Session: 13-02-01: Design and Fabrication, Analysis, Processes, and Technology for Micro and Nano Devices and Systems

Paper Number: 142167

142167 - Rapid Manufacturing Solid Microneedle Array by Integrated Digital Light Processing With Machine Learning (Dlp-Ml) 

Microneedle arrays (μNA) are gaining popularity in the field of drug delivery due to their potential to minimize side effects compared to conventional hypodermic needles. Generally, μNA is manufacturing though three or two stages which lack of flexibility in design. 3d printing is one of the powerful method that could be employed in three or two stages. However, it could be extended to single stage by directly manufacturing μNA from designated material. Digital light processing (DLP) is a kind of 3d printing and using in this study. A further understanding of DLP printing parameters would be investigated such as LED current (mA), curing time (sec), z-thickness (μm), and grayscale level image (0 to 255). This study explores the integration of machine learning (ML) with DLP technology, namely DLP-ML, to manufacture μNA arrays with customizable sizes, rapid production processes, and reduced material wastage. Additionally, the dataset is developed as the data training by experimental approach which simplified with Taguchi method. The Taguchi method is contained five factors and five levels, L₂₅. In this approach, machine learning algorithms are employed to determine the optimal digital mask patterns and printing parameters for DLP-ML manufacturing. The μNA are designed to maintain a consistent conical shape, ensuring uniformity and efficiency in drug delivery. The study is employed various ML configurations in term of algorithm and number of hidden layer. Under different algorithm, the sort of larger to lower accuracy is arranged Bayesian regularization backpropagation (BR₁₀), Levenberg-Marquardt backpropagation (LM₁₀), and scaled conjugate gradient backpropagation (SCG₁₀), respectively. It also notices that the deviation of BR₁₀ is proving that μNA is manufactured uniformly on a substrate. It is ultimately selecting Bayesian regularization backpropagation for its superior accuracy, exceeding 90%. For different number of hidden layer, the default value, 10, is also resulting highest accuracy among others. Then, BR₁₀ could be concluded as the best ML configuration. This algorithm empowers DLP-ML manufacturing to produce μNA arrays with aspect ratios (AR) of up to 15 (1500/100) , representing the ratio between the height and base diameter of the needles, and the critical AR of μNA bending is found at 7 (700/100). By harnessing the synergy of DLP-ML technologies, this research presents a promising avenue for the advancement of drug delivery systems, offering enhanced precision, scalability, and therapeutic efficacy in medical applications. Finally, DLP-ML is successfully developed a rapid μNA manufacturing with different dimensions very accurately.

Presenting Author: Dwi Mardika Lestari National Taiwan University of Science and Technology

Presenting Author Biography: I am a PhD Student in National Taiwan University of Science and Technology (NTUST). I also graduated from NTUST for Master Program. I am studying in Mechanical Engineering Department. I join Mini Micro Manufacturing Lab (M3Lab) which is focusing on fabricating a micro size tool. Currently, my research topic is mostly used digital light processing (DLP) for manufacturing tool or device. As I presented in here, I manufacture the microneedle array (μNA).

Authors:

Dwi Mardika Lestari National Taiwan University of Science and Technology
Pin-Chuan Chen National Taiwan University of Science and Technology