Murad Samhouri

Electricity Consumption in the Industrial Sector of Jordan: Application of Multivariate Linear Regression and Adaptive Neuro-Fuzzy Techniques

In this study two techniques, for modeling electricity consumption of the Jordanian industrial sector, are presented: (i) multivariate linear regression and (ii) neuro‐fuzzy models. Electricity consumption is modeled as function of different variables such as number of establishments, number of employees, electricity tariff, prevailing fuel prices, production outputs, capacity utilizations, and structural effects. It was found that industrial production and capacity utilization are the most important variables that have significant effect on future electrical power demand. The results showed that both the multivariate linear regression and neuro‐fuzzy models are generally comparable and can be used adequately to simulate industrial electricity consumption. However, comparison that is based on the square root average squared error of data suggests that the neuro‐fuzzy model performs slightly better for future prediction of electricity consumption than the multivariate linear regression model. Such results are in full agreement with similar work, using different methods, for other countries.

An intelligent opportunistic maintenance (OM) system: A genetic algorithm approach

Complex systems like aircrafts, space shuttles, nuclear power stations, and some complicated process industries operate under high reliability and safety requirements due to the complicated technology involved and hazardous consequences to the larger community in case of failures. The maintenance regime of complex systems most often consists of a variety of maintenance strategies, like preventive maintenance, corrective maintenance, condition-based maintenance and so on. Opportunistic or opportunity-based maintenance (OM) gives the maintenance staff an opportunity to replace or repair those items, which are found to be defective or needs replacement in the immediate future, during the maintenance of a machine or component. This work presents an intelligent method of how to decide whether a particular item requires opportunistic maintenance or not, and if so how cost effective this opportunity-based maintenance will be when compared to a probable future grounding. This maintenance strategy is considered important when dealing with complex systems that contain expensive items with hard lives with condition-based maintenance (CBM) strategies. Genetic algorithms (GA) are employed to decide whether opportunistic maintenance is cost effective or not. An example of applying opportunistic maintenance strategy in process industry is used to describe the methodology for genetic algorithms.

Fuzzy Identification and Modeling of a Gum-Protein Emulsifier in a Model Mayonnaise Color Development System

The aim of this study was to employ iota-carrageenan (IC) and wheat protein (WP) as an emulsifier alternative to egg yolk in a model mayonnaise system. A solution of 0.1% IC and 4% WP was prepared and used as an emulsifier in five different mayonnaise formulas. All mayonnaise treatments were evaluated and compared based on lightness and yellowness (i.e., L and b values respectively) at 4, 23, and 40°C. In addition, an adaptive neuro-fuzzy inference system (ANFIS) was used to model and identify the properties of the resulted mayonnaise, with the temperature and ratios. Experimental validation runs were conducted to compare the measured values and the predicted ones. The L value of the mayonnaise produced from different emulsifiers decreased at the lower storage temperature. The b-value was significantly the highest for mayonnaise formulated from 100% egg yolk. The comparison showed that the adoption of this neuro-fuzzy modeling technique (i.e., ANFIS) achieved a very satisfactory prediction accuracy of about 98%.

A Fuzzy Logic Approach for Scheduling Preventive Maintenance in ERP System

Many firms have proceeded to the adoption of Enterprise Resources Planning ERP solutions to maintain competitiveness. ERP is a packaged software system that enables enterprises to integrate operations, business processes and functions through common database. However, the majority of ERP systems do not support Preventive Maintenance (PM) scheduling process. The objective of PM is to minimize equipment downtime using the limited resources of an organization. Therefore, prioritizing PM activities for equipment is essential. In this paper, a fuzzy logic-based system for PM scheduling is proposed to interpret the linguistic variables extracted from experts knowledge for determining equipment priorities, which could be incorporated as a custom module in ERP systems. The system was tested and proved to be reliable in solving PM scheduling problem.