Inverse design for material anisotropy and its application for a compact X-cut TFLN on-chip wavelength demultiplexer

Inverse design focuses on identifying photonic structures to optimize the performance of photonic devices.Conventional scalar-based inverse design approaches are insufficient to design photonic devices of anisotropic materials such as lithium niobate(LN).To the best of our knowledge,this work proposes for the first time the inverse design method for anisotropic materials to optimize the structure of anisotropic-material based photonics devices.Specifically,the orientation dependent properties of anisotropic materials are included in the adjoint method,which provides a more precise prediction of light propagation within such materials.The proposed method is used to design ultra-compact wavelength division demultiplexers in the X-cut thin-film lithium niobate(TFLN)platform.By benchmarking the device performances of our method with those of classical scalar-based inverse design,we demonstrate that this method properly addresses the critical issue of material anisotropy in the X-cut TFLN platform.This proposed method fills the gap of inverse design of anisotropic materials based photonic devices,which finds prominent applications in TFLN platforms and other anisotropicmaterial based photonic integration platforms.

Inverse design and realization of an optical cavity-based displacement transducer with arbitrary responses

Optical cavity has long been critical for a variety of applications ranging from precise measurement to spectral analysis.A number of theories and methods have been successful in describing the optical response of a stratified optical cavity,while the inverse problem,especially the inverse design of a displacement sensitive cavity,remains a significant challenge due to the cost of computation and comprehensive performance requirements.This paper reports a novel inverse design methodology combining the characteristic matrix method,mixed-discrete variables optimization algorithm,and Monte Carlo method-based tolerance analysis.The material characteristics are indexed to enable the mixed-discrete variables optimization,which yields considerable speed and efficiency improvements.This method allows arbitrary response adjustment with technical feasibility and gives a glimpse into the analytical characterization of the optical response.Two entirely different light-displacement responses,including an asymmetric sawtooth-like response and a highly symmetric response,are dug out and experimentally achieved,which fully confirms the validity of the method.The compact Fabry-Perot cavities have a good balance between performance and feasibility,making them promising candidates for displacement transducers.More importantly,the proposed inverse design paves the way for a universal design of optical cavities,or even nanophotonic devices.

High performance integrated photonic circuit based on inverse design method

The basic indexes of all-optical integrated photonic circuits include high-density integration,ultrafast response and ultralow energy consumption.Traditional methods mainly adopt conventional micro/nano-structures.The overall size of the circuit is large,usually reaches hundreds of microns.Besides,it is difficult to balance the ultrafast response and ultra-low energy consumption problem,and the crosstalk between two traditional devices is difficult to overcome.Here,we propose and experimentally demonstrate an approach based on inverse design method to realize a high-density,ultrafast and ultra-low energy consumption integrated photonic circuit with two all-optical switches controlling the input states of an all-optical XOR logic gate.The feature size of the whole circuit is only 2.5μm×7μm,and that of a single device is 2μm×2μm.The distance between two adjacent devices is as small as 1.5μm,within wavelength magnitude scale.Theoretical response time of the circuit is 150 fs,and the threshold energy is within 10 fJ/bit.We have also considered the crosstalk problem.The circuit also realizes a function of identifying two-digit logic signal results.Our work provides a new idea for the design of ultrafast,ultra-low energy consumption all-optical devices and the implementation of high-density photonic integrated circuits.

Review on Applications of 3D Inverse Design Method for Pump

The 3D inverse design method, which methodology is far superior to the conventional design method that based on geometrical description, is gradually applied in pump blade design. However, no complete description about the method is outlined. Also, there are no general rules available to set the two important input parameters, blade loading distribution and stacking condition. In this sense, the basic theory and the mechanism why the design method can suppress the formation of secondary flow are summarized. And also, several typical pump design cases with different specific speeds ranging from centrifugal pump to axial pump are surveyed. The results indicates that, for centrifugal pump and mixed pump or turbine, the ratio of blade loading on the hub to that on the shroud is more than unit in the fore part of the blade, whereas in the aft part, the ratio is decreased to satisfy the same wrap angle for hub and shroud. And the choice of blade loading type depends on the balancing of efficiency and cavitation. If the cavitation is more weighted, the better choice is aft-loaded, otherwise, the fore-loaded or mid-loaded is preferable to improve the efficiency. The stacking condition, which is an auxiliary to suppress the secondary flow, can have great effect on the jet-wake outflow and the operation range for pump. Ultimately, how to link the design method to modem optimization techniques is illustrated. With the know-how design methodology and the know-how systematic optimization approach, the application of optimization design is promising for engineering. This paper summarizes the 3D inverse design method systematically.

Benchmarking deep learning-based models on nanophotonic inverse design problems

Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive.Recently,deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.Although most of these neural network models have demonstrated high accuracy in different inverse design problems,no previous study has examined the potential effects under given constraints in nanomanufacturing.Additionally,the relative strength of different deep learning-based inverse design approaches has not been fully investigated.Here,we benchmark three commonly used deep learning models in inverse design:Tandem networks,Variational Auto-Encoders,and Generative Adversarial Networks.We provide detailed comparisons in terms of their accuracy,diversity,and robustness.We find that tandem networks and Variational Auto-Encoders give the best accuracy,while Generative Adversarial Networks lead to the most diverse predictions.Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations.In addition,our code and data are publicly available,which could be used for future inverse design model development and benchmarking.

Inverse design-based metamaterial transparent device and its multilayer realization

We propose an inverse method to determine the material parameters of a transparent device without any knowledge of the corresponding transformation function. The required parameters are independently obtained and expressed as functions of the introduced generator. Moreover, to remove the inhomogeneity and anisotropy of material parameters, a layered transparent device composed of only homogeneous and isotropic materials is presented based on the effective medium theory. The feasibility of using the layered device in antenna protection is also investigated. Full-wave simulation is carried out for verification. This work paves a new way toward designing metamaterial devices without specifying the underlying coordinate transformation, and has great guiding significance for the practical fabrication of transparent devices.

Inverse design of highly efficient and broadband mode splitter on SOI platform

Mode splitters that directly separate modes without changing their orders are highly promising to improve the flexibility of the mode-division multiplexing systems.In this paper,we design a high-performance mode splitter on the silicon-oninsulator platform with a compact footprint of 14μm×2.5μm using an inverse design method based on shape optimization.The fabrication of this mode splitter requires only a single lithography step and exhibits good fabrication tolerances.The experimental results show that the proposed device exhibits state-of-the-art insertion loss(<0.9 dB)and cross talk(<-16 dB)over a broad bandwidth(1500-1600 nm).Furthermore,the shape optimization method used is implemented to design a dual-mode(de)multiplexer,and the experimental results fulfill the design objective,demonstrating the excellent generality of the design method in this paper.

Double-decoupled inverse design of natural laminar flow nacelle under transonic conditions

The inverse design based on the pressure distribution is an essential approach to realize the improvement of Natural Laminar Flow(NLF) performance for nacelles. However, the direct definition of target pressure distribution at design point is challenging for the dilemma to consider the constraints of shock wave and laminar flow at the same time. In addition, the universality of method will be limited when the inverse design is strongly coupled with the solver. Thus, a double-decoupled methodology based on the relationship of pressure distributions between design and off-design points is proposed in this paper, which realizes the decoupling of constraints in shock wave and laminar flow on target pressure distribution as well as the decoupling of flow field solution and inverse design method. Aimed at an isolated flow-through-nacelle of high bypass ratio, the target pressure distribution with appropriate favorable gradient and shock-free feature is defined according to physical principles at the off-design point of Ma = 0.80 while the transonic and laminar performance are examined at the design point of Ma = 0.85. The solution of flow field is based on γ-Re_(θ) transition model and the inverse design is based on residual-correction method. With the inverse design starting from off-design point, the performance of shock wave and laminar flow at design point are both improved. The local shock wave after the lip of nacelle is eliminated effectively while the streamwise length of laminar flow region is doubled and exceeds to 30% of the chord length. The percentage of drag reduction for outboard surface is 12.7% for friction drag, 7.8%for pressure drag and 10.5% for total drag. The effects of inverse design on the process of transition are analyzed with detailed flow features. The robustness of laminar flow is examined under different variation factors of freestream which are deviated from the design point.

Inverse design and accurate optimization of layered structured seeding mechanism for sugarcane planters

Existing sugarcane planters are difficult to have ideal seeding trajectory and motion attitude at the same time, and the speed is difficult to meet the requirements at the critical stage, resulting in poor stability, which ultimately makes it impossible to ensure that the sugarcane seeding is carried out in accordance with the agronomic requirements to ensure that the cane buds are oriented toward the wall of the seeding trench. Aiming at the second-order non-circular planetary gear system pendulum seeding mechanism of the planter, the paper innovatively adopts the combination of inverse design and multi-objective layered accurate optimization to solve the problems of attitude, speed and trajectory that do not meet the requirements of fixed-attitude seeding that still exists in the process of sugarcane seeding. The second-order non-circular planetary gear system is simplified into a three-rod two-degree-of-freedom mechanism, and the radius of the pitch curve of each non-circular gear is solved inversely by actively preplanning the static trajectory of the cane seed motion and analyzing the law of motion of the rod assembly. Determining the range of cane seed attitude angles in different motion phases as the first layer optimization objective, and fine-tuning the position of static trajectory key type value points to achieve the first layer optimization. Based on the non-circular gear pitch curve obtained from optimization, the interpolation points are marked on each non-circular gear pitch curve of the second-order non-circular planetary gear system, and based on the parameter optimization method of human-computer interaction, the radius values corresponding to the interpolation points of the non-circular gear pitch curve are fine-tuned to optimize the pitch curves, so as to satisfy the speed requirements of the cane species in each stage, and at the same time to make the convexity of non-circular gears in line with the principle of gear mesh, so as to complete the second layer of accurate optimization. The results of simulation verification show that the motion trajectory attitude of the virtual prototype is basically consistent with the theoretical model, which verifies the feasibility of the mechanism design. This study provides a new optimized design method for the cane seeding mechanism of sugarcane planters to achieve directional seeding.

A general alternate loading technique and its applications in the inverse designs of centrifugal and mixed-flow pump impellers

For the inverse designs of centrifugal and mixed-flow pump impellers,clarifying the generation process of secondary flows and putting forward corresponding suppression measures is an important approach to improve the impeller performance.In this paper,to provide a better qualitative insight into the generation mechanism of secondary flows in the impeller,a simple kinematic equation is derived based on the ideal assumptions,which indicates that the potential rothalpy gradient(PRG)is the most important dynamic source that actively induces secondary vortical flows.Induced by the natural adverse PRG on the S1 and S2 stream surfaces,two typical secondary flows,H-S and P-S secondary flows,are clearly presented.To specially suppress these typical secondary flows,a general alternate loading technique(GALT)is proposed,aiming to adjust the real blade loadingδp to control the PRG features.At the blade fore part,theδp on the hub streamline should be slowly increased to avoid breakneck growth of the potential rothalpy to reduce adverse streamwise PRG on the S2 streamsurface.At the blade middle part,theδp should be moderately decreased to reduce adverse streamwise PRG on the S1 streamsurface.At the blade aft part,the difference in theδp between the shroud and hub streamlines should be decreased faster to control the exit uniformity.By applying the GALT to the impeller designs of three typical pump types in hydraulic engineering,the organizational effect of the PRG on fundamental flow structures is proven.The GALT can effectively control the PRG distributions and suppress the secondary flows,thereby widening the pump’s high-efficiency zone,improving flow uniformity and suppressing pressure fluctuations.Compared with the current Z-G method and the ALT,the GALT can meet the requirements of"de-experience"better,thereby enabling the designers to obtain good products explicitly and quickly.

Inverse design of digital nanophotonic devices using the adjoint method

A high-efficiency inverse design of"digital"subwavelength nanophotonic devices using the adjoint method is proposed.We design a single-mode 3dB power divider and a dual-mode demultiplexer to demonstrate the efficiency of the proposed inverse design approach,called the digitized adjoint method,for single-and dual-object optimization,respectively.The optimization comprises three stages:1)continuous variation for an"analog"pattern;2)forced permittivity biasing for a"quasi-digital"pattern;and 3)a multilevel digital pattern.Compared with the conventional brute-force method,the proposed method can improve design efficiency by about five times,and the performance optimization can reach approximately the same level.The method takes advantages of adjoint sensitivity analysis and digital subwavelength structure and creates a new way for the efficient and high-performance design of compact digital subwavelength nanophotonic devices,which could overcome the efficiency bottleneck of the brute-force method,which is restricted by the number of pixels of a digital pattern,and improve the device performance by extending a conventional binary pattern to a multilevel one.

Inverse design of mission success space for combat aircraft contribution evaluation

This paper presents a novel design method of the Mission Success Space(MSS) for the evaluation on aircraft contribution effectiveness. MSS concept was proposed for giving success criterion of a mission and judging the success by conventional mission effectiveness with regards to the aircraft capabilities. This space is created by the Mission Success Function(MSF) and the original Effectiveness Index Space(EIS) where empirical equations are usually assumed to be MSFs. Based on this MSS concept, this paper firstly defines the MSS-based evaluation, then further summarizes the evaluation process of the Contribution to System-of-Systems(CSS). More importantly, based on the thought of Inverse Design(ID), a new design method of MSF is presented comprehensively analyzing aircraft's CSS in a combat mission without using any empirical MSF. The definition of MSS based ID is given and the design procedure is sequentially introduced. Two different confrontation cases are depicted with many details as the simulation validation: Air-to-ground and Penetration. There are two design variables considered for designing MSS in the latter case while only one for the former. However, in both cases, the best design is given by evaluating the Gaussian fitting performance of CSS.

Entropy based inverse design of aircraft mission success space in system-of-systems confrontation

This paper presents a practical and efficient design method for aircraft Mission Success Space(MSS)based on the entropy measurement(EM).First,fundamentals regarding MSS,Inverse Design(ID)and entropy are discussed.Then,two EM schemes of entropy-based ID and the whole MSS ID procedure are given to demonstrate alternative ways of entropy quantification and MSS design.After that,Genetic Algorithm(GA)is utilized as a search algorithm to find the optimal MSS design with the minimum objective,entropy,in each EM scheme.A simulation case of aircraft penetration mission is given for the method validation where the best aircraft MSS design is obtained by GA according to the minimum entropy.Results from two schemes are compared at the end.

An inverse design method for supercritical airfoil based on conditional generative models

Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.

Metaheuristic-based inverse design of materials--A survey

There is a growing interest in the inverse approach to material deign,in which the desired target properties are used as input to identify the atomic identity,composition and structure(ACS)that exhibit such properties.As an overview,this paper surveys and summarizes previous works in metaheuristicbased inverse design of various materials.The basics of metaheuristic-based inverse design of materials are presented,including feature identification(fingerprinting),machine learning of ACS→property models(forward design),metaheuristic algorithms for property→ACS predictions(inverse design),and experimental validations,with focus on inverse design.The past studies are organized into a two-level hierarchy with how properties are predicted at the higher level,either by first principles,simulation,or machine learning model,and the number of target properties considered at the lower level,either one or more than one.The uniqueness and limitation of previous research are discussed and several possible topics for future research are identified.This review intends to serve as the steppingstone/springboard for those interested in advancing this area of research.

Inverse design of mesoscopic models for compressible flow using the Chapman-Enskog analysis

In this paper,based on simplified Boltzmann equation,we explore the inverse-design of mesoscopic models for compressible flow using the Chapman-Enskog analysis.Starting from the single-relaxation-time Boltzmann equation with an additional source term,two model Boltzmann equations for two reduced distribution functions are obtained,each then also having an additional undetermined source term.Under this general framework and using Navier-Stokes-Fourier(NSF)equations as constraints,the structures of the distribution functions are obtained by the leading-order Chapman-Enskog analysis.Next,five basic constraints for the design of the two source terms are obtained in order to recover the NSF system in the continuum limit.These constraints allow for adjustable bulk-to-shear viscosity ratio,Prandtl number as well as a thermal energy source.The specific forms of the two source terms can be determined through proper physical considerations and numerical implementation requirements.By employing the truncated Hermite expansion,one design for the two source terms is proposed.Moreover,three well-known mesoscopic models in the literature are shown to be compatible with these five constraints.In addition,the consistent implementation of boundary conditions is also explored by using the Chapman-Enskog expansion at the NSF order.Finally,based on the higher-order Chapman-Enskog expansion of the distribution functions,we derive the complete analytical expressions for the viscous stress tensor and the heat flux.Some underlying physics can be further explored using the DNS simulation data based on the proposed model.

Inverse design of 1D color splitter for high-efficiency color imaging

We introduce a simple one-dimensional(1D)structure in the design of 1D color splitters(1D-CSs)with RGB unit cells for color imaging and propose a single-to-double-layer design in 1D-CSs.Based on inverse design metasurfaces,we demonstrate numerically a single-layer 1D-CS with a full-color efficiency of 46.2%and a double-layer 1D-CS with a full-color efficiency of48.2%;both of them are significantly higher than that of traditional color filters.Moreover,we demonstrate a 1D-CS that has application value by evaluating the double-layer 1D-CS’s performances in terms of incident angle sensitivity,polarization angle sensitivity,and assembly tolerance.

Inverse Molecule Design with Invertible Neural Networks as Generative Models

Using neural networks for supervised learning means learning a function that maps input x to output y. However, in many applications, the inverse learning is also wanted, i.e., inferring y from x, which requires invertibility of the learning. Since the dimension of input is usually much higher than that of the output, there is information loss in the forward learning from input to output. Thus, creating invertible neural networks is a difficult task. However, recent development of invertible learning techniques such as normalizing flows has made invertible neural networks a reality. In this work, we applied flow-based invertible neural networks as generative models to inverse molecule design. In this context, the forward learning is to predict chemical properties given a molecule, and the inverse learning is to infer the molecules given the chemical properties. Trained on 100 and 1000 molecules, respectively, from a benchmark dataset QM9, our model identified novel molecules that had chemical property values well exceeding the limits of the training molecules as well as the limits of the whole QM9 of 133,885 molecules, moreover our generative model could easily sample many molecules (x values) from any one chemical property value (y value). Compared with the previous method in the literature that could only optimize one molecule for one chemical property value at a time, our model could be trained once and then be sampled any multiple times and for any chemical property values without the need of retraining. This advantage comes from treating inverse molecule design as an inverse regression problem. In summary, our main contributions were two: 1) our model could generalize well from the training data and was very data efficient, 2) our model could learn bidirectional correspondence between molecules and their chemical properties, thereby offering the ability to sample any number of molecules from any y values. In conclusion, our findings revealed the efficiency and effectiveness of using invertible neural networks as generative models in inverse molecule design.

Basic Problems in Design and Inverse Engineering Solution for Outer Characteristic of Vehicle Suspension Shock Absorbers

Based on the theory and the practical experiences of linearity design of feasible design area and inverse solution of non linear outer characteristic of suspension shock absorber, in accordance with non linearity outer characteristic formed by open up damping coefficient, full open damping coefficient and smoothness to safety ratio of suspension shock absorber, a method and a research conclusion of the feasible design and inverse solution for the basic problems of designing and inverse solution of non linear outer characteristic of suspension damping components are provided.

Inverse-designed Jones matrix metasurfaces for high-performance meta-polarizers

Polarizers have always been an important optical component for optical engineering and have played an indispensable part of polarization imaging systems.Metasurface polarizers provide an excellent platform to achieve miniaturization,high resolution,and low cost of polarization imaging systems.Here,we proposed freeform metasurface polarizers derived by adjoint-based inverse design of a full-Jones matrix with gradient-descent optimization.We designed multiple freeform polarizers with different filtered states of polarization(SOPs),including circular polarizers,elliptical polarizers,and linear polarizers that could cover the full Poincarésphere.Note that near-unitary polarization dichroism and the ultrahigh polarization extinction ratio(ER)reaching 50 d B were achieved for optimized circular polarizers.The multiple freeform polarizers with filtered polarization state locating at four vertices of an inscribed regular tetrahedron of the Poincarésphere are designed to form a full-Stokes parameters micropolarizer array.Our work provides a novel approach,we believe,for the design of meta-polarizers that may have potential applications in polarization imaging,polarization detection,and communication.