A method is discussed for using neural networks to control optical tweezers. Neural-net outputs are combined with scaling and tiling to generate 480X480-pixel control patterns for a spatial light modulator (SLM). The SLM can be combined in various ways with a microscope to create movable tweezers traps with controllable profiles. The neural nets are intended to respond to scattered light from carbon and silicon carbide nanotube sensors. The nanotube sensors are to be held by the traps for manipulation and calibration. Scaling and tiling allow the 100X100-pixel maximum resolution of the neural-net software to be applied in stages to exploit the full 480X480-pixel resolution of the SLM. One of these stages is intended to create sensitive null detectors for detecting variations in the scattered light from the nanotube sensors.
This paper answers some performance and calibration questions about a non-destructive-evaluation (NDE) procedure that uses artificial neural networks to detect structural damage or other changes from sub-sampled characteristic patterns. The method shows increasing sensitivity as the number of sub-samples increases from 108 to 6912. The sensitivity of this robust NDE method is not affected by noisy excitations of the first vibration mode. A calibration procedure is proposed and demonstrated where the output of a trained net can be correlated with the outputs of the point sensors usded for vibration testing. The calibration procedure is based on controlled changes of fastener torques. A heterodyne interferometer is used as a displacement sensor for a demonstration of the challenges to be handled in using standard point sensors for calibration.
This paper discusses progress in using spatial light modulators and interferometry to control the beam profile of an optical tweezers. The approach being developed is to use a spatial light modulator (SLM) to control the phase profile of the tweezers beam and to use a combination of the SLM and interferometry to control the intensity profile. The objective is to perform fine and calculable control of the moments and forces on a tip or tool to be used to manipulate and interrogate nanostructures. The performance of the SLM in generating multiple and independently controllable tweezers beams is also reported. Concurrent supporting research projects are mentioned and include tweezers beam scattering and neural-net processing of the interference patterns for control of the tweezers beams.
Artificial neural networks have been used for a number of years to process holography-generated characteristic patterns of vibrating structures. This technology depends critically on the selection and the conditioning of the training sets. A scaling operation called folding is discussed for conditioning training sets optimally for training feed-forward neural networks to process characteristic fringe patterns. Folding allows feed-forward nets to be trained easily to detect damage-induced vibration-displacement-distribution changes as small as 10 nanometers. A specific application to aerospace of neural-net processing of characteristic patterns is presented to motivate the conditioning and optimization effort.
Artificial neural networks can be used to process patterns corrupted by the laser speckle effect. This paper discusses an examples where neural networks were used to detect structural damage using characteristic fringe patterns as input. The artificial neural networks were trained with fringe patterns generated from a finite element model and a simple model of the laser speckle effect. The neural networks were tested on patterns generated by both models and real structures. The neural networks are being developed as high-speed processors for electronic holography. This paper quantifies the overhead required to make neural networks robust to the laser speckle effect. There is a discussion of the ability of these networks to generalize at finite element resolutions on the underlying fringe patterns. The ultimate objective is to test whether combinations of electronic holography and neural networks can be effective interfaces between computational models and experiments or tests.
Artificial neural networks are suitable for performing pattern-to-pattern calibrations. These calibrations are potentially useful for facilities operations in aeronautics, the control of optical alignment, and the like. This paper compares computed tomography with neural net calibration tomography for estimating density from its x-ray transform. X-ray transforms are measured, for example, in diffuse-illumination, holographic interferometry of fluids. Computed tomography and neural net calibration tomography are shown to have comparable performance for a 10 degree viewing cone and 29 interferograms within that cone. The system of tomography discussed is proposed as a relevant test of neural networks and other parallel processors intended for using flow visualization data.