Development of an internet and fuzzy based control system of manufacturing process

The aim of this work is to develop an Internet and fuzzy based control and data acquisition system for an industrial process plant which can ensure remote running and fuzzy control of a cement factory. Cases studies of the proposed system application in three cement factories in Algeria, SCAEK (Setif), SCIMAT (Batna), and SCT (Tebessa), are discussed. The remote process control consists of alarms generated during running of the processes while maintaining and synchronizing different regulation loops thus ensuring automatic running of processes smoothly. In addition, fuzzy control of the kiln and the other two mills ensures that the system is operational at all times with minimal downtime. The process control system contains different operator station (OP), alarms table and a provision to monitor trends analysis. The operator can execute any operation according to his authorised access assigned by the system administrator using user administration tool. The Internet technology is used for human security by avoiding all times presence of operators at site for maintenance. Further, in case of a breakdown, the problem would be remotely diagnosed and resolved avoiding requirement of an expert on site thus eliminating traveling cost, security risks, visa formalities, etc. These trips are difficult to organize (costs, visas, risks). So the enterprise can reduce downtimes and travel costs. In order to realize a process control system guided by operators in the main control room or through Internet, the process control is based on programming in PCS 7 utilizing Cemat library and Fuzzy Control++ Siemens tools.     

Modeling and solving a one-supplier multi-vehicle production-inventory-distribution problem with clustered retailers

This paper considers a supply chain management problem which integrates production, inventory, and distribution decisions. The supply chain is composed of one supplier production facility and several retailers located in a given geographic region. The supplier is responsible for the production and the replenishment of the inventory of retailers, in a vendor managed inventory (VMI) context. The distance between retailers is negligible compared to the distance between the supplier and the retailers’ region. Thus, for each vehicle, there is a major fixed cost for traveling to the cluster of retailers and a minor fixed cost for visiting each individual retailer. The problem consists of determining quantities to be produced, quantities to be delivered to retailers, vehicles to be used, and retailers to be serviced by each vehicle. This problem is an extension of the one warehouse multi-retailer problem with the consideration of production planning and storage and vehicle capacity limitations in addition to fixed vehicle utilization costs and retailer servicing costs. The objective is to minimize a total cost composed of production, transportation, and inventory holding costs at the supplier and at the retailers. Two mixed integer linear programming formulations are proposed and six families of valid inequalities are added to strengthen these formulations. Two of these families are new and the others are adapted from the literature. The numerical results show that the valid inequalities considerably improve the quality of the formulations. Moreover, the parameters that influence the most computational times are analyzed.     

New fusion and selection approaches for estimating the remaining useful life using Gaussian process regression and induced ordered weighted averaging operators

In this paper, we propose new fusion and selection approaches to accurately predict the remaining useful life. The fusion scheme is built upon the combination of outcomes delivered by an ensemble of Gaussian process regression models. Each regressor is characterized by its own covariance function and initial hyperparameters. In this context, we adopt the induced ordered weighted averaging as a fusion tool to achieve such combination. Two additional fusion techniques based on the simple averaging and the ordered weighted averaging operators besides a selection approach are implemented. The differences between adjacent elements of the raw data are used for training instead of the original values. Experimental results conducted on lithium-ion battery data report a significant improvement in the obtained results. This work may provide some insights regarding the development of efficient intelligent fusion alternatives for further prognostic advances.     

Fault diagnosis of rotary kiln using SVM and binary ACO

This paper proposes a novel hybrid algorithm for fault diagnosis of rotary kiln based on a binary ant colony (BACO) and support vector machine (SVM). The algorithm can find a subset selection which is attained through the elimination of the features that produce noise or are strictly correlated with other already selected features. The BACO algorithm can improve classification accuracy with an appropriate feature subset and optimal parameters of SVM. The proposed algorithm is easily implemented and because of use of a simple filter in that, its computational complexity is very low. The performance of the proposed algorithm is evaluated through two real Rotary Cement kiln datasets. The results show that our algorithm outperforms existing algorithms.