Search Results (26)

The main thrust of the study is the need to cut down the time taken for mold changes in plastic injection molding which is fundamental to the productivity and efficiency of the process. The research encompasses Lean Manufacturing, DMAIC, and SMED which are improved using fuzzy logic and AI for rapid changeover optimization on the NEGRI BOSSI 650 machine. A decrease in downtime by 65% and an improvement in the Process Cycle Efficiency by 46.8% followed the identification of bottlenecks, externalizing tasks, and streamlining workflows. AI-driven analysis could make on-the-fly adjustments, which would ensure that resources are better allocated, and thus sustainable performance is maintained. The findings highlight how integrating Lean methods with advanced technologies enhances operational agility and competitiveness, offering a scalable model for continuous improvement in industrial settings. Full article

The real-time creation of machine-learning models via active or on-the-fly learning has attracted considerable interest across various scientific and engineering disciplines. These algorithms enable machines to build models autonomously while remaining operational. Through a series of query strategies, the machine can evaluate whether newly encountered data fall outside the scope of the existing training set. In this study, we introduce PowerModel-AI, an end-to-end machine learning software designed to accurately predict AC power flow solutions. We present detailed justifications for our model design choices and demonstrate that selecting the right input features effectively captures load flow decoupling inherent in power flow equations. Our approach incorporates on-the-fly learning, where power flow calculations are initiated only when the machine detects a need to improve the dataset in regions where the model’s suboptimal performance is based on specific criteria. Otherwise, the existing model is used for power flow predictions. This study includes analyses of five Texas A&M synthetic power grid cases, encompassing the 14-, 30-, 37-, 200-, and 500-bus systems. The training and test datasets were generated using PowerModels.jl, an open-source power flow solver/optimizer developed at Los Alamos National Laboratory, NM, USA. Full article

Embedded systems, particularly when integrated into the Internet of Things (IoT) landscape, are critical for projects requiring robust, energy-efficient interfaces to collect real-time data from the environment. As these systems become complex, the need for dynamic reconfiguration, improved availability, and stability becomes increasingly important. This paper presents the design of a framework architecture that supports dynamic reconfiguration and “on-the-fly” code execution in IoT-enabled embedded systems, including a virtual machine capable of hot reloads, ensuring system availability even during configuration updates. A “hardware-in-the-loop” workflow manages communication between the embedded components, while low-level coding constraints are accessible through an additional abstraction layer, with examples such as MicroPython or Lua. The study results demonstrate the VM’s ability to handle serialization and deserialization with minimal impact on system performance, even under high workloads, with serialization having a median time of 160 microseconds and deserialization having a median of 964 microseconds. Both processes were fast and resource-efficient under normal conditions, supporting real-time updates with occasional outliers, suggesting room for optimization and also highlighting the advantages of VM-based firmware update methods, which outperform traditional approaches like Serial and OTA (Over-the-Air, the ability to update or configure firmware, software, or devices via wireless connection) updates by achieving lower latency and greater consistency. With these promising results, however, challenges like occasional deserialization time outliers and the need for optimization in memory management and network protocols remain for future work. This study also provides a comparative analysis of currently available commercial solutions, highlighting their strengths and weaknesses. Full article

Oxide-dispersion-strengthened (ODS) steels have long been viewed as a prime solution for harsh environments. However, conventional manufacturing of ODS steels limits the final product geometry, is difficult to scale up to large components, and is expensive due to multiple highly involved, solid-state processing steps required. Additive manufacturing (AM) can directly incorporate dispersion elements (e.g., Y, Ti and O) during component fabrication, thus bypassing the need for an ODS steel supply chain, the scale-up challenges of powder processing routes, the buoyancy challenges associated with casting ODS steels, and the joining issues for net-shape component fabrication. In the AM process, the diffusion of the dispersion elements in the molten steel plays a key role in the precipitation of the oxide particles, thereby influencing the microstructure, thermal stability and high-temperature mechanical properties of the resulting ODS steels. In this work, the atomic diffusivities of Y, Ti, and O in molten 316L stainless steel (SS) as functions of temperature are determined by ab initio molecular dynamics simulations. The latest Vienna Ab initio Simulation Package (VASP) package that incorporates an on-the-fly machine learning force field for accelerated computation is used. At a constant temperature, the time-dependent coordinates of the target atoms in the molten 316L SS were analyzed in the form of mean square displacement in order to obtain diffusivity. The values of the diffusivity at multiple temperatures are then fitted to the Arrhenius form to determine the activation energy and the pre-exponential factor. Given the challenges in experimental measurement of atomic diffusivity at such high temperatures and correspondingly the lack of experimental data, this study provides important physical parameters for future modeling of the oxide precipitation kinetics during AM process. Full article

The study of the effects of impurity on grain boundaries is a critical aspect of materials science, particularly when it comes to understanding and controlling the properties of materials for specific applications. One of the related key issues is the segregation preference of impurity atoms in the grain boundary region. In this paper, we employed the on-the-fly machine learning to generate force fields, which were subsequently used to calculate the segregation energies of phosphorus and silicon in bcc iron containing the ∑5(310)[001] grain boundary. The generated force fields were successfully benchmarked using ab initio data. Our further calculations considered impurity atoms at a number of possible interstitial and substitutional segregation sites. Our predictions of the preferred sites agree with the experimental observations. Planar concentration of impurity atoms affects the segregation energy and, moreover, can change the preferred segregation sites. Full article

Consistent high volumetric performance of machine tools is an essential requirement for high-quality machining. Periodic machine tool calibration ensures said performance and allows for timely corrective actions preventing scrap or rework. Reducing the duration of the calibration process decreases associated cost through non-productive downtime and allows for data acquisition in thermal real-time. The authors enhance an indirect calibration method based on measuring points within the machine volume using a laser tracker by removing the necessity for standstill. To circumvent requiring high fidelity space and time synchronization between metrology system and machine tool, only deviations perpendicular to the path are considered. To do so, the 3D laser tracker data are rotationally transformed such that one axis aligns with the motion direction and can subsequently be omitted as input data for the system of equations solving for geometric errors. Due to the absence of unique measurement-point-to-machine-point mapping, data alignment between nominal path and measurement data is proposed as an iterative alignment process of points to path. The method is tested simulatively and experimentally. It demonstrated conformity to the simulation as well as to the pre-existing calibration method based on laser trackers and shows good agreement with the direct calibration device API XD Laser. Full article

‘Slide scanners’ are rapid optical microscopes equipped with automated and accurate x-y travel stages with virtual z-motion that cannot be rotated. In biomedical microscopic imaging, they are widely deployed to generate whole-slide images (WSI) of tissue samples in various modes of illumination. The availability of WSI has motivated the development of instrument-agnostic advanced image analysis software, helping drug development, pathology, and many other areas of research. Slide scanners are now being modified to enable polarised petrographic microscopy by simulating stage rotation with the acquisition of multiple rotation angles of the polariser–analyser pair for observing randomly oriented anisotropic materials. Here we report on the calibration strategy of one repurposed slide scanner and describe a pilot image analysis pipeline designed to introduce the wider audience to the complexity of performing computer-assisted feature recognition on mineral groups. The repurposed biological scanner produces transmitted light plane- and cross-polarised (TL-PPL and XPL) and unpolarised reflected light (RL) WSI from polished thin sections or slim epoxy mounts at various magnifications, yielding pixel dimensions from ca. 2.7 × 2.7 to 0.14 × 0.14 µm. A data tree of 14 WSI is regularly obtained, containing two RL and six of each PPL and XPL WSI (at 18° rotation increments). This pyramidal image stack is stitched and built into a local server database simultaneously with acquisition. The pyramids (multi-resolution ‘cubes’) can be viewed with freeware locally deployed for teaching petrography and collaborative research. The main progress reported here concerns image analysis with a pilot open-source software pipeline enabling semantic segmentation on petrographic imagery. For this purpose, all WSI are post-processed and aligned to a ‘fixed’ reflective surface (RL), and the PPL and XPL stacks are then summarised in one image, each with ray tracing that describes visible light reflection, absorption, and O- and E-wave interference phenomena. The maximum red-green-blue values were found to best overcome the limitation of refractive index anisotropy for segmentation based on pixel-neighbouring feature maps. This strongly reduces the variation in dichroism in PPL and interference colour in XPL. The synthetic ray trace WSI is then combined with one RL to estimate modal mineralogy with multi-scale algorithms originally designed for object-based cell segmentation in pathological tissues. This requires generating a small number of polygonal expert annotations that inform a training dataset, enabling on-the-fly machine learning classification into mineral classes. The accuracy of the approach was tested by comparison with modal mineralogy obtained by energy-dispersive spectroscopy scanning electron microscopy (SEM-EDX) for a suite of rocks of simple mineralogy (granulites and peridotite). The strengths and limitations of the pixel-based classification approach are described, and phenomena from sample preparation imperfections to semantic segmentation artefacts around fine-grained minerals and/or of indiscriminate optical properties are discussed. Finally, we provide an outlook on image analysis strategies that will improve the status quo by using the first-pass mineralogy identification from optical WSI to generate a location grid to obtain targeted chemical data (e.g., by SEM-EDX) and by considering the rock texture. Full article

Thermoelectric materials have attracted extensive attention because they can directly convert waste heat into electric energy. As a brand-new method of alloying, high-entropy alloys (HEAs) have attracted much attention in the fields of materials science and engineering. Recent researches have found that HEAs could be potentially good thermoelectric (TE) materials. In this study, special quasi-random structures (SQS) of PbSnTeSe high-entropy alloys consisting of 64 atoms have been generated. The thermoelectric transport properties of the highest-entropy PbSnTeSe-optimized structure were investigated by combining calculations from first-principles density-functional theory and on-the-fly machine learning with the semiclassical Boltzmann transport theory and Green–Kubo theory. The results demonstrate that PbSnTeSe HEA has a very low lattice thermal conductivity. The electrical conductivity, thermal electronic conductivity and Seebeck coefficient have been evaluated for both n-type and p-type doping. N-type PbSnTeSe exhibits better power factor (PF = S²σ) than p-type PbSnTeSe because of larger electrical conductivity for n-type doping. Despite high electrical thermal conductivities, the calculated ZT are satisfactory. The maximum ZT (about 1.1) is found at 500 K for n-type doping. These results confirm that PbSnTeSe HEA is a promising thermoelectric material. Full article

Machine learning (ML) is frequently used to identify malicious traffic flows on a network. However, the requirement of complex preprocessing of network data to extract features or attributes of interest before applying the ML models restricts their use to offline analysis of previously captured network traffic to identify attacks that have already occurred. This paper applies machine learning analysis for network security with low preprocessing overhead. Raw network data are converted directly into bitmap files and processed through a Two-Dimensional Convolutional Neural Network (2D-CNN) model to identify malicious traffic. The model has high accuracy in detecting various malicious traffic flows, even zero-day attacks, based on testing with three open-source network traffic datasets. The overhead of preprocessing the network data before applying the 2D-CNN model is very low, making it suitable for on-the-fly network traffic analysis for malicious traffic flows. Full article

Stephen Wolfram (2002) proposed the concept of computational equivalence, which implies that almost any dynamical system can be considered as a computation, including programmable matter and nonlinear materials such as, so called, quantum matter. Memristors are often used in building and evaluating hardware neural networks. Ukil (2011) demonstrated a theoretical relationship between piezoelectrical materials and memristors. We review that work as a necessary background prior to our work on exploring a piezoelectric material for neural network computation. Our method consisted of using a cubic block of unpoled lead zirconate titanate (PZT) ceramic, to which we have attached wires for programming the PZT as a programmable substrate. We then, by means of pulse trains, constructed on-the-fly internal patterns of regions of aligned polarization and unaligned, or disordered regions. These dynamic patterns come about through constructive and destructive interference and may be exploited as a type of reservoir network. Using MNIST data we demonstrate a learning machine. Full article

In this paper, a machine learning-based approach for the automation of topology selection of integrated analog amplifier circuits is presented. A dataset of 480,000 circuits for 30 different amplifier topologies is generated for the prediction algorithm based on a precomputed lookup tables (LUTs) approach. A first approach based on neural networks is presented where the required specifications act as inputs to the networks, and the output of the network is the suitable topology for such a set of specifications. A modified cascaded neural network approach is examined to reduce the training time of the network while maintaining the prediction accuracy. Using the cascaded neural network approach, the network is trained in only one minute on a standard computer, and a 90.8% prediction accuracy is achieved. This allows on-the-fly changes in the input specifications, and consequently the neural network, to enable examining different design scenarios. Full article

In this study, a laser scanning machining system supporting on-the-fly machining and laser power follow-up adjustment was developed to address the increasing demands for high-speed, wide-area, and high-quality laser scanning machining. The developed laser scanning machining system is based on the two-master and multi-slave architecture with synchronization mechanism, and realizes the integrated and synchronous collaborative control of the motion stage or robot, the galvanometer scanner, and the laser over standard industrial ethernet networks. The galvanometer scanner can be connected to the industrial ethernet topology as a node, via the self-developed galvanometer scanner control gateway module, and a “one-transmission and multiple-conversion” approach is proposed to ensure real-time ability and synchronization. The proposal of a laser power follow-up adjustment approach could realize real-time synchronous modulation of the laser power, along with the motion of the galvanometer scanner, which is conducive to ensuring the machining quality. In addition, machining software was developed to realize timesaving and high-quality laser scanning machining. The feasibility and practicability of this laser scanning machining system were verified using specific cases. Results showed that the proposed system overcame the limitation of working field size and isolation between the galvanometer scanner controller with the stage motion controller, and achieved high-speed and efficient laser scanning machining for both large-area consecutively and discontinuously arrayed patterns. Moreover, the integration of laser power follow-up adjustment into the system was conducive to ensuring welding quality and inhibiting welding defects. The proposed system paves the way for high-speed, wide-area, and high-quality laser scanning machining and provides technical convenience and cost advantages for customized laser-processing applications, exhibiting great research value and application potential in the field of material processing engineering. Full article

The normalized difference vegetation index (NDVI) is a key parameter in precision agriculture. It has been used globally since the 1970s as a proxy to monitor crop growth and correlates to the crop coefficient (Kc), leaf area index (LAI), crop cover, and more. Yet, it is susceptible to clouds and other atmospheric conditions that might alter the crop’s real NDVI value. Synthetic Aperture Radar (SAR), on the other hand, can penetrate clouds and is hardly affected by atmospheric conditions, but it is sensitive to the physical structure of the crop and therefore does not give a direct indication of the NDVI. Several SAR indices and methods have been suggested to estimate NDVIs via SAR; however, they tend to work for local spatial and temporal conditions and do not work well globally. This is because they are not flexible enough to capture the changing NDVI–SAR relationship throughout the crop-growing season. This study suggests a new method for converting Sentinel-1 to NDVIs for Agricultural Fields (SNAF) by utilizing a hyperlocal machine learning approach. This method generates multiple on-the-fly disposal field- and time-specific models for every available Sentinel-1 image across 2021. Each model learns the field-specific NDVI (from Sentinel-2 and Landsat-8) –SAR (Sentinel-1) relationship based on recent NDVI and SAR time series and consequently estimates the optimal NDVI value from the current SAR image. The SNAF was tested on 548 commercial fields from 18 countries with 28 crop types and, based on 6880 paired NDVI–SAR images, achieved an RMSE, bias, and R² of 0.06, 0.00, and 0.92, respectively. The outcome of this study aspires to a persistent seamless stream of NDVI values, regardless of the atmospheric conditions, illumination, or local conditions, which can assist in agricultural decision making. Full article

Solutions to assess walking deficiencies are widespread and largely used in healthcare. Wearable sensors are particularly appealing, as they offer the possibility to monitor gait in everyday life, outside a facility in which the context of evaluation biases the measure. While some wearable sensors are powerful enough to integrate complex walking activity recognition models, non-invasive lightweight sensors do not always have the computing or memory capacity to run them. In this paper, we propose a walking activity recognition model that offers a viable solution to this problem for any wearable sensors that measure rotational motion of body parts. Specifically, the model was trained and tuned using data collected by a motion sensor in the form of a unit quaternion time series recording the hip rotation over time. This time series was then transformed into a real-valued time series of geodesic distances between consecutive quaternions. Moving average and moving standard deviation versions of this time series were fed to standard machine learning classification algorithms. To compare the different models, we used metrics to assess classification performance (precision and accuracy) while maintaining the detection prevalence at the level of the prevalence of walking activities in the data, as well as metrics to assess change point detection capability and computation time. Our results suggest that the walking activity recognition model with a decision tree classifier yields the best compromise in terms of precision and computation time. The sensor that was used had purposely low computing and memory capacity so that reported performances can be thought of as the lower bounds of what can be achieved. Walking activity recognition is performed online, i.e., on-the-fly, which further extends the range of applicability of our model to sensors with very low memory capacity. Full article

A Pseudo-satellite system that transmits signals similar to GNSS can provide positioning services in places where GNSS signals are not captured and have enormous potential for indoor machine system and airports. Different paths of the device have different carrier phase initial solution positioning accuracy. Existing methods rely on measuring instruments or use many coordinate points for solving ambiguity resolution (AR), which creates inconvenience for real-time ground positioning. This study aims to find a new on-the-fly (OTF) method to achieve high accuracy and convenient positioning. A new method is proposed based on a two-difference observation model for ground-based high-precision point positioning. We used an adaptive particle swarm algorithm to solve the initial solution, followed by a nonlinear least-squares method to optimize the localization solution. It is free of priori information or measuring instruments. We designed several different paths, such as circular trajectory and square trajectory, to study the positioning accuracy of the solution. Simulation experiments with different trajectories showed that geometric changes significantly impact solutions. In addition, it does not require precise time synchronization of the base stations, making the whole system much easier to deploy. We built a real-world pseudo-satellite system and used a multi-sensor crewless vehicle as a receiver. Real-world experiments showed that our approach could achieve centimeter-level positioning accuracy in applications. Full article