A generic process visualization method is introduced, which visualizes real-time process information and correlations among variables on a 2D map using parametric t-SNE. As an unsupervised learning method, it learns the mapping by minimizing the Kullback−Leibler divergence between the original high-dimensional space and the latent space using a deep neural network. In practice, it is observed that the original parametric t-SNE method lacks generalization and struggles to visualize unseen operating conditions correctly. In this work, two steps to improve its generalization capacity are proposed. In the first step, the neural network is trained with additional dummy data, which is generated to mimic the possible unseen conditions. Additionally, the structure of the neural network is reformulated with a new activation function that was designed to improve generalization for process data. The capability of the proposed approach was tested on two case studies, the Tennessee Eastman Process (TEP) and an industrial pyrolysis reactor. The results indicate that the proposed approach outperforms conventional methods in visualization as well as generalization capacity for unseen process conditions.

No abstract

No abstract

Process monitoring seeks to identify anomalous plant operating states so that operators can take the appropriate actions for recovery. Instrumental to process monitoring is the labeling of known operating states in historical data, so that departures from these states can be identified. This task can be challenging and time consuming as plant data is typically high dimensional and extensive. Moreover, automation of this procedure is not trivial since ground truth labels are often unavailable. In this contribution, this problem is approached as a multi-mode classification one, and an automatic framework for labeling using unsupervised Machine Learning (ML) methods is presented. The implementation was tested using data from the Tennessee Eastman Process and an industrial pyrolysis process. A total of 9 ML ensembles were included. Hyperparameters were optimized using a multi-objective evolutionary optimization algorithm. Unsupervised clustering metrics (silhouette score, Davies-Bouldin index, and Calinski-Harabasz Index) were investigated as candidates for objective functions in the optimization implementation. Results show that ensembles and hyperparameter selection can be aided by multi-objective optimization. It was found that Silhouette score and Davies-Bouldin index are strong predictions of the ensemble’s performance and can then be used to obtain good initial results for subsequent fault detection and fault diagnosis procedures.

Stimulation of muscarinic receptors within the PHN of the rat evokes a pressor response. It is not known whether this cholinergic system is activated during a depressor event in an effort to overcome the depressed blood pressure. The goal of the present study was to evaluate whether the PHN cholinergic system is activated during the compensatory reflex response to moderate hemorrhage. Since cannabinoids (CBs) appear to modulate acetylcholine release, the effect of the presence of a CB agonist in the PHN during recovery to hemorrhage was also studied. Carbachol (CCh), a cholinergic agonist, methyl‐atropine (MeATR), a muscarinic receptor antagonist, or CP 55,940, a CB1 receptor agonist, were administered into the PHN of urethane‐anesthetized rats following moderate hemorrhage (20% blood loss). None of the treatments affected the percent MAP recovery or the change in heart rate post‐hemorrhage. While CCh did not affect the rate of recovery of the mean arterial pressure (MAP), both MeATR and CP 55,940 decreased the recovery rate of MAP. The decreased rate of MAP recovery in the presence of CP 55,940 was reversed by pretreatment with AM 251, a CB1 receptor antagonist/inverse agonist. Furthermore, CP 55,940 decreased survival compared to saline‐treated rats. These results suggest that cholinergic activity within the PHN increases during the reflex compensatory response to moderate hemorrhage, and that CBs can decrease this activity through the CB1 cannabinoid receptor. (Supported by a grant from the KCOM Graduate Program Committee.)