The research, led by Kabiru Dahiru Ibrahim of the College of Nuclear and Automation Engineering at Chengdu University of Technology, together with colleagues from Chengdu University of Technology, Khalifa University, the University of Dundee, and the University of Electronic Science and Technology of China, introduces a two-stage framework abbreviated WT-PSO-RBFNN. The name encodes its three building blocks: a wavelet transform for extracting fault signatures from current waveforms, particle swarm optimization for tuning a neural network, and a radial basis function neural network for making the final classification decision. The work was supported by the National Natural Science Foundation of China under grant U23A20651, and it targets a setting where the stakes are unusually high: power networks in critical installations, including nuclear facilities, where fast and dependable fault isolation is not optional but essential to safety.

The first stage of the framework addresses the hardest part of the problem, which is simply deciding whether a fault has occurred at all. Underground cable faults announce themselves through brief, high-frequency transients superimposed on the three-phase current waveforms, but these transients are fleeting and easily masked by routine switching events. The researchers pass the acquired current signals through a discrete wavelet transform using the Daubechies db4 mother wavelet, decomposed to level three, with adaptive thresholding applied to the resulting coefficients. Wavelet decomposition acts like a mathematical microscope: unlike a Fourier transform, which assumes a signal repeats indefinitely and therefore blurs the exact moment a transient begins, the wavelet transform localizes information in both time and frequency. Multi-resolution analysis splits the signal into approximation coefficients that capture slow trends and detail coefficients that isolate the sharp, sudden changes most sensitive to fault events. The db4 wavelet is a popular choice in power system protection because its compact support and near-symmetry make it well suited to detecting abrupt discontinuities in current signals without excessive distortion.

Adaptive thresholding is the second ingredient of the detection stage. Rather than applying a fixed cutoff that might miss weak faults or falsely flag benign disturbances, the method adjusts the threshold applied to the wavelet detail coefficients according to the statistical properties of the signal itself. When a genuine fault strikes, the detail coefficients at the finer decomposition levels surge well above the adaptive threshold, providing a clear and computationally cheap detection flag. This design choice matters for practical deployment: a protection relay has milliseconds to decide whether to trip a circuit breaker, so the detection logic must be simple enough to execute in real time on modest hardware. The authors emphasize that the online computational structure of their framework is consistent with real-time relay implementation requirements, a claim that distinguishes it from heavier deep learning approaches that may achieve strong accuracy in offline studies but struggle to meet the latency and memory budgets of field-deployed protective devices.

Once a fault is detected, the second stage must answer two questions: which phases are involved, and is the fault a ground fault? The researchers feed normalized wavelet-domain features into a radial basis function neural network, a class of neural network whose architecture differs fundamentally from the deep convolutional networks that dominate headlines. An RBF network consists of an input layer, a hidden layer of neurons whose activation functions are radial basis functions, typically Gaussian bumps centered at learned points in feature space, and a linear output layer. Each hidden neuron responds strongly when the input vector is close to its center, so the network effectively measures how similar a new fault signature is to the fault signatures it learned during training. This locality of response gives RBF networks fast training, interpretable structure, and, crucially, a very fast inference step, since classification reduces to evaluating a modest number of Gaussian functions and a weighted sum.

The performance of an RBF network, however, depends heavily on its internal parameters: the positions of the Gaussian centers, the widths of those Gaussians, and the output weights. Traditionally these are chosen by heuristics or by grid search, an exhaustive but computationally expensive procedure that samples parameter combinations on a fixed lattice. The Chengdu-led team instead turned to particle swarm optimization, a nature-inspired algorithm in which a population of candidate solutions, called particles, flies through the parameter space, each one remembering the best position it has personally found and being attracted toward the best position discovered by the whole swarm. This social information-sharing dynamic allows the swarm to converge on high-quality parameter settings far more efficiently than exhaustive search, and it is particularly effective for continuous optimization problems like neural network tuning. In the proposed framework, PSO searches for the RBF network parameters that minimize classification error on the training data, producing a network that is better matched to the fault classification task than one tuned by conventional means.

To evaluate the framework rigorously, the authors built a MATLAB/Simulink model of an underground transmission cable using pi-section modeling, in which the cable is represented as a cascade of series impedance and shunt admittance segments that reproduce its distributed electrical behavior. Three-phase current waveforms were generated under a diverse set of fault and no-fault operating conditions, then processed through the wavelet stage to produce the feature vectors used for classification. The dataset was split using a stratified 70/15/15 protocol into training, validation, and test sets, a design that preserves the class proportions in each subset and guards against the misleading results that can arise when rare fault types cluster in one split. Under this protocol, the PSO-optimized network achieved 98.12 percent test accuracy with a mean squared error of 0.0834.

Those numbers become meaningful in comparison with the baseline. Under identical parameter bounds, a grid search-tuned RBFNN reached 96.56 percent accuracy with an MSE of 0.087. The difference of roughly one and a half percentage points may sound modest, but in protection engineering the margin matters: every misclassified fault represents either a missed trip that allows damage to propagate or a false trip that unnecessarily de-energizes a healthy circuit. In a nuclear facility power network, either outcome carries costs that far exceed the inconvenience of an ordinary distribution outage. The comparison also demonstrates a methodological point: the improvement came purely from smarter optimization within the same search space, not from a larger model or more data, which suggests that the PSO tuning found parameter regions that grid search simply could not reach at practical computational cost.

The broader context of this work is a field in transition. The study’s bibliography surveys a decade of approaches to power system fault detection, from time-domain reflectometry and travelling wave methods, which locate faults by timing reflected signals along the cable, to singular value decomposition techniques, support vector machines, and more recently deep architectures including convolutional neural networks, LSTM networks, graph convolutional networks, and hybrid CNN-LSTM models. Deep learning methods have shown impressive results on large datasets, but they bring heavy computational demands, opaque decision-making, and a hunger for training data that underground cable fault scenarios, which are by nature rare and varied, cannot always satisfy. Wavelet-plus-RBF schemes occupy a middle ground: physically motivated feature extraction, compact classifiers, and inference speeds compatible with hardware relays. The new study positions itself squarely in that tradition while adding the swarm-optimized tuning that closes part of the accuracy gap with heavier models.

The authors are careful about the scope of their claims. The evaluation was performed on a simulation model rather than on live grid hardware, and simulated faults, however diverse, cannot capture every degradation mechanism, noise source, and measurement imperfection found in real buried cables. Validation on physical test beds and field data remains the necessary next step before such a framework could be certified for deployment in safety-critical environments. Nevertheless, the study makes a persuasive case that the path to reliable underground cable protection does not necessarily run through ever-larger neural networks. By combining a mathematically principled signal decomposition, an adaptive detection threshold, a compact classifier, and a biologically inspired optimizer, the WT-PSO-RBFNN framework delivers near-state-of-the-art accuracy with an architecture simple enough to live inside the protective relays that guard the hidden arteries of the power grid. For the operators of nuclear facilities and other critical infrastructure, where a fault that goes undetected for even a few extra cycles can cascade into serious consequences, that combination of accuracy, speed, and deployability may prove to be exactly what the field has been looking for.

Subject of Research: Computational intelligence for fault detection and classification in underground power transmission cable networks

Article Title: A computational intelligence approach for reliable fault protection of underground transmission networks

Article References: Ibrahim, K. D., Ukwuoma, C. C., Abubakar, A., Bamisile, O., Qi, H., & Cai, D. (2026). A computational intelligence approach for reliable fault protection of underground transmission networks. Cluster Computing, 29(12), Article 702. https://doi.org/10.1007/s10586-026-06357-6

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06357-6

Keywords: underground cable fault detection, wavelet transform, radial basis function neural network, particle swarm optimization, adaptive thresholding, power system protection, transmission networks, nuclear facility power systems, MATLAB Simulink, fault classification, computational intelligence, real-time relays

The foundation of the new approach is the Joint Drought Index, or JDI, a multivariate measure constructed from three complementary drought dimensions: meteorological, hydrological, and soil moisture conditions. Rather than averaging separate indices or treating them independently, the researchers used copulas, mathematical functions that describe how random variables depend on one another while preserving each variable’s individual statistical behavior. Standardized precipitation (SPI), standardized runoff (SRI), and soil moisture indices (SMI) were combined through Frank and Gaussian copulas, which model the trivariate dependence structure among the three variables. The resulting joint cumulative probability was then transformed into a standardized drought index, yielding a single number that reflects the full water-status picture of the basin at any given time.

The data underpinning the index span three decades, from 1993 to 2022, and include precipitation, temperature, evapotranspiration, streamflow, soil moisture, soil temperature, and the Normalized Difference Vegetation Index (NDVI), a satellite-derived measure of vegetation greenness. This long hydro-meteorological record allowed the team to capture drought episodes across a wide range of intensities and durations. When the researchers compared the JDI against the individual twelve-month SPI, SRI, and SMI series, they found strong consistency, with correlations ranging from 0.60 to 0.81 and agreement indices between 0.58 and 0.79. Crucially, however, the JDI offered a more coherent and persistent representation of drought episodes, showing higher mean intensity and longer duration than any single-variable index alone.

This persistence matters for practical water management. Single-variable drought indices often flicker, signaling drought onset one month and normal conditions the next, because each captures only one slice of the water cycle. By contrast, the copula-based JDI smooths these contradictions by encoding the joint probability that precipitation, runoff, and soil moisture are simultaneously deficient. For a basin like the Minab, where farmers, water managers, and ecosystems all depend on the timing and severity of dry spells, an index that integrates the full drought signal provides a more trustworthy basis for decisions about irrigation scheduling, reservoir operation, and emergency response.

Constructing a better index was only half the challenge. The team also wanted to predict how drought would evolve, a notoriously difficult task because drought dynamics are nonlinear: small changes in one component can amplify or dampen the trajectory of the whole system. To capture this behavior, the researchers turned to phase space reconstruction (PSR), a technique from chaos theory that rebuilds the geometry of a dynamical system from a single time series. Using methods originally developed by Takens and refined through mutual information and false-nearest-neighbor analyses, they identified optimal embedding parameters of dimension m = 8 and time delay τ = 8. The lagged components of the JDI in this reconstructed phase space then served as inputs to machine learning predictors.

Two learning machines were tested: support vector regression (SVR) and a radial basis function neural network (RBFNN). To squeeze the best performance from each, the team employed the Firefly Algorithm, a nature-inspired optimization method that mimics the flashing behavior of fireflies to search efficiently for optimal hyperparameter settings. The resulting hybrid models, PSR–SVR–FFA and PSR–RBFNN–FFA, were evaluated with a battery of statistical metrics including the coefficient of determination (R²), root mean square error, mean absolute error, uncertainty amplitude, and prediction interval coverage. The results were striking. The PSR–SVR–FFA model achieved an R² of 0.96 during training and 0.94 during testing, while the PSR–RBFNN–FFA model reached approximately 0.91 and 0.89 respectively, indicating that the framework generalizes well to unseen data rather than merely memorizing the training record.

Uncertainty quantification, often neglected in drought forecasting, formed a central pillar of the evaluation. The uncertainty amplitude, a measure of how wide and unreliable the model’s prediction bands are, dropped dramatically from baseline levels of roughly 3.06 to 3.52 down to 0.47 for the PSR–SVR–FFA model and 0.78 for the PSR–RBFNN–FFA model. Prediction intervals covered up to 88 percent of observations, meaning that when the model issues a forecast, it can also state, with quantified confidence, the range within which the true drought condition is likely to fall. For decision-makers, this transparency is as valuable as accuracy itself: a forecast that admits its own uncertainty can be weighed appropriately against other risks.

The study also employed Sobol sensitivity analysis, a global sensitivity method that decomposes the variance of model output to determine which inputs drive predictions. By attributing portions of predictive variance to individual lagged JDI components, the analysis provides interpretability in a field often criticized for opaque black-box models. The findings point to phase space reconstruction as the key factor enhancing stability and accuracy, suggesting that explicitly encoding the nonlinear dynamics of drought evolution, rather than feeding raw time series into a learner, is what unlocks the hybrid models’ superior performance. This insight has implications well beyond the Minab Basin, since PSR is computationally inexpensive and applicable to any sufficiently long environmental time series.

The broader context makes the work timely. Iran has experienced recurrent and intensifying droughts, and arid regions worldwide face growing water stress as climate change alters precipitation patterns and increases atmospheric evaporative demand, a factor that recent research has shown to be increasingly important in global drought dynamics. Multivariate, copula-based approaches have gained traction in hydrology precisely because droughts are compound events, and the Minab study demonstrates how such statistical rigor can be married with modern machine learning to produce operational forecasting tools. The framework is described by its developers as robust and interpretable, offering a template that other water-stressed basins could adapt using locally available hydro-meteorological and remote sensing data.

For the communities of the Minab River Basin, the practical promise is concrete: earlier, more reliable warnings of drought onset, better estimates of how long dry spells will persist, and forecasts whose confidence bounds are honest about what remains unknown. For the scientific community, the study is a demonstration of methodological synthesis, showing how copula statistics, chaos-theoretic reconstruction, swarm-intelligence optimization, and supervised learning can be assembled into a pipeline greater than the sum of its parts. As water scarcity intensifies across the world’s drylands, tools of this kind, grounded in three decades of local data and validated against rigorous uncertainty metrics, may become essential instruments in the effort to anticipate, rather than merely react to, the slow-moving disasters that droughts represent.

Subject of Research: Copula-based multivariate drought index modeling and nonlinear machine learning prediction of drought in an arid Iranian river basin

Article Title: Copula-based multivariate joint drought index (JDI) modeling and nonlinear prediction using PSR–machine learning framework with sobol sensitivity analysis in the Arid Region

Article References: Golsefidi, E. H., Esmaeilpour, Y., Bazrafshan, O., Zamani, H., & Biniaz, M. (2026). Copula-based multivariate joint drought index (JDI) modeling and nonlinear prediction using PSR–machine learning framework with sobol sensitivity analysis in the Arid Region. Theoretical and Applied Climatology, 157(11), Article 692. https://doi.org/10.1007/s00704-026-06620-1

Image Credits: AI Generated

DOI: 10.1007/s00704-026-06620-1

Keywords: drought, joint drought index, copulas, phase space reconstruction, machine learning, support vector regression, radial basis function neural network, Firefly Algorithm, Sobol sensitivity analysis, arid region, Minab River Basin, uncertainty analysis

The material at the heart of the work is the magnetorheological elastomer, or MRE, a class of smart composite in which micrometer-scale magnetic particles are suspended in an elastic polymer matrix. When an external magnetic field is applied, the particles align and interact, stiffening the material and shifting its effective stiffness and damping properties within milliseconds. This reversible, field-controlled behavior makes MREs attractive for semi-active vibration isolation, in which the isolator adjusts its own mechanical properties in real time rather than relying on a fixed spring-damper design or consuming large amounts of power like a fully active actuator. Because the device modifies an inherent property of its material rather than injecting energy into a structure, semi-active systems also carry inherent stability advantages that have made them popular in automotive suspensions, seismic protection, and machinery mounting.

Yet MREs bring a notorious complication: their behavior is strongly nonlinear and hysteretic. The relationship between the applied magnetic field, the deformation of the elastomer, and the resulting force does not follow a simple algebraic rule. Instead, the material’s response depends on its deformation history, and its stiffness changes with both field strength and the amplitude and frequency of vibration. A controller designed under one set of assumptions can perform poorly, or even destabilize the system, when excitation conditions change. This is precisely the challenge the research team set out to address, focusing on excitations whose frequency and amplitude vary over a realistic operating envelope.

The experimental platform described in the study is a purpose-built MRE isolator with an orthogonal magnetic flux configuration. In this arrangement, the magnetic field is directed perpendicular to the plane in which the elastomer is sheared or compressed, maximizing the interaction between the field and the embedded particles while making efficient use of the magnetic circuit. The team fabricated the isolator and then systematically characterized its dynamic behavior under harmonic excitation across a frequency range of 15 to 80 hertz. This range is significant for practical isolation problems, because it spans many resonant frequencies of machinery mounts, vehicle subframes, and structural components where vibration damage and comfort problems concentrate. Mapping the isolator’s response across this band revealed the frequency-dependent shifts in stiffness and damping that any controller would need to handle.

To exploit the material’s adaptability without falling victim to its unpredictability, the researchers designed a hybrid controller built from two complementary elements. The first is a radial basis function neural network, or RBF network, a machine learning architecture whose output is a weighted sum of responses from localized, bell-shaped basis functions distributed across the input space. Because each basis function responds strongly only to inputs near its center, RBF networks can approximate nonlinear, spatially varying relationships efficiently and can be trained or updated online. In this application, the network’s job is to learn and adaptively estimate the isolator’s nonlinearities and hysteresis as they manifest under changing vibration conditions, providing a continuously refined model of the plant that a fixed mathematical model could never supply.

The second element is the sliding mode controller, a robust control technique with a long pedigree in engineering practice. Sliding mode control drives the system’s state trajectory onto a deliberately chosen sliding surface, along which the desired dynamic behavior is guaranteed, and then holds it there using a discontinuous control action that is insensitive to matched uncertainties. Its strength is robustness: once on the sliding surface, the closed-loop system tolerates a defined class of modeling errors and disturbances. Its weakness is that aggressive switching can amplify noise and induce chattering, and it traditionally requires a reasonably accurate bound on system uncertainties. The hybrid design resolves this tension elegantly, with the neural network absorbing the burden of representing the nonlinear, hysteretic dynamics while the sliding mode framework guarantees stability and rejects residual disturbances.

The division of labor matters because vibration isolation is a moving target. As excitation frequency sweeps through the resonance region, the isolator’s transmissibility changes rapidly; as amplitude grows, hysteresis loops widen and effective damping shifts. A purely neural approach risks drifting toward inaccurate estimates when conditions move outside its training experience, while a purely sliding mode approach would demand conservative margins that sacrifice performance. By integrating the two, the controller adapts its internal estimate of the system in real time while the sliding mode law enforces stable tracking of the isolation objective. The researchers evaluated this architecture both in simulation and experimentally, providing converging lines of evidence that the scheme works not only on paper but on a physical device subjected to real harmonic excitation.

The headline result is the maximum vibration reduction of 55.8 percent achieved near the resonance region under the tested conditions, the operating point where conventional passive isolators typically struggle most. Near resonance, even modest input forces can produce large transmitted vibrations, so effective attenuation there is the gold standard for isolator performance. Equally important, the study reports that the semi-active MRE isolator maintained stable performance across the full range of investigated excitation frequencies, indicating that the hybrid controller did not merely optimize for one narrow condition but adapted gracefully as the excitation environment changed. Stable adaptive performance under varying frequency and amplitude is the property that distinguishes an engineering solution from a laboratory demonstration tuned to a single test case.

The implications extend across several industries. Automotive engineers could apply such isolators to engine mounts and suspension elements, where excitation frequency changes constantly with driving conditions. Aerospace and marine systems, which encounter broadband vibration from rotating machinery and fluid-structure interaction, could benefit from isolators that retune themselves without mechanical adjustment. Precision manufacturing and semiconductor fabrication equipment, which must sit motionless on floors that are never truly still, represent another natural application. In earthquake engineering, semi-active devices built on similar principles have already been explored for structural protection, and a controller that handles nonlinear material behavior robustly could strengthen the case for MRE-based seismic isolators. Because semi-active systems require only modest power to drive the magnetic field rather than to generate control forces, they remain practical for battery-backed or low-power installations.

The work also speaks to a broader trend in control engineering: the marriage of learning-based models with provably robust control laws. Purely data-driven controllers often struggle to offer formal guarantees, while classical robust controllers can be overly conservative when systems are too nonlinear for simple models. Hybrid architectures such as the one demonstrated here let each approach cover the other’s weaknesses, a pattern that is spreading through robotics, energy systems, and aerospace. For magnetorheological elastomers specifically, the study suggests that the material’s most daunting property, its hysteresis, can be converted from an obstacle into a managed characteristic. The authors position the framework as an effective solution for handling nonlinear dynamics and a route toward greater adaptability in smart vibration isolation systems. As smart materials mature and machine learning hardware becomes inexpensive enough to embed in everyday devices, the vision of structures that sense, decide, and quiet themselves in milliseconds moves closer to routine engineering practice, and this research offers a concrete, experimentally validated blueprint for how that quieting can be achieved.

Subject of Research: Hybrid neural network and sliding mode control of a magnetorheological elastomer vibration isolator under variable excitation conditions

Article Title: Hybrid RBF neural network–based sliding mode control for a magnetorheological elastomer isolator under variable frequency and amplitude excitations

Article References: Katari, K., Poojary, U. R., Hegde, A., & K. V., G. (2026). Hybrid RBF neural network–based sliding mode control for a magnetorheological elastomer isolator under variable frequency and amplitude excitations. PLOS One, 21(10), e0360069. https://doi.org/10.1371/journal.pone.0360069

Image Credits: AI Generated

DOI: 10.1371/journal.pone.0360069

Keywords: magnetorheological elastomer, vibration isolation, sliding mode control, radial basis function neural network, semi-active control, smart materials, hysteresis, nonlinear dynamics, adaptive control, resonance, magnetic field, PLOS One

The core challenge the researchers tackled is one that has haunted robotics engineers for decades. A robotic manipulator is a strongly coupled, nonlinear system: moving one joint changes the forces acting on every other joint, and the equations governing its motion involve inertia, Coriolis and centrifugal effects, gravity, and friction that all shift as the arm moves through space. When the actual mass or inertia of a link differs from the values in the controller’s internal model, when Coulomb and viscous friction resist motion in ways that are hard to characterize, or when external torques push on the arm, tracking accuracy degrades and stability can be compromised. The team, led by Xiaole Ma and corresponding author Chenghu Jing, built their approach on a rigorous mathematical model of the UR10 that explicitly accounts for these perturbations, lumping all the unknown dynamics into a single disturbance term that their controller must confront head-on.

Their solution rests on a division of labor between two complementary technologies. The first is a radial basis function neural network, a lightweight learning architecture prized for its simple structure and its ability to approximate any continuous nonlinear function within a defined region. Placed in the feedforward path of the controller, the network observes the robot’s state in real time and learns to predict the lumped unknown dynamics, from friction quirks to inertia mismatches. By absorbing the dominant nonlinearities before they can corrupt the motion, the network dramatically shrinks the size of the residual disturbance that the robust part of the controller must handle. This matters because the size of that residual directly determines how aggressive, and how energy-hungry, the robust control term needs to be.

That robust term is where the super-twisting algorithm enters the picture. Sliding-mode control is a classic robust technique: it drives the system’s tracking error onto a carefully chosen sliding surface and then uses aggressive switching to hold it there, making the system immune to a broad class of disturbances. The trouble is that conventional sliding-mode control relies on discontinuous switching, which produces the infamous phenomenon of chattering, a high-frequency oscillation in the control torque that excites unmodeled vibrations, wastes energy, and accelerates wear on actuators and gears. The super-twisting algorithm, a second-order sliding-mode technique, solves this problem elegantly. Instead of switching the torque itself, it applies a continuous combination of a term proportional to the square root of the sliding variable’s magnitude and an integral term, achieving the same finite-time convergence and disturbance rejection while producing a smooth, continuous control signal.

The Chinese team’s contribution is a carefully engineered synthesis of these two elements, backed by a rigorous stability proof. They defined a linear sliding surface based on the tracking error and its derivative, then constructed a control law with three modules: a nominal dynamic compensation term built from the robot’s known model, the neural network feedforward term for online approximation of unknown dynamics, and the super-twisting robust term to suppress residual disturbances. To keep the neural network’s weights from drifting to unbounded values, a common failure mode of adaptive schemes, they introduced a projection-based adaptive law that mathematically guarantees the weight estimates never exceed a preset safety boundary. Using Lyapunov stability theory, the researchers proved that both the sliding variable and the tracking error converge in finite time, with explicit gain conditions relating the super-twisting parameters to the disturbance bound.

The proof framework itself represents a departure from conventional practice. Rather than using the adaptive law to exactly cancel uncertainty terms, which can lead to gain drift and complicated derivations, the team adopted a decoupled design in which the neural network physically reduces the total disturbance bound. This allows the super-twisting gains to be substantially relaxed, cutting energy consumption and further suppressing chattering while preserving the finite-time stability guarantee. It is a design philosophy that treats the neural network and the robust controller as partners rather than competitors, each doing the job it is best suited for.

To test the approach, the researchers ran simulations on a full six-degree-of-freedom UR10 model using experimentally identified nominal parameters. They deliberately made the task hard: the masses of joints two and three were increased by twenty percent, centers of mass were shifted, inertias were perturbed by five percent, and a smooth sigmoidal friction model captured Coulomb and viscous effects in every joint. A sinusoidal external disturbance of 0.5 newton-meters was applied to all joints, and a fixed-gain study showed the method maintained tracking errors below 0.005 radians even when disturbances reached 2.0 newton-meters. The robot was commanded to move from one pose to another along a fifth-order polynomial trajectory over ten seconds, with a control period of one millisecond.

The results were emphatic. Under pure neural network control, lacking any robust term, the steady-state errors of the wrist joints ballooned to as much as 0.82 radians, with maximum errors exceeding one radian, an unacceptable failure. Conventional sliding-mode control fared far better, reducing steady-state errors to the thousandth-of-a-radian range, but the proposed composite controller cut them further still: joints four and five achieved steady-state errors of 0.0005 and 0.0017 radians, improvements of more than fifty percent and seventy-eight percent over pure sliding-mode control. All joints except one achieved steady-state errors better than one-thousandth of a radian. Measured by the integral of time-weighted absolute error, a standard metric combining response speed and steady-state accuracy, the composite controller outperformed pure sliding-mode control by 86.1 percent and pure neural network control by 99.7 percent. In Cartesian space, the end effector’s steady-state error shrank to 0.0002 meters, compared with 0.0007 meters for sliding-mode control and a disastrous 0.1031 meters for the network alone.

Just as important as the accuracy is the character of the control signals. The composite controller produced continuous, smooth torques free of the high-frequency chattering that traditional sliding-mode schemes generate, with peak torques around 62 newton-meters at joint two, comfortably below actuator saturation limits. The neural network’s weights, rather than growing without bound as they did under pure network control, stabilized at a low value after a brief transient, confirming that the super-twisting term was shouldering the main disturbance rejection burden while the network handled fine compensation. The method also proved its generality on continuous sinusoidal trajectories simulating industrial operation, with all joint root-mean-square errors below 0.003 radians. The authors note that future work will focus on experimental validation on a physical UR10 platform, adaptive optimization of the network structure, and integration of iterative learning with neural sliding-mode control. If hardware trials confirm the simulation results, this hybrid of learning and robust control could find a home in precision assembly, medical assistance, and any application where a robot arm must move exactly where it is told, even when the world pushes back.

Subject of Research: Composite neural network and super-twisting sliding-mode control for high-precision trajectory tracking of the UR10 robotic manipulator

Article Title: Trajectory-tracking control of the UR10 manipulator based on radial basis function neural network and super-twisting sliding mode

Article References: Ma, X., Jing, C., Zhang, K., Chen, C., & Wang, Y. (2026). Trajectory-tracking control of the UR10 manipulator based on radial basis function neural network and super-twisting sliding mode. Mechanical Sciences, 17(2), 759-767. https://doi.org/10.5194/ms-17-759-2026

Image Credits: AI Generated

DOI: 10.5194/ms-17-759-2026

Keywords: robotics, UR10 manipulator, trajectory tracking, sliding-mode control, super-twisting algorithm, radial basis function neural network, chattering suppression, adaptive control, Lyapunov stability, finite-time convergence, collaborative robots, nonlinear friction

Construction and demolition waste, commonly abbreviated as CDW, is generated in staggering quantities wherever buildings rise and fall. It includes concrete, bricks, mortar, tiles, timber, metals, and a heterogeneous mixture of residual materials that end up stockpiled on vacant lots, dumped along roadsides, or spread informally across land at the edges of expanding neighborhoods. While much of this material appears inert, decades of research have shown that rainwater percolating through rubble can dissolve and carry away a suite of toxic elements. Lead, arsenic, cadmium, copper, zinc, and manganese are among the most frequently detected, and each behaves differently once it enters the soil environment. The new study led by Francis Agyapong of the Department of Materials Engineering at Kwame Nkrumah University of Science and Technology set out to quantify exactly which of these elements are escaping from waste piles in Kumasi, how concentrated they are, and how far they travel through the ground.

The research team collected samples of construction and demolition waste from an active construction site in Kumasi, along with samples of the soil lying directly beneath and around the waste deposits. Back in the laboratory, the samples were digested and analyzed to determine the concentrations of six target heavy metals: lead, arsenic, zinc, copper, manganese, and cadmium. These six were chosen deliberately. Lead and arsenic are notorious for their toxicity even at low exposures, cadmium accumulates in the kidneys and bones of humans and animals, and copper, zinc, and manganese, although essential micronutrients at trace levels, become damaging contaminants when concentrations climb beyond natural background ranges. By comparing metal levels in the waste itself with levels in the underlying soil, the researchers could infer which elements were actively leaching out of the debris and entering the soil column.

One of the study’s most consequential findings concerns the physical character of the waste itself. Analysis showed that the construction and demolition waste in Kumasi is dominated by sand-sized particles. This composition matters enormously for contaminant transport. Coarse, sandy material has large pore spaces between grains, allowing water to infiltrate quickly and percolate downward with minimal filtration. In contrast, fine-grained clays and silts tend to slow water movement and can adsorb metals onto particle surfaces, effectively immobilizing them. The sandy nature of the Kumasi waste therefore acts like a permeable conduit, helping leachate, the contaminated liquid that forms as water passes through waste, move easily through the deposit and into the underlying ground. In practical terms, the rubble piles scattered across the city are not merely unsightly; they function as diffuse, unlined chemical reactors that release their contents whenever it rains.

To move beyond simple concentration measurements, the team employed two complementary modeling approaches to map how contamination spreads through space. The first, inverse distance weighting, or IDW, is a geostatistical interpolation technique that estimates values at unsampled locations based on the measured values at surrounding sampling points, weighting nearby observations more heavily than distant ones. IDW is widely used in environmental monitoring because it is computationally straightforward and produces intuitive contamination surfaces. The second approach was more sophisticated: a radial basis function neural network, or RBF network, a machine learning architecture that uses radial basis functions as activation functions to approximate complex, nonlinear relationships in data. Radial basis function networks have a long history in engineering, having been applied to problems ranging from power system stabilization to function approximation, and they excel at fitting irregular multidimensional surfaces. By training the network on the measured metal concentrations, the researchers could predict both the vertical and horizontal spread of contaminants through the site, generating predictive maps of where pollution is heading rather than merely where it has already been detected.

The modeling results revealed a clear hierarchy of mobility among the six metals. Copper, zinc, and manganese emerged as the most mobile contaminants, spreading appreciably from their source and dispersing through the soil profile. Lead and arsenic, by contrast, tended to remain localized near the waste deposits, showing limited migration. This contrast reflects fundamental differences in geochemical behavior. Zinc and manganese form relatively soluble species under the mildly acidic conditions that often develop in decomposing waste, while copper, though it binds strongly to organic matter, can still be transported when complexing agents are present. Lead and arsenic, meanwhile, tend to adsorb strongly onto iron oxides and clay minerals or precipitate as insoluble compounds, anchoring them in place. The distinction is critical for risk assessment: mobile metals threaten groundwater and wider soil ecosystems, whereas immobile ones create persistent hotspots that can poison anything rooted directly in them and can be remobilized if soil chemistry changes.

The environmental consequences of this mobility are far-reaching. The study highlights soil degradation as a primary concern, since accumulating metals alter soil chemistry, disrupt nutrient cycling, and diminish fertility. Plants growing in contaminated ground take up metals through their roots, introducing toxins into the food chain and suppressing growth. Soil microbial communities, the invisible engines that decompose organic matter and sustain soil health, are also vulnerable, as elevated metal concentrations reduce microbial diversity and activity. In a city like Kumasi, where urban agriculture and informal gardening are common and where many residents rely on shallow wells, the migration of copper, zinc, and manganese through sandy soils raises the specter of contaminated drinking water and contaminated food produced on or near waste dumps. Because these impacts unfold gradually and invisibly, they often escape regulatory attention until damage is well advanced.

What makes the study particularly timely is the trajectory of urbanization in Ghana and across sub-Saharan Africa. Construction booms in rapidly growing cities generate enormous volumes of demolition debris, yet formal recycling infrastructure remains limited, and enforcement of disposal regulations is inconsistent. Much of the region’s CDW is managed informally, with little consideration of where waste is placed or what it contains. Previous international research, including life cycle assessments and leaching studies of recycled concrete aggregates in Europe, has documented similar contamination pathways, but localized data from African cities has been scarce. The Kumasi study helps fill that gap, demonstrating that the tools of modern environmental science, from laboratory digestion analysis to GIS-based interpolation and neural network modeling, can be deployed effectively in data-scarce settings to characterize risks that would otherwise go unmeasured.

The authors do not stop at diagnosis. Their recommendations form a three-pronged response to the problem. First, they call for regulatory reform, arguing that existing frameworks governing construction and demolition waste disposal are inadequate to the scale of the challenge and need stronger standards for where and how debris may be stockpiled. Second, they advocate sustainable construction practices, including better sorting of waste streams, reuse of clean materials, and reduction of hazardous components in building products, so that less toxic material enters the waste cycle in the first place. Third, they recommend chemical stabilization, a remediation technique in which binding agents such as lime, cement, or phosphate amendments are mixed into contaminated soil or waste to immobilize metals chemically, reducing their solubility and preventing further leaching. Applied together, these measures could transform CDW from an unmanaged hazard into a managed resource stream.

The broader lesson of the Kumasi research is that the environmental cost of a building does not end when the building comes down. Rubble piles are active chemical systems whose behavior depends on their composition, their particle size, the local climate, and the chemistry of the ground beneath them. As cities worldwide pursue circular economy goals and seek to recycle more construction waste into new roads, embankments, and aggregates, studies like this one serve as a caution: recycled does not automatically mean safe. Understanding what leaches from waste, how far it travels, and who is exposed downstream is a prerequisite for any genuinely sustainable construction future. For Kumasi, and for the countless cities following the same growth trajectory, the metals hidden in the rubble are now on the scientific record, and the clock on remediation is running.

Subject of Research: Leaching and spatial migration of heavy metals from construction and demolition waste in Kumasi, Ghana

Article Title: Assessment of leached heavy metals from construction and demolition waste

Article References: Agyapong, F., Koomson, B., Kwofie, S., Gidigasu, S. S. R., & Gyamfi, C. (2026). Assessment of leached heavy metals from construction and demolition waste. Environmental Monitoring and Assessment, 198(10), Article 1097. https://doi.org/10.1007/s10661-026-15868-z

Image Credits: AI Generated

DOI: 10.1007/s10661-026-15868-z

Keywords: heavy metals, construction and demolition waste, leaching, soil contamination, Ghana, Kumasi, groundwater, inverse distance weighting, radial basis function neural network, GIS mapping, waste management, chemical stabilization