Predicting ambient noise is critical for tactical decision aids (TDAs) and simulated-stimulation (SIM/STIM) trainers. The Fleet requires a noise model with additional spatial and directional dependence; frequency range; sources of sound; and temporal statistics. The Fleet also requires a capability for forward-deployed noise modeling. ARiA, a research and development firm that brings together top-quality research scientists with system and software engineers, is developing the Multi-Dimensional Ambient Noise Model (MDANM) service-oriented architecture (SOA), along with algorithms and software, to support deployment into TDAs and SIM/STIM trainers. These capabilities include soundscape scene analysis tools to support population databases and use on forward-deployed platforms; deep generative models for compression and transmission to forward-deployed platforms and in-situ data assimilation; and directional-noise array-gain prediction tools.
Esail Cloud is a 3D acoustic modeling application developed by ARiA, a research and development firm that brings together top-quality research scientists with system and software engineers. Esail Cloud leverages accurate data to teach basic through advanced levels of tactical oceanography and integrates with learning management systems where scenarios can be practiced outside of scheduled simulation times. This allows more flexibility for those enlisted to learn and test their knowledge with or without instructors present. Simulating the acoustic environment offers a safe environment to test skills to ensure mission readiness. Learners can also revisit and relearn concepts. With excellent 3D acoustic modeling, Esail Cloud is an innovative and powerful tool for those who want the highest level of preparation and training with accurate acoustic modeling.
This technology combines edge-diffraction modeling, boundary-element methods, and parallel processing to create a model of acoustic scattering of midfrequency active sonar from underwater targets that are larger than mines and smaller than conventional submarines. ARiA’s approach offers an accurate and efficient method for calculating acoustic scattering of midfrequency threats that is 10 times faster than current state-of-the-art target-scattering models and scales well at high frequencies. This method has been validated against third party BEM software and analytical solutions. ARiA provides research and development in interdisciplinary acoustics, signal processing, modeling & simulation, machine learning, and artificial intelligence. The goal is to transition this technology as a tool for ONR, NAVAIR, and NAVSEA to use in creating midfrequency synthetic target signatures for developing signal-processing algorithms.
Performance of detection and classification of targets in active sonar systems may be degraded in the presence of stationary clutter, ownship motion-induced clutter, and active interference. Applied Research in Acoustics’ (ARiA) sparse estimation algorithms estimate and separate targets, reverberation, and mutual interference signals from a cluttered signal and enable novel classification features to be computed from sparse representations. Integration of ARiA’s advanced signal and information processing enables automated and semi-automated sonar signal detection and classification, thus reducing operator workload. ARiA’s signal and information processing enhancements are targeted for the AN/SQQ89A(V)15 Integrated Undersea Warfare (USW) Combat System Suite’s pulsed active sonar (PAS) function segment (PASFS) echo tracker classifier (ETC). However, the developed algorithms are suitable for integration into most active sonar or radar platforms.
Performance of active sonar systems may be degraded by strong backscattering from resonant biological acoustic scatterers such as air-filled swim bladders in fish. Applied Research in Acoustics’ (ARiA) adaptive signal processing algorithms unmask targets near regions of strong biological clutter to prevent target suppression in the detector. Better-preserved signals and new secondary classification features enable better target discrimination from clutter. Integration of ARiA’s advanced signal processing, enables automated and semi-automated sonar signal detection and classification, thus reducing operator workload. ARiA’s signal processing enhancements are targeted for the AN/SQQ89A(V)15 Integrated Undersea Warfare (USW) Combat System Suite’s pulsed active sonar (PAS) function segment (PASFS) echo tracker classifier (ETC). However, the developed algorithms are suitable for integration into most active sonar or radar platforms.
Expert anti-submarine-warfare (ASW) operators employ mental models to understand environmental conditions and target properties and select acoustic-sensor settings to optimize probability of detection (Pd) in target-specific missions. The Environment for Surface ASW Interactive Learning (ESAIL) helps sonar operators develop and maintain mental models that enable analysis and employment providing the highest Pd. ESAIL employs video-game interfaces to establish mission-relevant training environments from which operators draw connections between physical scenarios and corresponding AN/SQQ-89A(V)15 ASW Combat System displays. Leveraging ARiA’s expertise in game-based learning and simulation-based training, ESAIL uses recorded tape data and real-time simulation to accelerate expertise acquisition. ESAIL implementation has been targeted for the AN/SQQ-89A(V)15 and employs a platform-agnostic build environment suitable for all Navy sonar-system variants. ESAIL is easily tailored to work across platforms and sensor types.