This paper focuses on the channel impairments separability of two histogram-based features, asynchronous amplitude histograms (AAH) and asynchronous delay-tap plot (ADTP), commonly used in direct-detection optical performance monitoring (OPM) techniques. This paper presents an in-depth study of the conditions under which these two histogram features are applicable in OPM. These high-dimensional features, AAH and ADTP, are dimensionally reduced using a state-of-the-art data visualization algorithm called Uniform Manifold Approximation and Projection (UMAP) algorithm. After data visualization, it can be found these two histogram-based features have some limitations in distinguishing between different levels of impairments in some specific cases. These features cannot achieve high accuracy in monitoring optical performance in these given situations, no matter how complex the classifier is designed. Extensive simulation experiments were performed to study the classification performance of the two histogram features in the single and multiple impairments cases. The results show that both AAH and ADTP can be used to monitor cumulative dispersion (CD) and optical signal to noise ratio (OSNR) in the case of the single impairment. In addition, the monitoring performance of both features is better for dispersion in the case of multiple impairments coexistence, while both have limitations for OSNR monitoring. However, the anti-dispersion interference ability of ADTP is better than that of AAH. The plausibility of the study results is verified by estimating the channel impairments under different conditions using a deep neural network-based (DNN) identifier. The impairments separation visualization results of UMAP are highly consistent with the estimation results of the DNN-based classifier, achieving the interconnection of usefulness and practicality.

本文重点研究两种基于直方图的特征的通道损伤可分离性，即异步幅度直方图（AAH）和异步延迟抽头图（ADTP），这两种特征常用于直接检测光学性能监测（OPM）技术。本文深入研究了这两种直方图特征在 OPM 中的应用条件。这些高维特征 AAH 和 ADTP 使用最先进的数据可视化算法（称为统一流形逼近和投影 (UMAP) 算法）进行降维。经过数据可视化，可以发现这两种基于直方图的特征在区分某些特定情况下不同程度的损伤时存在一定的局限性。无论分类器设计得多么复杂，这些特征都无法在这些给定情况下实现监测光学性能的高精度。进行了大量的模拟实验来研究两种直方图特征在单一和多重损伤情况下的分类性能。结果表明，AAH和ADTP均可用于监测单一损伤情况下的累积色散（CD）和光信噪比（OSNR）。此外，这两种特性的监测性能在多种损伤共存的情况下对于色散来说都较好，但在OSNR监测方面都存在局限性。但ADTP的抗色散干扰能力优于AAH。通过使用基于深度神经网络 (DNN) 的标识符估计不同条件下的通道损伤，验证了研究结果的合理性。 UMAP的损伤分离可视化结果与基于DNN的分类器的估计结果高度一致，实现了有用性和实用性的互联。