University of California

Lawrence Livermore National Security, LLC

Yuanping Song

Jonathan Hopkins

Robert Matthew Panas

Andrew J Pascall

Julie A Mancini

Ali Hatamizadeh

A boundary learning optimization tool for training neural networks with accurate models of parameterized flexure using a minimal number of numerically generated performance solutions generated from different design instantiations of those topologies. Performance boundaries are output by the neural network in optimization steps, with geometric parameters varied from smallest allowable feature sizes to largest geometrically compatible feature sizes for given constituent materials. The plotted performance boundaries define the design spaces of flexure systems toward allowing designers to visually identify which geometric versions of their synthesized topologies best achieve desired combinations of performance capabilities.

Apparatus and method for boundary learning optimization

The present disclosure is directed to various mechanical logic gates. In one example a mechanical logic NOT gate system is formed which has a first pair of bi-stable buckling structures each being operatively connected at a first connection point thereof to one another, and also to a first rigid structure at second connection points, the first rigid structure being held stationary. A second pair of bi-stable buckling flexures is each operatively connected at first connection points thereof to each other and at second connection points thereof to a second rigid structure being held stationary. An output element is coupled a first one of each of the first and second pairs of bi-stable buckling structures. An input element is coupled to a second one of each of the first and second pairs of bi-stable buckling structures. The output element moves from a logic 1 position to a logic 0 position in response to movement of the input element from a logic 0 position to a logic 1 positions, respectively.

Systems for mechanical logic based on additively manufacturable micro-mechanical logic gates

A microarchitectured material having a plurality of interconnected unit cells in 2D or 3D configurations. The permanent interconnections to adjacent unit cells include mechanical output structures driven by mechanical actuators. One or more sensors are preferably utilized, such as utilizing a sensing mode of the actuator, for detecting forces and or displacements applied to the unit cell. The unit cells are each controlled by a control circuit for generating drive signals to the actuators in the unit cell so that desired mechanical properties and/or shapes are exhibited by the microarchitectured material.

Growing community of inventors

Los Angeles, CA, United States of America

Yuanping Song