fuzzy inference system

The absence of active export consortia and the lack of a technical, serious, and codified plan for their development are among the most important reasons for Iran's small and medium-sized enterprises (EMSs) remaining in the country's export coordinates. In this study, the data are collected and analyzed with a mixed (qualitative-quantitative) approach, which is a critical paradigm. The data are collected using library research and field methods. In the field section, structured, exploratory, and collaborative interviews are used in the qualitative phase, and the researcher-made questionnaires are used in the quantitative phase. The data are analyzed using grounded theory, brainstorming sessions, fuzzy cognitive map (FCM), fuzzy inference system (FIS), and system dynamics modeling (SDM). According to the results, "features of consortium members", "export operational plan", "consortium strengthening factor", "recognition of export support", "transnational factors", "government factors", and "product features" are the seven main success factors of private sector export consortia in Iranian industries. Furthermore, identifying a suitable promoter, identifying potential members, conducting the desired study and contacting interested companies, appointing representatives, holding meetings between potential members, conducting a feasibility study and preparing a business plan, officially forming a consortium, and following up on consortium affairs are eight steps for establishing private sector export consortiums in Iranian industries.

Utilizing fuzzy techniques, especially fuzzy type-2, is one of the most widely used methods in machine learning to model uncertainty. In addition to algorithm provision, the hardware implementation capability, and proper performance in real-time applications are other challenges. The use of hardware platforms that have biological similarities and are comparable to human neural systems in terms of implementation volume has always been considered. Memristor is one of the emerging elements for the implementation of fuzzy logic based algorithms. In this element, by providing current and selecting the appropriate direction for the applied current, the resistance of the memristor (memristance) will increase or decrease. Various implementations of type-1 fuzzy systems exist, but no implementation of type-2 fuzzy systems has been done based on memristors. In this paper, memristor-crossbar structures are used to implement type-2 fuzzy membership functions. In the proposed hardware, the membership functions can have any shape and resolution. Our proposed implementation of type-2 fuzzy membership function has the potential to learn (On-Chip learning capability regardless of host system). Besides, the proposed hardware is analog and can be used as a basis in the construction of evolutionary systems. Furthermore, the proposed approach is applied to memristor emulator to demonstrate its correct operation.

In recent years, regarding the issues such as lack of natural resources, government laws, environmental concerns and social responsibility reverse and closed-loop supply chains has been in the center of attention of researchers and decision-makers. Then, in this paper, a multi-objective multi-product multi-period mathematical model is presented in the sustainable closed-loop supply chain to locate distribution, collection, recycling, and disposal centers, considering the risk criterion. Conditional value at risk is used as the criterion of risk evaluation. The objectives of this research are to minimize the costs of the chain, reducing the adverse environmental effects and social responsibility in order to maximize job opportunities. Uncertainty in demand and demand-dependent parameters are modeled and determined by the fuzzy inference system. The proposed model has been solved using multi objective particle swarm optimization algorithm (MOPSO) approach and the results have been compared with Epsilon constraint method. Sensitivity analysis was performed on the problem parameters and the efficiency of the studied methods was investigated.

The problem of insufficient data and uncertainty in modeling play a significant role in many engineering and management problems. Therefore, applying some techniques and decision-making processes is essential to attain proper solutions for aforementioned problems under accurate consideration. In this paper, an application of fuzzy inference system for modeling the indeterminacy involved in the problem of HSE risk assessment is presented. For this purpose, Failure Mode and Effect Analysis (FMEA), one of the most practical techniques with high reliability in HSE risk assessment is integrated with fuzzy inference system. The proposed model is executed according to the Mamdani algorithm and fuzzy logic toolbox of MATLAB software. With respect to a case study, a comparison between the proposed model and common FMEA risk assessment approach is made for prioritization of the HSE risks. The selected HSE risk factors which were analyzed are listed in three categories as follows: (a) health risks; (b) safety risks and (c) environmental risks. Based on the proposed model, falling and slipping of workers grouping with safety risks is ranked as the first serious risk with the risk priority number of 0.7938 and skin injury which is classified with health risks is considered as an inconsiderable risk with the lowest risk priority number of 0.0223. Ultimately, by applying the method on a case study, the results indicate that the proposed model by considering economic aspects as an intelligent risk evaluation tool provides more detailed and precise results.

In this study, Back-propagation neural network (BPNN) and adaptive neuro-fuzzy inference system (ANFIS) methods were applied to estimate the particle size of silica prepared by sol-gel technique. Simulated annealing algorithm (SAA) employed to determine the optimum practical parameters of the silica production. Accordingly, the process parameters, i.e. tetraethyl orthosilicate (TEOS), H2O and NH3 were introduced to BPNN and ANFIS methods. Average mean absolute percentage error (MAPE) and correlation relation (R) indexes were chosen as criteria to estimate the simulation error. Comparison of proposed optimum condition and the experimental data reveal that the ANFIS/SAA strategies are powerful techniques to find the optimal practical conditions with the minimum particles size of silica prepared by sol-gel technique and the accuracy of ANFIS model was higher than the results of ANN. Moreover, sensitivity analysis was employed to determine the effect of each practical parameter on the size of silica nano particles. The results showed that the water content and TEOS have the maximum and minimum effect on the particle size of silica, respectively. Since, water acts as diluent and synthesis of monodisperse silica in diluent solution will decrease the growth probability of nucleate, leading to a the lower silica particle size.

Slewing bearing, which is widely applied in tank, excavator and wind turbine, is a critical component of rotational machine. Standard procedure for bearing life calculation and condition assessment was established in general rolling bearings, nevertheless, relatively less literatures, in regard to the health condition assessment of slewing bearing, were published in past. Real time health condition assessment for slewing bearing is used for the purpose of avoiding catastrophic failures by detectable and preventative measurement. In this paper, a new strategy was present for health evaluation of slewing bearing based on multiple characteristic parameters, and ANN (Artificial Neural Network) and ANFIS(Adaptive Neuro-Fuzzy Inference System) models were demonstrated to predicted the health condition of slewing bearings. The prediction capabilities offered by ANN and ANFIS were shown by using data obtained from full life test of slewing bearings in NJUT test System. Various statistical performance indexes were utilized to compare the performance of two predicted models. The results suggest that ANFIS-based prediction model outperforms ANN models.