Spectra to Structure: Deep Reinforcement Learning for Molecular Inverse Problem

Spectroscopy is the study of how matter interacts with electromagnetic radiations of specific frequencies that has led to several monumental discoveries in science. The spectra of any particular molecule is highly information-rich, yet the inverse relation from the spectra to the molecular structure is still an unsolved problem. Nuclear Magnetic Resonance (NMR) spectroscopy is one such critical tool in the tool-set for scientists to characterise any chemical sample. In this work, a novel framework is proposed that attempts to solve this inverse problem by navigating the chemical space to find the correct structure that resulted in the target spectra. The proposed framework uses a combination of online Monte- Carlo-Tree-Search (MCTS) and a set of offline trained Graph Convolution Networks to build a molecule iteratively from scratch. Our method is able to predict the correct structure of the molecule ∼80% of the time in its top 3 guesses. We believe that the proposed framework is a significant step in solving the inverse design problem of NMR spectra to molecule.

RANGE-GAN: Design Synthesis Under Constraints Using Conditional Generative Adversarial Networks

Typical engineering design tasks require the effort to modify designs iteratively until they meet certain constraints, i.e., performance or attribute requirements. Past work has proposed ways to solve the inverse design problem, where desired designs are directly generated from specified requirements, thus avoid the trial and error process. Among those approaches, the conditional deep generative model shows great potential since 1) it works for complex high-dimensional designs and 2) it can generate multiple alternative designs given any condition. In this work, we propose a conditional deep generative model, Range-GAN, to achieve automatic design synthesis subject to range constraints. The proposed model addresses the sparse conditioning issue in data-driven inverse design problems by introducing a label-aware self-augmentation approach. We also propose a new uniformity loss to ensure generated designs evenly cover the given requirement range. Through a real-world example of constrained 3D shape generation, we show that the label-aware self-augmentation leads to an average improvement of14% on the constraint satisfaction for generated 3D shapes, and the uniformity loss leads to a 125% average increase on the uniformity of generated shapes' attributes. This work laid the foundation for data-driven inverse design problems where we consider range constraints and there are sparse regions in the condition space.

Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis

Typical engineering design tasks require the effort to modify designs iteratively until they meet certain constraints, i.e., performance or attribute requirements. Past work has proposed ways to solve the inverse design problem, where desired designs are directly generated from specified requirements, thus avoid the trial and error process. Among those approaches, the conditional deep generative model shows great potential since 1) it works for complex high-dimensional designs and 2) it can generate multiple alternative designs given any condition. In this work, we propose a conditional deep generative model, Range-GAN, to achieve automatic design synthesis subject to range constraints. The proposed model addresses the sparse conditioning issue in data-driven inverse design problems by introducing a label-aware self-augmentation approach. We also propose a new uniformity loss to ensure generated designs evenly cover the given requirement range. Through a real-world example of constrained 3D shape generation, we show that the label-aware self-augmentation leads to an average improvement of 14% on the constraint satisfaction for generated 3D shapes, and the uniformity loss leads to a 125% average increase on the uniformity of generated shapes’ attributes. This work laid the foundation for data-driven inverse design problems where we consider range constraints and there are sparse regions in the condition space. For further information and code for this paper please refer to http://decode.mit.edu/projects/rangegan/.

A Nonlinear Inverse Design Problem for a Pipe Type Heat Exchanger Equipped with Internal Z-Shape Lateral Fins and Ribs

A non-linear three-dimensional inverse shape design problem was investigated for a pipe type heat exchanger to estimate the design variables of continuous lateral ribs on internal Z-shape lateral fins for maximum thermal performance factor η. The design variables were considered as the positions, heights, and number of ribs while the physical properties of air were considered as a polynomial function of temperature; this makes the problem non-linear. The direct problem was solved using software package CFD-ACE+, and the Levenberg–Marquardt method (LMM) was utilized as the optimization tool because it has been proven to be a powerful algorithm for solving inverse problems. Z-shape lateral fins were found to be the best thermal performance among Z-shape, S-shape, and V-shape lateral fins. The objective of this study was to include continuous lateral ribs to Z-shape lateral fins to further improve η. Firstly, the numerical solutions of direct problem were solved using both polynomial and constant air properties and then compared with the corrected solutions to verify the necessity for using polynomial air properties. Then, four design cases, A, B, C and D, based on various design variables were conducted numerically, and the resultant η values were computed and compared. The results revealed that considering continuous lateral ribs on the surface of Z-shape lateral fins can indeed improve η value at the design working condition Re = 5000. η values of designs A, B and C were approximately 13% higher than that for Z-shape lateral fins, however, when the rib numbers were increased, i.e., design D, the value of η became only 11.5 % higher. This implies that more ribs will not guarantee higher η value.

Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures

This work describes neural network surrogate models for calculating the effective mechanical properties of a periodic composites. The models achieve good accuracy even when only provided with training data sampling a small portion of the design space. As an example, the surrogate models are applied to solving the inverse design problem of finding structures with optimal mechanical properties. The surrogate models are sufficiently accurate to recover optimal solutions in general agreement with established topology optimization methods. However, improvements will be required to develop robust, efficient neural network-based surrogate models and several directions for future research are highlighted here.

Temperature identification of a heat source in conjugate heat transfer problems via an inverse analysis

Purpose The present study aims to perform inverse analysis of a conjugate heat transfer problem including conduction and forced convection via the quasi-Newton method. The inverse analysis is defined for a heat source that is surrounded by a solid medium which is exposed to a free stream in external flow. Design/methodology/approach The objective of the inverse design problem is finding temperature distribution of the heat source as thermal boundary condition to establish a prescribed temperature along the interface of solid body and fluid. This problem is a simplified version of thermal-based ice protection systems in which the formation of ice is avoided by maintaining the interface of fluid and solid at a specified temperature. Findings The effects of the different pertinent parameters such as Reynolds number, interface temperature and thermal conductivity ratio of fluid and solid mediums are analyzed. Originality/value This paper fulfils the analysis to study how thermal based anti-icing system can be used with different heat source shapes.

The dependence of the appearance of the aircraft on the conditions of the Arctic basing

Positioning on the global political arena of the Arctic Territory as the exclusive economic zone of the Russian Federation requires, first of all, the development of a regional transport network, including cargo and passenger traffic for the sustainable development of the region. The solution of such a transportation problem is a compromise of the aircraft performance. The purpose of the article is to analyze and find out how dependent is the appearance of the aircraft on the conditions of stationing in the Arctic. An analysis of the scientific and methodological support and well-known design solutions was carried out, which showed that to create a successful sample of the automatic part of the safety system, it is necessary to solve the FOS problem based on the solution of the inverse design problem from the inner layout of the aircraft .Mathematical dependences of the landing mass on the ice thickness were identified. The main stages of the transport operation in the Arctic were pointed. On the basis of the developed formal heuristic models, a subsystem of moment-inertial analysis has been created. The analysis of the research results showed that by 2050 the flight range will increase with a decrease in the landing mass.

Designing photonic topological insulators with quantum-spin-Hall edge states using topology optimization

Designing photonic topological insulators (PTIs) is highly non-trivial because it requires inversion of band symmetries around the band gap, which was so far done using intuition combined with meticulous trial and error. Here we take a completely different approach: we consider the design of PTIs as an inverse design problem and use topology optimization to maximize the transmission through an edge mode past a sharp bend. Two design domains composed of two different but initially identical C6ν-symmetric unit cells define the geometrical design problem. Remarkably, the optimization results in a PTI reminiscent of the shrink-and-grow approach to quantum-spin-Hall PTIs but with notable differences in the crystal structure as well as qualitatively different band structures and with significantly improved performance as gauged by the band-gap sizes, which are at least 50% larger than in previous designs. Furthermore, we find a directional β-factor exceeding 99% and very low losses for sharp bends. Our approach allows the introduction of fabrication limitations by design and opens an avenue towards designing PTIs with hitherto-unexplored symmetry constraints.