Data

PCI DSS: A Critical Analysis of Implementation, Effectiveness, and Legislative Impact in Payment Card Security

The Payment Card Industry Data Security Standard (PCI DSS) has emerged as a pivotal framework in securing payment card transactions across global financial systems. This article presents a comprehensive analysis of PCI DSS, examining its evolution from disparate security programs to a unified standard, technical framework, and implementation challenges across different merchant levels. The article evaluates the effectiveness of the compliance validation mechanisms, including self-assessment questionnaires and third-party assessments, while analyzing the standard's incorporation into state legislation and its legal implications. This article reveals a complex relationship between compliance validation and actual security effectiveness by examining documented security breaches and industry responses. The findings indicate significant gaps between formal compliance and real-world security outcomes, highlighting the need for a more dynamic approach to payment card security. This article contributes to the ongoing discourse on payment security standards by identifying key challenges in implementation and suggesting potential areas for improvement in future iterations of the standard.

Optimizing the oil and natural gas industry: The role of ai and data analytics in ERP integration

Global energy requirements depend on the oil and natural gas industry which deals with efficiency issues and must meet both regulatory standards and environmental protection needs. Our research shows how adding artificial intelligence and data analysis tools into ERP systems solves industry problems. Enterprise resource planning systems powered by artificial intelligence make better supply chain decisions while helping businesses predict equipment maintenance needs leading to lower costs and more efficient operations. Research findings from case studies and industry data show that businesses reducing maintenance costs by 25% and improving logistics savings by 15% through AI-ERP implementation. While legacy systems, high costs and data security risks pose challenges the positive outcomes of merging AI with ERP systems prove greater in value. The research shows how these systems help energy companies operate more sustainably and emit less carbon in our modern energy environment. The sector will progress further as new developments like generative AI plus blockchain and edge computing enter the market. Companies need to train their teams, work with experts in the field and use clean technology solutions to stay ahead in today's changing market.

Expanding horizons in the Middle East: evaluating the Hair Addict’s strategies for growth

Research methodology The case was developed using a combination of primary and secondary data collection. The main source of primary data collection was an interview with the founder of The Hair Addict, Doaa Gawish, in August 2023, with later follow-up calls to clarify some aspects of the business model and obtain more specific information. For secondary sources of information, the authors relied on the company website, as well as a couple of published interviews with the founder in an online business magazine [1] and an independent news website that covers Egyptian news, culture and lifestyle topics (Makary, 2021). The case also relies on macroeconomic and industry data obtained from various databases and research report providers, which are referenced in the case and teaching note.

Research on meshing method for industrial CT volume data based on iterative smooth signed distance surface reconstruction

Industrial Computed Tomography (CT) technology is increasingly applied in fields such as additive manufacturing and non-destructive testing, providing rich three-dimensional information for various fields, which is crucial for internal structure detection, defect detection, and product development. In subsequent processes such as analysis, simulation, and editing, three-dimensional volume data models often need to be converted into mesh models, making effective meshing of volume data essential for expanding the application scenarios and scope of industrial CT. However, the existing Marching Cubes algorithm has issues with low efficiency and poor mesh quality during the volume data meshing process. To overcome these limitations, this study proposes an innovative method for industrial CT volume data meshing based on the Iterative Smooth Signed Surface Distance (iSSD) algorithm. This method first refines the segmented voxel model, accurately extracts boundary voxels, and constructs a high-quality point cloud model. By randomly initializing the normals of the point cloud and iteratively updating the point cloud normals, the mesh is reconstructed using the SSD algorithm after each iteration update, ultimately achieving high-quality, watertight, and smooth mesh model reconstruction, ensuring the accuracy and reliability of the reconstructed mesh. Qualitative and quantitative analyses with other methods have further highlighted the excellent performance of the method proposed in this paper. This study not only improves the efficiency and quality of volume data meshing but also provides a solid foundation for subsequent three-dimensional analysis, simulation, and editing, and has important industrial application prospects and academic value.

Influence of tin on crystallization processes in iron-carbon alloys (review)

Currently, iron foundries and production facilities are experiencing great difficulties in providing such an integral charge material for smelting cast iron as high-quality unalloyed steel scrap. Due to the fact that press and forging industries and enterprises are increasingly using high-strength steels to produce their products, which significantly reduce the weight of the products obtained, microalloyed with such elements-carbidizing agents as, for example, Mo, W, Nb, V, Ti, B, the charge yards of iron foundries are supplied waste “infected” with these elements. As a rule, in such industries, products are made from several grades of steels, both microalloyed with carbide-forming elements and without them, and due to the objective complexity, the waste sorting process is not organized organizationally, therefore, waste from all available grades of steel falls uncontrollably into steel bags, mixing in arbitrary proportions. In addition to carbide-forming elements, surfactants such as Cu, Sn, As and Sb are also the most common residual elements in steel and cast iron scrap. If the accumulation of carbide-forming elements to a certain extent can be considered a positive factor, then the accumulation of surfactants, which are practically impossible to remove from steel and cast iron, has a sharply negative effect on the mechanical and operational properties of iron-carbon alloys. Tin is used as an alloying element to produce both steels and cast irons with a fully pearlitic matrix. The addition of tin in an amount of no more than 0.10–0.15% seems to be the only practical way to avoid the growth of ferrite in a stable eutectoid reaction and completely transform the metal base of steel and cast iron into pearlite in a metastable eutectoid Fe–C system. At the same time, the question of how tin affects eutectoid transformations in steels and cast irons and, in general, the entire cycle of structure formation, is still a matter of debate. In this paper, an overview of the Fe–Sn system is performed, as well as experimental and industrial data available in the literature on the Fe–C–Sn system to assess the effect of tin on crystallization processes in iron-carbon alloys.

Fault diagnostic method based on transfer dynamic deep learning for few shot temporal–spatial correlation industry process

AbstractData‐based fault diagnosis plays a crucial role in ensuring the safety of industrial processes. However, the complex industry process often has temporal–spatial correlation with insufficient labelled fault data. To settle these problems, a new transfer dynamic deep learning strategy that combines autoencoder (AE) with gate recurrent unit (GRU) is proposed. First, dynamic AE networks are introduced to extract the single‐attribute time series features, and the dynamic GRU is employed to extract the spatial correlation features among multiple feature dimensions and temporal correlation among samples. Then, to solve the problem of insufficiently labelled industrial data, the model‐based transfer learning between the sufficient laboratory data and insufficient labelled industrial data is executed. Experimental results based on the Tennessee Eastman (TE) process and the benchmark simulation model 1 (BSM1) process show that the proposed approach has excellent performance.

Co-combustion of coal and sawdust in a three-dimensional industrial scale BFB boiler (BG-043, 67TPH): a numerical approach

ABSTRACT Experiments in large-scale CFBC boilers are expensive and time-consuming, while simulations are economical, time-saving, and provide better control over the physical process. In the current research, mathematical modeling of industrial scale CFBC boiler (BG-043, 67TPH capacity, ACC cement factory Bargarh, Odisha, India) using coal and sawdust blended fuel (90% coal + 10% sawdust) is performed by considering the four distinct (coal, sawdust, sand, and mixture gas) phases using Eulerian–Eulerian multifluid model. Heterogenous chemical reactions kinetics are implemented using user-defined functions. The numerical methodology is validated with the onsite industrial data. The comparison of pressure drop, fluidized bed height, axial velocity profiles, sand, and mixture gas temperature variations, gas compositions, and pollutant emissions (SO2 and NO) using solo coal and sawdust blended fuel are presented in the result section. Hydrodynamics study reveals the recirculation of sand particles in the fluidized bed region of the boiler. The comparison of solo coal and sawdust blended fuel combustion study reveals a 10.61% reduction in pressure drop, 12.13% increase in O2 mass fraction, 9.63% reduction in CO mass fraction, 19.64% reduction in SO2 mass fraction, and 8.67% reduction in NO mass fraction while using the 10% sawdust blends with 90% coal.

Optimization of an Industrial Circulating Water System Based on Process Simulation and Machine Learning

As an important part of industrial production, the optimization of circulating water systems is of great significance for improving energy efficiency and reducing operating costs. However, traditional optimization methods lack real-time and dynamic adjustment capabilities and often cannot fully cope with the complex and changeable industrial environment and energy demands. Advances in computer technology can enable people to use machine learning models to process information and data and ultimately help simplify simulation and optimization. In this paper, the circulating water system of a Fluid Catalytic Cracking (FCC) unit is optimized and evaluated based on process simulation and machine learning, adopting 284 sets of industrial operating data. The cooler network of the system is modified from a parallel structure to a series mode, and the effect is clarified using the ASPEN HYSYS software V12. Meanwhile, the fan power of the cooling tower is predicted by employing an optimized Gradient Boosting Regression (GBR) model, and the influence of the parallel-to-series transformation on the fan power is discussed. It is shown that the computer modeling results are in coincidence with the industrial data. Converting the parallel design to a series arrangement of the cooler network can significantly decrease the water consumption, with a reduction of 11%. The fan power of the cooling tower is also reduced by 8% after the optimization. Considering the changes in both water consumption and fan power, the saved total economic cost is 8.65%, and the decreased gas emission is 2142.06 kg/h. By building the optimization prediction system, the real-time sequencing and monitoring of equipment parameters are realized, which saves costs and improves process safety.

Demand forecasting in clearance season for fast fashion retail: a residual learning approach

PurposeThis study focuses on forecasting demand for markdown pricing in situations where historical data are limited and proposes using a hybrid knowledge-based residual (KRL) network to enhance the accuracy of demand predictions in fast fashion retailing.Design/methodology/approachWe use a hybrid KRL network structure to increase forecasting accuracy in fast fashion data by combining artificial neural network (ANN) and theoretical demand models (TDMs) such as linear, exponential and multinomial logit. We used a linear demand model (LDM) as a theoretical demand model, which is one of the popular TDMs in the literature, and combined it with neural networks utilizing the residual network structure. We tested it on real fast fashion data to estimate the next week’s demand at the clearance seasons of 5 years.FindingsThe results underscore KRL’s capability to derive mutual benefits from both neural networks and LDM, especially in the specific context of limited fast fashion data. Furthermore, KRL outperforms LDM and ANN models when used individually in forecasting accuracy.Originality/valueThe research paper proposes a scientific, quantitative method for forecasting the sales for markdown settings, combining data driven and TDMs using residual learning thereby resolving the issue of insufficient sales data in the fashion industry.

An Integrated Framework for TFT-LCD Quality Prediction Based on L1 Regularized Feature Selection and SSA-Optimized MLP-XGBoost Ensemble

With the rapid development of display technology, accurate quality prediction of TFT-LCD is crucial because its performance directly affects the user experience. Traditional quality prediction methods rely on manual inspection or rule-based methods, facing the challenges of low efficiency, strong subjectivity, and lack of robustness to changes in production environment. To address these limitations, this paper proposes a novel regression model based on L1 regularized feature selection, Salp Swarm algorithm (SSA) optimization, and MLP-XGBoost integration. L1 regularization is used to automatically select key features from high-dimensional industrial data, reduce redundancy and enhance model generalization. Subsequently, SSA optimizes the hyperparameters of MLP and XGBoost, enabling effective exploration of the parameter space and thus improving model performance. The integrated MLP-XGBoost model combines the nonlinear feature extraction capability of MLP with the regression accuracy of XGBoost. Experimental results show that the proposed model outperforms traditional models in various indicators. Compared with the unoptimized MLP-XGBoost, the model achieves a significant reduction in prediction error, verifying its effectiveness in solving TFT-LCD quality prediction.

Industrial multivariate time-series data anomaly detection incorporating attention mechanisms and adversarial training

ABSTRACT To address the challenges faced in industrial anomaly detection, including data sample imbalance, lack of anomaly labels, and complex spatiotemporal relationships in high-dimensional data, this paper proposes a novel multi-modal time-series anomaly detection model that combines attention mechanisms and adversarial training. In this model, the first step involves utilizing graph attention mechanisms to extract sequence correlation features from multi-modal time-series data, which are then summed with the original data to form a dual-feature-based data representation. Subsequently, a self-supervised learning approach is employed to input this data representation into a variational autoencoder’s encoding-decoding network for reconstruction. Anomaly detection is performed by analyzing the error between the input and reconstructed data. The model also employs spatiotemporal attention mechanisms and adversarial training during reconstruction to enhance feature extraction and model generalization. By comparing our proposed model to five commonly used baseline models, we demonstrate its effectiveness in detecting anomalies in scenarios involving high-dimensional data and imbalanced abnormal samples, demonstrating superior anomaly detection performance, as well as excellent performance on real industrial production and processing datasets.

Real-Time Analysis of Industrial Data Using the Unsupervised Hierarchical Density-Based Spatial Clustering of Applications with Noise Method in Monitoring the Welding Process in a Robotic Cell

The application of modern machine learning methods in industrial settings is a relatively new challenge and remains in the early stages of development. Current computational power enables the processing of vast numbers of production parameters in real time. This article presents a practical analysis of the welding process in a robotic cell using the unsupervised HDBSCAN machine learning algorithm, highlighting its advantages over the classical k-means algorithm. This paper also addresses the problem of predicting and monitoring undesirable situations and proposes the use of the real-time graphical representation of noisy data as a particularly effective solution for managing such issues.

An adaptive ensemble learning capacity prediction method with dual-modal data in lithium-ion battery manufacturing

ABSTRACT To measure the capacity of lithium-ion batteries in manufacturing, it is necessary to go through the formation, standing, and grading processes. The existing data-driven capacity prediction methods can only reduce a portion of the grading process and do not comprehensively use both time series data and statistical feature data. In response to the above problems, this paper proposes an adaptive ensemble learning method, which does not go through the grading process and only uses the statistical features and time series of dual-modal data in the formation process to predict the capacity. The LightGBM algorithm is used to predict statistical feature data, while the multi-channel GRU and multi-head self-attention network are used to predict time series data. Then, the two parts are fused through adaptive ensemble learning to estimate the capacity. Furthermore, the proposed method could be flexibly applied to the prediction of single-modal dirty data as required. The method is verified using actual industrial production line data. The experimental results show that the MAE and MAPE of the test set are 0.948 Ah and 0.324%, respectively. For single-modal dirty data (accounting for about 4%), MAPE of its prediction results is less than 0.65%.

Impact of Digital Transformation on Administrative Management: Perspectives from Cloud Computing and Big Data in Industry 4.0

Digital transformation is revolutionizing administrative management by integrating technologies such as cloud computing and Big Data within the framework of Industry 4.0. This article explores how these tools drive efficiency, data-driven decision-making, and business competitiveness. Recent implementation cases, the advantages of digitalization and the associated challenges, such as data security and resistance to organizational change, are analyzed. The research uses a qualitative and quantitative approach, based on academic studies and interviews with experts in the sector. The results show a significant improvement in operational agility and a reduction in costs, although barriers to technology adoption persist.