Front-end signal processing for metal scrap classification using online measurements based on laser-induced breakdown spectroscopy

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

Geographical analysis of “conflict minerals” utilizing laser-induced breakdown spectroscopy

The application of machine learning (ML) has accelerated the development of laser-induced breakdown spectroscopy (LIBS) in soil analysis. However, analyzing remote LIBS data in real time using ML is challenging due to several factors. Firstly, building robust ML models requires extensive calibration datasets, which are not always possible with limited LIBS experimental data. Secondly, matrix effects can worsen LIBS performance, and changes in sample physical properties or the apparatus can impact the distribution and intensity of emission lines. These issues may lead to concept drift in real-time/online data streaming, causing the relationship between the input and the target spectra to change over time. Consequently, an ML model designed for one LIBS system may not apply to another. To conquer these challenges, we propose a framework based on transfer learning to use limited experimental data and adapt to the emission line variation in the LIBS streaming. A model is first pre-trained using a large labelled source dataset and then fine-tuned with new experimental measurements to classify soil samples. LIBS measurements are conducted with variations in sample properties and experimental parameters to simulate differences in remote LIBS sensors. The collected spectra are fed into the model by chunks, and data evolution is dynamically learned by self-balanced learning to self-adapt to the domain shift. The proposed framework is found effective in improving classification accuracy during data streaming by implementing transfer learning and supporting adaptation compared to the literature. The code of the proposed method is available in the GitHub at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/kelci2017/LIBS_streaming</uri> .

Batteries, recognized as effective energy storage solutions, are considered the main facilitators of the world-wide transition towards clean and renewable energy sources. Among different types of batteries, lithium-ion (Li-ion) variants offer higher energy densities and relatively longer life spans when compared to other types. Nonetheless, a primary concern with these batteries is their lifetime. Batteries undergo various degradation mechanisms under storage and use, significantly impacting their lifespan. To this end, it is crucial to predict the degradation and lifetime of Li-ion batteries under given conditions.Researchers use three main methodologies to perform battery health diagnostics and to predict the lifetime of batteries. One approach revolves around using mechanistic, first-principle electrochemical models, also known as physics-based models. If equipped with proper thermodynamic theories, such models can show promising capabilities; however, holistic degradation prediction with these models is still challenging due to the computational complexities and the multitude of parameters that need to be fine-tuned in this approach. The other common strategy is to use empirical models to predict battery degradation. These models generally entail fewer parameters to be identified and are computationally less intensive to solve. Nonetheless, empirical models can suffer from the accuracy point-of-view as they are constrained to predict degradation trends introduced by certain degradation modes. Another common technique in battery life prediction is to utilize purely data-driven methods, such as machine learning (ML) algorithms, which also have shown promising results in the literature on rapid health predictions. However, these methods require large volumes of experimental data for training and testing ML models to ensure accuracy. In addition, data-driven methods are likely to extrapolate poorly to conditions beyond their training data and are indifferent towards the underlying degradation mechanisms. Recently, physics-informed machine learning (PI-ML) methods have garnered significant attention. They integrate physics-based or empirical models (developed based on physics) with a data-driven approach and allow one to train ML models on a smaller set of experimental data.To the best of the authors’ knowledge, the performance comparison between first-principle and empirical models when integrated within PI-ML remains unclear. Therefore, in this work, we aim to compare these two models when applied to prognostics (capacity forecasting and remaining useful life prediction) of a set of Li-ion batteries. To perform this study, we generate aging data for 40 Li-ion coin cells cycled under randomized conditions. Each cell undergoes a three-step charging stage followed by a two-step discharge stage. After obtaining the aging data, we will develop two PI-ML models, one equipped with a physics-based model and another with a set of empirical models. Both PI-ML models in this work will follow the sequential integration approach, where the training data for the final PI-ML model come from both experimental and computational data, the latter of which are obtained from the physics-based or empirical models. The parameters for the physics-based and empirical models are identified from another set of experimental data. Finally, the PI-ML models will be tested with experimental data obtained at different cycling conditions. The data flow for the sequential architecture of PI-ML is shown in the attached figure. This comparative study will help identify the performance of physics-based and empirical models when integrated into PI-ML. The main performance metric considered in this work is each model’s ability to extrapolate beyond the experimental training data set, hence aiding the final PI-ML model in generalizing to conditions not covered by its experimental training data set. Figure 1

The future 6G network will be able to connect massive and various unmanned vehicles (UxVs) into the network, bringing novel requirements toward UxV network security and data privacy. Deploying machine learning (ML)-based intrusion detection on UxVs can be one promising approach. The conventional approach cannot fulfill security and privacy requirements, as the structure can be more flexible, and there may be a lack of a central node in the 6G-based UxV network. Moreover, UxV clients can exhibit high heterogeneity with extremely class-imbalanced training samples. With the presence of federated learning (FL), UxVs can collaborate to train and update ML models while preserving data privacy in the UxV security critical scenario. However, most past works focused on centralized approaches, using cloud servers to assist intrusion detection and service deployments. This article introduces an FL framework with a decentralized design for training ML models on UxVs using intrusion detection as a study case. This scheme can be more flexible, as UxV clients can collaborate to train and synchronize models without the central server. Simulation experiments were conducted to evaluate the efficiency of the proposed approach. Experimental results and theoretical analysis confirm that the proposed method outperforms baseline models with FedAvg and local-trained client models.

A feasibility of real-time quantitative multielemental analysis during parts growth by additive manufacturing technology has been demonstrating for the first time using laser induced breakdown spectroscopy (LIBS). A low weight and compact LIBS probe was developed to equip the laser cladding head installed at six axis industrial robot. LIBS quantitative analysis of key components (carbon and tungsten) has been demonstrated in real-time conditions during synthesis of high wear resistant coatings of nickel alloy reinforced with tungsten carbide particles. Hot solidified clad as well as a melt pool surface was sampled by LIBS probe but better analytical results were achieved for the latter case due to low partial sinking of heavy tungsten carbide particles in nickel matrix. LIBS system was calibrated for quantitative measurements by offline analysis with energy dispersive X-ray spectrometry (EDX). We didn’t observe any impact of laser ablation (LIBS sampling) on clad dimensions even when LIBS probe ablated melt pool. LIBS system was capable to quantify concentrations for both light (carbon, silicon) and heavy (nickel, tungsten, chromium, etc.) elements at frequency of 10 Hz. A good correspondence was achieved between online LIBS measurements and offline analysis opens wide perspectives for LIBS technique as a powerful tool for controlling process of parts growth by additive manufacturing

Laser-induced breakdown spectroscopy (LIBS) is one of the most promising methods for quantitative in-situ determination of fuel retention in plasma-facing components (PFCs) of magnetically confined fusion devices like ITER and JET. In this article, the current state of understanding in LIBS development for fusion applications will be presented, based on a complete review of existing results and complemented with newly obtained data. The work has been performed as part of a research programme, set up in the EUROfusion Consortium, to address the main requirements for ITER: (a) quantification of fuel from relevant surfaces with high sensitivity, (b) the technical demonstration to perform LIBS with a remote handling system and (c) accurate detection of fuel at ambient pressures relevant for ITER. For the first goal, the elemental composition of ITER-like deposits and proxies to them, including deuterium (D) or helium (He) containing W–Be, W, W–Al and Be–O–C coatings, was successfully determined with a typical depth resolution ranging from 50 up to 250 nm per laser pulse. Deuterium was used as a substitute for tritium (T) and in the LIBS experiments deuterium surface densities below 1016 D/cm2 could be measured with an accuracy of ∼30%, confirming the required high sensitivity for fuel-retention investigations. The performance of different LIBS configurations was explored, comprising LIBS systems based on single pulse (pulse durations: ps–ns) and double pulse lasers with different pulse durations. For the second goal, a remote handling application was demonstrated inside the Frascati-Tokamak-Upgrade (FTU), where a compact, remotely controlled LIBS system was mounted on a multipurpose deployer providing an in-vessel retention monitor system. During a shutdown phase, LIBS was performed at atmospheric pressure, for measuring the composition and fuel content of different area of the stainless-steel FTU first wall, and the titanium zirconium molybdenum alloy tiles of the toroidal limiter. These achievements underline the capability of a LIBS-based retention monitor, which complies with the requirements for JET and ITER operating in DT with a beryllium wall and a tungsten divertor. Concerning the capabilities of LIBS at pressure conditions relevant for ITER, quantitative determination of the composition of PFC materials at ambient pressures up to 100 mbar of N2, the D content could be determined with an accuracy of 25%, while for atmospheric pressure conditions, an accuracy of about 50% was found when using single-pulse lasers. To improve the LIBS performance in atmospheric pressure conditions, a novel approach is proposed for quantitative determination of the retained T and the D/T ratio. This scenario is based on measuring the LIBS plume emission at two different time delays after each laser pulse. On virtue of application of a double pulse LIBS system, for LIBS application at N2 atmospheric pressure the distinguishability of the spectra from H isotopes could be significantly improved, but further systematic research is required.

LIBS (Laser Induced Breakdown Spectroscopy) systems are capable of real-time chemical analysis with little or no sample preparation. A Q-switched laser is configured such that laser induced plasma is produced on targeted material. Chemical element line spectra are created, collected and analyzed by a fiber spectrometer. Line spectra emission data is instantly viewed on a head mounted display. "Eye-safe" Class I erbium glass lasers provide for insitu LIBS applications without the need for eye-protection goggles. This is due to the fact that Megawatt peak power Q-switched lasers operating in the narrow spectral window between 1.5um and 1.6um are approximately 8000 times more "eye-safe" than other laser devices operating in the UV, visible and near infrared. In this work we construct and demonstrate a LIBS system that includes a hand held eye-safe laser gun. The laser gun is fitted with a micro-integrating sphere in-situ target interface and is designed to facilitate chemical analysis in remote locations. The laser power supply, battery pack, computer controller and spectrophotometer components are packaged into a utility belt. A head mounted display is employed for "hands free" viewing of the emitted line spectra. The system demonstrates that instant qualitative and semi-quantitative chemical analyses may be performed in remote locations utilizing lightweight commercially available system components ergonomically fitted to the operator.

Spectrochemical analysis of powdered biological samples using transversely excited atmospheric carbon dioxide laser plasma excitation

LIBS measurements inside the FTU vacuum vessel by using a robotic arm

The problems of adulteration and mislabeling are very common in the food industry. Laser-induced breakdown spectroscopy (LIBS) coupled with chemometric methods has many intrinsic advantages on adulteration analysis of various materials. In this work, several chemometric algorithms, i.e., principal component analysis (PCA), decision tree (DT), random forest (RF), partial least squares discriminant analysis (PLS-DA), linear discriminant analysis (LDA), and support vector machine (SVM), were carried out assisted by LIBS technology to study the classification performances on rice geographic origins. A series of samples, including 20 kinds of rice samples from different geographic origins, was detected using LIBS with no pretreatment processes. For data analysis, PCA was employed to reduce the input variables, and to reduce the collinearity of LIBS spectral results as well. The results showed the classification accuracies of the mentioned chemometric algorithms of DT, RF, PLS-DA, LDA, and SVM with 89 input variables of 86.80%, 96.30%, 96.80%, 98.60%, and 99.20%, respectively. At the same time, the operation times of these algorithms were 3.81 s, 54.64 s, 3.63 s, 2.09 s, and 531.01 s, respectively. On the other hand, 30 principal components of input variables were also tested under the same conditions. The classification accuracies for the above algorithms were 81.60%, 98.00%, 95.70%, 98.40%, and 99.20%, respectively. The operation times were 2.01 s, 4.88 s, 3.67 s, 0.36 s, and 308.55 s, respectively. In addition, the five-fold cross-validation classification accuracies with 30 input variables for DT, RF, PLS-DA, LDA, and SVM were 83.75%, 97.95%, 94.75%, 98.35%, and 99.25%, respectively. As a result, LDA was demonstrated to be the best and most efficient tool for rice geographic origin classification assisted by LIBS with high accuracy and analytical speed, which has great potential for rapid identification of adulterated products in agriculture without use of any chemical reagent.

Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models

For the rapid and precise sorting of steel scrap with relatively high contents of copper, laser-induced breakdown spectroscopy (LIBS) is a promising method. It has several advantages such that it can work under ambient air atmospheres, and specimens can be tested without any pretreatment, such as acid digestion, polishing of the surface of the specimens, etc. For the application of LIBS for actual steel scrap, we obtained emission spectra by an LIBS system, which was mainly comprised of an Nd:YAG laser, an Echelle-type spectrometer, and an ICCD detector. The standard reference materials (SRMs) of JISF FXS 350-352, which are Fe-Cu binary alloy and have certified concentrations of copper, were employed for making calibration lines. Considering spectral interferences from the emission lines of the iron matrix in the alloys, Cu I lines having wavelengths of 324.754 and 327.396 nm could be chosen. In five replicate measurements of each SRM, shorter delay times after laser irradiation and longer gate widths for detecting the transient emission signal are suggested to be the optimal experiment parameters. In the determination process, utilizing the calibration line from Cu I 327.396 nm was better because of less spectral interference. By using 200 pulsed laser shots for the measurement sequence, a limit of detection of 0.004 Cu at% could be obtained.

Time-resolved data acquisition is crucial for compositional analysis using Laser-Induced Breakdown Spectroscopy (LIBS). It can be managed by adjusting the delay time and gate width of the spectrometer. This study describes the compositional analysis of molybdenum (Mo) ore utilizing charge coupled device (CCD) and intensified charge-coupled device (ICCD) based LIBS systems. LIBS was successfully used for both quantitative and qualitative analysis of molybdenum ore. Spectra were recorded with CCD and ICCD spectrometers. Plasma parameters were estimated from LIBS spectra to diagnose the plasma thoroughly. A performance comparison was conducted among LIBS measurements using ICCD, CCD, and x-ray fluorescence (XRF). The quantitative analysis of molybdenum ore was carried out using calibration-free LIBS. Both major and trace elements were identified in the spectra. Optical emission spectra showed varying element concentrations of Mo, silicon, aluminum, iron, calcium, potassium, tungsten, and sodium. The XRF was used to compare the performance of LIBS techniques. Results from the compositional analysis of molybdenum ore using ICCD, CCD-based LIBS, and XRF showed good agreement. It is demonstrated that CCD can produce nearly the same results as ICCD within acceptable error margins. The CCD-based LIBS system is a cost-effective analytical method with additional benefits for field applications because it does not require a temperature-controlled environment for operation.

Achieving operational excellence and efficiency is a constant goal in manufacturing and production, driven by the need to reduce waste and optimize processes in today’s competitive environment. The era of Industry 4.0 offers advanced technologies such as Artificial Intelligence (AI), robotics, IoT and cloud computing to support this pursuit, aligning with philosophies like lean manufacturing. However, modeling and optimizing complex production systems, which involve nonlinear behavior, interdependencies and time delays, remains a significant challenge. This research proposes a hybrid AI solution for optimizing production efficiency by combining Data Envelopment Analysis (DEA), Machine Learning (ML)-based simulation and Genetic Algorithms (GA). DEA is used to identify the efficient frontier of the production system based on historical or synthetic data. This data is used to train an ML model capable of simulating system behavior. GA is then applied to search for the optimal input configurations and control parameters to maximize efficiency, considering operational constraints. The methodology was applied and validated using real sensor data from a thermoelectric power plant. The process included data preparation with outlier removal using the Z-score method, calculation of relative efficiency using DEA-CCR, training ML models to predict outputs and efficiencies, and applying GA to identify ideal settings. The implementation resulted in significant improvements, with efficiency gains of 25% and 58% in two tested models, outperforming conventional closed-loop control systems. The approach also demonstrated that separating the optimization phase using GA from the DEA and ML training phases can significantly reduce computational time. As a result, the solution not only optimizes resource use and reduces production costs but also provides greater flexibility to production systems by reducing the direct dependency between high output levels and overall efficiency. The developed framework presents a practical, accessible and effective solution for production systems. It is adaptable to various industrial sectors and contributes to the data-driven digital transformation within the scope of Industry 4.0.