Statistical modeling and optimal energy distribution of cogeneration units by genetic algorithms

Our main objective is to evaluate the performance of a new method to optimize the energy management of a production system composed of six cogeneration units using artificial intelligence. The optimization criterion is economic and environmental in order to minimize the total fuel cost, as well as the reduction of polluting gas emissions such as COx, NOx and SOx. First, a statistical model has been developed to determine the power that the cogeneration units can provide. Then, an economic model of operation was developed: fuel consumption and pollutant gas emissions as a function of the power produced. Finally, we studied the energy optimization of the system using genetic algorithms (GA), and contribute to the research on improving the efficiency of the studied power system. The GA has a better optimization performance, it can easily choose satisfactory solutions according to the optimization objectives, and compensate for these defects using its own characteristics. These characteristics make GA have outstanding advantages in iterative optimization. The robustness of the proposed algorithm is validated by testing six cogeneration units, and the obtained simulation results of the proposed system prove the value and effectiveness of GA for efficiency improvement as well as operating cost minimization.

An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms

Nowadays, recommendation systems offer a method of facilitating the user’s desire. It is useful for recommending items from a variety of areas such as in the e-commerce, medical, education, tourism, and industry domains. The e-commerce area represents the most active research we found, which assists users in locating the things they want. A recommender system can also provide users with helpful knowledge about things that could be of interest. Sometimes, the user gets bored with recommendations which are similar to their profiles, which leads to the over-specialization problem. Over-specialization is caused by limited content data, under which content-based recommendation algorithms suggest goods directly related to the customer profile rather than new things. In this study, we are particularly interested in recommending surprising, new, and unexpected items that may likely be enjoyed by users and will mitigate this limited content. In order to recommend novel and serendipitous items along with familiar items, we need to introduce additional hacks and note of randomness, which can be achieved using genetic algorithms that brings diversity to recommendations being made. This paper describes a Revolutionary Recommender System using a Genetic Algorithm called RRSGA which improves the fitness functions for recommending optimal results. The proposed approach employs a genetic algorithm to address the over-specialization issue of content-based filtering. The proposed method aims to incorporate genetic algorithms that bring variety to recommendations and efficiently adjust and suggest unpredictable and innovative things to the user. Experiments objectively demonstrate that our technology can recommend additional products that every consumer is likely to appreciate. The results of RRSGA have been compared against recommendation results from the content-based filtering approach. The results indicate the effectiveness of RRSGA and its capacity to make more accurate predictions than alternative approaches.

Computational Scale-Up for Flood Fed/Starve Fed Single Screw Extrusion of Polymers

A novel scaling-up computer system for single screw extrusion of polymers has been developed. This system makes it possible to scale-up extrusion process with both starve feeding and flood feeding. Each of the scale-up criteria can be an objective function to be minimized, represented by single values or functional dependencies over the screw length. The basis of scaling-up is process simulation made with the use of the GSEM program (Global Screw Extrusion Model). Scaling-up is performed using the GASES program (Genetic Algorithms Screw Extrusion Scaling) based on Genetic Algorithms. Scaling-up the extrusion process has been performed to increase extrusion output according to the scaling-up criteria defined by the single parameters of unit energy consumption, polymer plasticating rate and polymer temperature, as well as by the process parameters profiles of the temperature and plasticating. The global objective function reached the lowest value for the selected process parameters, and extrusion throughput was significantly increased.