Yield Optimization using Hybrid Gaussian Process Regression and a Genetic Multi-Objective Approach

Quantification and minimization of uncertainty is an important task in the design of electromagnetic devices, which comes with high computational effort. We propose a hybrid approach combining the reliability and accuracy of a Monte Carlo analysis with the efficiency of a surrogate model based on Gaussian Process Regression. We present two optimization approaches. An adaptive Newton-MC to reduce the impact of uncertainty and a genetic multi-objective approach to optimize performance and robustness at the same time. For a dielectrical waveguide, used as a benchmark problem, the proposed methods outperform classic approaches.

Modelling, control and supervisory optimization of generalized predictive control in catalytic cracking reactor

As gasoline demand increases, the efficiency of operation of Fluidized Catalytic Cracking Unit (FCCU) becomes paramount importance. In this paper, a dynamic model for FCCU is simulated and integrated with yield model in order to estimate the yield of products namely gasoline, light gases and coke. Conventional PI controllers are designed for the control of reactor and regenerator temperature. Since, the complete reaction occurs in a very short duration, the controllers are tuned so as to achieve shorter settling time and minimum overshot. Further in order to increase the yield, optimization of FCCU using Generalized Predictive Controller (GPC) at supervisory level is attempted. Through optimization of objective function, the GPC will provide optimized set point for the PI controller in order to maintain maximum gasoline yield.

Effect of fertilizers type and watering methods on the agronomic performance of cucumber (Cucumis sativus L.) grown on substrate in southern Côte d'Ivoire

Cucumber (Cucumis sativus L.) is a plant of great importance for food, agriculture, economy and medicine. This importance explains its high demand, intensified by its cultivation conditions, particularly the growing rarity of fertile land and available water. To contribute to this species yield optimization, the effects of fertilizers type [chemical: NPK (12-22-22) and organic: Agribionate] and a control (C) combined to two watering modes (traditional sprinkler and bottle drip) on plants growth and yield have been studied from sowing to harvest. Plant growth (stem length and diameter at the collar, number of leaves and flowers per plant, leaf area) and yield (fruit weight, diameter and length, yield) were assessed. ANOVA2 tests revealed that fertilization (NPK and agribionate) favored plant growth (respectively 34.20 and 37.32 cm in height against 6.67 cm) and increased yield (7498, 66 and 6600.46 Kg/ha against 1558 Kg/ha) with the largest and heaviest fruits (145.69 and 142.80 g) compared to the control (C) that produced the smallest ones (59.35 g). About watering, the bottle drip mode was more beneficial than traditional sprinkler one for cucumber organ growth and plant yield. The interaction (fertilizer type × watering mode) indicated that the best results were obtained with the Agribionate fertilizer watered with the bottle drip method.

Carnival Optimizes Revenue and Inventory Across Heterogenous Cruise Line Brands

Carnival Corporation & plc identified the need for a cutting-edge revenue management system; however, existing solutions from the airline and hospitality industries were not compatible with the idiosyncrasies of the cruise domain. As such, the company partnered with revenue analytics to build a complete revenue and inventory management system to meet its requirements. Yield optimization and demand analytics (YODA) is a system that leverages a unique quadratic programming model to jointly determine cruise prices and allocate cabin inventory to multiple cruises (e.g., 14-day and 7-day lengths) offered simultaneously on a given ship. The optimization inputs come from several machine learning algorithms that predict demand. YODA combines these algorithms with an elasticity model derived from an exponential curve to represent the unique price-sensitivity behavior observed in the cruise industry. The system generates millions of price recommendations each day and has been used to price voyages on 65 Carnival ships, approximately one quarter of the ships in the entire cruise industry, since December 2017. During A/B testing, YODA generated a 1.5%–2.5% incremental uplift in net ticket revenue, which is a significant revenue increase because Carnival was a Fortune 300 company in 2019.