Industrial Monitoring Research Articles

Machine-learning-based sampling inspection under OQC capacity for real-time quality monitoring in the TFT-LCD industry

ABSTRACT In the thin film transistor-liquid crystal display (TFT-LCD) industry, the competition is fierce, and the external failure cost is high. To improve the quality of released products, sampling inspection under outgoing quality control (OQC) is conducted before products are released. Owing to the variety and complexity of inspection items, the task must be carried out manually while realising automation is difficult. Traditional random sampling inspection is limited by sampling quantity, manpower, and material resources. To effectively improve acceptable quality levels, this paper proposes a quality predictive monitoring framework tailored to the production and inspection characteristics of the TFT-LCD industry. This framework includes real-time automatic quality monitoring based on an optimal machine learning prediction model with two-phase feature creation, and it also addresses OQC inspection capacity constraints. Experimental results show the prediction performance based on proposed model is better than the traditional random sampling process. In practice, superior average outgoing quality improves by more than 70% at the same sampling level. In addition, the features of the process can be further controlled and managed based on the prediction model to monitor the key parameters in real time and respond to abnormalities quickly, thereby further improving the quality of released products.

CAN AUDIT COMMITTEE MODERATE FRAUD HEXAGON MODELS IN DETECT FRAUDULENT FINANCIAL REPORTS: AN EMPIRICAL STUDY OF PROPERTY AND REAL ESTATE SECTOR COMPANIES IN INDONESIA

This study seeks to provide empirical evidence of the impact of the Fraud Hexagon on fraudulent reports, with the Audit Committee serving as a moderating variable. The research focuses on companies in the property and real estate sectors listed on the Indonesia Stock Exchange 2020-2022 period. The object of this study is to examine the relationship between the elements of the fraud hexagon and financial statement fraud while considering the influence of the audit committee. This study employs regression analysis with MRA (modified regression analysis) for the purpose of data analysis. The findings of this study indicate that financial target, financial stability, external pressure, CEO education, nature of industry, CEO picture, audit opinion, and effective monitoring do not exert any influence on the likelihood of dishonest financial reporting. Simultaneously, alterations in leadership and political affiliations have an influence on deceitful financial statements within the property and real estate industries. Meanwhile, the audit committee can oversee the inadequate supervision of fraudulent financial reporting.

HOW DETECT FRAUD WITH HEXAGON MODEL ON FINANCIAL STATEMENT FRAUD IN PROPERTY AND REAL ESTATE INDONESIA

Examining how Freud's hexagon framework relates to financial statement fraud is the focus of this study. In total, ten factors were considered. Financial Target, Financial Stability, External Pressure, Change of Director, Nature of Industry, CEO Picture, Political Connection, Audit Opinion, CEO Education and Effective Monitoring. Financial statement fraud is measured using the Beneish M-Score Model. The research sample consists of industries in the property and real estate sector based on data from the Indonesia Stock Exchange (IDX) during the 2020-2022 period. The number of companies included in the sample was 35. This study uses panel data regression analysis for data analysis purposes. The results of this study indicate that Financial Target, Financial Stability, External Pressure, Change of Director, Nature of Industry, CEOPicture Audit Opinion and Effective Monitoring have no effect on the potential for fraudulent financial statements. While Change In Auditor and Political Connection have an effect on fraudulent financial statements in the Property and Real Estate sector.

Quantitative and qualitative evaluation of maltodextrin products in the industry using near‐infrared spectroscopy

SummaryMaltodextrin is a crucial ingredient in food and pharmaceutical sectors. Traditional quality assessment methods for maltodextrin are destructive and time consuming. This study aimed to employ near‐infrared (NIR) spectroscopy and chemometrics to differentiate maltodextrin variants and measure their quality parameters efficiently. NIR spectra were recorded in the range of 12 000–4000 cm−1 using the transflectance mode. The classification model effectively distinguished maltodextrin types based on their dextrose equivalent (DE) values using techniques such as partial least squares‐discriminant analysis and supervised self‐organising map (SSOM). Moreover, quality parameters including moisture content, DE value, maltose, maltotriose, pH, and SO2 were quantitatively assessed using partial least squares regression (PLSR) and SSOM models. Particularly, PLSR provided better results, with residual predictive deviation values exceeding 2.5 for moisture content, DE values, maltose, and maltotriose. These models can be applied for use in both laboratory settings and industrial monitoring.

VIGILÂNCIA SANITÁRIA DAS BOAS PRÁTICAS DE FABRICAÇÃO NAS INDÚSTRIAS ALIMENTÍCIAS PERTENCENTES A GERÊNCIA REGIONAL DE SAÚDE DE SÃO JOÃO DEL REI

Health Surveillance, defined as a set of actions capable of eliminating, reducing, or preventing health risks, carries out health control through inspections, which enable the detection of this risk. In this sense, Food Industries are evaluated through verification of Good Manufacturing Practices (GMP) to ensure the sanitary control of food consumed by the population. Therefore, this work aimed to evaluate the Good Manufacturing Practices of five (5) Food Industries inspected by VISA/GRS/SJDR. To this end, the research method used was the analysis of the checklist of Good Manufacturing Practices in Food Producer/Industrializing Establishments contained in Annex II of Resolution RDC 275/2002 ANVISA. The results found demonstrated that in the period of 5 years (2010 to 2014) in relation to compliance with Good Practice items there was an improvement, even though the majority classified themselves as group 2 (medium risk) at the end of the period. When the list is stratified, it is clear that “Industry and Commerce I.O.” highlighted the isolated attention to sub-items. Finally, it was concluded that continuous monitoring of food producing industries is necessary for constant improvement of sanitary control actions in the food area with a view to protecting the health of the population.

A smart look at monitoring while drilling (MWD) and optimizing using acoustic emission technique (AET)

Monitoring while drilling (MWD) is a crucial task in mining operations. Accurately measuring drill and rock-related operating parameters can significantly reduce the cost of drilling operations. This study explores the potential of monitoring drilling specific energy (SE) and optimizing drilling operations by processing vibroacoustic signals generated while drilling. For this purpose, 30 samples of different rocks, are used for drilling tests. During the drilling process, the acoustic and vibration signals are recorded and analyzed in the time, frequency, and time–frequency domains., and parameters related to the resulting spectra are extracted. After obtaining the vibroacoustic parameters for drilling, the relationship between them and the drilling SE was investigated. There is evidence that the progression of SE contributes to the magnitude of rock drilling vibroacoustic features, which could be employed to indicate energy conditions during drilling. Results obtained in this study have the potential to be used as the basis for an industrial monitoring system that can detect excessive energy consumption and advise the user of the end of the bit's useful life. This method can be an intelligent technique for measuring the behavior of real-time drilling operations based on the SE simply by installing vibroacoustic sensors on the drilling machines.

Explainable AI (XAI) Techniques for Convolutional Neural Network-Based Classification of Drilled Holes in Melamine Faced Chipboard

The furniture manufacturing sector faces significant challenges in machining composite materials, where quality issues such as delamination can lead to substandard products. This study aims to improve the classification of drilled holes in melamine-faced chipboard using Explainable AI (XAI) techniques to better understand and interpret Convolutional Neural Network (CNN) models’ decisions. We evaluated three CNN architectures (VGG16, VGG19, and ResNet101) pretrained on the ImageNet dataset and fine-tuned on our dataset of drilled holes. The data consisted of 8526 images, divided into three categories (Green, Yellow, Red) based on the drill’s condition. We used 5-fold cross-validation for model evaluation and applied LIME and Grad-CAM as XAI techniques to interpret the model decisions. The VGG19 model achieved the highest accuracy of 67.03% and the lowest critical error rate among the evaluated models. LIME and Grad-CAM provided complementary insights into the decision-making process of the model, emphasizing the significance of certain features and regions in the images that influenced the classifications. The integration of XAI techniques with CNN models significantly enhances the interpretability and reliability of automated systems for tool condition monitoring in the wood industry. The VGG19 model, combined with LIME and Grad-CAM, offers a robust solution for classifying drilled holes, ensuring better quality control in manufacturing processes.

Ultra-sensitivity in reconstructed exceptional systems

ABSTRACT Sensors are of fundamental importance and widely used in modern society, such as in industry and environmental monitoring, biomedical sample ingredient analysis and wireless networks. Although numerous sensors have been developed, there is a continuous demand for sensors with increased sensitivity, to detect signals that were previously undetectable. Recently, non-Hermitian degeneracies, also known as exceptional points (EPs), have attracted attention as a way of improving the responsiveness of sensors. In contrast to previous investigations, here we present a new approach to achieving ultra-sensitivity by reconstructing exceptional systems. In the reconstruction process, some eigenstates near the previous EPs are utilized, and non-reciprocal long-range couplings are introduced. The sensitivities of our reconstructed systems have improved by several orders of magnitude compared to those based on EPs. Furthermore, we design and fabricate corresponding integrated circuit sensors to demonstrate the scheme. Our work paves the way for the development of highly sensitive sensors, which have a wide range of applications in various fields.

Real-time IoT-powered AI system for monitoring and forecasting of air pollution in industrial environment

Air pollution in industrial environments, particularly in the chrome plating process, poses significant health risks to workers due to high concentrations of hazardous pollutants. Exposure to substances like hexavalent chromium, volatile organic compounds (VOCs), and particulate matter can lead to severe health issues, including respiratory problems and lung cancer. Continuous monitoring and timely intervention are crucial to mitigate these risks. Traditional air quality monitoring methods often lack real-time data analysis and predictive capabilities, limiting their effectiveness in addressing pollution hazards proactively. This paper introduces a real-time air pollution monitoring and forecasting system specifically designed for the chrome plating industry. The system, supported by Internet of Things (IoT) sensors and AI approaches, detects a wide range of air pollutants, including NH3, CO, NO2, CH4, CO2, SO2, O3, PM2.5, and PM10, and provides real-time data on pollutant concentration levels. Data collected by the sensors are processed using LSTM, Random Forest, and Linear Regression models to predict pollution levels. The LSTM model achieved a coefficient of variation (R²) of 99 % and a mean absolute percentage error (MAE) of 0.33 for temperature and humidity forecasting. For PM2.5, the Random Forest model outperformed others, achieving an R² of 84 % and an MAE of 10.11. The system activates factory exhaust fans to circulate air when high pollution levels are predicted to occur in the next hours, allowing for proactive measures to improve air quality before issues arise. This innovative approach demonstrates significant advancements in industrial environmental monitoring, enabling dynamic responses to pollution and improving air quality in industrial settings.

Continuous emission monitoring the trace Sr from simulant aerosol emission with LIPS

Continuous emission monitoring (CEM) of strontium in aerosols is of great significance for air pollution prevention and industrial facilities emission monitoring. Laser-induced plasma spectroscopy (LIPS, also LIBS) is a promising technology for direct and online monitoring aerosols because of the advantages of no sample preparation, rapid analysis, and online detection. An enhanced LIPS setup with high detection sensitivity and short detection cycles is integrated to meet the demand for continuous monitoring of trace element aerosols. The continuous monitoring of strontium in aerosols is introduced with an improved LIPS setup. The setup is calibrated and tested with different concentrations of strontium aerosols generated by aerosol generators. The enhanced LIPS setup can quantify 22 ng/m3 strontium in aerosol within 10 min. Based on experiments, a calibration curve for the strontium aerosol is established and the limit of detection (LOD) of the setup reaches 1.8 ng/m3, which meets the need for continuous monitoring of trace elements.

Fault diagnosis of complex industrial equipment based on chunked statistical global-local feature fusion

Abstract Industrial process equipment is bulky and complex in structure, which is easy to produce faults during operation and affect production efficiency, cause huge economic losses, and even threaten the safety of workers. To achieve sustainable operation of large-scale industrial processes, timely and accurate monitoring and handling of abnormal situations are essential. However, fault monitoring of large equipment requires the collection of abundant data, which includes many complex related variables, resulting in excessive redundant data generated during the fault monitoring process. Moreover, the existing principal component analysis (PCA) method can only retain the global characteristic of variance information, and cannot obtain the local characteristic that can characterize the topological relationship between the data points, which affects its monitoring reliability and intelligence level. In response to these issues, a fault diagnosis model for complex industrial processes based on chunked statistical global-local feature fusion (CSGLFF) is proposed in this paper. First, considering the correlation characteristics between industrial process variables, a correlation variable chunking method mutual information-based is designed to merge the variables with small correlation to obtain the optimal chunking of variables. Second, PCA and locality preserving projections (LPP) are combined to construct a global-local feature fusion (GLFF) model that can extract global and local features simultaneously. The chunked data are imported into the GLFF for the extraction of its features respectively, and the corresponding CSGLFF is established. In addition, Bayesian inference is used to fuse the statistics of each sub-chunk to establish an overall fault monitoring statistical indicators, and the reason for failure is found through the variable contribution graph. Finally, two cases of Tennessee Eastman process (TEP) and laboratory emulsion pump were used to conduct experimental research on the performance of CSGLFF. The results show that compared with the chunked statistical PCA, chunked statistical LPP, and GLFF algorithms, The accuracy of fault monitoring for TEP mean, flow pulsation impact, and pressure anomaly of this method reached 92.91%, 97%, and 90.30%, respectively. It has good monitoring effect in processing data with large variables, reducing the generation of redundant data, improving the accuracy of industrial monitoring, and accurately identifying the relevant variables of fault occurrence. This provides a theoretical basis for determining the fault location and points out the direction for maintenance by staff.

Detection of volatile primary aliphatic amines: Highly selective and sensitive vapoluminescent sensing of n-butylamine

Detection of volatile amines is of great interest for environmental and industrial monitoring for the protection of human health from exposure to toxic substances. This contribution describes the vapochromic and vapoluminescent properties of a Lewis acidic Zn(salen)-type Schiff-base complex and its application as a chemosensor for detection of n-butylamine (BA) vapors. Annealed films of the complex were initially involved for vapochromic and vapoluminescence screening experiments to evaluate their response towards compounds representative of each of the different chemical classes of volatile organic compounds (VOCs). Then, a cost-effective, disposable paper-based vapoluminescent sensor, characterized by high optical uniformity and repeatability, was developed for the selective and sensitive direct in-situ detection of BA vapors. Under static exposure conditions, the sensor allows a sensitive vapoluminescent detection of BA, with a LOD down to 2.0 ppm, below the permissible exposure limit of 5 ppm established by OSHA for BA, and a linear dynamic range up to 50 ppm. The sensor response is not affected by the exposure temperature, only a different exposure time is required as the temperature varies, while average relative humidity levels lead to almost negligible changes in the sensor response. The sensor is highly selective for BA with respect to ammonia and the different chemical classes of VOCs, including relevant primary aliphatic amines, with the exception of propylamine and sec-butylamine, especially at low concentrations (tens of ppm). Selectivity for BA is also demonstrated by competitive experiments in the presence of a 10-fold ppm amount of all representative VOCs of each class as potential interferents.

Portable and ultrasensitive detection of traces of water in alcoholic solvents by a polypyrrole-modified screen-printed electrode

In industrial production, the water content in alcoholic solvents is crucial for determining the quality and yield of the final products, and excessive water can potentially lead to accidents. However, in-situ, rapid, and accurate detection of trace amounts of water in alcoholic solvents has been a persistent challenge. Herein, we report a screen-printed electrode (SPE) modified with electroactive polypyrrole (PPy@SPE), which enables rapid and ultrasensitive quantification of water content in four alcoholic solvents. The amine groups on PPy provide hydrogen bonding sites, which, in conjunction with the rough surface of the SPE, enhance the adsorption of alcohol molecules and decrease the electrochemical response of the PPy@SPE due to the hindrance of charge transfer. Under optimal conditions, the PPy@SPE can detect water levels as low as 0.02 %, 0.01 %, 0.01 %, and 0.01 %, in methanol, ethanol, n-propanol, and isopropanol, respectively, and can be reused for six cycles or more. Furthermore, the capability for in-situ detection of water in alcoholic solvents was demonstrated by integrating the PPy@SPE with a miniaturized potentiostat. With the advantages of being ultrasensitive, robust, low-cost, and facile detection, this sensor is potentially a valuable tool for on-site water content monitoring in chemical industries.

Wide-field imaging and recognition through cascaded complex scattering media

Considering the obvious application value in the field of minimally invasive and non-destructive clinical healthcare, we explore the challenge of wide-field imaging and recognition through cascaded complex scattering media, a topic that has been less researched, by realizing wide-field imaging and pathological screening through multimode fibers (MMF) and turbid media. To address the challenge of extracting features from chaotic and globally correlated speckles formed by transmitting images through cascaded complex scattering media, we establish a deep learning approach based on SMixerNet. By efficiently using the parameter-free matrix transposition, SMixerNet achieves a broad receptive field with less inductive bias through concise multi-layer perceptron (MLP). This approach circumvents the parameter's intensive requirements of previous implementations relying on self-attention mechanisms for global receptive fields. Imaging and pathological screening results based on extensive datasets demonstrate that our approach achieves better performance with fewer learning parameters, which helps deploy deep learning models on desktop-level edge computing devices for clinical healthcare. Our research shows that, deep learning facilitates imaging and recognition through cascaded complex scattering media. This research extends the scenarios of medical and industrial imaging, offering additional possibilities in minimally invasive and non-destructive clinical healthcare and industrial monitoring in harsh and complex scenarios.

Metal-Organic Frameworks in Surface Enhanced Raman Spectroscopy-Based Analysis of Volatile Organic Compounds.

Volatile Organic Compounds (VOC) are a major class of environmental pollutants hazardous to human health, but also highly relevant in other fields including early disease diagnostics and organoleptic perception of aliments. Therefore, accurate analysis of VOC is essential, and a need for new analytical methods is witnessed for rapid on-site detection without complex sample preparation. Surface-Enhanced Raman Spectroscopy (SERS) offers a rapidly developing versatile analytical platform for the portable detection of chemical species. Nonetheless, the need for efficient docking of target analytes at the metallic surface significantly narrows the applicability of SERS. This limitation can be circumvented by interfacing the sensor surface with Metal-Organic Frameworks (MOF). These materials featuring chemical and structural versatility can efficiently pre-concentrate low molecular weight species such as VOC through their ordered porous structure. This review presents recent trends in the development of MOF-based SERS substrates with a focus on elucidating respective design rules for maximizing analytical performance. An overview of the status of the detection of harmful VOC is discussed in the context of industrial and environmental monitoring. In addition, a survey of the analysis of VOC biomarkers for medical diagnosis and emerging applications in aroma and flavor profiling is included.

A Sustainable Free-Standing Triboelectric Nanogenerator Made of Flexible Composite Film forBrake Pattern Recognition in Automobiles.

In recent years, the automotive industry has made significant progress in integrating multifunctional sensors to improve vehicle performance, safety, and efficiency. As the number of integrated sensors keeps increasing, there is a growing interest in alternative energy sources. Specifically, self-powered sensor systems based on energy harvesting are drawing much attention, with a main focus on sustainability and reducing reliance on typical batteries. This paper demonstrates the use of triboelectric nanogenerators (TENGs) in a computer mouse for efficient energy harvesting and in automobile braking systems for safety applications using SrBi2Ta2O9 (SBTO) perovskite, blended PDMS composite operating in free-standing mode with an interdigitated patterned aluminum electrode. This self-powered sensor is capable of distinguishing between normal and abnormal braking patterns using digital signal processing techniques. It is noteworthy that the addition of 15%wt. of the SBTO in PDMS composite-based TENG delivered 13.5V, 45nA, and an output power of 0.98µW. This new combination of energy harvesting and safety applications enables real-time monitoring and predictive maintenance in the automotive industry.

Firefighter Hose Rolling Method: Low Back Pain Risks Analysis with Full-Factorial Approach

Firefighters frequently face the risk of Low back pain (LBP) due to the strenuous nature of their duties, especially during hose rolling tasks. Prioritizing their safety and health is vital. This study aimed to evaluate and compare various hose rolling techniques to lower the LBP risk in firefighters. A full-factorial approach was employed to exhaustively examine every possible combination of three key factors: the hose rolling method (conventional, mechanical, motorized), hose condition (dry, wet, dirty), and hose length (10, 20, 30 meters). Across 27 different trials, an Industrial Lumbar Motion Monitor (iLMM) was used to assess the LBP risk, which is lift rate, average twisting velocity, maximum moment, maximum sagittal flexion, and maximum lateral velocity. The study's results indicated that conventional method had the highest LBP risk at 58.22%, with mechanical rolling at 34.33%. In contrast, the motorized hose rolling method showed a significantly lower risk, averaging at 17.44%. This denotes a 40.78% reduction in LBP risk compared to conventional hose rolling method, positioning the motorized roller as the most effective and safest option among those tested. This method's efficacy underscores its potential as a viable solution for improving firefighter safety. These findings offer important insights into occupational health and safety in firefighting. The data suggests that adopting motorized hose rolling tools could significantly alleviate the physical burdens and associated health hazards firefighters face. This advancement is a critical step towards enhancing their overall safety and well-being in the field.

Flexible ammonium ion-selective electrode based on inkjet-printed graphene solid contact

Miniaturization and mass-production of potentiometric sensor systems is paving the way towards distributed environmental sensing, on-body measurements and industrial process monitoring. Inkjet printing is gaining popularity as a highly adaptable and scalable production technique. Presented here is a scalable and low-cost route for flexible solid-contact ammonium ion-selective electrode fabrication by inkjet printing. Utilization of inkjet-printed melamine-intercalated graphene nanosheets as the solid-contact material significantly improved charge transport, while evading the detrimental water-layer formation. External polarization was investigated as a means of improving the inter-electrode reproducibility: the standard deviations of E0 values were reduced after electrode polarization, the linear region of the response was extended to the range 10−1–10−6 M of NH4Cl and LODs reduced to 0.88 ± 0.17 μM. Finally, we have shown that the electrodes are adequate for measurements in a complex real sample: ammonium concentration was determined in landfill leachate water, with less than 4 % deviation from the reference method.

Combination of generic novelty detection and supervised classification pipelines for industrial condition monitoring

Abstract Machine learning in industrial condition monitoring is currently a rapidly developing field of research, to improve the efficiency and reliability of industrial processes. Many of the used algorithms are supervised methods, which can learn and recognize hidden patterns in the data. However, training data is required to learn these patterns, which can only be generated to a limited extent in an industrial environment due to the high costs involved. Furthermore, it is impossible to represent all possible events in the training data. In contrast, unsupervised or semi-supervised methods can be used to detect new conditions or events. However, these usually do not allow diagnosis or quantification of a fault condition, which is why their usefulness for modern maintenance strategies is limited. Consequently, a robust condition monitoring system should combine the functionality of both approaches. This paper presents a methodology for the combination of supervised classification and semi-supervised novelty detection to build an expandable and adaptable condition monitoring by transferring recurring novelties as new conditions to the supervised classification. A superordinate algorithm is proposed to achieve a stepwise extension of the supervised model based on new conditions detected by novelty detection. With this approach, a condition monitoring system can at first be based on “normal” data of a new machine or process by adding failures or novel conditions step-by-step. Furthermore, the supervised methods can be used to help the corresponding staff identify unknown conditions by analyzing the features selected by the supervised classification. The general workflow is demonstrated for condition monitoring of the pneumatic drive system of a welding gun.

Experimental Assessment of Paper Formation Conditions and Structural Two-Sidedness and Their Impacts on Curl Phenomena

Curl propensity is a critical-to-quality (CTQ) property of paper, as it causes severe problems during printing and other final conversion operations. The main papermaking factor causing the curl phenomenon is the existence of a fiber orientation (FO) gradient across the thickness direction (or ZD), also known as two-sidedness. Therefore, a methodology that characterizes the FO across the ZD is fundamental for papermakers. In this work, we propose and validate an efficient and cost-effective protocol based on sheet splitting and image analysis. Besides assessing the level of FO two-sidedness, the methodology also provides insights into the flow dynamics in the draining zone of the forming section of the paper machine and the drying stresses built into the paper. This information is relevant for monitoring, optimizing, and troubleshooting activities in the paper industry.