6 results
Search Results
Now showing 1 - 6 of 6
Conference Object Citation - WoS: 1Citation - Scopus: 2Hardware-In Assessment of a Fault Tolerant Fuzzy Control Scheme for an Offshore Wind Farm Simulator(Elsevier, 2022) Simani, Silvio; Farsoni, Saverio; Turhan, CihanTo enhance both the safety and the efficiency of offshore wind park systems, faults must be accommodated in their earlier occurrence, in order to avoid costly unplanned maintenance. Therefore, this paper aims at implementing a fault tolerant control strategy by means of a data-driven approach relying on fuzzy logic. In particular, fuzzy modelling is considered here as it enables to approximate unknown nonlinear relations, while managing uncertain measurements and disturbance. On the other hand, the model of the fuzzy controller is directly estimated from the input-output signals acquired from the wind farm system, with fault tolerant capabilities. In general, the use of purely nonlinear relations and analytic methods would require more complex design tools. The design is therefore enhanced by the use of fuzzy model prototypes obtained via a data-driven approach, thus representing the key point if real-time solutions have to implement the proposed fault tolerant control strategy. Finally, a high-fidelity simulator relying on a hardware-in-the-loop tool is exploited to verify and validate the reliability and robustness characteristics of the developed methodology also for on-line and more realistic implementations. Copyright (C) 2022 The Authors.Article Citation - WoS: 28Development of an Intelligent Tutoring System Using Bayesian Networks and Fuzzy Logic for a Higher Student Academic Performance(Mdpi, 2020) Eryilmaz, Meltem; Adabashi, AfafIn this experimental study, an intelligent tutoring system called the fuzzy Bayesian intelligent tutoring system (FB-ITS), is developed by using artificial intelligence methods based on fuzzy logic and the Bayesian network technique to adaptively support students in learning environments. The effectiveness of the FB-ITS was evaluated by comparing it with two other versions of an Intelligent Tutoring System (ITS), fuzzy ITS and Bayesian ITS, separately. Moreover, it was evaluated by comparing it with an existing traditional e-learning system. In order to evaluate whether the academic performance of the students in different learning groups differs or not, analysis of covariance (ANCOVA) was used based on the students' pre-test and post-test scores. The study was conducted with 120 undergraduate university students. Results showed that students who studied using FB-ITS had significantly higher academic performance on average compared to other students who studied with the other systems. Regarding the time taken to perform the post-test, the results indicated that students who used the FB-ITS needed less time on average compared to students who used the traditional e-learning system. From the results, it could be concluded that the new system contributed in terms of the speed of performing the final exam and high academic success.Article Citation - WoS: 77Citation - Scopus: 101An Intelligent Process Planning System for Prismatic Parts Using Step Features(Springer London Ltd, 2007) Amaitik, Saleh M.; Kilic, S. EnginThis paper presents an intelligent process planning system using STEP features (ST-FeatCAPP) for prismatic parts. The system maps a STEP AP224 XML data file, without using a complex feature recognition process, and produces the corresponding machining operations to generate the process plan and corresponding STEP-NC in XML format. It carries out several stages of process planning such as operations selection, tool selection, machining parameters determination, machine tools selection and setup planning. A hybrid approach of most recent techniques ( neural networks, fuzzy logic and rule-based) of artificial intelligence is used as the inference engine of the developed system. An object-oriented approach is used in the definition and implementation of the system. An example part is tested and the corresponding process plan is presented to demonstrate and verify the proposed CAPP system. The paper thus suggests a new feature-based intelligent CAPP system for avoiding complex feature recognition and knowledge acquisition problems.Article Citation - WoS: 19Citation - Scopus: 21A Hybrid Approach for Selecting Material Handling Equipment in a Warehouse(Taylor & Francis Ltd, 2016) Saputro, Thomy Eko; Rouyendegh (Babek Erdebilli), Babak DaneshvarWarehouse operations are closely related to material handling activities. Loading, unloading, transporting and picking material constitute a huge part of the activities. In order to handle material properly as well as to contribute value to the material, the operator and the environment, utilizing Material Handling Equipment (MHE) is required. The selection of proper MHEs requires great focus since its consideration is linked to mutli-criteria and multi-objective decision making problems. Here, a hybrid method is proposed to address the MHE selection problem. An approach that integrates the entropy based hierarchical fuzzy Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) and Multi-Objective Mixed Integer Linear Programming (MOMILP) is used for seeking the best alternative. The evaluation of alternatives is performed based on both subjective and objective criteria. Subjective weights are derived from a fuzzy Analytic Hierarchy Process (AHP). To deal with objective criteria, the entropy method is adopted to determine the weights, and the integrated weights are also calculated. The alternatives are rated by using fuzzy TOPSIS. For final execution of the selection, an MOMILP model is developed incorporating two goals, namely to minimize the disadvantage of material handling operation and to minimize the total cost of material handling. The AUGMented E-CONtraint method (AUGMECON) is used to solve the model. A case study is given to illustrate the method. The results show the effectiveness of the hybrid method in complex decision making.Article Citation - WoS: 11Citation - Scopus: 22Ore-Age: a Hybrid System for Assisting and Teaching Mining Method Selection(Pergamon-elsevier Science Ltd, 2003) Guray, C; Celebi, N; Atalay, V; Pasamehmetoglu, AGMining method selection is among the most critical and problematic points in mining engineering profession. Choosing a suitable method for a given ore-body is very important for the economics, safety and the productivity of the mining work. In the past studies there are attempts to build up a systematic approach to help the engineers to make this selection. But, these approaches work based on static databases and fail in inserting the intuitive feelings and engineering judgments of experienced engineers to the selection process. In this study, a system based on 13 different expert systems and one interface agent is developed, to make mining method selection for the given ore-bodies. The agent Ore-Age, to follow his goal of supplying the maximum assistance to engineers in selecting the most suitable method for a specific ore-body, tries to learn the experiences of the experts he has faced. After this learning process the knowledge base is evolved to include these experiences, making the system more efficient and intuitive in mining method selection work. To realize the above goal, the system's tutoring procedure is executed by the agent, in case an inexperienced user enters the system, to complete his/her missing knowledge about mining method selection. (C) 2002 Elsevier Science Ltd. All rights reserved.Article Citation - WoS: 51Citation - Scopus: 63Cue-based aggregation with a mobile robot swarm: a novel fuzzy-based method(Sage Publications Ltd, 2014) Arvin, Farshad; Turgut, Ali Emre; Bazyari, Farhad; Arikan, Kutluk Bilge; Bellotto, Nicola; Yue, ShigangAggregation in swarm robotics is referred to as the gathering of spatially distributed robots into a single aggregate. Aggregation can be classified as cue-based or self-organized. In cue-based aggregation, there is a cue in the environment that points to the aggregation area, whereas in self-organized aggregation no cue is present. In this paper, we proposed a novel fuzzy-based method for cue-based aggregation based on the state-of-the-art BEECLUST algorithm. In particular, we proposed three different methods: naive, that uses a deterministic decision-making mechanism; vector-averaging, using a vectorial summation of all perceived inputs; and fuzzy, that uses a fuzzy logic controller. We used different experiment settings: one-source and two-source environments with static and dynamic conditions to compare all the methods. We observed that the fuzzy method outperformed all the other methods and it is the most robust method against noise.
