Isotropic Particles Research Articles

Light-propelled dimeric micro-rotor in a binary critical mixture

Industrial motors produce either linear or rotational motion, and enabling these engines on micrometer scales would have significant technological implications in the biomedical, biochemical, nanoscience, and nanotechnology areas. In this paper, we report a colloidal dimeric micro-rotor consisting of a pivot particle (isotropic dielectric particle) joined to a carbon Janus particle (anisotropic particle) embedded in a critical mixture. The two particles forming this dimer are trapped and illuminated by an optical tweezer, respectively. The carbon Janus particle heats its surroundings, producing a demixing flow that results in directed rotational motion. The pivot ensures the stability of the dimer’s rotation motion, allowing for a clean circular trajectory with low dispersion between cycles. This system converts thermal energy from the absorption of light by the carbon Janus particle into mechanical rotational work. By adjusting the laser power input energy, we obtained rotational work values ranging from 3300 to 270 kBT per cycle. However, there is a limit in the laser power that induces rotation, which depends on the balance between trapping and demixing forces required for stable rotation. This paper provides an efficient method to construct a rotational micro-rotor with a stable motion (standard deviation = 0,03 µm) for nano and micro devices.

Development and demonstration of a BISON–Griffin modeling framework for the design of targeted TRISO transient experiments in the Transient Reactor Test Facility

Uranium oxycarbide (UCO)-bearing tri-structural isotropic (TRISO) particle fuels are expected to be used in numerous U.S. commercial reactor applications within the next decade. In this work, we reviewed historical particle fuel transient experiments to identify gaps in TRISO fuel performance transient testing. A BISON–Griffin modeling framework was then developed to conduct preliminary TRISO transient analyses and begin to address these gaps. The framework was demonstrated using limiting-case transient conditions from a prototypic high-temperature gas-cooled reactor (HTGR). It was then applied to develop a matrix of experiments that could be performed in the Transient Reactor Test Facility (TREAT) to (1) evaluate UCO-fueled particle performance at moderate and high heat rates, (2) assess whether historical testing involving UO2-fueled particles is applicable to modern UCO-fueled particles, (3) deconvolute the impacts of temperature and heat rate on particle transient response, and (4) collect the data needed for fuel performance model validation and/or further development.

Kerr black hole energy extraction, irreducible mass feedback, and the effect of captured particles charge

We analyze the extraction of the rotational energy of a Kerr black hole (BH) endowed with a test charge and surrounded by an external test magnetic field and ionized low-density matter. For a magnetic field parallel to the BH spin, electrons move outward(inward) and protons inward(outward) in a region around the BH poles(equator). For zero charge, the polar region comprises spherical polar angles -60∘≲θ≲60∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$-60^\\circ \\lesssim \ heta \\lesssim 60^\\circ $$\\end{document} and the equatorial region 60∘≲θ≲120∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$60^\\circ \\lesssim \ heta \\lesssim 120^\\circ $$\\end{document}. The polar region shrinks for positive charge, and the equatorial region enlarges. For an isotropic particle density, we argue the BH could experience a cyclic behavior: starting from a zero charge, it accretes more polar protons than equatorial electrons, gaining net positive charge, energy and angular momentum. Then, the shrinking(enlarging) of the polar(equatorial) region makes it accrete more equatorial electrons than polar protons, gaining net negative charge, energy, and angular momentum. In this phase, the BH rotational energy is extracted. The extraction process continues until the new enlargement of the polar region reverses the situation, and the cycle repeats. We show that this electrodynamical process produces a relatively limited increase of the BH irreducible mass compared to gravitational mechanisms like the Penrose process, hence being a more efficient and promising mechanism for extracting the BH rotational energy.

Improving the Resolution and Computational Efficiency of Depletion Simulations on a TRISO-Fueled Microreactor

Modeling individual TRi-structural ISOtropic (TRISO) particles is possible using constructive solid geometry in Monte Carlo neutron transport codes (such as MCNP); however, the billions of surfaces required incurs considerable computational expense. Depletion simulations, in conjunction with Monte Carlo transport, are also inherently slow, requiring many individual criticality calculations to approximate time-dependent behavior. Additionally, choosing acceptable time step sizes, spatial zoning, and other depletion parameters involves prior knowledge and/or iteration by the user. The slow and complex nature of depletion calculations greatly increases the cost and duration of the design iteration process. The importance of tracked isotopes, spatial zones, and time stepping during depletion simulations is evaluated globally using neutron multiplication factor, total isotope inventory, and burnup. Different depletion schemes are compared using the TRISO-fueled Snowflake microreactor. Woodcock Delta Tracking and a Reactivity-equivalent Physical Transformation (RPT) are investigated as potential approaches to increase the speed of Monte Carlo neutron transport calculations involving TRISO fuel. The Monte Carlo N-Particle® Code (MCNP®) Version 6.3 is used to obtain the transport solution, and depletion calculations are performed using its internally coupled version of CINDER90. A prototype MCNP delta tracking module under development at Los Alamos National Laboratory is also used. Although a single spatial depletion region is sometimes acceptable, large errors in core lifetime and total 238Pu, 241Pu, and 242Pu mass are possible. The prototype delta tracking module significantly speeds up criticality calculations; however, depletion calculations are not always faster than those performed with surface tracking. The RPT method is effective at reducing CPU times in both criticality and depletion calculations, without significantly impacting neutron multiplication factor and total isotope inventory. The necessary number of time steps to converge total isotope inventory was also explored; the required number and spacing varied greatly depending on the objective of the depletion simulation.

Transverse optical torque from the magnetic spin angular momentum

Abstract We report a transverse optical torque exerted on a conventional isotropic spherical particle in a direction perpendicular to that of the illuminating wave propagation. By using full-wave simulations and deriving an analytical expression of the transverse optical torque for particle of arbitrary size, the origin of this transverse optical torque is traced exclusively to the magnetic part of the spin angular momentum, regardless of the size and composition of the illuminated particle. To our surprise, for a non-magnetic dielectric particle, the transverse optical torque is found to originate mainly from the magnetic response of the particle, even when the particle size is much smaller than the illuminating wavelength. This is contrary to the general intuition that the electric response of a non-magnetic dielectric particle dominates its magnetic response in the mechanical effect of light, especially in the Rayleigh limit.

Unravelling the impact of palladium on ruthenium-induced corrosion of SiC coatings in TRISO particles

Ru and Pd are fission products released through SiC layer in TRISO fuel at high temperature. This study investigates the corrosion behaviour of Ru-Pd on SiC layers of tri-structural isotropic (TRISO) particles. Specifically, it explores the effects of Pd (strongly reactive FP) on Ru (weakly reactive FP)-induced corrosion. In Pd-Ru/SiC systems, a Ru-Pd-Si liquid phase forms at high temperatures even with minimal Pd, accelerating corrosion along SiC grain boundaries. Comparing Pd’s role in Ru/SiC and Ag/SiC systems underscores the importance of liquid phases in FP migration. A novel approach is proposed for predicting the corrosion effects of multiple FPs on SiC through enthalpic interaction analysis.

Dynamics of paramagnetic permanent chains and self-assembled clusters under a rapidly rotating magnetic field.

We study experimentally and theoretically the dynamics of permanent paramagnetic chains and mixed clusters formed by permanent paramagnetic chains and paramagnetic particles under the influence of a time-varying magnetic field. First, we examine the dynamics of permanent chains at high frequencies (∼50 to 1000Hz). These permanent chains exhibit continuous rotational motion with a frequency several orders of magnitude lower than that of the magnetic field. We develop a theoretical model that accurately describes the dependence of the rotational dynamics of chains on their length, as well as the amplitude and frequency of the external magnetic field in this high frequency regime. Next, we examine how cluster dynamics are affected by the presence of permanent chains. We show that the rotation of clusters composed of a high proportion of permanent chains is slowed down but remains qualitatively well described by the theoretical model we developed for homogeneous clusters of isotropic particles. We propose that the decrease in angular velocity for mixed clusters is due to the hardening of the cluster's 2D elastic modulus caused by the increase of the steric interaction parameter stemming from the presence of chemical links between particles in the chains.

Multiscale, mechanistic modeling of irradiation-enhanced silver diffusion in TRISO particles

Tristructural isotropic (TRISO) particles are under consideration for use in several proposed advanced nuclear reactor concepts. The silicon carbide (SiC) layer in TRISO acts as a barrier to prevent the release of the fission products. However, despite remarkable retention, silver (Ag) release has been observed from intact particles, which requires investigation since the Ag isotope (110mAg) has a long half-life. Previous work focused on developing a multiscale, mechanistic model for Ag diffusion accounting for temperature and microstructure effect and has been successfully validated. In this work, we expand the previous model to account for irradiation-enhanced Ag diffusivity in SiC and improve its accuracy over a wider grain size and temperature ranges relevant for advanced reactor conditions. A temperature, grain size, and flux dependent diffusivity is therefore derived using the mesoscale code MARMOT and implemented in the fuel performance code BISON. The irradiation-enhanced Ag diffusivity in SiC is compared against experimental data and validated using BISON against Ag release measurements from the Advanced Gas Reactor Fuel Development and Qualification Program (AGR-1 and AGR-2). Herein, we quantify the impact of SiC grain size, irradiation, and temperature on Ag release. In agreement with previous studies, we find accounting for SiC grain size improves agreement between BISON predictions and experimental observations for most cases. We also find that accounting for irradiation improves agreement for cases where Ag release was underestimated, but the impact was less significant than accounting for microstructure.

Influence of Carbon Content on Element Diffusion in Silicon Carbide-Based TRISO Composite Fuel

The coating layers of Tri-structural Isotropic Particles (TRISO) serve to protect the kernel and act as barriers to fission products. Sintering aids in the silicon carbide matrix variably react with TRISO coating layers, leading to the destruction of the coating layers. Investigating how carbon content affects element diffusion in silicon carbide-based TRISO composite fuel is of great significance for predicting reactor safety. In this study, silicon carbide-based TRISO composite fuels with different carbon contents were prepared by adding varying amounts of phenolic resin to the silicon carbide matrix. X-ray diffraction (XRD) and Scanning Electron Microscopy (SEM) were employed to characterize the phase composition, morphology, and microstructure of the composite fuels. The elemental content in each coating layer of TRISO was quantified using Energy-Dispersive X-ray Spectroscopy (EDS). The results demonstrated that the addition of phenolic resin promoted the uniform distribution of sintering aids in the silicon carbide matrix. The atomic percentage (at.%) of aluminum (Al) in the pyrolytic carbon layer of the TRISO particles reached its lowest value of 0.55% when the phenolic resin addition was 1%. This is because the addition of phenolic resin caused the Al and silicon (Si) in the matrix to preferentially react with the carbon in the phenolic resin to form a metastable liquid phase, rather than preferentially consuming the pyrolytic carbon in the outer coating layer of the TRISO particles. The findings suggest that carbon addition through phenolic resin incorporation can effectively mitigate the deleterious reactions between the TRISO coating layers and sintering aids, thereby enhancing the durability and safety of silicon carbide-based TRISO composite fuels.

Exploring run-and-tumble movement in confined settings through simulation.

Motion in bounded domains is a fundamental concept in various fields, including billiard dynamics and random walks on finite lattices, and has important applications in physics, ecology, and biology. An important universal property related to the average return time to the boundary, the Mean Path Length Theorem (MPLT), has been proposed theoretically and experimentally confirmed in various contexts. We investigated a wide range of mechanisms that lead to deviations from this universal behavior, such as boundary effects, reorientation, and memory processes. This study investigates the dynamics of run-and-tumble particles within a confined two-dimensional circular domain. Through a combination of theoretical approaches and numerical simulations, we validate the MPLT under uniform and isotropic particle inflow conditions. This research demonstrates that although the MPLT is generally applicable for different step length distributions, deviations occur for non-uniform angular distributions, non-elastic boundary conditions, or memory processes. These results underline the crucial influence of boundary interactions and angular dynamics on the behavior of particles in confined spaces. Our results provide new insights into the geometry and dynamics of motion in confined spaces and contribute to a better understanding of a broad spectrum of phenomena ranging from the motion of bacteria to neutron transport. This type of analysis is crucial in situations where inhomogeneity occurs, such as multiple real-world scenarios within a limited domain.

Detection of diffusion anisotropy from an individual short particle trajectory

In parallel with advances in microscale imaging techniques, the fields of biology and materials science have focused on precisely extracting particle properties based on their diffusion behavior. Although the majority of real-world particles exhibit anisotropy, their behavior has been studied less than that of isotropic particles. In this study, we introduce a method for estimating the diffusion coefficients of individual anisotropic particles using short-trajectory data on the basis of a maximum likelihood framework. Traditional estimation techniques often use mean-squared displacement (MSD) values or other statistical measures that inherently remove angular information. Instead, we treated the angle as a latent variable and used belief propagation to estimate it while maximizing the likelihood using the expectation-maximization algorithm. Compared to conventional methods, this approach facilitates better estimation of shorter trajectories and faster rotations, as confirmed by numerical simulations and experimental data involving bacteria and quantum rods. Additionally, we performed an analytical investigation of the limits of detectability of anisotropy and provided guidelines for the experimental design. In addition to serving as a powerful tool for analyzing complex systems, the proposed method will pave the way for applying maximum likelihood methods to more complex diffusion phenomena. Published by the American Physical Society 2024

Analysis of micro-defect-induced cracking in the IPyC layer of TRISO particle with the XFEM

PurposeWe use the extended finite element method (XFEM) to model the whole process of initiation and propagation of cracks in the inner dense pyrolytic carbon (IPyC) layer of tri-structural isotropic (TRISO) particle induced by the microdefect in an irradiation-induced thermomechanical coupling environment and study the effect of microdefect sizes on the propagation path.Design/methodology/approachThe irradiation-induced thermal–mechanical coupling analysis is first conducted for the representative volume element (RVE) of the TRISO particle by using the conventional finite element method (CFEM) so that the stress distribution is obtained. The stress results are then restored for the enriched elements, and the simulation of crack initiation and propagation is eventually carried out by using the XFEM.Findings1. As a crack initiates in the IPyC layer, it will terminate at the free edge of the RVE TRISO particle in the end. 2. The size of the microdefect has a significant impact on the propagation path.Originality/valueThe ceramic dispersion microencapsulated (CDM) fuel is a good accident-resistant fuel whose safe operation is crucial to the safety and reliability of the whole nuclear reactor. It is of great scientific significance and practical value to study the irradiation-induced thermomechanical coupling stress distribution and cracking behavior in the IPyC layer of TRISO particles for the CDM fuel. Crack initiation and propagation analysis is challengeable for this complex multi-layer structure. This can help understand the failure mechanism of TRISO particles and evaluate the operation safety of the reactor.

Neutronic and thermal–hydraulic coupling of FCM and helium annular fuel as accident-tolerant fuel

The study aims to explore two types of Accident Tolerant Fuel (ATF) (helium annular fuel and Fully Ceramic Microencapsulated (FCM) fuel), both with Silicon Carbide (SiC) used as clad material and as a matrix material for TRISO (TRi-structural ISOtropic particle fuel) particles in FCM fuel. The safety characteristics (such as maximum fuel temperatures) were evaluated and compared against reference UO2-Zr for a Pressurised Water Reactor (PWR) with neutronic and thermal–hydraulic coupling during normal operation for fresh fuel. The results show that both annular and FCM fuels exhibit reduced maximum temperatures compared to the reference fuel, with a reduction of 479 K (25.3 %) for helium annular fuel and 798 K (42.2 %) in the FCM fuel. The annular fuel improved the burnup by 12.4 MWd/kgU (24.2 %) without the cycle length being affected significantly (−5.6 %). The FCM fuel significantly reduced in the cycle length by 44.1 % while the burnup was more than double the reference providing a 163.5 % increased burnup in comparison to the reference fuel assembly. Assembly pin power peaking factors showed no dramatic deviation from the reference and the axial power distribution of ATFs is more symmetrical than that of the reference fuels. In terms of coupling the pin models converged after eight iterations on average with maximum relative power errors per radial node below 2 %.

Modular gas-cooled reactor core optimal design and additive manufacturing performance based on SiC matrix dispersed with TRi-structural ISOtropic fuel

High-temperature gas-cooled reactors present significant technical competitiveness in various fields, such as low-carbon electricity, thermal energy, and hydrogen supply. Silicon Carbide (SiC) matrix dispersed with TRi-structural ISOtropic (TRISO) particle fuel is characterized by high-temperature tolerance, radiation resistance, and good neutron economy, which has emerged as a pivotal technological pathway for reactor core design. With the rapid advancement of SiC Additive Manufacturing (AM) technology, there is a substantial increase in core design flexibility, and an innovative gas-cooled reactor design was proposed by Monte Carlo (MC) method in this paper. The Non-uniform Rational B-spline (NURBS), Latin Hypercube Sampling (LHS), second-order polynomial response surface, as well as Genetic Algorithm (GA) were coupled to realize the optimization design for the coolant channel. Besides, a modular fuel design was proposed, and the AM SiC shell was fabricated using Binder Jetting (BJ) technology. Furthermore, the densification of the AM SiC shell and the matrix with SiC powder and SiC microspheres (TRISO simulator) was investigated by Chemical Vapor Infiltration (CVI). Finally, the microscopic morphology analysis and thermal-mechanical performance characterization of the samples were conducted, which demonstrated the technical feasibility and advanced capabilities of the SiC matrix dispersed with TRISO fuel based on AM technology.

Interception force assisted optical pulling of a dipole nanoparticle in a single plane wave.

The optical pulling force is generally believed to originate from the recoil force due to the simultaneous excitation of multipoles in the particle, which overcomes the interception force contributing to the optical pushing force. However, we show that the interception force can induce optical pulling force on a small isotropic spherical particle with gain in a uniform electromagnetic plane wave, in which multipole excitation is negligible within the dipole regime. Based on the multipole expansion theory, a rigorous analytical expression is derived for optical force acting on a spherical particle of arbitrary size and composition illuminated by a single plane wave, regardless of its polarization. The analytical results show that the interception force, which is typically positive in a conventional dielectric particle under illumination of a single plane wave, undergoes a crossover from positive to negative by introducing appropriate gain into the dipolar dielectric nanoparticle, thereby giving rise to the optical pulling. It's deserved to be noted that the optical pulling force assisted by the interception force does not weaken in magnitude, in fact, it exhibits a stronger magnitude compared to the optical pushing force experienced by a corresponding conventional dielectric particle.

Self-Assembly of Model Three- and Four-Patch Colloidal Particles in Two Dimensions.

A coarse-grained effective solvent model of two-patch particles is extended to study the self-assembly of three- and four-patch particles to two-dimensional honeycomb and square lattices, respectively. Employing this model, grand canonical ensemble simulations are done to calculate vapor-liquid equilibria and the critical temperatures for patchy particles of various patch widths. The range of stability of the liquid, although very limited compared to isotropic particles, which interact through a longer-range potential, depends on the patch width and on the number of patches. Biased sampling and unbiased simulations are also done to investigate the mechanism of nucleation and crystal growth for honeycomb and square lattices, self-assembled from three- and four-patch particles, respectively. A two-step mechanism governs the nucleation of both lattices. In the first step, the particles form a dense amorphous network, and in the second step, the particles inside the amorphous network reorient to form crystalline nuclei. Barrier heights for the nucleation of honeycomb and square lattices are 7.8 kBT and 7.4 kBT, which are close to the reported values for the nucleation of the kagome lattice. In agreement with confocal microscopy experiments, the self-assembly in a honeycomb lattice involves the formation of 5- to 7-membered rings. The 5- and 7-membered rings hamper the nucleation of the honeycomb lattice, through defect formation and rotation of the symmetry planes of crystals that form at their surfaces. With the progress of self-assembly, a substantial amount of restructuring of the defects and crystals in their vicinity is needed to heal the defects.

An automated calculation pipeline for differential pair interaction energies with molecular force fields using the Tinker Molecular Modeling Package

An automated pipeline for comprehensive calculation of intermolecular interaction energies based on molecular force-fields using the Tinker molecular modelling package is presented. Starting with non-optimized chemically intuitive monomer structures, the pipeline allows the approximation of global minimum energy monomers and dimers, configuration sampling for various monomer–monomer distances, estimation of coordination numbers by molecular dynamics simulations, and the evaluation of differential pair interaction energies. The latter are used to derive Flory–Huggins parameters and isotropic particle–particle repulsions for Dissipative Particle Dynamics (DPD). The computational results for force fields MM3, MMFF94, OPLS-AA and AMOEBA09 are analyzed with Density Functional Theory (DFT) calculations and DPD simulations for a mixture of the non-ionic polyoxyethylene alkyl ether surfactant C10E4 with water to demonstrate the usefulness of the approach.Scientific ContributionTo our knowledge, there is currently no open computational pipeline for differential pair interaction energies at all. This work aims to contribute an (at least academically available, open) approach based on molecular force fields that provides a robust and efficient computational scheme for their automated calculation for small to medium-sized (organic) molecular dimers. The usefulness of the proposed new calculation scheme is demonstrated for the generation of mesoscopic particles with their mutual repulsive interactions.

DNA sensing based on aggregation of Janus particles using dynamic light scattering

BackgroundThe aggregation of isotropic particles through interparticle reactions poses a challenge in control due to the ability of all surfaces to bind to each other, rendering the quantitative detection of such interparticle reactions based on particle size difficult. Here, we proposed a novel detection scheme for DNA utilizing an assembly of Janus particles (JPs) employing dynamic light scattering (DLS). DNA molecules are tethered on one hemisphere of the JP, while the other hemisphere retains its hydrophobic properties. ResultsAggregation of JPs was induced by the sandwich hybridization of target DNA between them. The assembly of JPs was effectively monitored by the changes in hydrodynamic diameter detected by DLS, revealing that aggregation peaks at 2–3 particles and further reaction was hindered due to the inability of one hemisphere of the JP to interact with another JP. The target DNA demonstrated detectability at concentrations as low as several tens of pM to several nM using a digital sensing method. The two types of target DNA, such as simple (14 base pairs) and HIV-2 specific sequences (20 base pairs) were detectable at nM and pM levels, respectively. Moreover, we substantiated the robustness of our detection scheme through stoichiometric calculations based on an equilibrium model. The present detection mechanism was well explained based on the binding affinity of DNA hybridization. SignificanceThis detection method harnesses the anisotropic nature of JPs and represents the first detection approach based on aggregation. By altering the modification molecules on JPs to match target molecules, such as proteins and organic compounds, a wide range of versatile molecules can be detected using this scheme with high sensitivity. This underscores the broad applicability of the present method.

Shutdown dose rate calculations in high-temperature gas-cooled reactors using the MCNP-ORIGEN activation automation tool

Background High-temperature gas-cooled reactors (HTGRs) have many distinct features from the current light water reactor (LWR) fleet, and potential decommissioning strategies should take them into consideration. The proper characterization of the shutdown dose rates can establish a suitable strategy. Methods This article introduces a new shutdown dose rate calculation capability that relies on the MCNP-ORIGEN activation automation tool and the MCNP repeated structures to explicitly model the TRistructural ISOtropic (TRISO) particles as decay radiation sources. Results Three exercises are conducted with this capability, and their results discussed. The first two exercises verify and demonstrate the workflow. The third exercise proposes a decommissioning strategy for a high-temperature gas-cooled microreactor and studies its feasibility from the shutdown dose rate standpoint. The calculations yield a dose rate map above at the reactor citadel after a three month cool-down, showing values above 40 mSv/h. Conclusions The findings imply that the decommissioning strategy based on placing the reactor in a safe shutdown state and allowing it to cool down for three months before removing various components and extracting the fuel assemblies, may not be sufficient to minimize unnecessary exposure of personnel.

Enhancing particle string detection in electrorheological plasmas using asymmetrical kernel convolutional networks

Under different plasma conditions and electric fields in a complex plasma the plasma particles organize themselves in a string-like or chain-like manner. A phase transition from string-like to an isotropic particle distribution is observed at different electrical conditions. The streaming of charged ions around plasma particles with the surrounding electric field gives the plasma its electrorheological properties. The visibility of individual particles in a complex plasma opens up the opportunity to examine properties and phase transitions of such electrorheological fluids in detail. Because of the limited one-dimensional symmetry, determining the configuration of a particle and recognizing strings in particle distributions is not always straightforward. Several approaches have already been used to analyse particle clouds while either considering each particle locally or considering the particle cloud as a whole without providing information about single particle configurations. This paper presents a new machine learning approach that takes advantage of particle distributions over the entire particle cloud and detects all string-like particles at once, using a convolutional neural network in form of an encoder-decoder network with asymmetric kernel convolutions. This not only enhances the result quality but also accelerates the evaluation process, possibly enabling real-time analyses on electrorheological phase transitions, while achieving an accuracy of over 95% on manually labelled data.