This paper presents a new paradigm of deep neural network (DNN) for the inverse design of microfluidic concentration gradient generators (µCGGs) with complex network topology. In this method, a concentration gradient (CG) and design parameters yielding the CG are, respectively, used as inputs and outputs of DNN, and the relationship between them is mapped. Several new elements are also proposed, including utilization of fast-running physics-based component model in the closed form to generate a large amount of data for DNN learning which otherwise is not available through computationally demanding computational fluid dynamics (CFD) simulation; and a divide-and-conquer strategy and DNN formulation combining classification and regression to mitigate many-to-one design complications for enhanced accuracy. Several DNN structures are investigated and developed, including single fully connected neural network (FCNN), convolutional neural network, and a new cascade FCNN for a divide-and-conquer implementation. Case studies are performed on a triple-Y µCGG to evaluate design performance of the proposed method in a six-dimensional space that only includes sample concentrations at inlet reservoirs as design parameters, and in a nine-dimensional design space, to which inlet flow pressures are also added. It is verified in high-fidelity CFD simulation that widely used CGs can be produced using DNN-predicted design parameters accurately with average error < 4% and < 8.5% relative to the prescribed CGs, respectively, in the six- and nine-dimensional design space. The learned design rules are packaged into the DNN model that allows to generate accurate µCGGs designs instantaneously (~ 3 ms) and eliminates requirements of simulation and optimization knowledge, facilitating distribution of the design capabilities to microfluidic end users.

本文提出了一种深度神经网络（DNN）的新范例，用于具有复杂网络拓扑的微流体浓度梯度发生器（µCGGs）的逆向设计。在这种方法中，浓度梯度（CG）和产生CG的设计参数分别用作DNN的输入和输出，并映射它们之间的关系。还提出了几个新元素，包括以封闭形式使用快速运行的基于物理的组件模型来生成大量数据以进行DNN学习，否则这些数据就无法通过对计算流体力学（CFD）的计算需求来模拟；分而治之策略和DNN公式结合了分类和回归，以减轻多对一的设计复杂性，从而提高准确性。研究和开发了几种DNN结构，包括单个全连接神经网络（FCNN），卷积神经网络以及用于分治的新级联FCNN。在三重Y µCGG上进行了案例研究，以评估所提出方法在六维空间中的设计性能，该空间仅包括入口储液器处的样品浓度作为设计参数，而在九维设计空间中，入口流动压力受到该影响。也被添加。在高保真CFD仿真中证明，可以使用DNN预测的设计参数精确地生产广泛使用的CG，在六维和九维设计中，相对于规定的CG而言，平均误差分别为<4％和<8.5％。空间。