Haiyue Yuan

Reducing distortion of spectral simulation signals in infrared detection systems is essential to improve the precision of detecting fine spectra in space-based carbon monitoring satellites. The rigid-flex printed circuit board (PCB), a vital interconnection structure between detectors and signal conditioning circuits, exhibits signal quality variations due to impedance fluctuations and parasitic capacitance changes induced by its meshed return plane geometry. This periodically varying structure necessitates full-wave field solutions to include longitudinal discontinuity. Although full-wave simulations provide accurate characterization, they demand substantial computational resources and time. To address these challenges, we propose an innovative approach to effectively determine optimal meshed return plane designs across various transmission rates. The method integrates a convolutional neural network (CNN) with improved particle swarm optimization (IPSO). First, a CNN model is employed efficiently to predict scattering parameters (S-parameters) for different design configurations, thereby overcoming the inefficiencies associated with iterative full-wave simulation optimization. Then, an IPSO algorithm has been implemented to address the optimization challenge of crosstalk and inter-symbol interference (ISI) in signal transmission. Furthermore, to increase the optimization speed and evaluate the system performance under extreme conditions, we propose a fitness function construction method based on double-edge responses (DER) to rapidly generate a worst-case peak distortion analysis (PDA) eye diagram within the IPSO algorithm. The proposed methodology reduces computational complexity by two orders of magnitude relative to the full-wave simulation. Quantitative analysis conducted at a transmission rate of 5 Gbps demonstrates substantial signal quality improvements compared to empirical PCB design: the eye height increased by 49.7%, and the eye width expanded by 35.7%. The effectiveness of these improvements has been verified through commercial simulation software, proving that the method can provide design support for infrared detection systems.

InGaAs detection systems have been increasingly used in the aerospace field, and due to the high signal-to-noise ratio requirements of short-wave infrared quantitative payloads, there is an urgent need for methods for the rapid and precise evaluation and the optimal design of these systems. The rigid-flex printed circuit board (PCB) is a vital component of InGaAs detectors, as its grid ground plane design parameters impact parasitic capacitance and thus affect weak infrared analog signals. To address the time-intensive and costly nature of design optimization achieved with simulations and experimental measurements, we propose an innovative method based on a neural network to predict the scattering parameters of rigid-flex boards for InGaAs detection links. This is the first study in which the effects of rigid-flex boards on weak infrared detection signals have been considered. We first obtained sufficient samples with software simulation. A backpropagation (BP) neural network prediction model was trained on existing sample sets and then verified on a rigid-flex board used in a crucial aerospace short-wave infrared quantitative mission. The model efficiently and accurately predicted high-speed interconnect scattering parameters under various rigid-flex board grid plane parameter conditions. The prediction error was less than 1% compared with a 3D field solver, indicating an overcoming of the iterative optimization inefficiency and showing improved design quality for InGaAs detection circuits.