The application of a supervised deep convolutional autoencoder was tested against partial least-squares-discriminant analysis (PLS-DA) for fault detection and diagnosis in a penicillin fed-batch process. In silico data was generated with a comprehensive simulator (IndPenSim) of an industrial-scale penicillin fed-batch simulator of operation under normal batch conditions and 8 fault batch conditions. A composite face-centered design response surface was applied to optimize key bioreactor design parameters based on a profit function that was directly dependent on fault detection results. The application of PLS-DA and the NN modeling resulted in an average fault detection rate (FDR) across all faults and process parameter configurations of 72.5% and 95.9%, respectively. In classifying complex fault conditions, the deep learning model greatly surpassed the PLS-DA model, and this improvement translated into a 25.0% increase in realized profit with the supervised deep convolutional autoencoder when compared to PLS-DA monitoring.

This paper outlines an end-to-end case study from ideation through to the development and deployment of a novel method to estimate SAGD depletion along a producing SAGD horizontal well from temperature fall off (TFO) events, from any temperature measurement point along the well. The methodology combines reservoir engineering first principals, analytics, simulation modelling and digital product delivery components. The outputs of this work are expected to drive rapid, data-driven, and standardized approaches to subsurface optimization of SAGD well pairs through quantified estimation of remaining oil in place opportunities that could be economically exploited through operations, re-completions, re-drills and technology applications.

Dihydroxyacetone, recognized as DHA, is a common additive used in spray tans responsible for providing pigmentation to the skin similar to a UV tan via the set of mechanisms known as the Maillard Reaction. When exposed to UV light, chemicals may experience reduced stability and form free radicals, reactive species commonly associated with toxicity. In order for spray tans to be considered safe by Health Canada, DHA should remain stable when irradiated by UV light. This report aims to determine whether DHA is capable of exhibiting signs of toxicity when exposed to UV light by assessing the literature examining DHA stability in the presence of UV light. While the evidence presented suggests a potential source of toxicity induced by UV-degraded DHA, further studies must be conducted to examine the correlation between the concentration of DHA and the concentration of free radicals and hydrogen peroxide formed. This may allow for a greater understanding of its toxicity to humans and improve consumer safety.Dihydroxyacétone, reconnu comme le DHA, est un additive courant utilisé dans les autobronzants chargés de fournir de la pigmentation à la peau semblable à un bronzage UV via l'ensemble des mécanismes connus comme la réaction de Maillard. Lorsqu'ils sont exposés à la lumière UV, les produits chimiques peuvent éprouver la stabilité réduite et former des radicaux libres, des espèces réactives couramment associés à la toxicité. Pour que les bronzages UV soient considérés sûr par Santé Canada, le DHA devrait rester stable lorsqu'il est irradié par la lumière UV. Ce rapport a l'intention de déterminer si le DHA est capable de présenter des signes de toxicité quand exposé à la lumière UV en évaluant les études qui ont examiné la stabilité du DHA en présence de la lumière UV. Bien que de la preuve a été trouvé suggérant une source potentielle de la toxicité induite par la dégradation UV du DHA, d'autres études doivent être menées pour étudier la corrélation entre la concentration de DHA et la concentration des radicaux libres et le peroxyde d'hydrogène formé. Cela peut permettre une plus grande compréhension de sa toxicité au genre humain et d'améliorer la sécurité des consommateurs.