Neural Network Meets Sliding Mode Control to Tame Smart Vibration Isolators

Vibration is one of the quietest enemies of modern engineering. It rattles sensitive instruments in laboratories, fatigues aircraft components, degrades the ride quality of vehicles, and can push precision manufacturing equipment out of tolerance within moments. Engineers have long sought materials and control strategies that can absorb unwanted motion before it propagates through a structure. A study published in PLOS One by Kiran Katari, Umanath R. Poojary, Ananda Hegde, and Gangadharan K. V. reports a meaningful step forward in this field: a hybrid control scheme that couples a radial basis function neural network with a sliding mode controller to command a magnetorheological elastomer isolator, achieving a maximum vibration reduction of 55.8 percent near the resonance region under the investigated operating conditions.

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