Process Monitoring Research Articles

A Pragmatic Approach for Rapid, Non-Destructive Assessment of Defect Types in Laser Powder Bed Fusion Based on Melt Pool Monitoring Data.

Process monitoring systems, e.g., systems based on photodiodes, could be used in laser-based powder bed fusion (PBF-LB/M) to measure various process parameters and process signatures to eventually allow for a local, detailed analysis of the produced parts. Here, simple statements only concerning the occurrence of defects in parts are sufficient in many cases, especially with respect to industrial application. Therefore, a pragmatic approach to rapidly infer the occurrence of defects and their types based on in situ data obtained by commercially available process monitoring systems is introduced. In this approach, a color distribution in form of a histogram is determined for each produced part using layer-wise screenshots of the visualized data provided by the monitoring software. Assessment of the histograms of AlSi10Mg samples, which were processed with different parameter combinations, revealed characteristics depending on the prevailing defect types. These characteristics enable the prediction of the occurring defect types without the necessity to apply conventional downstream testing methods, and thus, a straightforward separation of parts with good quality from defective components. Since the approach presented uses the data visualization of the monitoring software, it can be used even when direct access to the raw data is not provided by the machine manufacturer.

Brainwaves in the Cloud: Cognitive Workload Monitoring Using Deep Gated Neural Network and Industrial Internet of Things

Monitoring and classifying cognitive workload in real time is vital for optimizing human–machine interactions and enhancing performance while ensuring safety, particularly in industrial scenarios. Considering this significance, the authors aim to formulate a cognitive workload monitoring system (CWMS) by leveraging the deep gated neural network (DGNN), a hybrid model integrating bi-directional long short-term memory (Bi-LSTM) and gated recurrent unit (GRU) networks. In our experimental setup, each of the four virtual users is equipped with a Raspberry Pi Zero W module to ensure efficient data transmission, thereby enhancing the reliability and efficacy of the monitoring process. This seamless monitoring framework utilizes the constrained application protocol (CoAP) and the Things Board platform to evaluate cognitive workload in real time. The most popular EEG benchmark dataset, the STEW is utilized for workload classification in this study. We employ the short-time Fourier transformation (STFT) to extract frequency bands corresponding to users in both high and low cognitive workload modes. The proposed DGNN models achieve a perfect accuracy of 99.45%, outperforming every previous state-of-the-art model. We meticulously monitored critical parameters, including latency, classification processing time, and cognitive workload levels. This research demonstrates the importance of continuous monitoring for increasing productivity and safety in industries by introducing a novel method of real-time cognitive workload monitoring. The implementation codes for each experiment are documented and made available for reproducibility.

Smart Field Technologies in Petroleum Engineering (Control and Monitoring)

Aim of study is provide an introductory overview of “smart well” technologies in terms of control and monitoring, with the hope of contributing to the development of Libyan oil and gas fields and turning them into smart fields because the principle in petroleum engineering stipulates maximum profit, fastest time, least cost, maximum efficiency, minimum risk. Smart field technology can operate equipment automatically, improve oil field management, scientifically assist oil fields in decision making, monitor wells in real time, manage and monitor operations and control production, as well as predict potential risks and choose the best scenario for dealing with crises. This paper presents the definition and principle of smart wells and fields technology, a comparison between the types of smart technologies, their advantages and disadvantages, and how this technology contributes to the control and monitoring of oil and gas wells. Smart wells are technologies that use intelligent systems to improve the control and monitoring process in oil and gas wells. These technologies use the Skida system, wireless sensors, and data analytics, which use artificial intelligence to monitor and control operations within oil fields and facilities. Smart oil fields rely on wireless sensors and the Industrial Internet of Things. This technology makes it easier for oil companies to control performance, monitor in real time, and manage oil and gas fields, and makes it easier for management to make decisions. WSN is the most widespread technology used in oil and gas fields, as it provides sensors for remote control and monitoring and detecting faults if they occur. Internet of Things helps improve control and monitoring, as it is the operating system used by wireless sensors and connects them to the network so that we can control them.

Enhancing refinery heavy oil fractions analytical performance through real-time predicative modeling.

This study introduces a suite of robust models aimed to advance the determination of physiochemical properties in heavy oil refinery fractions. By integrating real-time analytical technique inside the refinery analysis, we have developed a single analyzer capable of employing six partial least square regression equations. These designed models enable to provide real-time prediction of critical petroleum properties, such as sulfur content, micro carbon residues (MCR), asphaltene content, heating value, and the concentrations of nickel and vanadium metals. Specifically tailored for heavy oil in refinery feeds with an American petroleum institute (API) gravity range of 3° to 32° and sulfur content of 2.8 to 5.5 wt%, the models streamline the analysis process within refinery operations, bridging the gap between catalytic and non-catalytic processes across refinery units. The accuracy of our physiochemical prediction models has been validated against American Society for Testing and Materials (ASTM) standards, demonstrating their capability to deliver precise real-time property values. This approach not only enhances the efficiency of refinery analysis but also sets a new standard for the monitoring and optimization of heavy oil processing in real-time approach.

IoT-driven reflectance-based multimode colorimeter for real-time monitoring of crystallization process: A study on oleogels

This study explores the application of an Internet of Things (IoT)-driven reflectance-based multimode colorimeter for real-time monitoring of the crystallization process in oleogels-a novel class of structured lipids gaining popularity in the food industries. These structured lipids offer a healthier alternative to solid fats, but their texture and stability rely on precise control of crystallization process. Traditional monitoring methods, such as atomic force microscopy and spectroscopy, are expensive and lack real-time capabilities. The proposed device can operate in two modes: quality testing and process monitoring modes. In the quality testing mode, the device exhibits superior color accuracy compared to a commercial device, making it a reliable tool for color assessment (ΔE values < 10). In the process monitoring mode, the device effectively tracks crystallization kinetics at different incubation temperatures (5 °C, 15 °C, and 25 °C), revealing the impact of sunflower lecithin on primary and secondary crystallization phases. Further, the temperature vs. L* data offers more profound insights into oleogel crystallization, validated by Differential Scanning Calorimetry (DSC) analysis. Additionally, the device's performance was tested by monitoring the crystallization process of butter. The results obtained from the device closely matched the DSC findings, which enhanced our understanding of the crystallization processes in butter. This showcases the potential of the device for analyzing food samples.

Blend uniformity monitoring in a continuous manufacturing mixing process for a low-dosage formulation using a stream sampler and near infrared spectroscopy

Continuous manufacturing has the potential to offer several benefits for the production of oral solid dosage forms, including reduced costs, low-scale equipment, and the application of process analytical technology (PAT) for real-time process control. This study focuses on the implementation of a stream sampler to develop a near infrared (NIR) calibration model for blend uniformity monitoring in a continuous manufacturing mixing process. Feeding and mixing characterizations were performed for three loss-in-weight feeders and a commercial continuous mixer to prepare powder blends of 2.5–7.5 % w/w ibuprofen DC 85 W with a total throughput of 33 kg/h. The NIR spectral acquisition was performed after the mixing stage using a stream sampler for flowing powders. A continuous mixer shaft speed of 250 RPM was selected to operate the mixing process based on a variability analysis developed with in-line spectral data acquired using the stream sampler at 6 RPM. A partial least squares regression (PLS-R) model was performed and evaluated, yielding a root-mean-square error of prediction (RMSEP) of 0.39 % w/w and a bias of 0.05 % w/w. An independent experimental run conducted two days later revealed that the continuous mixing process and the NIR calibration model presented low day-to-day variation. The minimum practical error (MPE) and sill values through variographic analysis showed low variance associated with the sampling process using the stream sampler. Results demonstrated the promising capacity of the stream sampler coupled to an NIR probe to be implemented within continuous manufacturing processes for the real-time determination of API concentration.

Adaptive two-dimensional subspace identification for monitoring batch processes with limited batch data

Data-driven based batch process monitoring is of critical importance in ensuring stable operating processes and consistent product quality. For long-duration batch processes, it is unrealistic to involve expensive data to train a statistical model for monitoring. To model the inherently batch-wise and variable-wise dynamics, nonlinearity, and time-varying characteristics, this paper proposes a local learning-based two-dimensional subspace identification (LL-2D-SID) scheme based on the similarity between the ongoing batch and the previous batches. The similarity is estimated by the extended extrapolative time-warping. Unlike the conventional statistical models using rich batch data, LL-2D-SID through online optimizing mechanism using limited batch data still has good prediction performance. The application of the sintering process in the polytetrafluoroethylene production has demonstrated that the LL-2D-SID based process monitoring scheme can not only accurately track temperature changes but also timely give fault alarms with a lower error alarm rate than the other SID-based process monitoring schemes.

Assessing the economic-statistical performance of an attribute SVSSI-np control chart based on genetic algorithms

The SVSSI scheme, featuring three variable sample sizes and two variable sampling intervals, considerably enhances the performance of control charts in detecting shifts. As a novel contribution, this study proposes an optimized design of the SVSSI-np control chart using genetic algorithms, illustrating its superior performance over other sampling schemes by considering economic and statistical perspectives in a unified model. The outcomes of implementing the SVSSI alongside other sampling schemes are assessed via a numerical example, demonstrating the influence of varying parameters such as process failure rate, shift value, and proportion of nonconforming items. Based on the obtained results, the SVSSI scheme outperforms other schemes by achieving over a 10% reduction in costs and over a 30% improvement in reducing time to signal and false alarm rates in most runs. The impact of inaccurately estimating the shift size is also investigated, revealing that incorrect estimates can lead to ineffective adjustments and improvements. Finally, optimal SVSSI designs are explored through comprehensive sensitivity analysis and robust optimization to address uncertainty, and the results of applying fractional factorial design are statistically analyzed. In summary, the SVSSI-np control chart demonstrates potential for enhanced cost reduction, process monitoring, and efficiency gains.

State of the Art and Future Trends in Monitoring for Industrial Induction Heating Applications

Induction surface hardening (ISH) processes are widely used in the heat treatment of numerous industrial components, especially in the automotive industry. Since this industry operates under very demanding quality standards, it is crucial for these heat treatment processes to meet rigorous specifications to ensure the safety and reliability of the produced components. This implies the precise and repeatable control of certain parameters throughout the manufacturing process of each of the parts treated, through precise and reliable instrumentation in electromagnetically harsh environments. The main objective of this work is to define the monitoring process for an industrial IHS application, determining the control needs and the methods of measurement, recording, and verification of the parameters that ensure the quality of the process. This paper describes the monitoring process of induction surface hardening, emphasizing the use of sensors and modern measurement and control systems. A comprehensive monitoring system supported by a programmable logic controller (PLC) and mixed acquisition and instrumentation systems (analog and digital) implemented with a high-performance Field Programmable Gate Array (FPGA) will be presented.

Fault Diagnosis and Prediction System for Metal Wire Feeding Additive Manufacturing.

In the process of metal wire and additive manufacturing, due to changes in temperature, humidity, current, voltage, and other parameters, as well as the failure of machinery and equipment, a failure may occur in the manufacturing process that seriously affects the current situation of production efficiency and product quality. Based on the demand for monitoring of the key impact parameters of additive manufacturing, this paper develops a parameter monitoring and prediction system for the additive manufacturing feeding process to provide a basis for future fault diagnosis. The fault diagnosis and prediction system for metal wire supply and additive manufacturing utilizes STM 32 as its core, enabling the capture and transmission of temperature, humidity, current, and voltage data. The upper computer system, designed on the LabVIEW 2019 virtual instrument platform, incorporates an LSTM neural network model and facilitates a connection between LabVIEW and MATLAB 2019 to achieve the prediction function. The monitoring and prediction system established in this study is intended to provide basic research assistance in the field of fault diagnosis.

LS-ICE: A Load State Intercase Encoding framework for improved predictive monitoring of business processes

Research on developing techniques for predictive process monitoring has generally relied on feature encoding schemes that extract intra-case features from events to make predictions. In doing so, the processing of cases is assumed to be solely influenced by the attributes of the cases themselves. However, cases are not processed in isolation and can be influenced by the processing of other cases or, more generally, the state of the process under investigation. In this work, we propose the LS-ICE (load state intercase encoding) framework for encoding intercase features that enriches events with a depiction of the state of relevant load points in a business process. To assess the benefits of the intercase features generated using the LS-ICE framework, we compare the performance of predictive process monitoring models constructed using the encoded features against baseline models without these features. The models are evaluated for remaining trace and runtime prediction using five real-life event logs. Across the board, a consistent improvement in performance is noted for models that integrate intercase features encoded through the proposed framework, as opposed to baseline models that lack these encoded features.

Innovations in nondestructive assessment of baked products: Current trends and future prospects.

Rising consumer awareness, coupled with advances in sensor technology, is propelling the food manufacturing industry to innovate and employ tools that ensure the production of safe, nutritious, and environmentally sustainable products. Amidst a plethora of nondestructive techniques available for evaluating the quality attributes of both raw and processed foods, the challenge lies in determining the most fitting solution for diverse products, given that each method possesses its unique strengths and limitations. This comprehensive review focuses on baked goods, wherein we delve into recently published literature on cutting-edge nondestructive methods to assess their feasibility for Industry 4.0 implementation. Emphasizing the need for quality control modalities that align with consumer expectations regarding sensory traits such as texture, flavor, appearance, and nutritional content, the review explores an array of advanced methodologies, including hyperspectral imaging, magnetic resonance imaging, terahertz, acoustics, ultrasound, X-ray systems, and infrared spectroscopy. By elucidating the principles, applications, and impacts of these techniques on the quality of baked goods, the review provides a thorough synthesis of the most current published studies and industry practices. It highlights how these methodologies enable defect detection, nutritional content prediction, texture evaluation, shelf-life forecasting, and real-time monitoring of baking processes. Additionally, the review addresses the inherent challenges these nondestructive techniques face, ranging from cost considerations to calibration, standardization, and the industry's overreliance on big data.

Lanthanide metal-organic frameworks as ratiometric fluorescent probes for real-time monitoring of PFOA photocatalytic degradation process

The assessment of perfluorooctanoic acid (PFOA) photocatalytic degradation usually involves tedious pre-treatment and sophisticated instrumentation, making it impractical to evaluate the degradation process in real-time. Herein, we synthesized a series of lanthanide metal-organic frameworks (Ln-MOFs) with outstanding fluorescent sensing properties and applied them as luminescent probes in the photocatalytic degradation reaction of PFOA for real-time evaluation. As the catalytic reaction proceeds, the fluorescence color changes significantly from green to orange-red due to the different interaction mechanisms between the electron-deficient PFOA and smaller radius F− with the ratiometric fluorescent probe MOF-76 (Tb: Eu = 29:1). The limit of detection (LOD) was calculated to be 0.0127 mM for PFOA and 0.00746 mM for F−. In addition, the conversion rate of the catalytic reaction can be read directly based on the chromaticity value by establishing a three-dimensional relationship graph of G/R value-conversion rate-time (G/R indicates the ratio between green and red luminance values in the image.), allowing for real-time and rapid tracking of the PFOA degradation. The recoveries of PFOA and F− in the actual water samples were 99.3–102.7% (RSD = 2.2–4.4%) and 100.7–105.3% (RSD = 3.9–6.8%), respectively. Both theoretical calculations and experiments reveal that the detection mechanism was attributed to the photoinduced electron transfer and energy transfer between the analytes and the probe. This method simplifies the sample analysis process and avoids the use of bulky instruments, and thus has great potential on the design and development of quantitative time-resolved visualization methods to assess catalytic performance and reveal mechanisms.

Monitoring of absorptive model biogas purification process using sensor matrices and gas chromatography

This study examined the process of purifying model biogas using a new type of absorbent based on a Deep Eutectic Solvent (DES) and a commercially available absorbent (Genosorb) to remove acetone, toluene, and cyclohexane. The main aim of the research was to control the purification efficiency using gas chromatography (GC) and an alternative method based on sensor matrices (SM). As a result of comparing the multidimensional SM signals with the GC result, the lowest difference between SM and GC (3.69%) was achieved with the DES. When using Genosorb, the differences between the methods were slightly more pronounced, reaching 10.26%. The studies also confirmed that SM results showed significant agreement, accuracy, precision, and equivalence compared to GC results. Nowadays, the literature has not reported this issue. The presented research fills the current gap in the literature and contributes to the development of knowledge in the practical application of SM.

Integration of maintenance policy and statistical process monitoring for a cascade process with multiple assignable causes and random failures

This study develops an integrated model of statistical process monitoring and maintenance policy (MP) for a two-stage cascade process, involving two machines in series where the output of one stage affects the next stage. Instead of a single assignable cause (AC) affecting the quality characteristic, this production process experiences multiple ACs to more precisely simulate real conditions. Traditional and Hotelling’s T2 charts cannot detect the specific stage in which a shift occurs; therefore, this study employs a Cause-selecting control chart. The possibility of equipment failure and system stoppage are considered, with the process failure mechanism following a Weibull distribution. Depending on the conditions affecting the process or equipment, four MPs are considered to acheive the system’s initial condition, resulting in sixteen defined scenarios. The goal is to determine decision variables by minimizing a cost function subject to some statistical measures. This economic-statistical design can improve statistical and/or economic measures. However, it creates a more complex problem. Due to this complexity, a particle swarm optimization algorithm is used for optimization. The proposed model is implemented for a system that produces cotton yarn, with fiber length and skein strength are as the outputs of the first and second stages, respectively. Comparisons with two models validate the proposed model’s performance in cost reduction. A sensitivity analysis is performed for further investigations. The results indicate significant cost savings of the proposed model.

Magnetoelastic resonators functionalized with metal–organic framework water harvesters as wireless humidity sensors

Relative humidity is a crucial parameter in several fields, such as air quality monitoring, food storage, or control of industrial processes. In this study, we propose a wireless humidity sensor based on magnetoelastic resonance sensors functionalized with Metal–Organic Frameworks (MOFs). Different MOF water harvesters were tested as sensor active coatings: MOF-801, MOF-808, UiO-66-NH2, Al-Fumarate, and CAU-23. Their water absorption capacity and overall performance, when integrated into the sensors, were evaluated. As expected, the selected MOFs showed promising water harvesting capacity, enabling a successful sensor response to humidity in a wide range of relative humidity: 3%–85%. These humidity sensors showed a great sensitivity, stability, and selectivity to water molecules. The response time of the devices was around 15 s, with stabilization and recovery times in adsorption and desorption processes of less than 1 min for certain ranges of operation. In addition to the satisfactory behavior as humidity sensors, magnetoelastic resonators have emerged as a promising tool for the characterization of the dynamic adsorption capacity of MOF materials, as they easily provide a quantitative measure of the water mass adsorbed by the material.

Real-time multivariate statistical monitoring of biopharmaceutical processes with no prior product-specific history

Biologics drug substance manufacturing normally comprises several processing steps including cell culture, purification, etc. Real-time Multivariate Statistical Process Monitoring (RT-MSPM) is an integral need in order to achieve early fault detection and prevention to guarantee robust and efficient process performance. As a part of RT-MSPM framework, Batch Evolution Models (BEMs), which take into account the transient phase of a batch prior to reaching full maturity (steady state), are the standard methods for real-time early fault detection in batch processes. Prior product-specific knowledge and training dataset are critical in order to model time (batch maturity) dependencies. Unlike traditional settings, modern biopharmaceutical manufacturing and clinical facilities use modular designs to enable simultaneous production of multiple medicines and quickly pivot from producing one medicine to another where no prior product-specific historical data might be available. In this article, first, a framework is proposed to detect the steady state operation of a manufacturing scale cell culture bioreactor. This is critical to achieve the ultimate goal to demonstrate feasibility of developing a continuous statistical process monitoring framework to monitor the steady state operation of a batch with no prior product specific history. Steady state time series data from previous step are processed following a systematic approach. The requirements for statistical properties of the processed time series in order to leverage data from different products to monitor a new product are outlined. The new framework establishes a guideline to develop models using datasets from other products with different recipes to monitor new products with no prior product-specific history. A novel software product is developed to test the framework. The framework is successfully applied for real-time monitoring of fast-rate sensors of a manufacturing cell culture bioreactor.

Nanostructured transition metal dichalcogenides-based colorimetric sensors: Synthesis, characterization, and emerging applications.

Nanostructured transition metal dichalcogenides (TMDCs) have garnered significant attention as prospective materials for the development of highly sensitive and versatile colorimetric sensors. This work explores the synthesis, characterization, and emerging applications of TMDC-based sensors, focusing on their unique structural aspects and inherent properties. The synthesis methods involve tailored fabrication techniques, such as chemical vapor deposition and hydrothermal processes, aimed at producing well-defined nanostructures that enhance sensor performance. Characterization techniques, including microscopy, spectroscopy, and surface analysis, are employed to elucidate the structural and chemical features of the nanostructured TMDCs. These analyses provide insights into the correlation between the material's morphology and its sensing capabilities. The colorimetric sensing mechanism relies on the modulation of optical properties in response to specific analytes, enabling rapid and visual detection. The emerging applications of TMDC-based colorimetric sensors span diverse fields, including environmental monitoring, healthcare, and industrial processes. The sensors exhibit high sensitivity, selectivity, and real-time response, making them ideal candidates for detecting various target analytes. Furthermore, their integration with complementary technologies such as microfluidics, can facilitate the development of on-site and point-of-care applications. This work highlights the interdisciplinary significance of nanostructured TMDC-based colorimetric sensors and underscores their potential contributions to addressing contemporary challenges in sensing technology.

CNNs for remote extraction of urban features: A survey-driven benchmarking

Accurate extraction of urban features such as buildings and roads lays the foundation for the current trends of digital twins of urban systems to support planning, monitoring, navigation, and decision processes. The process of such extraction involves training convolutional neural networks (CNNs) on high-resolution earth observation (EO) images. The spatial resolution of images has increased to a centimetre level and the CNNs are fast evolving in computer vision. The last 10 years of this development have resulted in both high-performance and computationally efficient CNNs, but they are merely benchmarked under a uniform setting. We present a survey-driven benchmark of CNNs starting with a systematic survey of 165 research articles to understand the state-of-the-art of urban feature extraction. The survey looks for the most prominent urban feature, EO source, benchmark dataset, CNN-based deep learning configuration, and hyperparameters. Further, more CNNs are searched in the computer vision domain. Identified from the survey and search, 65 CNNs are trained and evaluated in an encoder–decoder configuration using a benchmark dataset under uniform settings. Extensive hyperparameter tuning of the best-performing CNN is performed with six optimisers and nine loss functions. The tuned CNN is then tested as an encoder in other state-of-the-art encoder–decoder networks. The CNNs and network configurations with the highest scores are further benchmarked on the Massachusetts Building and WHU Building datasets. The findings from this survey-driven benchmark of CNNs will be useful for both academia and industry involved in the science of earth observation and computer vision.

Quantum‐safe Lattice‐based mutual authentication and key‐exchange scheme for the smart grid

AbstractThe smart grid network (SGN) is expected to leverage advances in the Internet of Things (IoT) to enable effective delivery and monitoring of energy. By integrating communication, computing, and information tools like smart sensors and meters to facilitate the process of monitoring, predictions, and management of power usage, the SGN can improve competence of power‐grid architecture. However, the effective deployment of IoT‐powered SGNs hinges on the deployment of strong security protocols. With the advent of quantum computers, classic cryptographic algorithms based on integer factorization and the Diffie‐Hellman assumptions may not be suitable to secure the sensitive data of SGNs. Therefore, in this paper, a secure quantum‐safe mutual authentication and key‐exchange (MAKe) mechanism is proposed for SGNs, that make use of the hard assumptions of small integer solution and inhomogeneous small integer solution problems of lattice. The proposed protocol is intended to offer confidentiality, anonymity, and hashed‐based mutual authentication with a key‐exchange agreement. Similarly, this scheme allows creation and validation of the mutual trust among the smart‐meters (SMs) and neighbourhood‐area network gateway over an insecure wireless channel. A random oracle model is then used to perform the formal security analysis of the proposed approach. A thorough formal analysis demonstrates proposed algorithm's ability to withstand various known attacks. The performance analysis shows that the proposed approach outperforms other comparative schemes with respect to at least 22.07% of minimal energy utilization, 51.48% effective storage and communications costs, as well as 76.28% computational costs, and thus suitable for resource‐constrained SGNs.