In this work, we present a framework for process monitoring focusing on the dynamics of reaction mechanisms based purely on online spectroscopic data. This is accomplished by developing an explicit duration hidden semi-Markov model (HSMM) that is used to monitor changes in reaction mechanisms with changing temperatures in a complex reacting system by dynamically identifying groups of spectroscopic samples that belong to a mode, and the mode duration of the reaction mechanism associated with the samples. An expectation maximization algorithm is used for parameter re-estimation, and Viterbi state decoding is used to identify the most likely sequence of hidden states/modes that may have generated the observed sequence of spectra. The reaction mechanism associated with samples of a mode is then deduced by extracting latent features among spectra of the mode and learning a probabilistic graphical structure among the features using Bayesian networks, which represent a network or mechanism of hypothesized reactions. The technique is demonstrated on case studies related to the partial upgrading of bitumen using thermochemical conversion based on the acquisition of Fourier transform infrared spectroscopic data. This system is complex enough that prior information regarding both species and reactions is unavailable. Both offline and online monitoring are implemented for mode identification, and the technique provides monitoring of the multi-modal process and, at the same time, provides insight into the chemistry specific to each mode, which makes it useful both for process control and fundamental studies into process chemistry. Synthetic dynamic spectral data, that is derived through interpolation from real spectral data obtained at various static conditions of temperature and residence time, is used in the study.

在这项工作中，我们提出了一个过程监控框架，重点关注纯粹基于在线光谱数据的反应机制的动力学。这是通过开发一个显式持续时间隐藏半马尔可夫模型 (HSMM) 来实现的，该模型用于通过动态识别属于一种模式的光谱样本组和模式持续时间来监控复杂反应系统中反应机制随温度变化的变化与样品相关的反应机理。期望最大化算法用于参数重新估计，维特比状态解码用于识别可能已生成观察到的光谱序列的最可能的隐藏状态/模式序列。然后通过提取模式光谱中的潜在特征并使用贝叶斯网络学习特征之间的概率图形结构来推断与模式样本相关的反应机制，贝叶斯网络表示假设反应的网络或机制。该技术在与使用基于傅里叶变换红外光谱数据采集的热化学转化沥青部分升级相关的案例研究中得到证明。该系统足够复杂，以至于无法获得有关物种和反应的先验信息。离线和在线监测都用于模式识别，该技术提供了对多模式过程的监测，同时提供了对每种模式特有的化学成分的洞察，这使得它对于过程控制和过程化学的基础研究都非常有用。合成动态光谱数据是通过从在各种静态温度和停留时间条件下获得的真实光谱数据插值得出的，用于研究。