In the equipment maintenance plans of many manufacturing companies, it is necessary to evaluate the performance of certain equipment with a relatively low failure frequency. It is complex to monitor its statistical behavior with the traditional engineering models, because most of the information, in a short time interval, the values are zero, that is to say, the failure count is zero in the equipment. This paper presents a case study in a compound fertilizer company, where the failures of a hydraulic pump are monitored over time, using a ZIP model with excess zeros. The results indicate a rethinking of maintenance plans, considering that there is a high measure of probability of failure, which is unacceptable in chemical processes.
The evaluation of performance with respect to the specifications in production processes is generally measured by means of univariate capacity indicators, but this is inadequate when there quality characteristics, adding that these characteristics have extreme values by their nature. It is suitable for this type of robust process indicators that use distances such as Canberra's that more accurately express the actual process conditions. The results obtained with the Canberra distance made the values given by the traditional indicators that used the Euclidean distance more flexible, showing that this new indicator is adjusted to processes with extreme values.
Company's rankings are usually based on a single criterion, so that results vary according to the criterion used. The objective of this paper is to make a ranking of companies in Colombia in the period from 2012 to 2016 using an approach multicriteria based on their financial statements in a dataset a sample of 40 companies. This classification was carried out by combining two techniques: the fuzzy analytical hierarchy process (fuzzy AHP) and the technique of preference for similarity to the ideal solution (TOPSIS). With the fuzzy AHP the weightings of the selected criteria are obtained, and then with the TOPSIS technique the ratings of the different companies are made.
In the Atlántico Department of Colombia, more than 4000 companies from different industrial sectors are established. However, less than 20% of them are exporting their products, although this department is located in a privileged geographic location that allows easy access to river, sea and air ports. The main objective of this research was to characterize the productive profile of the exporting and nonexporting companies of the Department of the Atlantic to identify their main differences. For this, multivariate statistical analysis was used, specifically the discriminant analysis that allows to find classification functions for each type of company and a discriminant function that summarizes the main differences of the 4130 Cabarcas Reyes Juan Carlos et al.two populations, based on a series of previously identified variables. As a result of the research, the relevant variables were obtained to compare the two types of companies, an instrument for measuring these variables, the classification functions and the discriminant function. As a central conclusion, it was shown that there are differences in the productive profiles of the exporting and non-exporting companies of the Atlántico Department of Colombia.
The CVRP is a problem that aims to determine the routes that each of the vehicles in a fleet should follow in order to reach their destination points in a distribution network, so that the total distance travelled or the time spent by the set of vehicles is the least. The CVRP is considered a combinatorial problem, given that as the number of clients to be served increases, the number of possible routing solutions also grows exponentially. This exponential growth immediately exceeds the processing capacity of current computers, so it is advisable to use approximate methods, which do not ensure finding the optimal solution, but if they generate very good solutions (such as heuristics and metaheuristics), and on the contrary the use of exact methods is unsuccessful, since the computational time consumption is very high. In essence, this article presents a proposal to address the problem of vehicle 4220 Cabarcas Reyes Juan Carlos et al. routing, based on heuristic and metaheuristic methods, competitive in terms of response quality and computational time.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.