Papers by Keyword: Fuzzy

Abstract: Batteries have an important thing in development of energy needs. A good performance battery, will support the device it supports. The energy that can save a battery is limited, so the battery will increase its charge and discharge cycles. Incorrect charging and discharging processes can cause battery performance to decrease. Therefore battery management is needed so that the battery can reach the maximum. One aspect of battery management is setting the state which is the ratio of available energy capacitance to maximum energy capacity. One method for estimating load states is the fuzzy logic method, namely by assessing the input and output systems of prediction. Predictor of State of Charge use Mamdani Fuzzy Logic that have temperature and voltage as input variables and State of Charge as output variable. A result of prediction State of Charge battery is represented by the number of Root Mean Square Error. Battery in charge condition has 2.7 for RMSE and level of accuracy 81.5%. Whereas Battery in discharge condition has RMSE 1.5 and level of accuracy 84.7%.

Abstract: The surface treatment conditions of a plastic surface are related to the quality of finished products. Usually, more than 20 causes dominate the success of electroplating for acrylonitrile butadiene styrene (ABS). Thus, the quality control is very complicated and challenging. Even nowadays, most of the production quality still relies on the operator's experience and intuition. This research takes a company of water hardware in Taiwan as the research object. We propose a revolutionary concept of quality management, combining artificial intelligence and surface treatment process altogether. We set up a parameter monitoring system during production to predict the quality of ABS metallization using neural network models such as artificial intelligence forms the basis of the intelligent manufacturing system. It can be used as a quality control tool to improve quality yield and industrial competitiveness. Totally 13 operational parameters (causes) and one quality parameter (consequence) of the electroplating tanks were collected from time to time to build the NN models. Interestingly, we finally find the fuzzy NN model performs better than the precise NN model. We conclude this is resulting from the limitation and vagueness of data.

Abstract: This presented article focuses on surface characterization and assessing the satisfactory machining condition of WEDMed Inconel 625. This work material has been received remarkable attention to the industrial and academic organization for its end use applications. WEDM is well-known machining process for intricate shape cutting and machining hard materials. The experimental design was planned according to L₂₇ orthogonal array (OA), by varying controllable process parameter (i.e. Wire-Tension, Wire-speed, Flushing-Pressure, Discharge-Current and Spark-on Time), each parameter varied at four discrete levels, within the selected parametric domain. WEDMed surfaces have been investigated with a focus to the surface characterization of selected machined surface through captured images from scanning electron microscope (SEM). Eventually, multi-response optimization of process parameters was sought by using a combination of nonlinear regression modelling, fuzzy inference system (FIS) with Teaching Learning-Based Optimization (TLBO) algorithm. The obtained TLBO result was compared with the Genetic algorithm (GA). The results show that optimization algorithms are effective tools for getting satisfactory optimal machining conditions during WEDM process of Inconel 625.

Abstract: Knowledge is essential for early flood warning as it can save life and property. This paper presents a novel knowledge-based framework based on rainfall, river water level, sediment, cloud distance and cloud strength that contributes to flood in Malaysia as the criteria in the AHP for Multiple Criteria Decision Analysis (MCDM). AHP caters complex decisions during flood events in uncertainty condition and provides fast decision making. The proposed framework is applied to the Bernam River Basin dataset located in Selangor, Malaysia. The framework is expected to produce early flood warning to the public.

Abstract: The adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the removal of ammonium () from wastewater. The ANFIS model was developed and validated with a data set from a pilot-scale of adsorption system treating aqueous solutions and wastewater from fish farms. The data sets consist of four parameters, which include pH, temperature, an initial concentration of ammonium and amount of adsorbent. The adsorbent was biochar obtained from rice straw. The ANFIS models performance was assessed through the root mean absolute error (RMSE) and was validated by testing data. The results of the study show that the adaptive neuro-fuzzy inference system (ANFIS) is able to predict the percentage of ammonium removal from adsorption column according to the input variables with acceptable accuracy, suggesting that the adaptive neuro-fuzzy inference system model is a valuable tool for estimating the quality of fish farms water. This model of ANFIS leads to cost reduction because prediction can be done without resorting to efforts that require cost and time.

Abstract: The constant evolution of the energy industry, has introduced the need for ongoing research studies about climate change due to its direct action on the production of alternative energies. Thus, they have focused on developing predictive algorithms in order to resolve, in an early way, the climate action on each point of energy production. In the development of this work, the ANFIS algorithm and information from the NASA Langley research center virtual database were implemented. They being oriented to the analysis and prediction of solar radiation over the geographic area of the Nueva Granada Military University campus, Cajicá, Colombia, with the purpose of making appropriate use of the power generating system located in the zone. The development of such systems, would allow the early identification of solar radiation that can be present in different geographical areas of Colombia, in order to provide the necessary power to cover the electricity demand required in each region, achieving as results an approximation error less than 1%.

Abstract: The estimation performance of interactive multiple model (IMM) estimator for tracking a maneuvering target is influenced by the target motion models and application of filters. An improved IMM estimation algorithm combined with the intelligent input estimation technique is proposed in this study. The target motion models include the constant velocity (CV) model and the modified Singer acceleration model. The intelligent fuzzy weighted input estimation (IFWIE) is used to compute the acceleration input for the modified Singer acceleration model besides the application of standard Kalman filter (KF). The combination of KF and IFWIE can estimate the target motion state precisely and the proposed method is compared with the common IMM estimator. The simulation results prove the improved IMM estimator has superior estimation performance than the common IMM estimator, especially when the target changes the acceleration violently. The utilization of IFWIE for the improved IMM estimator can estimate the acceleration input effectively.

Abstract: According to the all set theory, a fuzzy-random creep fracture model was presented in this work. To deal with the function, the following steps were taken. First, the steady state creep coefficient (A) and steady state creep exponent (n) were considered in the fuzzy-random variables, then the C*-integral was considered in a fuzzy-random variable. Finally, with the interval analysis, the result of the fuzzy-random creep fracture model was given.

Abstract: This paper discusses the state-of-art of adaptive control approaches for nonlinear systems to date and presents a new classification framework, in which the existing adaptive control approaches can be broadly classified into two categories: model-driven methods and data-driven methods. The principle, main research progress, and inherent problems of these methods are reviewed. Finally, some practical considerations and future directions are also briefly explored and discussed.

Abstract: Multi-objective optimization technology and Fuzzy theory were applied to design truck differential based on consideration on its force condition. The mathematical model for the multi-objective optimization design was set up under the objective of the minimum volume of the differential, maximal strength of planet gear, with the design variable of planet gear teeth number Z1, axle shaft gear teeth number Z2, section modulus ms and working width b. Then, the fuzzy solution of multi-objective optimization were use to solve the model. Practical example of calculation shows that, the fuzzy optimization result is superior to that of regular optimization and traditional design, differential volume deceased by 32.73% and 1.92% respectively. Comparing with nominal design, the load of planet gear increases 17%, but is far below its permissible value, and also reduced by 9.04% than that of regular optimization.