Data based monitoring methods are often utilized to carry out fault detection (FD) when process models may not necessarily be available. The partial least square (PLS) and principle component analysis (PCA) are two basic types of multivariate FD methods, however, both of them can only be used to monitor linear processes. Among these extended data based methods, the kernel PCA (KPCA) and kernel PLS (KPLS) are the most well-known and widely adopted. KPCA and KPLS models have several advantages, since, they do not require nonlinear optimization, and only the solution of an eigenvalue problem is required. Also, they provide a better understanding of what kind of nonlinear features are extracted: the number of the principal components (PCs) in a feature space is fixed a priori by selecting the appropriate kernel function. Therefore, the objective of this work is to use KPCA and KPLS techniques to monitor nonlinear data. The improved FD performance of KPCA and KPLS is illustrated through two simulated examples, one using synthetic data and the other using simulated continuously stirred tank reactor (CSTR) data. The results demonstrate that both KPCA and KPLS methods are able to provide better detection compared to the linear versions.
Process safety is a critical component in various process industries. Statistical process monitoring techniques were initially developed to maximize efficiency and productivity, but over the past few decades with catastrophic industrial disasters, process safety has become a top priority. Sensors play a crucial role in recording process measurements, and according to the number of monitored variables, process monitoring techniques can be classified into univariate or multivariate techniques. Most univariate process monitoring techniques rely on three fundamental assumptions: that process residuals contain a moderate level of noise, are independent, and are normally distributed. Practically, however, due to a variety of reasons such as modeling errors and malfunctioning sensors, these assumptions are violated, which can lead to catastrophic incidents. Fortunately, multiscale wavelet-based representation of data inherently possesses characteristics that are able to deal with these violations of assumptions. Therefore, in this work, multiscale representation is utilized to enhance the performance of the Shewhart chart (which is a well-known univariate fault detection method) to help improve its performance. The performance of the developed multiscale Shewhart chart was assessed and compared to the conventional chart through two examples, one using synthetic data, and the other using simulated distillation column data. The results of both examples clearly show that the developed multiscale Shewhart chart provides lower missed detection and false alarm rates, as well as lower ARL 1 values (i.e., quicker detection) for most cases where the fundamental assumptions of the Shewhart chart are violated. Additionally, the relative simplicity of the proposed algorithm encourages its implementation in practice to help improve process safety.
Chemical industries focus primarily on profitable operations, resulting in growing attention and advances in the field of digital twins and optimal control algorithms.However, most industries still struggle due to a lack of physical sensors, infrequent measurements, and asynchronous sampling. Thus, in this work, we have designed a multi-rate state observer for state estimation from plant measurements and developed a model predictive controller (MPC) that maximized the profitability of an industry-scale fermentation process (fermenter volume < 378,500 L).Additionally, as the fermentation process is complex due to the use of microorganisms, which cannot be accurately captured using a first-principles model, we utilize a previously developed hybrid model in the proposed MPC formulation.The MPC uses a GAMS-MATLAB framework to determine the optimal input profiles while considering practical process constraints. It is shown using multiple datasets, that the MPC can increase productivity while also decreasing the plant operating cost.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.